mirror of
https://github.com/langgenius/dify.git
synced 2026-01-24 05:46:13 +08:00
Compare commits
2 Commits
feat/updat
...
fix/model-
| Author | SHA1 | Date | |
|---|---|---|---|
| 3bfb26d571 | |||
| ccf4bd8555 |
3
.github/workflows/api-tests.yml
vendored
3
.github/workflows/api-tests.yml
vendored
@ -76,7 +76,7 @@ jobs:
|
||||
- name: Run Workflow
|
||||
run: poetry run -C api bash dev/pytest/pytest_workflow.sh
|
||||
|
||||
- name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch)
|
||||
- name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale)
|
||||
uses: hoverkraft-tech/compose-action@v2.0.0
|
||||
with:
|
||||
compose-file: |
|
||||
@ -90,6 +90,5 @@ jobs:
|
||||
pgvecto-rs
|
||||
pgvector
|
||||
chroma
|
||||
elasticsearch
|
||||
- name: Test Vector Stores
|
||||
run: poetry run -C api bash dev/pytest/pytest_vdb.sh
|
||||
|
||||
3
.github/workflows/expose_service_ports.sh
vendored
3
.github/workflows/expose_service_ports.sh
vendored
@ -6,6 +6,5 @@ yq eval '.services.chroma.ports += ["8000:8000"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services["milvus-standalone"].ports += ["19530:19530"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services.pgvector.ports += ["5433:5432"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services["pgvecto-rs"].ports += ["5431:5432"]' -i docker/docker-compose.yaml
|
||||
yq eval '.services["elasticsearch"].ports += ["9200:9200"]' -i docker/docker-compose.yaml
|
||||
|
||||
echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs, elasticsearch"
|
||||
echo "Ports exposed for sandbox, weaviate, qdrant, chroma, milvus, pgvector, pgvecto-rs."
|
||||
4
.github/workflows/style.yml
vendored
4
.github/workflows/style.yml
vendored
@ -45,10 +45,6 @@ jobs:
|
||||
if: steps.changed-files.outputs.any_changed == 'true'
|
||||
run: poetry run -C api dotenv-linter ./api/.env.example ./web/.env.example
|
||||
|
||||
- name: Ruff formatter check
|
||||
if: steps.changed-files.outputs.any_changed == 'true'
|
||||
run: poetry run -C api ruff format --check ./api
|
||||
|
||||
- name: Lint hints
|
||||
if: failure()
|
||||
run: echo "Please run 'dev/reformat' to fix the fixable linting errors."
|
||||
|
||||
1
.gitignore
vendored
1
.gitignore
vendored
@ -178,4 +178,3 @@ pyrightconfig.json
|
||||
api/.vscode
|
||||
|
||||
.idea/
|
||||
.vscode
|
||||
0
api/.idea/icon.png → .idea/icon.png
generated
0
api/.idea/icon.png → .idea/icon.png
generated
|
Before Width: | Height: | Size: 1.7 KiB After Width: | Height: | Size: 1.7 KiB |
0
api/.idea/vcs.xml → .idea/vcs.xml
generated
0
api/.idea/vcs.xml → .idea/vcs.xml
generated
@ -5,8 +5,8 @@
|
||||
"name": "Python: Flask",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"python": "${workspaceFolder}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder}",
|
||||
"python": "${workspaceFolder}/api/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder}/api",
|
||||
"envFile": ".env",
|
||||
"module": "flask",
|
||||
"justMyCode": true,
|
||||
@ -18,15 +18,15 @@
|
||||
"args": [
|
||||
"run",
|
||||
"--host=0.0.0.0",
|
||||
"--port=5001"
|
||||
"--port=5001",
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "Python: Celery",
|
||||
"type": "debugpy",
|
||||
"request": "launch",
|
||||
"python": "${workspaceFolder}/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder}",
|
||||
"python": "${workspaceFolder}/api/.venv/bin/python",
|
||||
"cwd": "${workspaceFolder}/api",
|
||||
"module": "celery",
|
||||
"justMyCode": true,
|
||||
"envFile": ".env",
|
||||
73
README.md
73
README.md
@ -4,7 +4,7 @@
|
||||
<a href="https://cloud.dify.ai">Dify Cloud</a> ·
|
||||
<a href="https://docs.dify.ai/getting-started/install-self-hosted">Self-hosting</a> ·
|
||||
<a href="https://docs.dify.ai">Documentation</a> ·
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Enterprise Inquiry</a>
|
||||
<a href="https://udify.app/chat/22L1zSxg6yW1cWQg">Enterprise inquiry</a>
|
||||
</p>
|
||||
|
||||
<p align="center">
|
||||
@ -41,36 +41,41 @@
|
||||
<a href="./README_VI.md"><img alt="README Tiếng Việt" src="https://img.shields.io/badge/Ti%E1%BA%BFng%20Vi%E1%BB%87t-d9d9d9"></a>
|
||||
</p>
|
||||
|
||||
Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, Agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. Here's a list of the core features:
|
||||
|
||||
Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. Here's a list of the core features:
|
||||
</br> </br>
|
||||
|
||||
**1. Workflow**:
|
||||
Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
|
||||
**1. Workflow**:
|
||||
Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
|
||||
|
||||
https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
|
||||
|
||||
**2. Comprehensive model support**:
|
||||
Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
|
||||
https://github.com/langgenius/dify/assets/13230914/356df23e-1604-483d-80a6-9517ece318aa
|
||||
|
||||
|
||||
|
||||
**2. Comprehensive model support**:
|
||||
Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found [here](https://docs.dify.ai/getting-started/readme/model-providers).
|
||||
|
||||
|
||||
|
||||
**3. Prompt IDE**:
|
||||
Intuitive interface for crafting prompts, comparing model performance, and adding additional features such as text-to-speech to a chat-based app.
|
||||
|
||||
**4. RAG Pipeline**:
|
||||
Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats.
|
||||
**3. Prompt IDE**:
|
||||
Intuitive interface for crafting prompts, comparing model performance, and adding additional features such as text-to-speech to a chat-based app.
|
||||
|
||||
**5. Agent capabilities**:
|
||||
You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DALL·E, Stable Diffusion and WolframAlpha.
|
||||
**4. RAG Pipeline**:
|
||||
Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats.
|
||||
|
||||
**6. LLMOps**:
|
||||
Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations.
|
||||
**5. Agent capabilities**:
|
||||
You can define agents based on LLM Function Calling or ReAct, and add pre-built or custom tools for the agent. Dify provides 50+ built-in tools for AI agents, such as Google Search, DALL·E, Stable Diffusion and WolframAlpha.
|
||||
|
||||
**6. LLMOps**:
|
||||
Monitor and analyze application logs and performance over time. You could continuously improve prompts, datasets, and models based on production data and annotations.
|
||||
|
||||
**7. Backend-as-a-Service**:
|
||||
All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.
|
||||
|
||||
**7. Backend-as-a-Service**:
|
||||
All of Dify's offerings come with corresponding APIs, so you could effortlessly integrate Dify into your own business logic.
|
||||
|
||||
## Feature comparison
|
||||
|
||||
<table style="width: 100%;">
|
||||
<tr>
|
||||
<th align="center">Feature</th>
|
||||
@ -140,28 +145,30 @@ All of Dify's offerings come with corresponding APIs, so you could effortlessly
|
||||
## Using Dify
|
||||
|
||||
- **Cloud </br>**
|
||||
We host a [Dify Cloud](https://dify.ai) service for anyone to try with zero setup. It provides all the capabilities of the self-deployed version, and includes 200 free GPT-4 calls in the sandbox plan.
|
||||
We host a [Dify Cloud](https://dify.ai) service for anyone to try with zero setup. It provides all the capabilities of the self-deployed version, and includes 200 free GPT-4 calls in the sandbox plan.
|
||||
|
||||
- **Self-hosting Dify Community Edition</br>**
|
||||
Quickly get Dify running in your environment with this [starter guide](#quick-start).
|
||||
Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.
|
||||
Quickly get Dify running in your environment with this [starter guide](#quick-start).
|
||||
Use our [documentation](https://docs.dify.ai) for further references and more in-depth instructions.
|
||||
|
||||
- **Dify for enterprise / organizations</br>**
|
||||
We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
|
||||
We provide additional enterprise-centric features. [Log your questions for us through this chatbot](https://udify.app/chat/22L1zSxg6yW1cWQg) or [send us an email](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) to discuss enterprise needs. </br>
|
||||
> For startups and small businesses using AWS, check out [Dify Premium on AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) and deploy it to your own AWS VPC with one-click. It's an affordable AMI offering with the option to create apps with custom logo and branding.
|
||||
|
||||
|
||||
## Staying ahead
|
||||
|
||||
Star Dify on GitHub and be instantly notified of new releases.
|
||||
|
||||
|
||||
|
||||
## Quick start
|
||||
|
||||
|
||||
## Quick start
|
||||
> Before installing Dify, make sure your machine meets the following minimum system requirements:
|
||||
>
|
||||
> - CPU >= 2 Core
|
||||
> - RAM >= 4GB
|
||||
>
|
||||
>- CPU >= 2 Core
|
||||
>- RAM >= 4GB
|
||||
|
||||
</br>
|
||||
|
||||
@ -190,16 +197,15 @@ If you'd like to configure a highly-available setup, there are community-contrib
|
||||
#### Using Terraform for Deployment
|
||||
|
||||
##### Azure Global
|
||||
|
||||
Deploy Dify to Azure with a single click using [terraform](https://www.terraform.io/).
|
||||
|
||||
- [Azure Terraform by @nikawang](https://github.com/nikawang/dify-azure-terraform)
|
||||
|
||||
## Contributing
|
||||
|
||||
For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
For those who'd like to contribute code, see our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
At the same time, please consider supporting Dify by sharing it on social media and at events and conferences.
|
||||
|
||||
|
||||
> We are looking for contributors to help with translating Dify to languages other than Mandarin or English. If you are interested in helping, please see the [i18n README](https://github.com/langgenius/dify/blob/main/web/i18n/README.md) for more information, and leave us a comment in the `global-users` channel of our [Discord Community Server](https://discord.gg/8Tpq4AcN9c).
|
||||
|
||||
**Contributors**
|
||||
@ -210,15 +216,16 @@ At the same time, please consider supporting Dify by sharing it on social media
|
||||
|
||||
## Community & contact
|
||||
|
||||
- [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
|
||||
- [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
- [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
|
||||
- [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
|
||||
* [Github Discussion](https://github.com/langgenius/dify/discussions). Best for: sharing feedback and asking questions.
|
||||
* [GitHub Issues](https://github.com/langgenius/dify/issues). Best for: bugs you encounter using Dify.AI, and feature proposals. See our [Contribution Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md).
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). Best for: sharing your applications and hanging out with the community.
|
||||
* [Twitter](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
|
||||
|
||||
## Star history
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
||||
|
||||
## Security disclosure
|
||||
|
||||
To protect your privacy, please avoid posting security issues on GitHub. Instead, send your questions to security@dify.ai and we will provide you with a more detailed answer.
|
||||
|
||||
19
README_VI.md
19
README_VI.md
@ -152,7 +152,7 @@ Nhanh chóng chạy Dify trong môi trường của bạn với [hướng dẫn
|
||||
Sử dụng [tài liệu](https://docs.dify.ai) của chúng tôi để tham khảo thêm và nhận hướng dẫn chi tiết hơn.
|
||||
|
||||
- **Dify cho doanh nghiệp / tổ chức</br>**
|
||||
Chúng tôi cung cấp các tính năng bổ sung tập trung vào doanh nghiệp. [Ghi lại câu hỏi của bạn cho chúng tôi thông qua chatbot này](https://udify.app/chat/22L1zSxg6yW1cWQg) hoặc [gửi email cho chúng tôi](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) để thảo luận về nhu cầu doanh nghiệp. </br>
|
||||
Chúng tôi cung cấp các tính năng bổ sung tập trung vào doanh nghiệp. [Lên lịch cuộc họp với chúng tôi](https://cal.com/guchenhe/30min) hoặc [gửi email cho chúng tôi](mailto:business@dify.ai?subject=[GitHub]Business%20License%20Inquiry) để thảo luận về nhu cầu doanh nghiệp. </br>
|
||||
> Đối với các công ty khởi nghiệp và doanh nghiệp nhỏ sử dụng AWS, hãy xem [Dify Premium trên AWS Marketplace](https://aws.amazon.com/marketplace/pp/prodview-t22mebxzwjhu6) và triển khai nó vào AWS VPC của riêng bạn chỉ với một cú nhấp chuột. Đây là một AMI giá cả phải chăng với tùy chọn tạo ứng dụng với logo và thương hiệu tùy chỉnh.
|
||||
|
||||
|
||||
@ -221,6 +221,23 @@ Triển khai Dify lên Azure chỉ với một cú nhấp chuột bằng cách s
|
||||
* [Discord](https://discord.gg/FngNHpbcY7). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
|
||||
* [Twitter](https://twitter.com/dify_ai). Tốt nhất cho: chia sẻ ứng dụng của bạn và giao lưu với cộng đồng.
|
||||
|
||||
Hoặc, lên lịch cuộc họp trực tiếp với một thành viên trong nhóm:
|
||||
|
||||
<table>
|
||||
<tr>
|
||||
<th>Điểm liên hệ</th>
|
||||
<th>Mục đích</th>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/guchenhe/15min' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/9ebcd111-1205-4d71-83d5-948d70b809f5' alt='Git-Hub-README-Button-3x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Yêu cầu kinh doanh & phản hồi sản phẩm</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><a href='https://cal.com/pinkbanana' target='_blank'><img class="schedule-button" src='https://github.com/langgenius/dify/assets/13230914/d1edd00a-d7e4-4513-be6c-e57038e143fd' alt='Git-Hub-README-Button-2x' style="width: 180px; height: auto; object-fit: contain;"/></a></td>
|
||||
<td>Đóng góp, vấn đề & yêu cầu tính năng</td>
|
||||
</tr>
|
||||
</table>
|
||||
|
||||
## Lịch sử Yêu thích
|
||||
|
||||
[](https://star-history.com/#langgenius/dify&Date)
|
||||
|
||||
@ -130,12 +130,6 @@ TENCENT_VECTOR_DB_DATABASE=dify
|
||||
TENCENT_VECTOR_DB_SHARD=1
|
||||
TENCENT_VECTOR_DB_REPLICAS=2
|
||||
|
||||
# ElasticSearch configuration
|
||||
ELASTICSEARCH_HOST=127.0.0.1
|
||||
ELASTICSEARCH_PORT=9200
|
||||
ELASTICSEARCH_USERNAME=elastic
|
||||
ELASTICSEARCH_PASSWORD=elastic
|
||||
|
||||
# PGVECTO_RS configuration
|
||||
PGVECTO_RS_HOST=localhost
|
||||
PGVECTO_RS_PORT=5431
|
||||
@ -247,8 +241,8 @@ API_TOOL_DEFAULT_READ_TIMEOUT=60
|
||||
HTTP_REQUEST_MAX_CONNECT_TIMEOUT=300
|
||||
HTTP_REQUEST_MAX_READ_TIMEOUT=600
|
||||
HTTP_REQUEST_MAX_WRITE_TIMEOUT=600
|
||||
HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760
|
||||
HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576
|
||||
HTTP_REQUEST_NODE_MAX_BINARY_SIZE=10485760 # 10MB
|
||||
HTTP_REQUEST_NODE_MAX_TEXT_SIZE=1048576 # 1MB
|
||||
|
||||
# Log file path
|
||||
LOG_FILE=
|
||||
@ -267,13 +261,4 @@ APP_MAX_ACTIVE_REQUESTS=0
|
||||
|
||||
|
||||
# Celery beat configuration
|
||||
CELERY_BEAT_SCHEDULER_TIME=1
|
||||
|
||||
# Position configuration
|
||||
POSITION_TOOL_PINS=
|
||||
POSITION_TOOL_INCLUDES=
|
||||
POSITION_TOOL_EXCLUDES=
|
||||
|
||||
POSITION_PROVIDER_PINS=
|
||||
POSITION_PROVIDER_INCLUDES=
|
||||
POSITION_PROVIDER_EXCLUDES=
|
||||
CELERY_BEAT_SCHEDULER_TIME=1
|
||||
161
api/app.py
161
api/app.py
@ -1,6 +1,6 @@
|
||||
import os
|
||||
|
||||
if os.environ.get("DEBUG", "false").lower() != "true":
|
||||
if os.environ.get("DEBUG", "false").lower() != 'true':
|
||||
from gevent import monkey
|
||||
|
||||
monkey.patch_all()
|
||||
@ -57,7 +57,7 @@ warnings.simplefilter("ignore", ResourceWarning)
|
||||
if os.name == "nt":
|
||||
os.system('tzutil /s "UTC"')
|
||||
else:
|
||||
os.environ["TZ"] = "UTC"
|
||||
os.environ['TZ'] = 'UTC'
|
||||
time.tzset()
|
||||
|
||||
|
||||
@ -70,14 +70,13 @@ class DifyApp(Flask):
|
||||
# -------------
|
||||
|
||||
|
||||
config_type = os.getenv("EDITION", default="SELF_HOSTED") # ce edition first
|
||||
config_type = os.getenv('EDITION', default='SELF_HOSTED') # ce edition first
|
||||
|
||||
|
||||
# ----------------------------
|
||||
# Application Factory Function
|
||||
# ----------------------------
|
||||
|
||||
|
||||
def create_flask_app_with_configs() -> Flask:
|
||||
"""
|
||||
create a raw flask app
|
||||
@ -93,7 +92,7 @@ def create_flask_app_with_configs() -> Flask:
|
||||
elif isinstance(value, int | float | bool):
|
||||
os.environ[key] = str(value)
|
||||
elif value is None:
|
||||
os.environ[key] = ""
|
||||
os.environ[key] = ''
|
||||
|
||||
return dify_app
|
||||
|
||||
@ -101,10 +100,10 @@ def create_flask_app_with_configs() -> Flask:
|
||||
def create_app() -> Flask:
|
||||
app = create_flask_app_with_configs()
|
||||
|
||||
app.secret_key = app.config["SECRET_KEY"]
|
||||
app.secret_key = app.config['SECRET_KEY']
|
||||
|
||||
log_handlers = None
|
||||
log_file = app.config.get("LOG_FILE")
|
||||
log_file = app.config.get('LOG_FILE')
|
||||
if log_file:
|
||||
log_dir = os.path.dirname(log_file)
|
||||
os.makedirs(log_dir, exist_ok=True)
|
||||
@ -112,24 +111,23 @@ def create_app() -> Flask:
|
||||
RotatingFileHandler(
|
||||
filename=log_file,
|
||||
maxBytes=1024 * 1024 * 1024,
|
||||
backupCount=5,
|
||||
backupCount=5
|
||||
),
|
||||
logging.StreamHandler(sys.stdout),
|
||||
logging.StreamHandler(sys.stdout)
|
||||
]
|
||||
|
||||
logging.basicConfig(
|
||||
level=app.config.get("LOG_LEVEL"),
|
||||
format=app.config.get("LOG_FORMAT"),
|
||||
datefmt=app.config.get("LOG_DATEFORMAT"),
|
||||
level=app.config.get('LOG_LEVEL'),
|
||||
format=app.config.get('LOG_FORMAT'),
|
||||
datefmt=app.config.get('LOG_DATEFORMAT'),
|
||||
handlers=log_handlers,
|
||||
force=True,
|
||||
force=True
|
||||
)
|
||||
log_tz = app.config.get("LOG_TZ")
|
||||
log_tz = app.config.get('LOG_TZ')
|
||||
if log_tz:
|
||||
from datetime import datetime
|
||||
|
||||
import pytz
|
||||
|
||||
timezone = pytz.timezone(log_tz)
|
||||
|
||||
def time_converter(seconds):
|
||||
@ -164,24 +162,24 @@ def initialize_extensions(app):
|
||||
@login_manager.request_loader
|
||||
def load_user_from_request(request_from_flask_login):
|
||||
"""Load user based on the request."""
|
||||
if request.blueprint not in ["console", "inner_api"]:
|
||||
if request.blueprint not in ['console', 'inner_api']:
|
||||
return None
|
||||
# Check if the user_id contains a dot, indicating the old format
|
||||
auth_header = request.headers.get("Authorization", "")
|
||||
auth_header = request.headers.get('Authorization', '')
|
||||
if not auth_header:
|
||||
auth_token = request.args.get("_token")
|
||||
auth_token = request.args.get('_token')
|
||||
if not auth_token:
|
||||
raise Unauthorized("Invalid Authorization token.")
|
||||
raise Unauthorized('Invalid Authorization token.')
|
||||
else:
|
||||
if " " not in auth_header:
|
||||
raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
|
||||
if ' ' not in auth_header:
|
||||
raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
|
||||
auth_scheme, auth_token = auth_header.split(None, 1)
|
||||
auth_scheme = auth_scheme.lower()
|
||||
if auth_scheme != "bearer":
|
||||
raise Unauthorized("Invalid Authorization header format. Expected 'Bearer <api-key>' format.")
|
||||
if auth_scheme != 'bearer':
|
||||
raise Unauthorized('Invalid Authorization header format. Expected \'Bearer <api-key>\' format.')
|
||||
|
||||
decoded = PassportService().verify(auth_token)
|
||||
user_id = decoded.get("user_id")
|
||||
user_id = decoded.get('user_id')
|
||||
|
||||
account = AccountService.load_logged_in_account(account_id=user_id, token=auth_token)
|
||||
if account:
|
||||
@ -192,11 +190,10 @@ def load_user_from_request(request_from_flask_login):
|
||||
@login_manager.unauthorized_handler
|
||||
def unauthorized_handler():
|
||||
"""Handle unauthorized requests."""
|
||||
return Response(
|
||||
json.dumps({"code": "unauthorized", "message": "Unauthorized."}),
|
||||
status=401,
|
||||
content_type="application/json",
|
||||
)
|
||||
return Response(json.dumps({
|
||||
'code': 'unauthorized',
|
||||
'message': "Unauthorized."
|
||||
}), status=401, content_type="application/json")
|
||||
|
||||
|
||||
# register blueprint routers
|
||||
@ -207,36 +204,38 @@ def register_blueprints(app):
|
||||
from controllers.service_api import bp as service_api_bp
|
||||
from controllers.web import bp as web_bp
|
||||
|
||||
CORS(
|
||||
service_api_bp,
|
||||
allow_headers=["Content-Type", "Authorization", "X-App-Code"],
|
||||
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
|
||||
)
|
||||
CORS(service_api_bp,
|
||||
allow_headers=['Content-Type', 'Authorization', 'X-App-Code'],
|
||||
methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH']
|
||||
)
|
||||
app.register_blueprint(service_api_bp)
|
||||
|
||||
CORS(
|
||||
web_bp,
|
||||
resources={r"/*": {"origins": app.config["WEB_API_CORS_ALLOW_ORIGINS"]}},
|
||||
supports_credentials=True,
|
||||
allow_headers=["Content-Type", "Authorization", "X-App-Code"],
|
||||
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
|
||||
expose_headers=["X-Version", "X-Env"],
|
||||
)
|
||||
CORS(web_bp,
|
||||
resources={
|
||||
r"/*": {"origins": app.config['WEB_API_CORS_ALLOW_ORIGINS']}},
|
||||
supports_credentials=True,
|
||||
allow_headers=['Content-Type', 'Authorization', 'X-App-Code'],
|
||||
methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'],
|
||||
expose_headers=['X-Version', 'X-Env']
|
||||
)
|
||||
|
||||
app.register_blueprint(web_bp)
|
||||
|
||||
CORS(
|
||||
console_app_bp,
|
||||
resources={r"/*": {"origins": app.config["CONSOLE_CORS_ALLOW_ORIGINS"]}},
|
||||
supports_credentials=True,
|
||||
allow_headers=["Content-Type", "Authorization"],
|
||||
methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"],
|
||||
expose_headers=["X-Version", "X-Env"],
|
||||
)
|
||||
CORS(console_app_bp,
|
||||
resources={
|
||||
r"/*": {"origins": app.config['CONSOLE_CORS_ALLOW_ORIGINS']}},
|
||||
supports_credentials=True,
|
||||
allow_headers=['Content-Type', 'Authorization'],
|
||||
methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH'],
|
||||
expose_headers=['X-Version', 'X-Env']
|
||||
)
|
||||
|
||||
app.register_blueprint(console_app_bp)
|
||||
|
||||
CORS(files_bp, allow_headers=["Content-Type"], methods=["GET", "PUT", "POST", "DELETE", "OPTIONS", "PATCH"])
|
||||
CORS(files_bp,
|
||||
allow_headers=['Content-Type'],
|
||||
methods=['GET', 'PUT', 'POST', 'DELETE', 'OPTIONS', 'PATCH']
|
||||
)
|
||||
app.register_blueprint(files_bp)
|
||||
|
||||
app.register_blueprint(inner_api_bp)
|
||||
@ -246,29 +245,29 @@ def register_blueprints(app):
|
||||
app = create_app()
|
||||
celery = app.extensions["celery"]
|
||||
|
||||
if app.config.get("TESTING"):
|
||||
if app.config.get('TESTING'):
|
||||
print("App is running in TESTING mode")
|
||||
|
||||
|
||||
@app.after_request
|
||||
def after_request(response):
|
||||
"""Add Version headers to the response."""
|
||||
response.set_cookie("remember_token", "", expires=0)
|
||||
response.headers.add("X-Version", app.config["CURRENT_VERSION"])
|
||||
response.headers.add("X-Env", app.config["DEPLOY_ENV"])
|
||||
response.set_cookie('remember_token', '', expires=0)
|
||||
response.headers.add('X-Version', app.config['CURRENT_VERSION'])
|
||||
response.headers.add('X-Env', app.config['DEPLOY_ENV'])
|
||||
return response
|
||||
|
||||
|
||||
@app.route("/health")
|
||||
@app.route('/health')
|
||||
def health():
|
||||
return Response(
|
||||
json.dumps({"pid": os.getpid(), "status": "ok", "version": app.config["CURRENT_VERSION"]}),
|
||||
status=200,
|
||||
content_type="application/json",
|
||||
)
|
||||
return Response(json.dumps({
|
||||
'pid': os.getpid(),
|
||||
'status': 'ok',
|
||||
'version': app.config['CURRENT_VERSION']
|
||||
}), status=200, content_type="application/json")
|
||||
|
||||
|
||||
@app.route("/threads")
|
||||
@app.route('/threads')
|
||||
def threads():
|
||||
num_threads = threading.active_count()
|
||||
threads = threading.enumerate()
|
||||
@ -279,34 +278,32 @@ def threads():
|
||||
thread_id = thread.ident
|
||||
is_alive = thread.is_alive()
|
||||
|
||||
thread_list.append(
|
||||
{
|
||||
"name": thread_name,
|
||||
"id": thread_id,
|
||||
"is_alive": is_alive,
|
||||
}
|
||||
)
|
||||
thread_list.append({
|
||||
'name': thread_name,
|
||||
'id': thread_id,
|
||||
'is_alive': is_alive
|
||||
})
|
||||
|
||||
return {
|
||||
"pid": os.getpid(),
|
||||
"thread_num": num_threads,
|
||||
"threads": thread_list,
|
||||
'pid': os.getpid(),
|
||||
'thread_num': num_threads,
|
||||
'threads': thread_list
|
||||
}
|
||||
|
||||
|
||||
@app.route("/db-pool-stat")
|
||||
@app.route('/db-pool-stat')
|
||||
def pool_stat():
|
||||
engine = db.engine
|
||||
return {
|
||||
"pid": os.getpid(),
|
||||
"pool_size": engine.pool.size(),
|
||||
"checked_in_connections": engine.pool.checkedin(),
|
||||
"checked_out_connections": engine.pool.checkedout(),
|
||||
"overflow_connections": engine.pool.overflow(),
|
||||
"connection_timeout": engine.pool.timeout(),
|
||||
"recycle_time": db.engine.pool._recycle,
|
||||
'pid': os.getpid(),
|
||||
'pool_size': engine.pool.size(),
|
||||
'checked_in_connections': engine.pool.checkedin(),
|
||||
'checked_out_connections': engine.pool.checkedout(),
|
||||
'overflow_connections': engine.pool.overflow(),
|
||||
'connection_timeout': engine.pool.timeout(),
|
||||
'recycle_time': db.engine.pool._recycle
|
||||
}
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
app.run(host="0.0.0.0", port=5001)
|
||||
if __name__ == '__main__':
|
||||
app.run(host='0.0.0.0', port=5001)
|
||||
|
||||
415
api/commands.py
415
api/commands.py
@ -27,29 +27,32 @@ from models.provider import Provider, ProviderModel
|
||||
from services.account_service import RegisterService, TenantService
|
||||
|
||||
|
||||
@click.command("reset-password", help="Reset the account password.")
|
||||
@click.option("--email", prompt=True, help="The email address of the account whose password you need to reset")
|
||||
@click.option("--new-password", prompt=True, help="the new password.")
|
||||
@click.option("--password-confirm", prompt=True, help="the new password confirm.")
|
||||
@click.command('reset-password', help='Reset the account password.')
|
||||
@click.option('--email', prompt=True, help='The email address of the account whose password you need to reset')
|
||||
@click.option('--new-password', prompt=True, help='the new password.')
|
||||
@click.option('--password-confirm', prompt=True, help='the new password confirm.')
|
||||
def reset_password(email, new_password, password_confirm):
|
||||
"""
|
||||
Reset password of owner account
|
||||
Only available in SELF_HOSTED mode
|
||||
"""
|
||||
if str(new_password).strip() != str(password_confirm).strip():
|
||||
click.echo(click.style("sorry. The two passwords do not match.", fg="red"))
|
||||
click.echo(click.style('sorry. The two passwords do not match.', fg='red'))
|
||||
return
|
||||
|
||||
account = db.session.query(Account).filter(Account.email == email).one_or_none()
|
||||
account = db.session.query(Account). \
|
||||
filter(Account.email == email). \
|
||||
one_or_none()
|
||||
|
||||
if not account:
|
||||
click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red"))
|
||||
click.echo(click.style('sorry. the account: [{}] not exist .'.format(email), fg='red'))
|
||||
return
|
||||
|
||||
try:
|
||||
valid_password(new_password)
|
||||
except:
|
||||
click.echo(click.style("sorry. The passwords must match {} ".format(password_pattern), fg="red"))
|
||||
click.echo(
|
||||
click.style('sorry. The passwords must match {} '.format(password_pattern), fg='red'))
|
||||
return
|
||||
|
||||
# generate password salt
|
||||
@ -62,87 +65,80 @@ def reset_password(email, new_password, password_confirm):
|
||||
account.password = base64_password_hashed
|
||||
account.password_salt = base64_salt
|
||||
db.session.commit()
|
||||
click.echo(click.style("Congratulations! Password has been reset.", fg="green"))
|
||||
click.echo(click.style('Congratulations! Password has been reset.', fg='green'))
|
||||
|
||||
|
||||
@click.command("reset-email", help="Reset the account email.")
|
||||
@click.option("--email", prompt=True, help="The old email address of the account whose email you need to reset")
|
||||
@click.option("--new-email", prompt=True, help="the new email.")
|
||||
@click.option("--email-confirm", prompt=True, help="the new email confirm.")
|
||||
@click.command('reset-email', help='Reset the account email.')
|
||||
@click.option('--email', prompt=True, help='The old email address of the account whose email you need to reset')
|
||||
@click.option('--new-email', prompt=True, help='the new email.')
|
||||
@click.option('--email-confirm', prompt=True, help='the new email confirm.')
|
||||
def reset_email(email, new_email, email_confirm):
|
||||
"""
|
||||
Replace account email
|
||||
:return:
|
||||
"""
|
||||
if str(new_email).strip() != str(email_confirm).strip():
|
||||
click.echo(click.style("Sorry, new email and confirm email do not match.", fg="red"))
|
||||
click.echo(click.style('Sorry, new email and confirm email do not match.', fg='red'))
|
||||
return
|
||||
|
||||
account = db.session.query(Account).filter(Account.email == email).one_or_none()
|
||||
account = db.session.query(Account). \
|
||||
filter(Account.email == email). \
|
||||
one_or_none()
|
||||
|
||||
if not account:
|
||||
click.echo(click.style("sorry. the account: [{}] not exist .".format(email), fg="red"))
|
||||
click.echo(click.style('sorry. the account: [{}] not exist .'.format(email), fg='red'))
|
||||
return
|
||||
|
||||
try:
|
||||
email_validate(new_email)
|
||||
except:
|
||||
click.echo(click.style("sorry. {} is not a valid email. ".format(email), fg="red"))
|
||||
click.echo(
|
||||
click.style('sorry. {} is not a valid email. '.format(email), fg='red'))
|
||||
return
|
||||
|
||||
account.email = new_email
|
||||
db.session.commit()
|
||||
click.echo(click.style("Congratulations!, email has been reset.", fg="green"))
|
||||
click.echo(click.style('Congratulations!, email has been reset.', fg='green'))
|
||||
|
||||
|
||||
@click.command(
|
||||
"reset-encrypt-key-pair",
|
||||
help="Reset the asymmetric key pair of workspace for encrypt LLM credentials. "
|
||||
"After the reset, all LLM credentials will become invalid, "
|
||||
"requiring re-entry."
|
||||
"Only support SELF_HOSTED mode.",
|
||||
)
|
||||
@click.confirmation_option(
|
||||
prompt=click.style(
|
||||
"Are you sure you want to reset encrypt key pair?" " this operation cannot be rolled back!", fg="red"
|
||||
)
|
||||
)
|
||||
@click.command('reset-encrypt-key-pair', help='Reset the asymmetric key pair of workspace for encrypt LLM credentials. '
|
||||
'After the reset, all LLM credentials will become invalid, '
|
||||
'requiring re-entry.'
|
||||
'Only support SELF_HOSTED mode.')
|
||||
@click.confirmation_option(prompt=click.style('Are you sure you want to reset encrypt key pair?'
|
||||
' this operation cannot be rolled back!', fg='red'))
|
||||
def reset_encrypt_key_pair():
|
||||
"""
|
||||
Reset the encrypted key pair of workspace for encrypt LLM credentials.
|
||||
After the reset, all LLM credentials will become invalid, requiring re-entry.
|
||||
Only support SELF_HOSTED mode.
|
||||
"""
|
||||
if dify_config.EDITION != "SELF_HOSTED":
|
||||
click.echo(click.style("Sorry, only support SELF_HOSTED mode.", fg="red"))
|
||||
if dify_config.EDITION != 'SELF_HOSTED':
|
||||
click.echo(click.style('Sorry, only support SELF_HOSTED mode.', fg='red'))
|
||||
return
|
||||
|
||||
tenants = db.session.query(Tenant).all()
|
||||
for tenant in tenants:
|
||||
if not tenant:
|
||||
click.echo(click.style("Sorry, no workspace found. Please enter /install to initialize.", fg="red"))
|
||||
click.echo(click.style('Sorry, no workspace found. Please enter /install to initialize.', fg='red'))
|
||||
return
|
||||
|
||||
tenant.encrypt_public_key = generate_key_pair(tenant.id)
|
||||
|
||||
db.session.query(Provider).filter(Provider.provider_type == "custom", Provider.tenant_id == tenant.id).delete()
|
||||
db.session.query(Provider).filter(Provider.provider_type == 'custom', Provider.tenant_id == tenant.id).delete()
|
||||
db.session.query(ProviderModel).filter(ProviderModel.tenant_id == tenant.id).delete()
|
||||
db.session.commit()
|
||||
|
||||
click.echo(
|
||||
click.style(
|
||||
"Congratulations! " "the asymmetric key pair of workspace {} has been reset.".format(tenant.id),
|
||||
fg="green",
|
||||
)
|
||||
)
|
||||
click.echo(click.style('Congratulations! '
|
||||
'the asymmetric key pair of workspace {} has been reset.'.format(tenant.id), fg='green'))
|
||||
|
||||
|
||||
@click.command("vdb-migrate", help="migrate vector db.")
|
||||
@click.option("--scope", default="all", prompt=False, help="The scope of vector database to migrate, Default is All.")
|
||||
@click.command('vdb-migrate', help='migrate vector db.')
|
||||
@click.option('--scope', default='all', prompt=False, help='The scope of vector database to migrate, Default is All.')
|
||||
def vdb_migrate(scope: str):
|
||||
if scope in ["knowledge", "all"]:
|
||||
if scope in ['knowledge', 'all']:
|
||||
migrate_knowledge_vector_database()
|
||||
if scope in ["annotation", "all"]:
|
||||
if scope in ['annotation', 'all']:
|
||||
migrate_annotation_vector_database()
|
||||
|
||||
|
||||
@ -150,7 +146,7 @@ def migrate_annotation_vector_database():
|
||||
"""
|
||||
Migrate annotation datas to target vector database .
|
||||
"""
|
||||
click.echo(click.style("Start migrate annotation data.", fg="green"))
|
||||
click.echo(click.style('Start migrate annotation data.', fg='green'))
|
||||
create_count = 0
|
||||
skipped_count = 0
|
||||
total_count = 0
|
||||
@ -158,103 +154,98 @@ def migrate_annotation_vector_database():
|
||||
while True:
|
||||
try:
|
||||
# get apps info
|
||||
apps = (
|
||||
db.session.query(App)
|
||||
.filter(App.status == "normal")
|
||||
.order_by(App.created_at.desc())
|
||||
.paginate(page=page, per_page=50)
|
||||
)
|
||||
apps = db.session.query(App).filter(
|
||||
App.status == 'normal'
|
||||
).order_by(App.created_at.desc()).paginate(page=page, per_page=50)
|
||||
except NotFound:
|
||||
break
|
||||
|
||||
page += 1
|
||||
for app in apps:
|
||||
total_count = total_count + 1
|
||||
click.echo(
|
||||
f"Processing the {total_count} app {app.id}. " + f"{create_count} created, {skipped_count} skipped."
|
||||
)
|
||||
click.echo(f'Processing the {total_count} app {app.id}. '
|
||||
+ f'{create_count} created, {skipped_count} skipped.')
|
||||
try:
|
||||
click.echo("Create app annotation index: {}".format(app.id))
|
||||
app_annotation_setting = (
|
||||
db.session.query(AppAnnotationSetting).filter(AppAnnotationSetting.app_id == app.id).first()
|
||||
)
|
||||
click.echo('Create app annotation index: {}'.format(app.id))
|
||||
app_annotation_setting = db.session.query(AppAnnotationSetting).filter(
|
||||
AppAnnotationSetting.app_id == app.id
|
||||
).first()
|
||||
|
||||
if not app_annotation_setting:
|
||||
skipped_count = skipped_count + 1
|
||||
click.echo("App annotation setting is disabled: {}".format(app.id))
|
||||
click.echo('App annotation setting is disabled: {}'.format(app.id))
|
||||
continue
|
||||
# get dataset_collection_binding info
|
||||
dataset_collection_binding = (
|
||||
db.session.query(DatasetCollectionBinding)
|
||||
.filter(DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id)
|
||||
.first()
|
||||
)
|
||||
dataset_collection_binding = db.session.query(DatasetCollectionBinding).filter(
|
||||
DatasetCollectionBinding.id == app_annotation_setting.collection_binding_id
|
||||
).first()
|
||||
if not dataset_collection_binding:
|
||||
click.echo("App annotation collection binding is not exist: {}".format(app.id))
|
||||
click.echo('App annotation collection binding is not exist: {}'.format(app.id))
|
||||
continue
|
||||
annotations = db.session.query(MessageAnnotation).filter(MessageAnnotation.app_id == app.id).all()
|
||||
dataset = Dataset(
|
||||
id=app.id,
|
||||
tenant_id=app.tenant_id,
|
||||
indexing_technique="high_quality",
|
||||
indexing_technique='high_quality',
|
||||
embedding_model_provider=dataset_collection_binding.provider_name,
|
||||
embedding_model=dataset_collection_binding.model_name,
|
||||
collection_binding_id=dataset_collection_binding.id,
|
||||
collection_binding_id=dataset_collection_binding.id
|
||||
)
|
||||
documents = []
|
||||
if annotations:
|
||||
for annotation in annotations:
|
||||
document = Document(
|
||||
page_content=annotation.question,
|
||||
metadata={"annotation_id": annotation.id, "app_id": app.id, "doc_id": annotation.id},
|
||||
metadata={
|
||||
"annotation_id": annotation.id,
|
||||
"app_id": app.id,
|
||||
"doc_id": annotation.id
|
||||
}
|
||||
)
|
||||
documents.append(document)
|
||||
|
||||
vector = Vector(dataset, attributes=["doc_id", "annotation_id", "app_id"])
|
||||
vector = Vector(dataset, attributes=['doc_id', 'annotation_id', 'app_id'])
|
||||
click.echo(f"Start to migrate annotation, app_id: {app.id}.")
|
||||
|
||||
try:
|
||||
vector.delete()
|
||||
click.echo(click.style(f"Successfully delete vector index for app: {app.id}.", fg="green"))
|
||||
click.echo(
|
||||
click.style(f'Successfully delete vector index for app: {app.id}.',
|
||||
fg='green'))
|
||||
except Exception as e:
|
||||
click.echo(click.style(f"Failed to delete vector index for app {app.id}.", fg="red"))
|
||||
click.echo(
|
||||
click.style(f'Failed to delete vector index for app {app.id}.',
|
||||
fg='red'))
|
||||
raise e
|
||||
if documents:
|
||||
try:
|
||||
click.echo(
|
||||
click.style(
|
||||
f"Start to created vector index with {len(documents)} annotations for app {app.id}.",
|
||||
fg="green",
|
||||
)
|
||||
)
|
||||
click.echo(click.style(
|
||||
f'Start to created vector index with {len(documents)} annotations for app {app.id}.',
|
||||
fg='green'))
|
||||
vector.create(documents)
|
||||
click.echo(click.style(f"Successfully created vector index for app {app.id}.", fg="green"))
|
||||
click.echo(
|
||||
click.style(f'Successfully created vector index for app {app.id}.', fg='green'))
|
||||
except Exception as e:
|
||||
click.echo(click.style(f"Failed to created vector index for app {app.id}.", fg="red"))
|
||||
click.echo(click.style(f'Failed to created vector index for app {app.id}.', fg='red'))
|
||||
raise e
|
||||
click.echo(f"Successfully migrated app annotation {app.id}.")
|
||||
click.echo(f'Successfully migrated app annotation {app.id}.')
|
||||
create_count += 1
|
||||
except Exception as e:
|
||||
click.echo(
|
||||
click.style(
|
||||
"Create app annotation index error: {} {}".format(e.__class__.__name__, str(e)), fg="red"
|
||||
)
|
||||
)
|
||||
click.style('Create app annotation index error: {} {}'.format(e.__class__.__name__, str(e)),
|
||||
fg='red'))
|
||||
continue
|
||||
|
||||
click.echo(
|
||||
click.style(
|
||||
f"Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.",
|
||||
fg="green",
|
||||
)
|
||||
)
|
||||
click.style(f'Congratulations! Create {create_count} app annotation indexes, and skipped {skipped_count} apps.',
|
||||
fg='green'))
|
||||
|
||||
|
||||
def migrate_knowledge_vector_database():
|
||||
"""
|
||||
Migrate vector database datas to target vector database .
|
||||
"""
|
||||
click.echo(click.style("Start migrate vector db.", fg="green"))
|
||||
click.echo(click.style('Start migrate vector db.', fg='green'))
|
||||
create_count = 0
|
||||
skipped_count = 0
|
||||
total_count = 0
|
||||
@ -262,77 +253,87 @@ def migrate_knowledge_vector_database():
|
||||
page = 1
|
||||
while True:
|
||||
try:
|
||||
datasets = (
|
||||
db.session.query(Dataset)
|
||||
.filter(Dataset.indexing_technique == "high_quality")
|
||||
.order_by(Dataset.created_at.desc())
|
||||
.paginate(page=page, per_page=50)
|
||||
)
|
||||
datasets = db.session.query(Dataset).filter(Dataset.indexing_technique == 'high_quality') \
|
||||
.order_by(Dataset.created_at.desc()).paginate(page=page, per_page=50)
|
||||
except NotFound:
|
||||
break
|
||||
|
||||
page += 1
|
||||
for dataset in datasets:
|
||||
total_count = total_count + 1
|
||||
click.echo(
|
||||
f"Processing the {total_count} dataset {dataset.id}. "
|
||||
+ f"{create_count} created, {skipped_count} skipped."
|
||||
)
|
||||
click.echo(f'Processing the {total_count} dataset {dataset.id}. '
|
||||
+ f'{create_count} created, {skipped_count} skipped.')
|
||||
try:
|
||||
click.echo("Create dataset vdb index: {}".format(dataset.id))
|
||||
click.echo('Create dataset vdb index: {}'.format(dataset.id))
|
||||
if dataset.index_struct_dict:
|
||||
if dataset.index_struct_dict["type"] == vector_type:
|
||||
if dataset.index_struct_dict['type'] == vector_type:
|
||||
skipped_count = skipped_count + 1
|
||||
continue
|
||||
collection_name = ""
|
||||
collection_name = ''
|
||||
if vector_type == VectorType.WEAVIATE:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": VectorType.WEAVIATE, "vector_store": {"class_prefix": collection_name}}
|
||||
index_struct_dict = {
|
||||
"type": VectorType.WEAVIATE,
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.QDRANT:
|
||||
if dataset.collection_binding_id:
|
||||
dataset_collection_binding = (
|
||||
db.session.query(DatasetCollectionBinding)
|
||||
.filter(DatasetCollectionBinding.id == dataset.collection_binding_id)
|
||||
.one_or_none()
|
||||
)
|
||||
dataset_collection_binding = db.session.query(DatasetCollectionBinding). \
|
||||
filter(DatasetCollectionBinding.id == dataset.collection_binding_id). \
|
||||
one_or_none()
|
||||
if dataset_collection_binding:
|
||||
collection_name = dataset_collection_binding.collection_name
|
||||
else:
|
||||
raise ValueError("Dataset Collection Bindings is not exist!")
|
||||
raise ValueError('Dataset Collection Bindings is not exist!')
|
||||
else:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": VectorType.QDRANT, "vector_store": {"class_prefix": collection_name}}
|
||||
index_struct_dict = {
|
||||
"type": VectorType.QDRANT,
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
|
||||
elif vector_type == VectorType.MILVUS:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
|
||||
index_struct_dict = {
|
||||
"type": VectorType.MILVUS,
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.RELYT:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
|
||||
index_struct_dict = {
|
||||
"type": 'relyt',
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.TENCENT:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
|
||||
index_struct_dict = {
|
||||
"type": VectorType.TENCENT,
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.PGVECTOR:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
|
||||
index_struct_dict = {
|
||||
"type": VectorType.PGVECTOR,
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.OPENSEARCH:
|
||||
dataset_id = dataset.id
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {
|
||||
"type": VectorType.OPENSEARCH,
|
||||
"vector_store": {"class_prefix": collection_name},
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.ANALYTICDB:
|
||||
@ -340,14 +341,9 @@ def migrate_knowledge_vector_database():
|
||||
collection_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {
|
||||
"type": VectorType.ANALYTICDB,
|
||||
"vector_store": {"class_prefix": collection_name},
|
||||
"vector_store": {"class_prefix": collection_name}
|
||||
}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
elif vector_type == VectorType.ELASTICSEARCH:
|
||||
dataset_id = dataset.id
|
||||
index_name = Dataset.gen_collection_name_by_id(dataset_id)
|
||||
index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
|
||||
dataset.index_struct = json.dumps(index_struct_dict)
|
||||
else:
|
||||
raise ValueError(f"Vector store {vector_type} is not supported.")
|
||||
|
||||
@ -357,41 +353,29 @@ def migrate_knowledge_vector_database():
|
||||
try:
|
||||
vector.delete()
|
||||
click.echo(
|
||||
click.style(
|
||||
f"Successfully delete vector index {collection_name} for dataset {dataset.id}.", fg="green"
|
||||
)
|
||||
)
|
||||
click.style(f'Successfully delete vector index {collection_name} for dataset {dataset.id}.',
|
||||
fg='green'))
|
||||
except Exception as e:
|
||||
click.echo(
|
||||
click.style(
|
||||
f"Failed to delete vector index {collection_name} for dataset {dataset.id}.", fg="red"
|
||||
)
|
||||
)
|
||||
click.style(f'Failed to delete vector index {collection_name} for dataset {dataset.id}.',
|
||||
fg='red'))
|
||||
raise e
|
||||
|
||||
dataset_documents = (
|
||||
db.session.query(DatasetDocument)
|
||||
.filter(
|
||||
DatasetDocument.dataset_id == dataset.id,
|
||||
DatasetDocument.indexing_status == "completed",
|
||||
DatasetDocument.enabled == True,
|
||||
DatasetDocument.archived == False,
|
||||
)
|
||||
.all()
|
||||
)
|
||||
dataset_documents = db.session.query(DatasetDocument).filter(
|
||||
DatasetDocument.dataset_id == dataset.id,
|
||||
DatasetDocument.indexing_status == 'completed',
|
||||
DatasetDocument.enabled == True,
|
||||
DatasetDocument.archived == False,
|
||||
).all()
|
||||
|
||||
documents = []
|
||||
segments_count = 0
|
||||
for dataset_document in dataset_documents:
|
||||
segments = (
|
||||
db.session.query(DocumentSegment)
|
||||
.filter(
|
||||
DocumentSegment.document_id == dataset_document.id,
|
||||
DocumentSegment.status == "completed",
|
||||
DocumentSegment.enabled == True,
|
||||
)
|
||||
.all()
|
||||
)
|
||||
segments = db.session.query(DocumentSegment).filter(
|
||||
DocumentSegment.document_id == dataset_document.id,
|
||||
DocumentSegment.status == 'completed',
|
||||
DocumentSegment.enabled == True
|
||||
).all()
|
||||
|
||||
for segment in segments:
|
||||
document = Document(
|
||||
@ -401,7 +385,7 @@ def migrate_knowledge_vector_database():
|
||||
"doc_hash": segment.index_node_hash,
|
||||
"document_id": segment.document_id,
|
||||
"dataset_id": segment.dataset_id,
|
||||
},
|
||||
}
|
||||
)
|
||||
|
||||
documents.append(document)
|
||||
@ -409,43 +393,37 @@ def migrate_knowledge_vector_database():
|
||||
|
||||
if documents:
|
||||
try:
|
||||
click.echo(
|
||||
click.style(
|
||||
f"Start to created vector index with {len(documents)} documents of {segments_count} segments for dataset {dataset.id}.",
|
||||
fg="green",
|
||||
)
|
||||
)
|
||||
click.echo(click.style(
|
||||
f'Start to created vector index with {len(documents)} documents of {segments_count} segments for dataset {dataset.id}.',
|
||||
fg='green'))
|
||||
vector.create(documents)
|
||||
click.echo(
|
||||
click.style(f"Successfully created vector index for dataset {dataset.id}.", fg="green")
|
||||
)
|
||||
click.style(f'Successfully created vector index for dataset {dataset.id}.', fg='green'))
|
||||
except Exception as e:
|
||||
click.echo(click.style(f"Failed to created vector index for dataset {dataset.id}.", fg="red"))
|
||||
click.echo(click.style(f'Failed to created vector index for dataset {dataset.id}.', fg='red'))
|
||||
raise e
|
||||
db.session.add(dataset)
|
||||
db.session.commit()
|
||||
click.echo(f"Successfully migrated dataset {dataset.id}.")
|
||||
click.echo(f'Successfully migrated dataset {dataset.id}.')
|
||||
create_count += 1
|
||||
except Exception as e:
|
||||
db.session.rollback()
|
||||
click.echo(
|
||||
click.style("Create dataset index error: {} {}".format(e.__class__.__name__, str(e)), fg="red")
|
||||
)
|
||||
click.style('Create dataset index error: {} {}'.format(e.__class__.__name__, str(e)),
|
||||
fg='red'))
|
||||
continue
|
||||
|
||||
click.echo(
|
||||
click.style(
|
||||
f"Congratulations! Create {create_count} dataset indexes, and skipped {skipped_count} datasets.", fg="green"
|
||||
)
|
||||
)
|
||||
click.style(f'Congratulations! Create {create_count} dataset indexes, and skipped {skipped_count} datasets.',
|
||||
fg='green'))
|
||||
|
||||
|
||||
@click.command("convert-to-agent-apps", help="Convert Agent Assistant to Agent App.")
|
||||
@click.command('convert-to-agent-apps', help='Convert Agent Assistant to Agent App.')
|
||||
def convert_to_agent_apps():
|
||||
"""
|
||||
Convert Agent Assistant to Agent App.
|
||||
"""
|
||||
click.echo(click.style("Start convert to agent apps.", fg="green"))
|
||||
click.echo(click.style('Start convert to agent apps.', fg='green'))
|
||||
|
||||
proceeded_app_ids = []
|
||||
|
||||
@ -480,7 +458,7 @@ def convert_to_agent_apps():
|
||||
break
|
||||
|
||||
for app in apps:
|
||||
click.echo("Converting app: {}".format(app.id))
|
||||
click.echo('Converting app: {}'.format(app.id))
|
||||
|
||||
try:
|
||||
app.mode = AppMode.AGENT_CHAT.value
|
||||
@ -492,139 +470,137 @@ def convert_to_agent_apps():
|
||||
)
|
||||
|
||||
db.session.commit()
|
||||
click.echo(click.style("Converted app: {}".format(app.id), fg="green"))
|
||||
click.echo(click.style('Converted app: {}'.format(app.id), fg='green'))
|
||||
except Exception as e:
|
||||
click.echo(click.style("Convert app error: {} {}".format(e.__class__.__name__, str(e)), fg="red"))
|
||||
click.echo(
|
||||
click.style('Convert app error: {} {}'.format(e.__class__.__name__,
|
||||
str(e)), fg='red'))
|
||||
|
||||
click.echo(click.style("Congratulations! Converted {} agent apps.".format(len(proceeded_app_ids)), fg="green"))
|
||||
click.echo(click.style('Congratulations! Converted {} agent apps.'.format(len(proceeded_app_ids)), fg='green'))
|
||||
|
||||
|
||||
@click.command("add-qdrant-doc-id-index", help="add qdrant doc_id index.")
|
||||
@click.option("--field", default="metadata.doc_id", prompt=False, help="index field , default is metadata.doc_id.")
|
||||
@click.command('add-qdrant-doc-id-index', help='add qdrant doc_id index.')
|
||||
@click.option('--field', default='metadata.doc_id', prompt=False, help='index field , default is metadata.doc_id.')
|
||||
def add_qdrant_doc_id_index(field: str):
|
||||
click.echo(click.style("Start add qdrant doc_id index.", fg="green"))
|
||||
click.echo(click.style('Start add qdrant doc_id index.', fg='green'))
|
||||
vector_type = dify_config.VECTOR_STORE
|
||||
if vector_type != "qdrant":
|
||||
click.echo(click.style("Sorry, only support qdrant vector store.", fg="red"))
|
||||
click.echo(click.style('Sorry, only support qdrant vector store.', fg='red'))
|
||||
return
|
||||
create_count = 0
|
||||
|
||||
try:
|
||||
bindings = db.session.query(DatasetCollectionBinding).all()
|
||||
if not bindings:
|
||||
click.echo(click.style("Sorry, no dataset collection bindings found.", fg="red"))
|
||||
click.echo(click.style('Sorry, no dataset collection bindings found.', fg='red'))
|
||||
return
|
||||
import qdrant_client
|
||||
from qdrant_client.http.exceptions import UnexpectedResponse
|
||||
from qdrant_client.http.models import PayloadSchemaType
|
||||
|
||||
from core.rag.datasource.vdb.qdrant.qdrant_vector import QdrantConfig
|
||||
|
||||
for binding in bindings:
|
||||
if dify_config.QDRANT_URL is None:
|
||||
raise ValueError("Qdrant url is required.")
|
||||
raise ValueError('Qdrant url is required.')
|
||||
qdrant_config = QdrantConfig(
|
||||
endpoint=dify_config.QDRANT_URL,
|
||||
api_key=dify_config.QDRANT_API_KEY,
|
||||
root_path=current_app.root_path,
|
||||
timeout=dify_config.QDRANT_CLIENT_TIMEOUT,
|
||||
grpc_port=dify_config.QDRANT_GRPC_PORT,
|
||||
prefer_grpc=dify_config.QDRANT_GRPC_ENABLED,
|
||||
prefer_grpc=dify_config.QDRANT_GRPC_ENABLED
|
||||
)
|
||||
try:
|
||||
client = qdrant_client.QdrantClient(**qdrant_config.to_qdrant_params())
|
||||
# create payload index
|
||||
client.create_payload_index(binding.collection_name, field, field_schema=PayloadSchemaType.KEYWORD)
|
||||
client.create_payload_index(binding.collection_name, field,
|
||||
field_schema=PayloadSchemaType.KEYWORD)
|
||||
create_count += 1
|
||||
except UnexpectedResponse as e:
|
||||
# Collection does not exist, so return
|
||||
if e.status_code == 404:
|
||||
click.echo(
|
||||
click.style(f"Collection not found, collection_name:{binding.collection_name}.", fg="red")
|
||||
)
|
||||
click.echo(click.style(f'Collection not found, collection_name:{binding.collection_name}.', fg='red'))
|
||||
continue
|
||||
# Some other error occurred, so re-raise the exception
|
||||
else:
|
||||
click.echo(
|
||||
click.style(
|
||||
f"Failed to create qdrant index, collection_name:{binding.collection_name}.", fg="red"
|
||||
)
|
||||
)
|
||||
click.echo(click.style(f'Failed to create qdrant index, collection_name:{binding.collection_name}.', fg='red'))
|
||||
|
||||
except Exception as e:
|
||||
click.echo(click.style("Failed to create qdrant client.", fg="red"))
|
||||
click.echo(click.style('Failed to create qdrant client.', fg='red'))
|
||||
|
||||
click.echo(click.style(f"Congratulations! Create {create_count} collection indexes.", fg="green"))
|
||||
click.echo(
|
||||
click.style(f'Congratulations! Create {create_count} collection indexes.',
|
||||
fg='green'))
|
||||
|
||||
|
||||
@click.command("create-tenant", help="Create account and tenant.")
|
||||
@click.option("--email", prompt=True, help="The email address of the tenant account.")
|
||||
@click.option("--language", prompt=True, help="Account language, default: en-US.")
|
||||
@click.command('create-tenant', help='Create account and tenant.')
|
||||
@click.option('--email', prompt=True, help='The email address of the tenant account.')
|
||||
@click.option('--language', prompt=True, help='Account language, default: en-US.')
|
||||
def create_tenant(email: str, language: Optional[str] = None):
|
||||
"""
|
||||
Create tenant account
|
||||
"""
|
||||
if not email:
|
||||
click.echo(click.style("Sorry, email is required.", fg="red"))
|
||||
click.echo(click.style('Sorry, email is required.', fg='red'))
|
||||
return
|
||||
|
||||
# Create account
|
||||
email = email.strip()
|
||||
|
||||
if "@" not in email:
|
||||
click.echo(click.style("Sorry, invalid email address.", fg="red"))
|
||||
if '@' not in email:
|
||||
click.echo(click.style('Sorry, invalid email address.', fg='red'))
|
||||
return
|
||||
|
||||
account_name = email.split("@")[0]
|
||||
account_name = email.split('@')[0]
|
||||
|
||||
if language not in languages:
|
||||
language = "en-US"
|
||||
language = 'en-US'
|
||||
|
||||
# generate random password
|
||||
new_password = secrets.token_urlsafe(16)
|
||||
|
||||
# register account
|
||||
account = RegisterService.register(email=email, name=account_name, password=new_password, language=language)
|
||||
account = RegisterService.register(
|
||||
email=email,
|
||||
name=account_name,
|
||||
password=new_password,
|
||||
language=language
|
||||
)
|
||||
|
||||
TenantService.create_owner_tenant_if_not_exist(account)
|
||||
|
||||
click.echo(
|
||||
click.style(
|
||||
"Congratulations! Account and tenant created.\n" "Account: {}\nPassword: {}".format(email, new_password),
|
||||
fg="green",
|
||||
)
|
||||
)
|
||||
click.echo(click.style('Congratulations! Account and tenant created.\n'
|
||||
'Account: {}\nPassword: {}'.format(email, new_password), fg='green'))
|
||||
|
||||
|
||||
@click.command("upgrade-db", help="upgrade the database")
|
||||
@click.command('upgrade-db', help='upgrade the database')
|
||||
def upgrade_db():
|
||||
click.echo("Preparing database migration...")
|
||||
lock = redis_client.lock(name="db_upgrade_lock", timeout=60)
|
||||
click.echo('Preparing database migration...')
|
||||
lock = redis_client.lock(name='db_upgrade_lock', timeout=60)
|
||||
if lock.acquire(blocking=False):
|
||||
try:
|
||||
click.echo(click.style("Start database migration.", fg="green"))
|
||||
click.echo(click.style('Start database migration.', fg='green'))
|
||||
|
||||
# run db migration
|
||||
import flask_migrate
|
||||
|
||||
flask_migrate.upgrade()
|
||||
|
||||
click.echo(click.style("Database migration successful!", fg="green"))
|
||||
click.echo(click.style('Database migration successful!', fg='green'))
|
||||
|
||||
except Exception as e:
|
||||
logging.exception(f"Database migration failed, error: {e}")
|
||||
logging.exception(f'Database migration failed, error: {e}')
|
||||
finally:
|
||||
lock.release()
|
||||
else:
|
||||
click.echo("Database migration skipped")
|
||||
click.echo('Database migration skipped')
|
||||
|
||||
|
||||
@click.command("fix-app-site-missing", help="Fix app related site missing issue.")
|
||||
@click.command('fix-app-site-missing', help='Fix app related site missing issue.')
|
||||
def fix_app_site_missing():
|
||||
"""
|
||||
Fix app related site missing issue.
|
||||
"""
|
||||
click.echo(click.style("Start fix app related site missing issue.", fg="green"))
|
||||
click.echo(click.style('Start fix app related site missing issue.', fg='green'))
|
||||
|
||||
failed_app_ids = []
|
||||
while True:
|
||||
@ -655,14 +631,15 @@ where sites.id is null limit 1000"""
|
||||
app_was_created.send(app, account=account)
|
||||
except Exception as e:
|
||||
failed_app_ids.append(app_id)
|
||||
click.echo(click.style("Fix app {} related site missing issue failed!".format(app_id), fg="red"))
|
||||
logging.exception(f"Fix app related site missing issue failed, error: {e}")
|
||||
click.echo(click.style('Fix app {} related site missing issue failed!'.format(app_id), fg='red'))
|
||||
logging.exception(f'Fix app related site missing issue failed, error: {e}')
|
||||
continue
|
||||
|
||||
if not processed_count:
|
||||
break
|
||||
|
||||
click.echo(click.style("Congratulations! Fix app related site missing issue successful!", fg="green"))
|
||||
|
||||
click.echo(click.style('Congratulations! Fix app related site missing issue successful!', fg='green'))
|
||||
|
||||
|
||||
def register_commands(app):
|
||||
|
||||
@ -12,14 +12,19 @@ from configs.packaging import PackagingInfo
|
||||
class DifyConfig(
|
||||
# Packaging info
|
||||
PackagingInfo,
|
||||
|
||||
# Deployment configs
|
||||
DeploymentConfig,
|
||||
|
||||
# Feature configs
|
||||
FeatureConfig,
|
||||
|
||||
# Middleware configs
|
||||
MiddlewareConfig,
|
||||
|
||||
# Extra service configs
|
||||
ExtraServiceConfig,
|
||||
|
||||
# Enterprise feature configs
|
||||
# **Before using, please contact business@dify.ai by email to inquire about licensing matters.**
|
||||
EnterpriseFeatureConfig,
|
||||
@ -31,14 +36,13 @@ class DifyConfig(
|
||||
env_file='.env',
|
||||
env_file_encoding='utf-8',
|
||||
frozen=True,
|
||||
|
||||
# ignore extra attributes
|
||||
extra='ignore',
|
||||
)
|
||||
|
||||
CODE_MAX_NUMBER: int = 9223372036854775807
|
||||
CODE_MIN_NUMBER: int = -9223372036854775808
|
||||
CODE_MAX_DEPTH: int = 5
|
||||
CODE_MAX_PRECISION: int = 20
|
||||
CODE_MAX_STRING_LENGTH: int = 80000
|
||||
CODE_MAX_STRING_ARRAY_LENGTH: int = 30
|
||||
CODE_MAX_OBJECT_ARRAY_LENGTH: int = 30
|
||||
@ -63,5 +67,3 @@ class DifyConfig(
|
||||
SSRF_PROXY_HTTPS_URL: str | None = None
|
||||
|
||||
MODERATION_BUFFER_SIZE: int = Field(default=300, description='The buffer size for moderation.')
|
||||
|
||||
MAX_VARIABLE_SIZE: int = Field(default=5 * 1024, description='The maximum size of a variable. default is 5KB.')
|
||||
|
||||
@ -406,7 +406,6 @@ class DataSetConfig(BaseSettings):
|
||||
default=False,
|
||||
)
|
||||
|
||||
|
||||
class WorkspaceConfig(BaseSettings):
|
||||
"""
|
||||
Workspace configs
|
||||
@ -443,63 +442,6 @@ class CeleryBeatConfig(BaseSettings):
|
||||
)
|
||||
|
||||
|
||||
class PositionConfig(BaseSettings):
|
||||
|
||||
POSITION_PROVIDER_PINS: str = Field(
|
||||
description='The heads of model providers',
|
||||
default='',
|
||||
)
|
||||
|
||||
POSITION_PROVIDER_INCLUDES: str = Field(
|
||||
description='The included model providers',
|
||||
default='',
|
||||
)
|
||||
|
||||
POSITION_PROVIDER_EXCLUDES: str = Field(
|
||||
description='The excluded model providers',
|
||||
default='',
|
||||
)
|
||||
|
||||
POSITION_TOOL_PINS: str = Field(
|
||||
description='The heads of tools',
|
||||
default='',
|
||||
)
|
||||
|
||||
POSITION_TOOL_INCLUDES: str = Field(
|
||||
description='The included tools',
|
||||
default='',
|
||||
)
|
||||
|
||||
POSITION_TOOL_EXCLUDES: str = Field(
|
||||
description='The excluded tools',
|
||||
default='',
|
||||
)
|
||||
|
||||
@computed_field
|
||||
def POSITION_PROVIDER_PINS_LIST(self) -> list[str]:
|
||||
return [item.strip() for item in self.POSITION_PROVIDER_PINS.split(',') if item.strip() != '']
|
||||
|
||||
@computed_field
|
||||
def POSITION_PROVIDER_INCLUDES_SET(self) -> set[str]:
|
||||
return {item.strip() for item in self.POSITION_PROVIDER_INCLUDES.split(',') if item.strip() != ''}
|
||||
|
||||
@computed_field
|
||||
def POSITION_PROVIDER_EXCLUDES_SET(self) -> set[str]:
|
||||
return {item.strip() for item in self.POSITION_PROVIDER_EXCLUDES.split(',') if item.strip() != ''}
|
||||
|
||||
@computed_field
|
||||
def POSITION_TOOL_PINS_LIST(self) -> list[str]:
|
||||
return [item.strip() for item in self.POSITION_TOOL_PINS.split(',') if item.strip() != '']
|
||||
|
||||
@computed_field
|
||||
def POSITION_TOOL_INCLUDES_SET(self) -> set[str]:
|
||||
return {item.strip() for item in self.POSITION_TOOL_INCLUDES.split(',') if item.strip() != ''}
|
||||
|
||||
@computed_field
|
||||
def POSITION_TOOL_EXCLUDES_SET(self) -> set[str]:
|
||||
return {item.strip() for item in self.POSITION_TOOL_EXCLUDES.split(',') if item.strip() != ''}
|
||||
|
||||
|
||||
class FeatureConfig(
|
||||
# place the configs in alphabet order
|
||||
AppExecutionConfig,
|
||||
@ -524,7 +466,6 @@ class FeatureConfig(
|
||||
UpdateConfig,
|
||||
WorkflowConfig,
|
||||
WorkspaceConfig,
|
||||
PositionConfig,
|
||||
|
||||
# hosted services config
|
||||
HostedServiceConfig,
|
||||
|
||||
@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
|
||||
|
||||
CURRENT_VERSION: str = Field(
|
||||
description='Dify version',
|
||||
default='0.7.1',
|
||||
default='0.6.16',
|
||||
)
|
||||
|
||||
COMMIT_SHA: str = Field(
|
||||
|
||||
@ -1 +1 @@
|
||||
HIDDEN_VALUE = "[__HIDDEN__]"
|
||||
HIDDEN_VALUE = '[__HIDDEN__]'
|
||||
|
||||
@ -1,22 +1,22 @@
|
||||
language_timezone_mapping = {
|
||||
"en-US": "America/New_York",
|
||||
"zh-Hans": "Asia/Shanghai",
|
||||
"zh-Hant": "Asia/Taipei",
|
||||
"pt-BR": "America/Sao_Paulo",
|
||||
"es-ES": "Europe/Madrid",
|
||||
"fr-FR": "Europe/Paris",
|
||||
"de-DE": "Europe/Berlin",
|
||||
"ja-JP": "Asia/Tokyo",
|
||||
"ko-KR": "Asia/Seoul",
|
||||
"ru-RU": "Europe/Moscow",
|
||||
"it-IT": "Europe/Rome",
|
||||
"uk-UA": "Europe/Kyiv",
|
||||
"vi-VN": "Asia/Ho_Chi_Minh",
|
||||
"ro-RO": "Europe/Bucharest",
|
||||
"pl-PL": "Europe/Warsaw",
|
||||
"hi-IN": "Asia/Kolkata",
|
||||
"tr-TR": "Europe/Istanbul",
|
||||
"fa-IR": "Asia/Tehran",
|
||||
'en-US': 'America/New_York',
|
||||
'zh-Hans': 'Asia/Shanghai',
|
||||
'zh-Hant': 'Asia/Taipei',
|
||||
'pt-BR': 'America/Sao_Paulo',
|
||||
'es-ES': 'Europe/Madrid',
|
||||
'fr-FR': 'Europe/Paris',
|
||||
'de-DE': 'Europe/Berlin',
|
||||
'ja-JP': 'Asia/Tokyo',
|
||||
'ko-KR': 'Asia/Seoul',
|
||||
'ru-RU': 'Europe/Moscow',
|
||||
'it-IT': 'Europe/Rome',
|
||||
'uk-UA': 'Europe/Kyiv',
|
||||
'vi-VN': 'Asia/Ho_Chi_Minh',
|
||||
'ro-RO': 'Europe/Bucharest',
|
||||
'pl-PL': 'Europe/Warsaw',
|
||||
'hi-IN': 'Asia/Kolkata',
|
||||
'tr-TR': 'Europe/Istanbul',
|
||||
'fa-IR': 'Asia/Tehran',
|
||||
}
|
||||
|
||||
languages = list(language_timezone_mapping.keys())
|
||||
@ -26,5 +26,6 @@ def supported_language(lang):
|
||||
if lang in languages:
|
||||
return lang
|
||||
|
||||
error = "{lang} is not a valid language.".format(lang=lang)
|
||||
error = ('{lang} is not a valid language.'
|
||||
.format(lang=lang))
|
||||
raise ValueError(error)
|
||||
|
||||
@ -5,79 +5,82 @@ from models.model import AppMode
|
||||
default_app_templates = {
|
||||
# workflow default mode
|
||||
AppMode.WORKFLOW: {
|
||||
"app": {
|
||||
"mode": AppMode.WORKFLOW.value,
|
||||
"enable_site": True,
|
||||
"enable_api": True,
|
||||
'app': {
|
||||
'mode': AppMode.WORKFLOW.value,
|
||||
'enable_site': True,
|
||||
'enable_api': True
|
||||
}
|
||||
},
|
||||
|
||||
# completion default mode
|
||||
AppMode.COMPLETION: {
|
||||
"app": {
|
||||
"mode": AppMode.COMPLETION.value,
|
||||
"enable_site": True,
|
||||
"enable_api": True,
|
||||
'app': {
|
||||
'mode': AppMode.COMPLETION.value,
|
||||
'enable_site': True,
|
||||
'enable_api': True
|
||||
},
|
||||
"model_config": {
|
||||
"model": {
|
||||
'model_config': {
|
||||
'model': {
|
||||
"provider": "openai",
|
||||
"name": "gpt-4o",
|
||||
"mode": "chat",
|
||||
"completion_params": {},
|
||||
"completion_params": {}
|
||||
},
|
||||
"user_input_form": json.dumps(
|
||||
[
|
||||
{
|
||||
"paragraph": {
|
||||
"label": "Query",
|
||||
"variable": "query",
|
||||
"required": True,
|
||||
"default": "",
|
||||
},
|
||||
},
|
||||
]
|
||||
),
|
||||
"pre_prompt": "{{query}}",
|
||||
'user_input_form': json.dumps([
|
||||
{
|
||||
"paragraph": {
|
||||
"label": "Query",
|
||||
"variable": "query",
|
||||
"required": True,
|
||||
"default": ""
|
||||
}
|
||||
}
|
||||
]),
|
||||
'pre_prompt': '{{query}}'
|
||||
},
|
||||
|
||||
},
|
||||
|
||||
# chat default mode
|
||||
AppMode.CHAT: {
|
||||
"app": {
|
||||
"mode": AppMode.CHAT.value,
|
||||
"enable_site": True,
|
||||
"enable_api": True,
|
||||
'app': {
|
||||
'mode': AppMode.CHAT.value,
|
||||
'enable_site': True,
|
||||
'enable_api': True
|
||||
},
|
||||
"model_config": {
|
||||
"model": {
|
||||
'model_config': {
|
||||
'model': {
|
||||
"provider": "openai",
|
||||
"name": "gpt-4o",
|
||||
"mode": "chat",
|
||||
"completion_params": {},
|
||||
},
|
||||
},
|
||||
"completion_params": {}
|
||||
}
|
||||
}
|
||||
},
|
||||
|
||||
# advanced-chat default mode
|
||||
AppMode.ADVANCED_CHAT: {
|
||||
"app": {
|
||||
"mode": AppMode.ADVANCED_CHAT.value,
|
||||
"enable_site": True,
|
||||
"enable_api": True,
|
||||
},
|
||||
'app': {
|
||||
'mode': AppMode.ADVANCED_CHAT.value,
|
||||
'enable_site': True,
|
||||
'enable_api': True
|
||||
}
|
||||
},
|
||||
|
||||
# agent-chat default mode
|
||||
AppMode.AGENT_CHAT: {
|
||||
"app": {
|
||||
"mode": AppMode.AGENT_CHAT.value,
|
||||
"enable_site": True,
|
||||
"enable_api": True,
|
||||
'app': {
|
||||
'mode': AppMode.AGENT_CHAT.value,
|
||||
'enable_site': True,
|
||||
'enable_api': True
|
||||
},
|
||||
"model_config": {
|
||||
"model": {
|
||||
'model_config': {
|
||||
'model': {
|
||||
"provider": "openai",
|
||||
"name": "gpt-4o",
|
||||
"mode": "chat",
|
||||
"completion_params": {},
|
||||
},
|
||||
},
|
||||
},
|
||||
"completion_params": {}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@ -1,7 +1,3 @@
|
||||
from contextvars import ContextVar
|
||||
|
||||
from core.workflow.entities.variable_pool import VariablePool
|
||||
|
||||
tenant_id: ContextVar[str] = ContextVar("tenant_id")
|
||||
|
||||
workflow_variable_pool: ContextVar[VariablePool] = ContextVar("workflow_variable_pool")
|
||||
tenant_id: ContextVar[str] = ContextVar('tenant_id')
|
||||
@ -17,7 +17,6 @@ from .app import (
|
||||
audio,
|
||||
completion,
|
||||
conversation,
|
||||
conversation_variables,
|
||||
generator,
|
||||
message,
|
||||
model_config,
|
||||
|
||||
@ -61,7 +61,6 @@ class AppListApi(Resource):
|
||||
parser.add_argument('name', type=str, required=True, location='json')
|
||||
parser.add_argument('description', type=str, location='json')
|
||||
parser.add_argument('mode', type=str, choices=ALLOW_CREATE_APP_MODES, location='json')
|
||||
parser.add_argument('icon_type', type=str, location='json')
|
||||
parser.add_argument('icon', type=str, location='json')
|
||||
parser.add_argument('icon_background', type=str, location='json')
|
||||
args = parser.parse_args()
|
||||
@ -95,7 +94,6 @@ class AppImportApi(Resource):
|
||||
parser.add_argument('data', type=str, required=True, nullable=False, location='json')
|
||||
parser.add_argument('name', type=str, location='json')
|
||||
parser.add_argument('description', type=str, location='json')
|
||||
parser.add_argument('icon_type', type=str, location='json')
|
||||
parser.add_argument('icon', type=str, location='json')
|
||||
parser.add_argument('icon_background', type=str, location='json')
|
||||
args = parser.parse_args()
|
||||
@ -169,7 +167,6 @@ class AppApi(Resource):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('name', type=str, required=True, nullable=False, location='json')
|
||||
parser.add_argument('description', type=str, location='json')
|
||||
parser.add_argument('icon_type', type=str, location='json')
|
||||
parser.add_argument('icon', type=str, location='json')
|
||||
parser.add_argument('icon_background', type=str, location='json')
|
||||
parser.add_argument('max_active_requests', type=int, location='json')
|
||||
@ -211,7 +208,6 @@ class AppCopyApi(Resource):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('name', type=str, location='json')
|
||||
parser.add_argument('description', type=str, location='json')
|
||||
parser.add_argument('icon_type', type=str, location='json')
|
||||
parser.add_argument('icon', type=str, location='json')
|
||||
parser.add_argument('icon_background', type=str, location='json')
|
||||
args = parser.parse_args()
|
||||
|
||||
@ -33,7 +33,7 @@ class CompletionConversationApi(Resource):
|
||||
@get_app_model(mode=AppMode.COMPLETION)
|
||||
@marshal_with(conversation_pagination_fields)
|
||||
def get(self, app_model):
|
||||
if not current_user.is_editor:
|
||||
if not current_user.is_admin_or_owner:
|
||||
raise Forbidden()
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('keyword', type=str, location='args')
|
||||
@ -108,7 +108,7 @@ class CompletionConversationDetailApi(Resource):
|
||||
@get_app_model(mode=AppMode.COMPLETION)
|
||||
@marshal_with(conversation_message_detail_fields)
|
||||
def get(self, app_model, conversation_id):
|
||||
if not current_user.is_editor:
|
||||
if not current_user.is_admin_or_owner:
|
||||
raise Forbidden()
|
||||
conversation_id = str(conversation_id)
|
||||
|
||||
@ -119,7 +119,7 @@ class CompletionConversationDetailApi(Resource):
|
||||
@account_initialization_required
|
||||
@get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
|
||||
def delete(self, app_model, conversation_id):
|
||||
if not current_user.is_editor:
|
||||
if not current_user.is_admin_or_owner:
|
||||
raise Forbidden()
|
||||
conversation_id = str(conversation_id)
|
||||
|
||||
@ -154,8 +154,6 @@ class ChatConversationApi(Resource):
|
||||
parser.add_argument('message_count_gte', type=int_range(1, 99999), required=False, location='args')
|
||||
parser.add_argument('page', type=int_range(1, 99999), required=False, default=1, location='args')
|
||||
parser.add_argument('limit', type=int_range(1, 100), required=False, default=20, location='args')
|
||||
parser.add_argument('sort_by', type=str, choices=['created_at', '-created_at', 'updated_at', '-updated_at'],
|
||||
required=False, default='-updated_at', location='args')
|
||||
args = parser.parse_args()
|
||||
|
||||
subquery = (
|
||||
@ -227,17 +225,7 @@ class ChatConversationApi(Resource):
|
||||
if app_model.mode == AppMode.ADVANCED_CHAT.value:
|
||||
query = query.where(Conversation.invoke_from != InvokeFrom.DEBUGGER.value)
|
||||
|
||||
match args['sort_by']:
|
||||
case 'created_at':
|
||||
query = query.order_by(Conversation.created_at.asc())
|
||||
case '-created_at':
|
||||
query = query.order_by(Conversation.created_at.desc())
|
||||
case 'updated_at':
|
||||
query = query.order_by(Conversation.updated_at.asc())
|
||||
case '-updated_at':
|
||||
query = query.order_by(Conversation.updated_at.desc())
|
||||
case _:
|
||||
query = query.order_by(Conversation.created_at.desc())
|
||||
query = query.order_by(Conversation.created_at.desc())
|
||||
|
||||
conversations = db.paginate(
|
||||
query,
|
||||
@ -268,7 +256,7 @@ class ChatConversationDetailApi(Resource):
|
||||
@get_app_model(mode=[AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT])
|
||||
@account_initialization_required
|
||||
def delete(self, app_model, conversation_id):
|
||||
if not current_user.is_editor:
|
||||
if not current_user.is_admin_or_owner:
|
||||
raise Forbidden()
|
||||
conversation_id = str(conversation_id)
|
||||
|
||||
|
||||
@ -1,61 +0,0 @@
|
||||
from flask_restful import Resource, marshal_with, reqparse
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
from controllers.console import api
|
||||
from controllers.console.app.wraps import get_app_model
|
||||
from controllers.console.setup import setup_required
|
||||
from controllers.console.wraps import account_initialization_required
|
||||
from extensions.ext_database import db
|
||||
from fields.conversation_variable_fields import paginated_conversation_variable_fields
|
||||
from libs.login import login_required
|
||||
from models import ConversationVariable
|
||||
from models.model import AppMode
|
||||
|
||||
|
||||
class ConversationVariablesApi(Resource):
|
||||
@setup_required
|
||||
@login_required
|
||||
@account_initialization_required
|
||||
@get_app_model(mode=AppMode.ADVANCED_CHAT)
|
||||
@marshal_with(paginated_conversation_variable_fields)
|
||||
def get(self, app_model):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('conversation_id', type=str, location='args')
|
||||
args = parser.parse_args()
|
||||
|
||||
stmt = (
|
||||
select(ConversationVariable)
|
||||
.where(ConversationVariable.app_id == app_model.id)
|
||||
.order_by(ConversationVariable.created_at)
|
||||
)
|
||||
if args['conversation_id']:
|
||||
stmt = stmt.where(ConversationVariable.conversation_id == args['conversation_id'])
|
||||
else:
|
||||
raise ValueError('conversation_id is required')
|
||||
|
||||
# NOTE: This is a temporary solution to avoid performance issues.
|
||||
page = 1
|
||||
page_size = 100
|
||||
stmt = stmt.limit(page_size).offset((page - 1) * page_size)
|
||||
|
||||
with Session(db.engine) as session:
|
||||
rows = session.scalars(stmt).all()
|
||||
|
||||
return {
|
||||
'page': page,
|
||||
'limit': page_size,
|
||||
'total': len(rows),
|
||||
'has_more': False,
|
||||
'data': [
|
||||
{
|
||||
'created_at': row.created_at,
|
||||
'updated_at': row.updated_at,
|
||||
**row.to_variable().model_dump(),
|
||||
}
|
||||
for row in rows
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
api.add_resource(ConversationVariablesApi, '/apps/<uuid:app_id>/conversation-variables')
|
||||
@ -16,7 +16,6 @@ from models.model import Site
|
||||
def parse_app_site_args():
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('title', type=str, required=False, location='json')
|
||||
parser.add_argument('icon_type', type=str, required=False, location='json')
|
||||
parser.add_argument('icon', type=str, required=False, location='json')
|
||||
parser.add_argument('icon_background', type=str, required=False, location='json')
|
||||
parser.add_argument('description', type=str, required=False, location='json')
|
||||
@ -54,7 +53,6 @@ class AppSite(Resource):
|
||||
|
||||
for attr_name in [
|
||||
'title',
|
||||
'icon_type',
|
||||
'icon',
|
||||
'icon_background',
|
||||
'description',
|
||||
|
||||
@ -74,7 +74,6 @@ class DraftWorkflowApi(Resource):
|
||||
parser.add_argument('hash', type=str, required=False, location='json')
|
||||
# TODO: set this to required=True after frontend is updated
|
||||
parser.add_argument('environment_variables', type=list, required=False, location='json')
|
||||
parser.add_argument('conversation_variables', type=list, required=False, location='json')
|
||||
args = parser.parse_args()
|
||||
elif 'text/plain' in content_type:
|
||||
try:
|
||||
@ -89,8 +88,7 @@ class DraftWorkflowApi(Resource):
|
||||
'graph': data.get('graph'),
|
||||
'features': data.get('features'),
|
||||
'hash': data.get('hash'),
|
||||
'environment_variables': data.get('environment_variables'),
|
||||
'conversation_variables': data.get('conversation_variables'),
|
||||
'environment_variables': data.get('environment_variables')
|
||||
}
|
||||
except json.JSONDecodeError:
|
||||
return {'message': 'Invalid JSON data'}, 400
|
||||
@ -102,8 +100,6 @@ class DraftWorkflowApi(Resource):
|
||||
try:
|
||||
environment_variables_list = args.get('environment_variables') or []
|
||||
environment_variables = [factory.build_variable_from_mapping(obj) for obj in environment_variables_list]
|
||||
conversation_variables_list = args.get('conversation_variables') or []
|
||||
conversation_variables = [factory.build_variable_from_mapping(obj) for obj in conversation_variables_list]
|
||||
workflow = workflow_service.sync_draft_workflow(
|
||||
app_model=app_model,
|
||||
graph=args['graph'],
|
||||
@ -111,7 +107,6 @@ class DraftWorkflowApi(Resource):
|
||||
unique_hash=args.get('hash'),
|
||||
account=current_user,
|
||||
environment_variables=environment_variables,
|
||||
conversation_variables=conversation_variables,
|
||||
)
|
||||
except WorkflowHashNotEqualError:
|
||||
raise DraftWorkflowNotSync()
|
||||
@ -459,7 +454,6 @@ class ConvertToWorkflowApi(Resource):
|
||||
if request.data:
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('name', type=str, required=False, nullable=True, location='json')
|
||||
parser.add_argument('icon_type', type=str, required=False, nullable=True, location='json')
|
||||
parser.add_argument('icon', type=str, required=False, nullable=True, location='json')
|
||||
parser.add_argument('icon_background', type=str, required=False, nullable=True, location='json')
|
||||
args = parser.parse_args()
|
||||
|
||||
@ -24,7 +24,7 @@ from fields.app_fields import related_app_list
|
||||
from fields.dataset_fields import dataset_detail_fields, dataset_query_detail_fields
|
||||
from fields.document_fields import document_status_fields
|
||||
from libs.login import login_required
|
||||
from models.dataset import Dataset, DatasetPermissionEnum, Document, DocumentSegment
|
||||
from models.dataset import Dataset, Document, DocumentSegment
|
||||
from models.model import ApiToken, UploadFile
|
||||
from services.dataset_service import DatasetPermissionService, DatasetService, DocumentService
|
||||
|
||||
@ -202,7 +202,7 @@ class DatasetApi(Resource):
|
||||
nullable=True,
|
||||
help='Invalid indexing technique.')
|
||||
parser.add_argument('permission', type=str, location='json', choices=(
|
||||
DatasetPermissionEnum.ONLY_ME, DatasetPermissionEnum.ALL_TEAM, DatasetPermissionEnum.PARTIAL_TEAM), help='Invalid permission.'
|
||||
'only_me', 'all_team_members', 'partial_members'), help='Invalid permission.'
|
||||
)
|
||||
parser.add_argument('embedding_model', type=str,
|
||||
location='json', help='Invalid embedding model.')
|
||||
@ -239,7 +239,7 @@ class DatasetApi(Resource):
|
||||
tenant_id, dataset_id_str, data.get('partial_member_list')
|
||||
)
|
||||
# clear partial member list when permission is only_me or all_team_members
|
||||
elif data.get('permission') == DatasetPermissionEnum.ONLY_ME or data.get('permission') == DatasetPermissionEnum.ALL_TEAM:
|
||||
elif data.get('permission') == 'only_me' or data.get('permission') == 'all_team_members':
|
||||
DatasetPermissionService.clear_partial_member_list(dataset_id_str)
|
||||
|
||||
partial_member_list = DatasetPermissionService.get_dataset_partial_member_list(dataset_id_str)
|
||||
@ -555,7 +555,7 @@ class DatasetRetrievalSettingApi(Resource):
|
||||
RetrievalMethod.SEMANTIC_SEARCH.value
|
||||
]
|
||||
}
|
||||
case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE | VectorType.ELASTICSEARCH:
|
||||
case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE:
|
||||
return {
|
||||
'retrieval_method': [
|
||||
RetrievalMethod.SEMANTIC_SEARCH.value,
|
||||
@ -573,13 +573,13 @@ class DatasetRetrievalSettingMockApi(Resource):
|
||||
@account_initialization_required
|
||||
def get(self, vector_type):
|
||||
match vector_type:
|
||||
case VectorType.MILVUS | VectorType.RELYT | VectorType.TIDB_VECTOR | VectorType.CHROMA | VectorType.TENCENT | VectorType.PGVECTO_RS:
|
||||
case VectorType.MILVUS | VectorType.RELYT | VectorType.PGVECTOR | VectorType.TIDB_VECTOR | VectorType.CHROMA | VectorType.TENCENT:
|
||||
return {
|
||||
'retrieval_method': [
|
||||
RetrievalMethod.SEMANTIC_SEARCH.value
|
||||
]
|
||||
}
|
||||
case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE | VectorType.ELASTICSEARCH | VectorType.PGVECTOR:
|
||||
case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB | VectorType.MYSCALE | VectorType.ORACLE:
|
||||
return {
|
||||
'retrieval_method': [
|
||||
RetrievalMethod.SEMANTIC_SEARCH.value,
|
||||
|
||||
@ -178,20 +178,11 @@ class DatasetDocumentListApi(Resource):
|
||||
.subquery()
|
||||
|
||||
query = query.outerjoin(sub_query, sub_query.c.document_id == Document.id) \
|
||||
.order_by(
|
||||
sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)),
|
||||
sort_logic(Document.position),
|
||||
)
|
||||
.order_by(sort_logic(db.func.coalesce(sub_query.c.total_hit_count, 0)))
|
||||
elif sort == 'created_at':
|
||||
query = query.order_by(
|
||||
sort_logic(Document.created_at),
|
||||
sort_logic(Document.position),
|
||||
)
|
||||
query = query.order_by(sort_logic(Document.created_at))
|
||||
else:
|
||||
query = query.order_by(
|
||||
desc(Document.created_at),
|
||||
desc(Document.position),
|
||||
)
|
||||
query = query.order_by(desc(Document.created_at))
|
||||
|
||||
paginated_documents = query.paginate(
|
||||
page=page, per_page=limit, max_per_page=100, error_out=False)
|
||||
|
||||
@ -25,8 +25,6 @@ class ConversationApi(Resource):
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('last_id', type=uuid_value, location='args')
|
||||
parser.add_argument('limit', type=int_range(1, 100), required=False, default=20, location='args')
|
||||
parser.add_argument('sort_by', type=str, choices=['created_at', '-created_at', 'updated_at', '-updated_at'],
|
||||
required=False, default='-updated_at', location='args')
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
@ -35,8 +33,7 @@ class ConversationApi(Resource):
|
||||
user=end_user,
|
||||
last_id=args['last_id'],
|
||||
limit=args['limit'],
|
||||
invoke_from=InvokeFrom.SERVICE_API,
|
||||
sort_by=args['sort_by']
|
||||
invoke_from=InvokeFrom.SERVICE_API
|
||||
)
|
||||
except services.errors.conversation.LastConversationNotExistsError:
|
||||
raise NotFound("Last Conversation Not Exists.")
|
||||
|
||||
@ -131,7 +131,7 @@ class MessageSuggestedApi(Resource):
|
||||
except services.errors.message.MessageNotExistsError:
|
||||
raise NotFound("Message Not Exists.")
|
||||
except SuggestedQuestionsAfterAnswerDisabledError:
|
||||
raise BadRequest("Suggested Questions Is Disabled.")
|
||||
raise BadRequest("Message Not Exists.")
|
||||
except Exception:
|
||||
logging.exception("internal server error.")
|
||||
raise InternalServerError()
|
||||
|
||||
@ -10,7 +10,7 @@ from core.model_runtime.entities.model_entities import ModelType
|
||||
from core.provider_manager import ProviderManager
|
||||
from fields.dataset_fields import dataset_detail_fields
|
||||
from libs.login import current_user
|
||||
from models.dataset import Dataset, DatasetPermissionEnum
|
||||
from models.dataset import Dataset
|
||||
from services.dataset_service import DatasetService
|
||||
|
||||
|
||||
@ -78,8 +78,6 @@ class DatasetListApi(DatasetApiResource):
|
||||
parser.add_argument('indexing_technique', type=str, location='json',
|
||||
choices=Dataset.INDEXING_TECHNIQUE_LIST,
|
||||
help='Invalid indexing technique.')
|
||||
parser.add_argument('permission', type=str, location='json', choices=(
|
||||
DatasetPermissionEnum.ONLY_ME, DatasetPermissionEnum.ALL_TEAM, DatasetPermissionEnum.PARTIAL_TEAM), help='Invalid permission.', required=False, nullable=False)
|
||||
args = parser.parse_args()
|
||||
|
||||
try:
|
||||
@ -87,8 +85,7 @@ class DatasetListApi(DatasetApiResource):
|
||||
tenant_id=tenant_id,
|
||||
name=args['name'],
|
||||
indexing_technique=args['indexing_technique'],
|
||||
account=current_user,
|
||||
permission=args['permission']
|
||||
account=current_user
|
||||
)
|
||||
except services.errors.dataset.DatasetNameDuplicateError:
|
||||
raise DatasetNameDuplicateError()
|
||||
|
||||
@ -53,22 +53,19 @@ class SegmentApi(DatasetApiResource):
|
||||
raise ProviderNotInitializeError(
|
||||
"No Embedding Model available. Please configure a valid provider "
|
||||
"in the Settings -> Model Provider.")
|
||||
except ProviderTokenNotInitError as ex:
|
||||
except ProviderTokenNotInitError as ex:
|
||||
raise ProviderNotInitializeError(ex.description)
|
||||
# validate args
|
||||
parser = reqparse.RequestParser()
|
||||
parser.add_argument('segments', type=list, required=False, nullable=True, location='json')
|
||||
args = parser.parse_args()
|
||||
if args['segments'] is not None:
|
||||
for args_item in args['segments']:
|
||||
SegmentService.segment_create_args_validate(args_item, document)
|
||||
segments = SegmentService.multi_create_segment(args['segments'], document, dataset)
|
||||
return {
|
||||
'data': marshal(segments, segment_fields),
|
||||
'doc_form': document.doc_form
|
||||
}, 200
|
||||
else:
|
||||
return {"error": "Segemtns is required"}, 400
|
||||
for args_item in args['segments']:
|
||||
SegmentService.segment_create_args_validate(args_item, document)
|
||||
segments = SegmentService.multi_create_segment(args['segments'], document, dataset)
|
||||
return {
|
||||
'data': marshal(segments, segment_fields),
|
||||
'doc_form': document.doc_form
|
||||
}, 200
|
||||
|
||||
def get(self, tenant_id, dataset_id, document_id):
|
||||
"""Create single segment."""
|
||||
|
||||
@ -26,8 +26,6 @@ class ConversationListApi(WebApiResource):
|
||||
parser.add_argument('last_id', type=uuid_value, location='args')
|
||||
parser.add_argument('limit', type=int_range(1, 100), required=False, default=20, location='args')
|
||||
parser.add_argument('pinned', type=str, choices=['true', 'false', None], location='args')
|
||||
parser.add_argument('sort_by', type=str, choices=['created_at', '-created_at', 'updated_at', '-updated_at'],
|
||||
required=False, default='-updated_at', location='args')
|
||||
args = parser.parse_args()
|
||||
|
||||
pinned = None
|
||||
@ -42,7 +40,6 @@ class ConversationListApi(WebApiResource):
|
||||
limit=args['limit'],
|
||||
invoke_from=InvokeFrom.WEB_APP,
|
||||
pinned=pinned,
|
||||
sort_by=args['sort_by']
|
||||
)
|
||||
except LastConversationNotExistsError:
|
||||
raise NotFound("Last Conversation Not Exists.")
|
||||
|
||||
@ -6,7 +6,6 @@ from configs import dify_config
|
||||
from controllers.web import api
|
||||
from controllers.web.wraps import WebApiResource
|
||||
from extensions.ext_database import db
|
||||
from libs.helper import AppIconUrlField
|
||||
from models.account import TenantStatus
|
||||
from models.model import Site
|
||||
from services.feature_service import FeatureService
|
||||
@ -29,10 +28,8 @@ class AppSiteApi(WebApiResource):
|
||||
'title': fields.String,
|
||||
'chat_color_theme': fields.String,
|
||||
'chat_color_theme_inverted': fields.Boolean,
|
||||
'icon_type': fields.String,
|
||||
'icon': fields.String,
|
||||
'icon_background': fields.String,
|
||||
'icon_url': AppIconUrlField,
|
||||
'description': fields.String,
|
||||
'copyright': fields.String,
|
||||
'privacy_policy': fields.String,
|
||||
|
||||
@ -64,19 +64,15 @@ class BaseAgentRunner(AppRunner):
|
||||
"""
|
||||
Agent runner
|
||||
:param tenant_id: tenant id
|
||||
:param application_generate_entity: application generate entity
|
||||
:param conversation: conversation
|
||||
:param app_config: app generate entity
|
||||
:param model_config: model config
|
||||
:param config: dataset config
|
||||
:param queue_manager: queue manager
|
||||
:param message: message
|
||||
:param user_id: user id
|
||||
:param agent_llm_callback: agent llm callback
|
||||
:param callback: callback
|
||||
:param memory: memory
|
||||
:param prompt_messages: prompt messages
|
||||
:param variables_pool: variables pool
|
||||
:param db_variables: db variables
|
||||
:param model_instance: model instance
|
||||
"""
|
||||
self.tenant_id = tenant_id
|
||||
self.application_generate_entity = application_generate_entity
|
||||
@ -449,7 +445,7 @@ class BaseAgentRunner(AppRunner):
|
||||
try:
|
||||
tool_responses = json.loads(agent_thought.observation)
|
||||
except Exception as e:
|
||||
tool_responses = dict.fromkeys(tools, agent_thought.observation)
|
||||
tool_responses = { tool: agent_thought.observation for tool in tools }
|
||||
|
||||
for tool in tools:
|
||||
# generate a uuid for tool call
|
||||
|
||||
@ -292,8 +292,6 @@ class CotAgentRunner(BaseAgentRunner, ABC):
|
||||
handle invoke action
|
||||
:param action: action
|
||||
:param tool_instances: tool instances
|
||||
:param message_file_ids: message file ids
|
||||
:param trace_manager: trace manager
|
||||
:return: observation, meta
|
||||
"""
|
||||
# action is tool call, invoke tool
|
||||
|
||||
@ -93,7 +93,6 @@ class DatasetConfigManager:
|
||||
reranking_model=dataset_configs.get('reranking_model'),
|
||||
weights=dataset_configs.get('weights'),
|
||||
reranking_enabled=dataset_configs.get('reranking_enabled', True),
|
||||
rerank_mode=dataset_configs.get('rerank_mode', 'reranking_model'),
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
import re
|
||||
|
||||
from core.app.app_config.entities import ExternalDataVariableEntity, VariableEntity, VariableEntityType
|
||||
from core.app.app_config.entities import ExternalDataVariableEntity, VariableEntity
|
||||
from core.external_data_tool.factory import ExternalDataToolFactory
|
||||
|
||||
|
||||
@ -13,7 +13,7 @@ class BasicVariablesConfigManager:
|
||||
:param config: model config args
|
||||
"""
|
||||
external_data_variables = []
|
||||
variable_entities = []
|
||||
variables = []
|
||||
|
||||
# old external_data_tools
|
||||
external_data_tools = config.get('external_data_tools', [])
|
||||
@ -30,41 +30,50 @@ class BasicVariablesConfigManager:
|
||||
)
|
||||
|
||||
# variables and external_data_tools
|
||||
for variables in config.get('user_input_form', []):
|
||||
variable_type = list(variables.keys())[0]
|
||||
if variable_type == VariableEntityType.EXTERNAL_DATA_TOOL:
|
||||
variable = variables[variable_type]
|
||||
if 'config' not in variable:
|
||||
for variable in config.get('user_input_form', []):
|
||||
typ = list(variable.keys())[0]
|
||||
if typ == 'external_data_tool':
|
||||
val = variable[typ]
|
||||
if 'config' not in val:
|
||||
continue
|
||||
|
||||
external_data_variables.append(
|
||||
ExternalDataVariableEntity(
|
||||
variable=variable['variable'],
|
||||
type=variable['type'],
|
||||
config=variable['config']
|
||||
variable=val['variable'],
|
||||
type=val['type'],
|
||||
config=val['config']
|
||||
)
|
||||
)
|
||||
elif variable_type in [
|
||||
VariableEntityType.TEXT_INPUT,
|
||||
VariableEntityType.PARAGRAPH,
|
||||
VariableEntityType.NUMBER,
|
||||
VariableEntityType.SELECT,
|
||||
elif typ in [
|
||||
VariableEntity.Type.TEXT_INPUT.value,
|
||||
VariableEntity.Type.PARAGRAPH.value,
|
||||
VariableEntity.Type.NUMBER.value,
|
||||
]:
|
||||
variable = variables[variable_type]
|
||||
variable_entities.append(
|
||||
variables.append(
|
||||
VariableEntity(
|
||||
type=variable_type,
|
||||
variable=variable.get('variable'),
|
||||
description=variable.get('description'),
|
||||
label=variable.get('label'),
|
||||
required=variable.get('required', False),
|
||||
max_length=variable.get('max_length'),
|
||||
options=variable.get('options'),
|
||||
default=variable.get('default'),
|
||||
type=VariableEntity.Type.value_of(typ),
|
||||
variable=variable[typ].get('variable'),
|
||||
description=variable[typ].get('description'),
|
||||
label=variable[typ].get('label'),
|
||||
required=variable[typ].get('required', False),
|
||||
max_length=variable[typ].get('max_length'),
|
||||
default=variable[typ].get('default'),
|
||||
)
|
||||
)
|
||||
elif typ == VariableEntity.Type.SELECT.value:
|
||||
variables.append(
|
||||
VariableEntity(
|
||||
type=VariableEntity.Type.SELECT,
|
||||
variable=variable[typ].get('variable'),
|
||||
description=variable[typ].get('description'),
|
||||
label=variable[typ].get('label'),
|
||||
required=variable[typ].get('required', False),
|
||||
options=variable[typ].get('options'),
|
||||
default=variable[typ].get('default'),
|
||||
)
|
||||
)
|
||||
|
||||
return variable_entities, external_data_variables
|
||||
return variables, external_data_variables
|
||||
|
||||
@classmethod
|
||||
def validate_and_set_defaults(cls, tenant_id: str, config: dict) -> tuple[dict, list[str]]:
|
||||
@ -174,4 +183,4 @@ class BasicVariablesConfigManager:
|
||||
config=config
|
||||
)
|
||||
|
||||
return config, ["external_data_tools"]
|
||||
return config, ["external_data_tools"]
|
||||
@ -3,9 +3,8 @@ from typing import Any, Optional
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.file.file_obj import FileExtraConfig
|
||||
from core.model_runtime.entities.message_entities import PromptMessageRole
|
||||
from models import AppMode
|
||||
from models.model import AppMode
|
||||
|
||||
|
||||
class ModelConfigEntity(BaseModel):
|
||||
@ -82,29 +81,43 @@ class PromptTemplateEntity(BaseModel):
|
||||
advanced_completion_prompt_template: Optional[AdvancedCompletionPromptTemplateEntity] = None
|
||||
|
||||
|
||||
class VariableEntityType(str, Enum):
|
||||
TEXT_INPUT = "text-input"
|
||||
SELECT = "select"
|
||||
PARAGRAPH = "paragraph"
|
||||
NUMBER = "number"
|
||||
EXTERNAL_DATA_TOOL = "external-data-tool"
|
||||
|
||||
|
||||
class VariableEntity(BaseModel):
|
||||
"""
|
||||
Variable Entity.
|
||||
"""
|
||||
class Type(Enum):
|
||||
TEXT_INPUT = 'text-input'
|
||||
SELECT = 'select'
|
||||
PARAGRAPH = 'paragraph'
|
||||
NUMBER = 'number'
|
||||
|
||||
@classmethod
|
||||
def value_of(cls, value: str) -> 'VariableEntity.Type':
|
||||
"""
|
||||
Get value of given mode.
|
||||
|
||||
:param value: mode value
|
||||
:return: mode
|
||||
"""
|
||||
for mode in cls:
|
||||
if mode.value == value:
|
||||
return mode
|
||||
raise ValueError(f'invalid variable type value {value}')
|
||||
|
||||
variable: str
|
||||
label: str
|
||||
description: Optional[str] = None
|
||||
type: VariableEntityType
|
||||
type: Type
|
||||
required: bool = False
|
||||
max_length: Optional[int] = None
|
||||
options: Optional[list[str]] = None
|
||||
default: Optional[str] = None
|
||||
hint: Optional[str] = None
|
||||
|
||||
@property
|
||||
def name(self) -> str:
|
||||
return self.variable
|
||||
|
||||
|
||||
class ExternalDataVariableEntity(BaseModel):
|
||||
"""
|
||||
@ -187,6 +200,11 @@ class TracingConfigEntity(BaseModel):
|
||||
tracing_provider: str
|
||||
|
||||
|
||||
class FileExtraConfig(BaseModel):
|
||||
"""
|
||||
File Upload Entity.
|
||||
"""
|
||||
image_config: Optional[dict[str, Any]] = None
|
||||
|
||||
|
||||
class AppAdditionalFeatures(BaseModel):
|
||||
@ -238,4 +256,4 @@ class WorkflowUIBasedAppConfig(AppConfig):
|
||||
"""
|
||||
Workflow UI Based App Config Entity.
|
||||
"""
|
||||
workflow_id: str
|
||||
workflow_id: str
|
||||
@ -1,7 +1,7 @@
|
||||
from collections.abc import Mapping
|
||||
from typing import Any, Optional
|
||||
|
||||
from core.file.file_obj import FileExtraConfig
|
||||
from core.app.app_config.entities import FileExtraConfig
|
||||
|
||||
|
||||
class FileUploadConfigManager:
|
||||
|
||||
@ -8,8 +8,6 @@ from typing import Union
|
||||
|
||||
from flask import Flask, current_app
|
||||
from pydantic import ValidationError
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.orm import Session
|
||||
|
||||
import contexts
|
||||
from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
|
||||
@ -20,20 +18,15 @@ from core.app.apps.advanced_chat.generate_task_pipeline import AdvancedChatAppGe
|
||||
from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedException, PublishFrom
|
||||
from core.app.apps.message_based_app_generator import MessageBasedAppGenerator
|
||||
from core.app.apps.message_based_app_queue_manager import MessageBasedAppQueueManager
|
||||
from core.app.entities.app_invoke_entities import (
|
||||
AdvancedChatAppGenerateEntity,
|
||||
InvokeFrom,
|
||||
)
|
||||
from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, InvokeFrom
|
||||
from core.app.entities.task_entities import ChatbotAppBlockingResponse, ChatbotAppStreamResponse
|
||||
from core.file.message_file_parser import MessageFileParser
|
||||
from core.model_runtime.errors.invoke import InvokeAuthorizationError, InvokeError
|
||||
from core.ops.ops_trace_manager import TraceQueueManager
|
||||
from core.workflow.entities.variable_pool import VariablePool
|
||||
from core.workflow.enums import SystemVariableKey
|
||||
from extensions.ext_database import db
|
||||
from models.account import Account
|
||||
from models.model import App, Conversation, EndUser, Message
|
||||
from models.workflow import ConversationVariable, Workflow
|
||||
from models.workflow import Workflow
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@ -46,7 +39,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
args: dict,
|
||||
invoke_from: InvokeFrom,
|
||||
stream: bool = True,
|
||||
):
|
||||
) -> Union[dict, Generator[dict, None, None]]:
|
||||
"""
|
||||
Generate App response.
|
||||
|
||||
@ -73,9 +66,8 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
|
||||
# get conversation
|
||||
conversation = None
|
||||
conversation_id = args.get('conversation_id')
|
||||
if conversation_id:
|
||||
conversation = self._get_conversation_by_user(app_model=app_model, conversation_id=conversation_id, user=user)
|
||||
if args.get('conversation_id'):
|
||||
conversation = self._get_conversation_by_user(app_model, args.get('conversation_id'), user)
|
||||
|
||||
# parse files
|
||||
files = args['files'] if args.get('files') else []
|
||||
@ -121,6 +113,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
|
||||
|
||||
return self._generate(
|
||||
app_model=app_model,
|
||||
workflow=workflow,
|
||||
user=user,
|
||||
invoke_from=invoke_from,
|
||||
@ -128,13 +121,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
conversation=conversation,
|
||||
stream=stream
|
||||
)
|
||||
|
||||
|
||||
def single_iteration_generate(self, app_model: App,
|
||||
workflow: Workflow,
|
||||
node_id: str,
|
||||
user: Account,
|
||||
args: dict,
|
||||
stream: bool = True):
|
||||
stream: bool = True) \
|
||||
-> Union[dict, Generator[dict, None, None]]:
|
||||
"""
|
||||
Generate App response.
|
||||
|
||||
@ -147,19 +141,18 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
"""
|
||||
if not node_id:
|
||||
raise ValueError('node_id is required')
|
||||
|
||||
|
||||
if args.get('inputs') is None:
|
||||
raise ValueError('inputs is required')
|
||||
|
||||
|
||||
extras = {
|
||||
"auto_generate_conversation_name": False
|
||||
}
|
||||
|
||||
# get conversation
|
||||
conversation = None
|
||||
conversation_id = args.get('conversation_id')
|
||||
if conversation_id:
|
||||
conversation = self._get_conversation_by_user(app_model=app_model, conversation_id=conversation_id, user=user)
|
||||
if args.get('conversation_id'):
|
||||
conversation = self._get_conversation_by_user(app_model, args.get('conversation_id'), user)
|
||||
|
||||
# convert to app config
|
||||
app_config = AdvancedChatAppConfigManager.get_app_config(
|
||||
@ -187,6 +180,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
contexts.tenant_id.set(application_generate_entity.app_config.tenant_id)
|
||||
|
||||
return self._generate(
|
||||
app_model=app_model,
|
||||
workflow=workflow,
|
||||
user=user,
|
||||
invoke_from=InvokeFrom.DEBUGGER,
|
||||
@ -195,13 +189,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
stream=stream
|
||||
)
|
||||
|
||||
def _generate(self, *,
|
||||
def _generate(self, app_model: App,
|
||||
workflow: Workflow,
|
||||
user: Union[Account, EndUser],
|
||||
invoke_from: InvokeFrom,
|
||||
application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
conversation: Conversation | None = None,
|
||||
stream: bool = True):
|
||||
conversation: Conversation = None,
|
||||
stream: bool = True) \
|
||||
-> Union[dict, Generator[dict, None, None]]:
|
||||
is_first_conversation = False
|
||||
if not conversation:
|
||||
is_first_conversation = True
|
||||
@ -216,7 +211,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
# update conversation features
|
||||
conversation.override_model_configs = workflow.features
|
||||
db.session.commit()
|
||||
# db.session.refresh(conversation)
|
||||
db.session.refresh(conversation)
|
||||
|
||||
# init queue manager
|
||||
queue_manager = MessageBasedAppQueueManager(
|
||||
@ -228,69 +223,15 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
message_id=message.id
|
||||
)
|
||||
|
||||
# Init conversation variables
|
||||
stmt = select(ConversationVariable).where(
|
||||
ConversationVariable.app_id == conversation.app_id, ConversationVariable.conversation_id == conversation.id
|
||||
)
|
||||
with Session(db.engine) as session:
|
||||
conversation_variables = session.scalars(stmt).all()
|
||||
if not conversation_variables:
|
||||
# Create conversation variables if they don't exist.
|
||||
conversation_variables = [
|
||||
ConversationVariable.from_variable(
|
||||
app_id=conversation.app_id, conversation_id=conversation.id, variable=variable
|
||||
)
|
||||
for variable in workflow.conversation_variables
|
||||
]
|
||||
session.add_all(conversation_variables)
|
||||
# Convert database entities to variables.
|
||||
conversation_variables = [item.to_variable() for item in conversation_variables]
|
||||
|
||||
session.commit()
|
||||
|
||||
# Increment dialogue count.
|
||||
conversation.dialogue_count += 1
|
||||
|
||||
conversation_id = conversation.id
|
||||
conversation_dialogue_count = conversation.dialogue_count
|
||||
db.session.commit()
|
||||
db.session.refresh(conversation)
|
||||
|
||||
inputs = application_generate_entity.inputs
|
||||
query = application_generate_entity.query
|
||||
files = application_generate_entity.files
|
||||
|
||||
user_id = None
|
||||
if application_generate_entity.invoke_from in [InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API]:
|
||||
end_user = db.session.query(EndUser).filter(EndUser.id == application_generate_entity.user_id).first()
|
||||
if end_user:
|
||||
user_id = end_user.session_id
|
||||
else:
|
||||
user_id = application_generate_entity.user_id
|
||||
|
||||
# Create a variable pool.
|
||||
system_inputs = {
|
||||
SystemVariableKey.QUERY: query,
|
||||
SystemVariableKey.FILES: files,
|
||||
SystemVariableKey.CONVERSATION_ID: conversation_id,
|
||||
SystemVariableKey.USER_ID: user_id,
|
||||
SystemVariableKey.DIALOGUE_COUNT: conversation_dialogue_count,
|
||||
}
|
||||
variable_pool = VariablePool(
|
||||
system_variables=system_inputs,
|
||||
user_inputs=inputs,
|
||||
environment_variables=workflow.environment_variables,
|
||||
conversation_variables=conversation_variables,
|
||||
)
|
||||
contexts.workflow_variable_pool.set(variable_pool)
|
||||
|
||||
# new thread
|
||||
worker_thread = threading.Thread(target=self._generate_worker, kwargs={
|
||||
'flask_app': current_app._get_current_object(),
|
||||
'application_generate_entity': application_generate_entity,
|
||||
'queue_manager': queue_manager,
|
||||
'conversation_id': conversation.id,
|
||||
'message_id': message.id,
|
||||
'context': contextvars.copy_context(),
|
||||
'user': user,
|
||||
'context': contextvars.copy_context()
|
||||
})
|
||||
|
||||
worker_thread.start()
|
||||
@ -303,7 +244,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
conversation=conversation,
|
||||
message=message,
|
||||
user=user,
|
||||
stream=stream,
|
||||
stream=stream
|
||||
)
|
||||
|
||||
return AdvancedChatAppGenerateResponseConverter.convert(
|
||||
@ -314,7 +255,9 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
def _generate_worker(self, flask_app: Flask,
|
||||
application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
queue_manager: AppQueueManager,
|
||||
conversation_id: str,
|
||||
message_id: str,
|
||||
user: Account,
|
||||
context: contextvars.Context) -> None:
|
||||
"""
|
||||
Generate worker in a new thread.
|
||||
@ -341,7 +284,8 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
user_id=application_generate_entity.user_id
|
||||
)
|
||||
else:
|
||||
# get message
|
||||
# get conversation and message
|
||||
conversation = self._get_conversation(conversation_id)
|
||||
message = self._get_message(message_id)
|
||||
|
||||
# chatbot app
|
||||
@ -349,6 +293,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
runner.run(
|
||||
application_generate_entity=application_generate_entity,
|
||||
queue_manager=queue_manager,
|
||||
conversation=conversation,
|
||||
message=message
|
||||
)
|
||||
except GenerateTaskStoppedException:
|
||||
@ -362,7 +307,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
logger.exception("Validation Error when generating")
|
||||
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
|
||||
except (ValueError, InvokeError) as e:
|
||||
if os.environ.get("DEBUG", "false").lower() == 'true':
|
||||
if os.environ.get("DEBUG") and os.environ.get("DEBUG").lower() == 'true':
|
||||
logger.exception("Error when generating")
|
||||
queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
|
||||
except Exception as e:
|
||||
@ -371,17 +316,14 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
finally:
|
||||
db.session.close()
|
||||
|
||||
def _handle_advanced_chat_response(
|
||||
self,
|
||||
*,
|
||||
application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
workflow: Workflow,
|
||||
queue_manager: AppQueueManager,
|
||||
conversation: Conversation,
|
||||
message: Message,
|
||||
user: Union[Account, EndUser],
|
||||
stream: bool = False,
|
||||
) -> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
|
||||
def _handle_advanced_chat_response(self, application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
workflow: Workflow,
|
||||
queue_manager: AppQueueManager,
|
||||
conversation: Conversation,
|
||||
message: Message,
|
||||
user: Union[Account, EndUser],
|
||||
stream: bool = False) \
|
||||
-> Union[ChatbotAppBlockingResponse, Generator[ChatbotAppStreamResponse, None, None]]:
|
||||
"""
|
||||
Handle response.
|
||||
:param application_generate_entity: application generate entity
|
||||
@ -401,7 +343,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
|
||||
conversation=conversation,
|
||||
message=message,
|
||||
user=user,
|
||||
stream=stream,
|
||||
stream=stream
|
||||
)
|
||||
|
||||
try:
|
||||
|
||||
@ -16,10 +16,12 @@ from core.app.entities.app_invoke_entities import (
|
||||
from core.app.entities.queue_entities import QueueAnnotationReplyEvent, QueueStopEvent, QueueTextChunkEvent
|
||||
from core.moderation.base import ModerationException
|
||||
from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
|
||||
from core.workflow.entities.node_entities import SystemVariable
|
||||
from core.workflow.nodes.base_node import UserFrom
|
||||
from core.workflow.workflow_engine_manager import WorkflowEngineManager
|
||||
from extensions.ext_database import db
|
||||
from models import App, Message, Workflow
|
||||
from models.model import App, Conversation, EndUser, Message
|
||||
from models.workflow import Workflow
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@ -29,12 +31,10 @@ class AdvancedChatAppRunner(AppRunner):
|
||||
AdvancedChat Application Runner
|
||||
"""
|
||||
|
||||
def run(
|
||||
self,
|
||||
application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
queue_manager: AppQueueManager,
|
||||
message: Message,
|
||||
) -> None:
|
||||
def run(self, application_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
queue_manager: AppQueueManager,
|
||||
conversation: Conversation,
|
||||
message: Message) -> None:
|
||||
"""
|
||||
Run application
|
||||
:param application_generate_entity: application generate entity
|
||||
@ -48,43 +48,53 @@ class AdvancedChatAppRunner(AppRunner):
|
||||
|
||||
app_record = db.session.query(App).filter(App.id == app_config.app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError('App not found')
|
||||
raise ValueError("App not found")
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=app_config.workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError('Workflow not initialized')
|
||||
raise ValueError("Workflow not initialized")
|
||||
|
||||
inputs = application_generate_entity.inputs
|
||||
query = application_generate_entity.query
|
||||
files = application_generate_entity.files
|
||||
|
||||
user_id = None
|
||||
if application_generate_entity.invoke_from in [InvokeFrom.WEB_APP, InvokeFrom.SERVICE_API]:
|
||||
end_user = db.session.query(EndUser).filter(EndUser.id == application_generate_entity.user_id).first()
|
||||
if end_user:
|
||||
user_id = end_user.session_id
|
||||
else:
|
||||
user_id = application_generate_entity.user_id
|
||||
|
||||
# moderation
|
||||
if self.handle_input_moderation(
|
||||
queue_manager=queue_manager,
|
||||
app_record=app_record,
|
||||
app_generate_entity=application_generate_entity,
|
||||
inputs=inputs,
|
||||
query=query,
|
||||
message_id=message.id,
|
||||
queue_manager=queue_manager,
|
||||
app_record=app_record,
|
||||
app_generate_entity=application_generate_entity,
|
||||
inputs=inputs,
|
||||
query=query,
|
||||
message_id=message.id
|
||||
):
|
||||
return
|
||||
|
||||
# annotation reply
|
||||
if self.handle_annotation_reply(
|
||||
app_record=app_record,
|
||||
message=message,
|
||||
query=query,
|
||||
queue_manager=queue_manager,
|
||||
app_generate_entity=application_generate_entity,
|
||||
app_record=app_record,
|
||||
message=message,
|
||||
query=query,
|
||||
queue_manager=queue_manager,
|
||||
app_generate_entity=application_generate_entity
|
||||
):
|
||||
return
|
||||
|
||||
db.session.close()
|
||||
|
||||
workflow_callbacks: list[WorkflowCallback] = [
|
||||
WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)
|
||||
]
|
||||
workflow_callbacks: list[WorkflowCallback] = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
|
||||
if bool(os.environ.get('DEBUG', 'False').lower() == 'true'):
|
||||
if bool(os.environ.get("DEBUG", 'False').lower() == 'true'):
|
||||
workflow_callbacks.append(WorkflowLoggingCallback())
|
||||
|
||||
# RUN WORKFLOW
|
||||
@ -96,29 +106,43 @@ class AdvancedChatAppRunner(AppRunner):
|
||||
if application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
|
||||
else UserFrom.END_USER,
|
||||
invoke_from=application_generate_entity.invoke_from,
|
||||
user_inputs=inputs,
|
||||
system_inputs={
|
||||
SystemVariable.QUERY: query,
|
||||
SystemVariable.FILES: files,
|
||||
SystemVariable.CONVERSATION_ID: conversation.id,
|
||||
SystemVariable.USER_ID: user_id
|
||||
},
|
||||
callbacks=workflow_callbacks,
|
||||
call_depth=application_generate_entity.call_depth,
|
||||
call_depth=application_generate_entity.call_depth
|
||||
)
|
||||
|
||||
def single_iteration_run(
|
||||
self, app_id: str, workflow_id: str, queue_manager: AppQueueManager, inputs: dict, node_id: str, user_id: str
|
||||
) -> None:
|
||||
def single_iteration_run(self, app_id: str, workflow_id: str,
|
||||
queue_manager: AppQueueManager,
|
||||
inputs: dict, node_id: str, user_id: str) -> None:
|
||||
"""
|
||||
Single iteration run
|
||||
"""
|
||||
app_record = db.session.query(App).filter(App.id == app_id).first()
|
||||
app_record: App = db.session.query(App).filter(App.id == app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError('App not found')
|
||||
|
||||
raise ValueError("App not found")
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError('Workflow not initialized')
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)]
|
||||
raise ValueError("Workflow not initialized")
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
|
||||
workflow_engine_manager = WorkflowEngineManager()
|
||||
workflow_engine_manager.single_step_run_iteration_workflow_node(
|
||||
workflow=workflow, node_id=node_id, user_id=user_id, user_inputs=inputs, callbacks=workflow_callbacks
|
||||
workflow=workflow,
|
||||
node_id=node_id,
|
||||
user_id=user_id,
|
||||
user_inputs=inputs,
|
||||
callbacks=workflow_callbacks
|
||||
)
|
||||
|
||||
def get_workflow(self, app_model: App, workflow_id: str) -> Optional[Workflow]:
|
||||
@ -126,25 +150,22 @@ class AdvancedChatAppRunner(AppRunner):
|
||||
Get workflow
|
||||
"""
|
||||
# fetch workflow by workflow_id
|
||||
workflow = (
|
||||
db.session.query(Workflow)
|
||||
.filter(
|
||||
Workflow.tenant_id == app_model.tenant_id, Workflow.app_id == app_model.id, Workflow.id == workflow_id
|
||||
)
|
||||
.first()
|
||||
)
|
||||
workflow = db.session.query(Workflow).filter(
|
||||
Workflow.tenant_id == app_model.tenant_id,
|
||||
Workflow.app_id == app_model.id,
|
||||
Workflow.id == workflow_id
|
||||
).first()
|
||||
|
||||
# return workflow
|
||||
return workflow
|
||||
|
||||
def handle_input_moderation(
|
||||
self,
|
||||
queue_manager: AppQueueManager,
|
||||
app_record: App,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
inputs: Mapping[str, Any],
|
||||
query: str,
|
||||
message_id: str,
|
||||
self, queue_manager: AppQueueManager,
|
||||
app_record: App,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
inputs: Mapping[str, Any],
|
||||
query: str,
|
||||
message_id: str
|
||||
) -> bool:
|
||||
"""
|
||||
Handle input moderation
|
||||
@ -171,20 +192,17 @@ class AdvancedChatAppRunner(AppRunner):
|
||||
queue_manager=queue_manager,
|
||||
text=str(e),
|
||||
stream=app_generate_entity.stream,
|
||||
stopped_by=QueueStopEvent.StopBy.INPUT_MODERATION,
|
||||
stopped_by=QueueStopEvent.StopBy.INPUT_MODERATION
|
||||
)
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def handle_annotation_reply(
|
||||
self,
|
||||
app_record: App,
|
||||
message: Message,
|
||||
query: str,
|
||||
queue_manager: AppQueueManager,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity,
|
||||
) -> bool:
|
||||
def handle_annotation_reply(self, app_record: App,
|
||||
message: Message,
|
||||
query: str,
|
||||
queue_manager: AppQueueManager,
|
||||
app_generate_entity: AdvancedChatAppGenerateEntity) -> bool:
|
||||
"""
|
||||
Handle annotation reply
|
||||
:param app_record: app record
|
||||
@ -199,27 +217,29 @@ class AdvancedChatAppRunner(AppRunner):
|
||||
message=message,
|
||||
query=query,
|
||||
user_id=app_generate_entity.user_id,
|
||||
invoke_from=app_generate_entity.invoke_from,
|
||||
invoke_from=app_generate_entity.invoke_from
|
||||
)
|
||||
|
||||
if annotation_reply:
|
||||
queue_manager.publish(
|
||||
QueueAnnotationReplyEvent(message_annotation_id=annotation_reply.id), PublishFrom.APPLICATION_MANAGER
|
||||
QueueAnnotationReplyEvent(message_annotation_id=annotation_reply.id),
|
||||
PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
|
||||
self._stream_output(
|
||||
queue_manager=queue_manager,
|
||||
text=annotation_reply.content,
|
||||
stream=app_generate_entity.stream,
|
||||
stopped_by=QueueStopEvent.StopBy.ANNOTATION_REPLY,
|
||||
stopped_by=QueueStopEvent.StopBy.ANNOTATION_REPLY
|
||||
)
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
def _stream_output(
|
||||
self, queue_manager: AppQueueManager, text: str, stream: bool, stopped_by: QueueStopEvent.StopBy
|
||||
) -> None:
|
||||
def _stream_output(self, queue_manager: AppQueueManager,
|
||||
text: str,
|
||||
stream: bool,
|
||||
stopped_by: QueueStopEvent.StopBy) -> None:
|
||||
"""
|
||||
Direct output
|
||||
:param queue_manager: application queue manager
|
||||
@ -230,10 +250,21 @@ class AdvancedChatAppRunner(AppRunner):
|
||||
if stream:
|
||||
index = 0
|
||||
for token in text:
|
||||
queue_manager.publish(QueueTextChunkEvent(text=token), PublishFrom.APPLICATION_MANAGER)
|
||||
queue_manager.publish(
|
||||
QueueTextChunkEvent(
|
||||
text=token
|
||||
), PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
index += 1
|
||||
time.sleep(0.01)
|
||||
else:
|
||||
queue_manager.publish(QueueTextChunkEvent(text=text), PublishFrom.APPLICATION_MANAGER)
|
||||
queue_manager.publish(
|
||||
QueueTextChunkEvent(
|
||||
text=text
|
||||
), PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
|
||||
queue_manager.publish(QueueStopEvent(stopped_by=stopped_by), PublishFrom.APPLICATION_MANAGER)
|
||||
queue_manager.publish(
|
||||
QueueStopEvent(stopped_by=stopped_by),
|
||||
PublishFrom.APPLICATION_MANAGER
|
||||
)
|
||||
|
||||
@ -4,7 +4,6 @@ import time
|
||||
from collections.abc import Generator
|
||||
from typing import Any, Optional, Union, cast
|
||||
|
||||
import contexts
|
||||
from constants.tts_auto_play_timeout import TTS_AUTO_PLAY_TIMEOUT, TTS_AUTO_PLAY_YIELD_CPU_TIME
|
||||
from core.app.apps.advanced_chat.app_generator_tts_publisher import AppGeneratorTTSPublisher, AudioTrunk
|
||||
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
|
||||
@ -48,8 +47,7 @@ from core.file.file_obj import FileVar
|
||||
from core.model_runtime.entities.llm_entities import LLMUsage
|
||||
from core.model_runtime.utils.encoders import jsonable_encoder
|
||||
from core.ops.ops_trace_manager import TraceQueueManager
|
||||
from core.workflow.entities.node_entities import NodeType
|
||||
from core.workflow.enums import SystemVariableKey
|
||||
from core.workflow.entities.node_entities import NodeType, SystemVariable
|
||||
from core.workflow.nodes.answer.answer_node import AnswerNode
|
||||
from core.workflow.nodes.answer.entities import TextGenerateRouteChunk, VarGenerateRouteChunk
|
||||
from events.message_event import message_was_created
|
||||
@ -73,8 +71,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
||||
_application_generate_entity: AdvancedChatAppGenerateEntity
|
||||
_workflow: Workflow
|
||||
_user: Union[Account, EndUser]
|
||||
# Deprecated
|
||||
_workflow_system_variables: dict[SystemVariableKey, Any]
|
||||
_workflow_system_variables: dict[SystemVariable, Any]
|
||||
_iteration_nested_relations: dict[str, list[str]]
|
||||
|
||||
def __init__(
|
||||
@ -84,7 +81,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
||||
conversation: Conversation,
|
||||
message: Message,
|
||||
user: Union[Account, EndUser],
|
||||
stream: bool,
|
||||
stream: bool
|
||||
) -> None:
|
||||
"""
|
||||
Initialize AdvancedChatAppGenerateTaskPipeline.
|
||||
@ -106,12 +103,11 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
||||
self._workflow = workflow
|
||||
self._conversation = conversation
|
||||
self._message = message
|
||||
# Deprecated
|
||||
self._workflow_system_variables = {
|
||||
SystemVariableKey.QUERY: message.query,
|
||||
SystemVariableKey.FILES: application_generate_entity.files,
|
||||
SystemVariableKey.CONVERSATION_ID: conversation.id,
|
||||
SystemVariableKey.USER_ID: user_id,
|
||||
SystemVariable.QUERY: message.query,
|
||||
SystemVariable.FILES: application_generate_entity.files,
|
||||
SystemVariable.CONVERSATION_ID: conversation.id,
|
||||
SystemVariable.USER_ID: user_id
|
||||
}
|
||||
|
||||
self._task_state = AdvancedChatTaskState(
|
||||
@ -249,7 +245,8 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
||||
"""
|
||||
for message in self._queue_manager.listen():
|
||||
if (message.event
|
||||
and getattr(message.event, 'metadata', None)
|
||||
and hasattr(message.event, 'metadata')
|
||||
and message.event.metadata
|
||||
and message.event.metadata.get('is_answer_previous_node', False)
|
||||
and publisher):
|
||||
publisher.publish(message=message)
|
||||
@ -616,9 +613,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
|
||||
|
||||
if route_chunk_node_id == 'sys':
|
||||
# system variable
|
||||
value = contexts.workflow_variable_pool.get().get(value_selector)
|
||||
if value:
|
||||
value = value.text
|
||||
value = self._workflow_system_variables.get(SystemVariable.value_of(value_selector[1]))
|
||||
elif route_chunk_node_id in self._iteration_nested_relations:
|
||||
# it's a iteration variable
|
||||
if not self._iteration_state or route_chunk_node_id not in self._iteration_state.current_iterations:
|
||||
|
||||
@ -1,7 +1,7 @@
|
||||
from collections.abc import Mapping
|
||||
from typing import Any, Optional
|
||||
|
||||
from core.app.app_config.entities import AppConfig, VariableEntity, VariableEntityType
|
||||
from core.app.app_config.entities import AppConfig, VariableEntity
|
||||
|
||||
|
||||
class BaseAppGenerator:
|
||||
@ -9,29 +9,29 @@ class BaseAppGenerator:
|
||||
user_inputs = user_inputs or {}
|
||||
# Filter input variables from form configuration, handle required fields, default values, and option values
|
||||
variables = app_config.variables
|
||||
filtered_inputs = {var.variable: self._validate_input(inputs=user_inputs, var=var) for var in variables}
|
||||
filtered_inputs = {var.name: self._validate_input(inputs=user_inputs, var=var) for var in variables}
|
||||
filtered_inputs = {k: self._sanitize_value(v) for k, v in filtered_inputs.items()}
|
||||
return filtered_inputs
|
||||
|
||||
def _validate_input(self, *, inputs: Mapping[str, Any], var: VariableEntity):
|
||||
user_input_value = inputs.get(var.variable)
|
||||
user_input_value = inputs.get(var.name)
|
||||
if var.required and not user_input_value:
|
||||
raise ValueError(f'{var.variable} is required in input form')
|
||||
raise ValueError(f'{var.name} is required in input form')
|
||||
if not var.required and not user_input_value:
|
||||
# TODO: should we return None here if the default value is None?
|
||||
return var.default or ''
|
||||
if (
|
||||
var.type
|
||||
in (
|
||||
VariableEntityType.TEXT_INPUT,
|
||||
VariableEntityType.SELECT,
|
||||
VariableEntityType.PARAGRAPH,
|
||||
VariableEntity.Type.TEXT_INPUT,
|
||||
VariableEntity.Type.SELECT,
|
||||
VariableEntity.Type.PARAGRAPH,
|
||||
)
|
||||
and user_input_value
|
||||
and not isinstance(user_input_value, str)
|
||||
):
|
||||
raise ValueError(f"(type '{var.type}') {var.variable} in input form must be a string")
|
||||
if var.type == VariableEntityType.NUMBER and isinstance(user_input_value, str):
|
||||
raise ValueError(f"(type '{var.type}') {var.name} in input form must be a string")
|
||||
if var.type == VariableEntity.Type.NUMBER and isinstance(user_input_value, str):
|
||||
# may raise ValueError if user_input_value is not a valid number
|
||||
try:
|
||||
if '.' in user_input_value:
|
||||
@ -39,14 +39,14 @@ class BaseAppGenerator:
|
||||
else:
|
||||
return int(user_input_value)
|
||||
except ValueError:
|
||||
raise ValueError(f"{var.variable} in input form must be a valid number")
|
||||
if var.type == VariableEntityType.SELECT:
|
||||
raise ValueError(f"{var.name} in input form must be a valid number")
|
||||
if var.type == VariableEntity.Type.SELECT:
|
||||
options = var.options or []
|
||||
if user_input_value not in options:
|
||||
raise ValueError(f'{var.variable} in input form must be one of the following: {options}')
|
||||
elif var.type in (VariableEntityType.TEXT_INPUT, VariableEntityType.PARAGRAPH):
|
||||
raise ValueError(f'{var.name} in input form must be one of the following: {options}')
|
||||
elif var.type in (VariableEntity.Type.TEXT_INPUT, VariableEntity.Type.PARAGRAPH):
|
||||
if var.max_length and user_input_value and len(user_input_value) > var.max_length:
|
||||
raise ValueError(f'{var.variable} in input form must be less than {var.max_length} characters')
|
||||
raise ValueError(f'{var.name} in input form must be less than {var.max_length} characters')
|
||||
|
||||
return user_input_value
|
||||
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
import time
|
||||
from collections.abc import Generator
|
||||
from typing import TYPE_CHECKING, Optional, Union
|
||||
from typing import Optional, Union
|
||||
|
||||
from core.app.app_config.entities import ExternalDataVariableEntity, PromptTemplateEntity
|
||||
from core.app.apps.base_app_queue_manager import AppQueueManager, PublishFrom
|
||||
@ -14,6 +14,7 @@ from core.app.entities.queue_entities import QueueAgentMessageEvent, QueueLLMChu
|
||||
from core.app.features.annotation_reply.annotation_reply import AnnotationReplyFeature
|
||||
from core.app.features.hosting_moderation.hosting_moderation import HostingModerationFeature
|
||||
from core.external_data_tool.external_data_fetch import ExternalDataFetch
|
||||
from core.file.file_obj import FileVar
|
||||
from core.memory.token_buffer_memory import TokenBufferMemory
|
||||
from core.model_manager import ModelInstance
|
||||
from core.model_runtime.entities.llm_entities import LLMResult, LLMResultChunk, LLMResultChunkDelta, LLMUsage
|
||||
@ -26,16 +27,13 @@ from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, Comp
|
||||
from core.prompt.simple_prompt_transform import ModelMode, SimplePromptTransform
|
||||
from models.model import App, AppMode, Message, MessageAnnotation
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from core.file.file_obj import FileVar
|
||||
|
||||
|
||||
class AppRunner:
|
||||
def get_pre_calculate_rest_tokens(self, app_record: App,
|
||||
model_config: ModelConfigWithCredentialsEntity,
|
||||
prompt_template_entity: PromptTemplateEntity,
|
||||
inputs: dict[str, str],
|
||||
files: list["FileVar"],
|
||||
files: list[FileVar],
|
||||
query: Optional[str] = None) -> int:
|
||||
"""
|
||||
Get pre calculate rest tokens
|
||||
@ -128,7 +126,7 @@ class AppRunner:
|
||||
model_config: ModelConfigWithCredentialsEntity,
|
||||
prompt_template_entity: PromptTemplateEntity,
|
||||
inputs: dict[str, str],
|
||||
files: list["FileVar"],
|
||||
files: list[FileVar],
|
||||
query: Optional[str] = None,
|
||||
context: Optional[str] = None,
|
||||
memory: Optional[TokenBufferMemory] = None) \
|
||||
@ -256,7 +254,6 @@ class AppRunner:
|
||||
:param invoke_result: invoke result
|
||||
:param queue_manager: application queue manager
|
||||
:param stream: stream
|
||||
:param agent: agent
|
||||
:return:
|
||||
"""
|
||||
if not stream:
|
||||
@ -279,7 +276,6 @@ class AppRunner:
|
||||
Handle invoke result direct
|
||||
:param invoke_result: invoke result
|
||||
:param queue_manager: application queue manager
|
||||
:param agent: agent
|
||||
:return:
|
||||
"""
|
||||
queue_manager.publish(
|
||||
@ -295,7 +291,6 @@ class AppRunner:
|
||||
Handle invoke result
|
||||
:param invoke_result: invoke result
|
||||
:param queue_manager: application queue manager
|
||||
:param agent: agent
|
||||
:return:
|
||||
"""
|
||||
model = None
|
||||
@ -371,7 +366,7 @@ class AppRunner:
|
||||
message_id=message_id,
|
||||
trace_manager=app_generate_entity.trace_manager
|
||||
)
|
||||
|
||||
|
||||
def check_hosting_moderation(self, application_generate_entity: EasyUIBasedAppGenerateEntity,
|
||||
queue_manager: AppQueueManager,
|
||||
prompt_messages: list[PromptMessage]) -> bool:
|
||||
@ -423,7 +418,7 @@ class AppRunner:
|
||||
inputs=inputs,
|
||||
query=query
|
||||
)
|
||||
|
||||
|
||||
def query_app_annotations_to_reply(self, app_record: App,
|
||||
message: Message,
|
||||
query: str,
|
||||
|
||||
@ -1,7 +1,6 @@
|
||||
import json
|
||||
import logging
|
||||
from collections.abc import Generator
|
||||
from datetime import datetime, timezone
|
||||
from typing import Optional, Union
|
||||
|
||||
from sqlalchemy import and_
|
||||
@ -37,17 +36,17 @@ logger = logging.getLogger(__name__)
|
||||
class MessageBasedAppGenerator(BaseAppGenerator):
|
||||
|
||||
def _handle_response(
|
||||
self, application_generate_entity: Union[
|
||||
ChatAppGenerateEntity,
|
||||
CompletionAppGenerateEntity,
|
||||
AgentChatAppGenerateEntity,
|
||||
AdvancedChatAppGenerateEntity
|
||||
],
|
||||
queue_manager: AppQueueManager,
|
||||
conversation: Conversation,
|
||||
message: Message,
|
||||
user: Union[Account, EndUser],
|
||||
stream: bool = False,
|
||||
self, application_generate_entity: Union[
|
||||
ChatAppGenerateEntity,
|
||||
CompletionAppGenerateEntity,
|
||||
AgentChatAppGenerateEntity,
|
||||
AdvancedChatAppGenerateEntity
|
||||
],
|
||||
queue_manager: AppQueueManager,
|
||||
conversation: Conversation,
|
||||
message: Message,
|
||||
user: Union[Account, EndUser],
|
||||
stream: bool = False,
|
||||
) -> Union[
|
||||
ChatbotAppBlockingResponse,
|
||||
CompletionAppBlockingResponse,
|
||||
@ -139,7 +138,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
|
||||
"""
|
||||
Initialize generate records
|
||||
:param application_generate_entity: application generate entity
|
||||
:conversation conversation
|
||||
:return:
|
||||
"""
|
||||
app_config = application_generate_entity.app_config
|
||||
@ -194,9 +192,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
|
||||
db.session.add(conversation)
|
||||
db.session.commit()
|
||||
db.session.refresh(conversation)
|
||||
else:
|
||||
conversation.updated_at = datetime.now(timezone.utc).replace(tzinfo=None)
|
||||
db.session.commit()
|
||||
|
||||
message = Message(
|
||||
app_id=app_config.app_id,
|
||||
@ -263,7 +258,7 @@ class MessageBasedAppGenerator(BaseAppGenerator):
|
||||
|
||||
return introduction
|
||||
|
||||
def _get_conversation(self, conversation_id: str):
|
||||
def _get_conversation(self, conversation_id: str) -> Conversation:
|
||||
"""
|
||||
Get conversation by conversation id
|
||||
:param conversation_id: conversation id
|
||||
@ -275,9 +270,6 @@ class MessageBasedAppGenerator(BaseAppGenerator):
|
||||
.first()
|
||||
)
|
||||
|
||||
if not conversation:
|
||||
raise ConversationNotExistsError()
|
||||
|
||||
return conversation
|
||||
|
||||
def _get_message(self, message_id: str) -> Message:
|
||||
|
||||
@ -11,8 +11,7 @@ from core.app.entities.app_invoke_entities import (
|
||||
WorkflowAppGenerateEntity,
|
||||
)
|
||||
from core.workflow.callbacks.base_workflow_callback import WorkflowCallback
|
||||
from core.workflow.entities.variable_pool import VariablePool
|
||||
from core.workflow.enums import SystemVariableKey
|
||||
from core.workflow.entities.node_entities import SystemVariable
|
||||
from core.workflow.nodes.base_node import UserFrom
|
||||
from core.workflow.workflow_engine_manager import WorkflowEngineManager
|
||||
from extensions.ext_database import db
|
||||
@ -27,7 +26,8 @@ class WorkflowAppRunner:
|
||||
Workflow Application Runner
|
||||
"""
|
||||
|
||||
def run(self, application_generate_entity: WorkflowAppGenerateEntity, queue_manager: AppQueueManager) -> None:
|
||||
def run(self, application_generate_entity: WorkflowAppGenerateEntity,
|
||||
queue_manager: AppQueueManager) -> None:
|
||||
"""
|
||||
Run application
|
||||
:param application_generate_entity: application generate entity
|
||||
@ -47,36 +47,25 @@ class WorkflowAppRunner:
|
||||
|
||||
app_record = db.session.query(App).filter(App.id == app_config.app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError('App not found')
|
||||
raise ValueError("App not found")
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=app_config.workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError('Workflow not initialized')
|
||||
raise ValueError("Workflow not initialized")
|
||||
|
||||
inputs = application_generate_entity.inputs
|
||||
files = application_generate_entity.files
|
||||
|
||||
db.session.close()
|
||||
|
||||
workflow_callbacks: list[WorkflowCallback] = [
|
||||
WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)
|
||||
]
|
||||
workflow_callbacks: list[WorkflowCallback] = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
|
||||
if bool(os.environ.get('DEBUG', 'False').lower() == 'true'):
|
||||
if bool(os.environ.get("DEBUG", 'False').lower() == 'true'):
|
||||
workflow_callbacks.append(WorkflowLoggingCallback())
|
||||
|
||||
# Create a variable pool.
|
||||
system_inputs = {
|
||||
SystemVariableKey.FILES: files,
|
||||
SystemVariableKey.USER_ID: user_id,
|
||||
}
|
||||
variable_pool = VariablePool(
|
||||
system_variables=system_inputs,
|
||||
user_inputs=inputs,
|
||||
environment_variables=workflow.environment_variables,
|
||||
conversation_variables=[],
|
||||
)
|
||||
|
||||
# RUN WORKFLOW
|
||||
workflow_engine_manager = WorkflowEngineManager()
|
||||
workflow_engine_manager.run_workflow(
|
||||
@ -86,33 +75,44 @@ class WorkflowAppRunner:
|
||||
if application_generate_entity.invoke_from in [InvokeFrom.EXPLORE, InvokeFrom.DEBUGGER]
|
||||
else UserFrom.END_USER,
|
||||
invoke_from=application_generate_entity.invoke_from,
|
||||
user_inputs=inputs,
|
||||
system_inputs={
|
||||
SystemVariable.FILES: files,
|
||||
SystemVariable.USER_ID: user_id
|
||||
},
|
||||
callbacks=workflow_callbacks,
|
||||
call_depth=application_generate_entity.call_depth,
|
||||
variable_pool=variable_pool,
|
||||
call_depth=application_generate_entity.call_depth
|
||||
)
|
||||
|
||||
def single_iteration_run(
|
||||
self, app_id: str, workflow_id: str, queue_manager: AppQueueManager, inputs: dict, node_id: str, user_id: str
|
||||
) -> None:
|
||||
def single_iteration_run(self, app_id: str, workflow_id: str,
|
||||
queue_manager: AppQueueManager,
|
||||
inputs: dict, node_id: str, user_id: str) -> None:
|
||||
"""
|
||||
Single iteration run
|
||||
"""
|
||||
app_record = db.session.query(App).filter(App.id == app_id).first()
|
||||
app_record: App = db.session.query(App).filter(App.id == app_id).first()
|
||||
if not app_record:
|
||||
raise ValueError('App not found')
|
||||
|
||||
raise ValueError("App not found")
|
||||
|
||||
if not app_record.workflow_id:
|
||||
raise ValueError('Workflow not initialized')
|
||||
raise ValueError("Workflow not initialized")
|
||||
|
||||
workflow = self.get_workflow(app_model=app_record, workflow_id=workflow_id)
|
||||
if not workflow:
|
||||
raise ValueError('Workflow not initialized')
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(queue_manager=queue_manager, workflow=workflow)]
|
||||
raise ValueError("Workflow not initialized")
|
||||
|
||||
workflow_callbacks = [WorkflowEventTriggerCallback(
|
||||
queue_manager=queue_manager,
|
||||
workflow=workflow
|
||||
)]
|
||||
|
||||
workflow_engine_manager = WorkflowEngineManager()
|
||||
workflow_engine_manager.single_step_run_iteration_workflow_node(
|
||||
workflow=workflow, node_id=node_id, user_id=user_id, user_inputs=inputs, callbacks=workflow_callbacks
|
||||
workflow=workflow,
|
||||
node_id=node_id,
|
||||
user_id=user_id,
|
||||
user_inputs=inputs,
|
||||
callbacks=workflow_callbacks
|
||||
)
|
||||
|
||||
def get_workflow(self, app_model: App, workflow_id: str) -> Optional[Workflow]:
|
||||
@ -120,13 +120,11 @@ class WorkflowAppRunner:
|
||||
Get workflow
|
||||
"""
|
||||
# fetch workflow by workflow_id
|
||||
workflow = (
|
||||
db.session.query(Workflow)
|
||||
.filter(
|
||||
Workflow.tenant_id == app_model.tenant_id, Workflow.app_id == app_model.id, Workflow.id == workflow_id
|
||||
)
|
||||
.first()
|
||||
)
|
||||
workflow = db.session.query(Workflow).filter(
|
||||
Workflow.tenant_id == app_model.tenant_id,
|
||||
Workflow.app_id == app_model.id,
|
||||
Workflow.id == workflow_id
|
||||
).first()
|
||||
|
||||
# return workflow
|
||||
return workflow
|
||||
|
||||
@ -42,8 +42,7 @@ from core.app.entities.task_entities import (
|
||||
from core.app.task_pipeline.based_generate_task_pipeline import BasedGenerateTaskPipeline
|
||||
from core.app.task_pipeline.workflow_cycle_manage import WorkflowCycleManage
|
||||
from core.ops.ops_trace_manager import TraceQueueManager
|
||||
from core.workflow.entities.node_entities import NodeType
|
||||
from core.workflow.enums import SystemVariableKey
|
||||
from core.workflow.entities.node_entities import NodeType, SystemVariable
|
||||
from core.workflow.nodes.end.end_node import EndNode
|
||||
from extensions.ext_database import db
|
||||
from models.account import Account
|
||||
@ -67,7 +66,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
|
||||
_user: Union[Account, EndUser]
|
||||
_task_state: WorkflowTaskState
|
||||
_application_generate_entity: WorkflowAppGenerateEntity
|
||||
_workflow_system_variables: dict[SystemVariableKey, Any]
|
||||
_workflow_system_variables: dict[SystemVariable, Any]
|
||||
_iteration_nested_relations: dict[str, list[str]]
|
||||
|
||||
def __init__(self, application_generate_entity: WorkflowAppGenerateEntity,
|
||||
@ -92,8 +91,8 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
|
||||
|
||||
self._workflow = workflow
|
||||
self._workflow_system_variables = {
|
||||
SystemVariableKey.FILES: application_generate_entity.files,
|
||||
SystemVariableKey.USER_ID: user_id
|
||||
SystemVariable.FILES: application_generate_entity.files,
|
||||
SystemVariable.USER_ID: user_id
|
||||
}
|
||||
|
||||
self._task_state = WorkflowTaskState(
|
||||
@ -520,7 +519,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
|
||||
"""
|
||||
nodes = graph.get('nodes')
|
||||
|
||||
iteration_ids = [node.get('id') for node in nodes
|
||||
iteration_ids = [node.get('id') for node in nodes
|
||||
if node.get('data', {}).get('type') in [
|
||||
NodeType.ITERATION.value,
|
||||
NodeType.LOOP.value,
|
||||
@ -531,3 +530,4 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
|
||||
node.get('id') for node in nodes if node.get('data', {}).get('iteration_id') == iteration_id
|
||||
] for iteration_id in iteration_ids
|
||||
}
|
||||
|
||||
@ -166,4 +166,4 @@ class WorkflowAppGenerateEntity(AppGenerateEntity):
|
||||
node_id: str
|
||||
inputs: dict
|
||||
|
||||
single_iteration_run: Optional[SingleIterationRunEntity] = None
|
||||
single_iteration_run: Optional[SingleIterationRunEntity] = None
|
||||
@ -1,7 +1,7 @@
|
||||
from .segment_group import SegmentGroup
|
||||
from .segments import (
|
||||
ArrayAnySegment,
|
||||
ArraySegment,
|
||||
FileSegment,
|
||||
FloatSegment,
|
||||
IntegerSegment,
|
||||
NoneSegment,
|
||||
@ -12,9 +12,11 @@ from .segments import (
|
||||
from .types import SegmentType
|
||||
from .variables import (
|
||||
ArrayAnyVariable,
|
||||
ArrayFileVariable,
|
||||
ArrayNumberVariable,
|
||||
ArrayObjectVariable,
|
||||
ArrayStringVariable,
|
||||
FileVariable,
|
||||
FloatVariable,
|
||||
IntegerVariable,
|
||||
NoneVariable,
|
||||
@ -29,6 +31,7 @@ __all__ = [
|
||||
'FloatVariable',
|
||||
'ObjectVariable',
|
||||
'SecretVariable',
|
||||
'FileVariable',
|
||||
'StringVariable',
|
||||
'ArrayAnyVariable',
|
||||
'Variable',
|
||||
@ -41,9 +44,10 @@ __all__ = [
|
||||
'FloatSegment',
|
||||
'ObjectSegment',
|
||||
'ArrayAnySegment',
|
||||
'FileSegment',
|
||||
'StringSegment',
|
||||
'ArrayStringVariable',
|
||||
'ArrayNumberVariable',
|
||||
'ArrayObjectVariable',
|
||||
'ArraySegment',
|
||||
'ArrayFileVariable',
|
||||
]
|
||||
|
||||
@ -1,2 +0,0 @@
|
||||
class VariableError(Exception):
|
||||
pass
|
||||
@ -1,11 +1,11 @@
|
||||
from collections.abc import Mapping
|
||||
from typing import Any
|
||||
|
||||
from configs import dify_config
|
||||
from core.file.file_obj import FileVar
|
||||
|
||||
from .exc import VariableError
|
||||
from .segments import (
|
||||
ArrayAnySegment,
|
||||
FileSegment,
|
||||
FloatSegment,
|
||||
IntegerSegment,
|
||||
NoneSegment,
|
||||
@ -15,9 +15,11 @@ from .segments import (
|
||||
)
|
||||
from .types import SegmentType
|
||||
from .variables import (
|
||||
ArrayFileVariable,
|
||||
ArrayNumberVariable,
|
||||
ArrayObjectVariable,
|
||||
ArrayStringVariable,
|
||||
FileVariable,
|
||||
FloatVariable,
|
||||
IntegerVariable,
|
||||
ObjectVariable,
|
||||
@ -27,37 +29,39 @@ from .variables import (
|
||||
)
|
||||
|
||||
|
||||
def build_variable_from_mapping(mapping: Mapping[str, Any], /) -> Variable:
|
||||
if (value_type := mapping.get('value_type')) is None:
|
||||
raise VariableError('missing value type')
|
||||
if not mapping.get('name'):
|
||||
raise VariableError('missing name')
|
||||
if (value := mapping.get('value')) is None:
|
||||
raise VariableError('missing value')
|
||||
def build_variable_from_mapping(m: Mapping[str, Any], /) -> Variable:
|
||||
if (value_type := m.get('value_type')) is None:
|
||||
raise ValueError('missing value type')
|
||||
if not m.get('name'):
|
||||
raise ValueError('missing name')
|
||||
if (value := m.get('value')) is None:
|
||||
raise ValueError('missing value')
|
||||
match value_type:
|
||||
case SegmentType.STRING:
|
||||
result = StringVariable.model_validate(mapping)
|
||||
return StringVariable.model_validate(m)
|
||||
case SegmentType.SECRET:
|
||||
result = SecretVariable.model_validate(mapping)
|
||||
return SecretVariable.model_validate(m)
|
||||
case SegmentType.NUMBER if isinstance(value, int):
|
||||
result = IntegerVariable.model_validate(mapping)
|
||||
return IntegerVariable.model_validate(m)
|
||||
case SegmentType.NUMBER if isinstance(value, float):
|
||||
result = FloatVariable.model_validate(mapping)
|
||||
return FloatVariable.model_validate(m)
|
||||
case SegmentType.NUMBER if not isinstance(value, float | int):
|
||||
raise VariableError(f'invalid number value {value}')
|
||||
raise ValueError(f'invalid number value {value}')
|
||||
case SegmentType.FILE:
|
||||
return FileVariable.model_validate(m)
|
||||
case SegmentType.OBJECT if isinstance(value, dict):
|
||||
result = ObjectVariable.model_validate(mapping)
|
||||
return ObjectVariable.model_validate(
|
||||
{**m, 'value': {k: build_variable_from_mapping(v) for k, v in value.items()}}
|
||||
)
|
||||
case SegmentType.ARRAY_STRING if isinstance(value, list):
|
||||
result = ArrayStringVariable.model_validate(mapping)
|
||||
return ArrayStringVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
case SegmentType.ARRAY_NUMBER if isinstance(value, list):
|
||||
result = ArrayNumberVariable.model_validate(mapping)
|
||||
return ArrayNumberVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
case SegmentType.ARRAY_OBJECT if isinstance(value, list):
|
||||
result = ArrayObjectVariable.model_validate(mapping)
|
||||
case _:
|
||||
raise VariableError(f'not supported value type {value_type}')
|
||||
if result.size > dify_config.MAX_VARIABLE_SIZE:
|
||||
raise VariableError(f'variable size {result.size} exceeds limit {dify_config.MAX_VARIABLE_SIZE}')
|
||||
return result
|
||||
return ArrayObjectVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
case SegmentType.ARRAY_FILE if isinstance(value, list):
|
||||
return ArrayFileVariable.model_validate({**m, 'value': [build_variable_from_mapping(v) for v in value]})
|
||||
raise ValueError(f'not supported value type {value_type}')
|
||||
|
||||
|
||||
def build_segment(value: Any, /) -> Segment:
|
||||
@ -70,7 +74,12 @@ def build_segment(value: Any, /) -> Segment:
|
||||
if isinstance(value, float):
|
||||
return FloatSegment(value=value)
|
||||
if isinstance(value, dict):
|
||||
# TODO: Limit the depth of the object
|
||||
return ObjectSegment(value=value)
|
||||
if isinstance(value, list):
|
||||
return ArrayAnySegment(value=value)
|
||||
# TODO: Limit the depth of the array
|
||||
elements = [build_segment(v) for v in value]
|
||||
return ArrayAnySegment(value=elements)
|
||||
if isinstance(value, FileVar):
|
||||
return FileSegment(value=value)
|
||||
raise ValueError(f'not supported value {value}')
|
||||
|
||||
@ -1,10 +1,11 @@
|
||||
import json
|
||||
import sys
|
||||
from collections.abc import Mapping, Sequence
|
||||
from typing import Any
|
||||
|
||||
from pydantic import BaseModel, ConfigDict, field_validator
|
||||
|
||||
from core.file.file_obj import FileVar
|
||||
|
||||
from .types import SegmentType
|
||||
|
||||
|
||||
@ -36,10 +37,6 @@ class Segment(BaseModel):
|
||||
def markdown(self) -> str:
|
||||
return str(self.value)
|
||||
|
||||
@property
|
||||
def size(self) -> int:
|
||||
return sys.getsizeof(self.value)
|
||||
|
||||
def to_object(self) -> Any:
|
||||
return self.value
|
||||
|
||||
@ -76,7 +73,14 @@ class IntegerSegment(Segment):
|
||||
value: int
|
||||
|
||||
|
||||
class FileSegment(Segment):
|
||||
value_type: SegmentType = SegmentType.FILE
|
||||
# TODO: embed FileVar in this model.
|
||||
value: FileVar
|
||||
|
||||
@property
|
||||
def markdown(self) -> str:
|
||||
return self.value.to_markdown()
|
||||
|
||||
|
||||
class ObjectSegment(Segment):
|
||||
@ -99,31 +103,32 @@ class ObjectSegment(Segment):
|
||||
class ArraySegment(Segment):
|
||||
@property
|
||||
def markdown(self) -> str:
|
||||
items = []
|
||||
for item in self.value:
|
||||
if hasattr(item, 'to_markdown'):
|
||||
items.append(item.to_markdown())
|
||||
else:
|
||||
items.append(str(item))
|
||||
return '\n'.join(items)
|
||||
return '\n'.join(['- ' + item.markdown for item in self.value])
|
||||
|
||||
def to_object(self):
|
||||
return [v.to_object() for v in self.value]
|
||||
|
||||
|
||||
class ArrayAnySegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_ANY
|
||||
value: Sequence[Any]
|
||||
value: Sequence[Segment]
|
||||
|
||||
|
||||
class ArrayStringSegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_STRING
|
||||
value: Sequence[str]
|
||||
value: Sequence[StringSegment]
|
||||
|
||||
|
||||
class ArrayNumberSegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_NUMBER
|
||||
value: Sequence[float | int]
|
||||
value: Sequence[FloatSegment | IntegerSegment]
|
||||
|
||||
|
||||
class ArrayObjectSegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_OBJECT
|
||||
value: Sequence[Mapping[str, Any]]
|
||||
value: Sequence[ObjectSegment]
|
||||
|
||||
|
||||
class ArrayFileSegment(ArraySegment):
|
||||
value_type: SegmentType = SegmentType.ARRAY_FILE
|
||||
value: Sequence[FileSegment]
|
||||
|
||||
@ -10,6 +10,8 @@ class SegmentType(str, Enum):
|
||||
ARRAY_STRING = 'array[string]'
|
||||
ARRAY_NUMBER = 'array[number]'
|
||||
ARRAY_OBJECT = 'array[object]'
|
||||
ARRAY_FILE = 'array[file]'
|
||||
OBJECT = 'object'
|
||||
FILE = 'file'
|
||||
|
||||
GROUP = 'group'
|
||||
|
||||
@ -4,9 +4,11 @@ from core.helper import encrypter
|
||||
|
||||
from .segments import (
|
||||
ArrayAnySegment,
|
||||
ArrayFileSegment,
|
||||
ArrayNumberSegment,
|
||||
ArrayObjectSegment,
|
||||
ArrayStringSegment,
|
||||
FileSegment,
|
||||
FloatSegment,
|
||||
IntegerSegment,
|
||||
NoneSegment,
|
||||
@ -42,6 +44,10 @@ class IntegerVariable(IntegerSegment, Variable):
|
||||
pass
|
||||
|
||||
|
||||
class FileVariable(FileSegment, Variable):
|
||||
pass
|
||||
|
||||
|
||||
class ObjectVariable(ObjectSegment, Variable):
|
||||
pass
|
||||
|
||||
@ -62,6 +68,9 @@ class ArrayObjectVariable(ArrayObjectSegment, Variable):
|
||||
pass
|
||||
|
||||
|
||||
class ArrayFileVariable(ArrayFileSegment, Variable):
|
||||
pass
|
||||
|
||||
|
||||
class SecretVariable(StringVariable):
|
||||
value_type: SegmentType = SegmentType.SECRET
|
||||
|
||||
@ -2,7 +2,7 @@ from typing import Any, Union
|
||||
|
||||
from core.app.entities.app_invoke_entities import AdvancedChatAppGenerateEntity, WorkflowAppGenerateEntity
|
||||
from core.app.entities.task_entities import AdvancedChatTaskState, WorkflowTaskState
|
||||
from core.workflow.enums import SystemVariableKey
|
||||
from core.workflow.entities.node_entities import SystemVariable
|
||||
from models.account import Account
|
||||
from models.model import EndUser
|
||||
from models.workflow import Workflow
|
||||
@ -13,4 +13,4 @@ class WorkflowCycleStateManager:
|
||||
_workflow: Workflow
|
||||
_user: Union[Account, EndUser]
|
||||
_task_state: Union[AdvancedChatTaskState, WorkflowTaskState]
|
||||
_workflow_system_variables: dict[SystemVariableKey, Any]
|
||||
_workflow_system_variables: dict[SystemVariable, Any]
|
||||
@ -1,19 +1,14 @@
|
||||
import enum
|
||||
from typing import Any, Optional
|
||||
from typing import Optional
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.app.app_config.entities import FileExtraConfig
|
||||
from core.file.tool_file_parser import ToolFileParser
|
||||
from core.file.upload_file_parser import UploadFileParser
|
||||
from core.model_runtime.entities.message_entities import ImagePromptMessageContent
|
||||
from extensions.ext_database import db
|
||||
|
||||
|
||||
class FileExtraConfig(BaseModel):
|
||||
"""
|
||||
File Upload Entity.
|
||||
"""
|
||||
image_config: Optional[dict[str, Any]] = None
|
||||
from models.model import UploadFile
|
||||
|
||||
|
||||
class FileType(enum.Enum):
|
||||
@ -119,7 +114,6 @@ class FileVar(BaseModel):
|
||||
)
|
||||
|
||||
def _get_data(self, force_url: bool = False) -> Optional[str]:
|
||||
from models.model import UploadFile
|
||||
if self.type == FileType.IMAGE:
|
||||
if self.transfer_method == FileTransferMethod.REMOTE_URL:
|
||||
return self.url
|
||||
|
||||
@ -5,7 +5,8 @@ from urllib.parse import parse_qs, urlparse
|
||||
|
||||
import requests
|
||||
|
||||
from core.file.file_obj import FileBelongsTo, FileExtraConfig, FileTransferMethod, FileType, FileVar
|
||||
from core.app.app_config.entities import FileExtraConfig
|
||||
from core.file.file_obj import FileBelongsTo, FileTransferMethod, FileType, FileVar
|
||||
from extensions.ext_database import db
|
||||
from models.account import Account
|
||||
from models.model import EndUser, MessageFile, UploadFile
|
||||
@ -99,7 +100,7 @@ class MessageFileParser:
|
||||
# return all file objs
|
||||
return new_files
|
||||
|
||||
def transform_message_files(self, files: list[MessageFile], file_extra_config: FileExtraConfig):
|
||||
def transform_message_files(self, files: list[MessageFile], file_extra_config: FileExtraConfig) -> list[FileVar]:
|
||||
"""
|
||||
transform message files
|
||||
|
||||
@ -144,7 +145,7 @@ class MessageFileParser:
|
||||
|
||||
return type_file_objs
|
||||
|
||||
def _to_file_obj(self, file: Union[dict, MessageFile], file_extra_config: FileExtraConfig):
|
||||
def _to_file_obj(self, file: Union[dict, MessageFile], file_extra_config: FileExtraConfig) -> FileVar:
|
||||
"""
|
||||
transform file to file obj
|
||||
|
||||
|
||||
@ -1,13 +1,15 @@
|
||||
import logging
|
||||
import time
|
||||
from enum import Enum
|
||||
from threading import Lock
|
||||
from typing import Optional
|
||||
from typing import Literal, Optional
|
||||
|
||||
from httpx import Timeout, post
|
||||
from httpx import get, post
|
||||
from pydantic import BaseModel
|
||||
from yarl import URL
|
||||
|
||||
from configs import dify_config
|
||||
from core.helper.code_executor.entities import CodeDependency
|
||||
from core.helper.code_executor.javascript.javascript_transformer import NodeJsTemplateTransformer
|
||||
from core.helper.code_executor.jinja2.jinja2_transformer import Jinja2TemplateTransformer
|
||||
from core.helper.code_executor.python3.python3_transformer import Python3TemplateTransformer
|
||||
@ -19,7 +21,7 @@ logger = logging.getLogger(__name__)
|
||||
CODE_EXECUTION_ENDPOINT = dify_config.CODE_EXECUTION_ENDPOINT
|
||||
CODE_EXECUTION_API_KEY = dify_config.CODE_EXECUTION_API_KEY
|
||||
|
||||
CODE_EXECUTION_TIMEOUT = Timeout(connect=10, write=10, read=60, pool=None)
|
||||
CODE_EXECUTION_TIMEOUT = (10, 60)
|
||||
|
||||
class CodeExecutionException(Exception):
|
||||
pass
|
||||
@ -64,7 +66,8 @@ class CodeExecutor:
|
||||
def execute_code(cls,
|
||||
language: CodeLanguage,
|
||||
preload: str,
|
||||
code: str) -> str:
|
||||
code: str,
|
||||
dependencies: Optional[list[CodeDependency]] = None) -> str:
|
||||
"""
|
||||
Execute code
|
||||
:param language: code language
|
||||
@ -84,6 +87,9 @@ class CodeExecutor:
|
||||
'enable_network': True
|
||||
}
|
||||
|
||||
if dependencies:
|
||||
data['dependencies'] = [dependency.model_dump() for dependency in dependencies]
|
||||
|
||||
try:
|
||||
response = post(str(url), json=data, headers=headers, timeout=CODE_EXECUTION_TIMEOUT)
|
||||
if response.status_code == 503:
|
||||
@ -110,10 +116,10 @@ class CodeExecutor:
|
||||
if response.data.error:
|
||||
raise CodeExecutionException(response.data.error)
|
||||
|
||||
return response.data.stdout or ''
|
||||
return response.data.stdout
|
||||
|
||||
@classmethod
|
||||
def execute_workflow_code_template(cls, language: CodeLanguage, code: str, inputs: dict) -> dict:
|
||||
def execute_workflow_code_template(cls, language: CodeLanguage, code: str, inputs: dict, dependencies: Optional[list[CodeDependency]] = None) -> dict:
|
||||
"""
|
||||
Execute code
|
||||
:param language: code language
|
||||
@ -125,12 +131,67 @@ class CodeExecutor:
|
||||
if not template_transformer:
|
||||
raise CodeExecutionException(f'Unsupported language {language}')
|
||||
|
||||
runner, preload = template_transformer.transform_caller(code, inputs)
|
||||
runner, preload, dependencies = template_transformer.transform_caller(code, inputs, dependencies)
|
||||
|
||||
try:
|
||||
response = cls.execute_code(language, preload, runner)
|
||||
response = cls.execute_code(language, preload, runner, dependencies)
|
||||
except CodeExecutionException as e:
|
||||
raise e
|
||||
|
||||
return template_transformer.transform_response(response)
|
||||
|
||||
|
||||
@classmethod
|
||||
def list_dependencies(cls, language: str) -> list[CodeDependency]:
|
||||
if language not in cls.supported_dependencies_languages:
|
||||
return []
|
||||
|
||||
with cls.dependencies_cache_lock:
|
||||
if language in cls.dependencies_cache:
|
||||
# check expiration
|
||||
dependencies = cls.dependencies_cache[language]
|
||||
if dependencies['expiration'] > time.time():
|
||||
return dependencies['data']
|
||||
# remove expired cache
|
||||
del cls.dependencies_cache[language]
|
||||
|
||||
dependencies = cls._get_dependencies(language)
|
||||
with cls.dependencies_cache_lock:
|
||||
cls.dependencies_cache[language] = {
|
||||
'data': dependencies,
|
||||
'expiration': time.time() + 60
|
||||
}
|
||||
|
||||
return dependencies
|
||||
|
||||
@classmethod
|
||||
def _get_dependencies(cls, language: Literal['python3']) -> list[CodeDependency]:
|
||||
"""
|
||||
List dependencies
|
||||
"""
|
||||
url = URL(CODE_EXECUTION_ENDPOINT) / 'v1' / 'sandbox' / 'dependencies'
|
||||
|
||||
headers = {
|
||||
'X-Api-Key': CODE_EXECUTION_API_KEY
|
||||
}
|
||||
|
||||
running_language = cls.code_language_to_running_language.get(language)
|
||||
if isinstance(running_language, Enum):
|
||||
running_language = running_language.value
|
||||
|
||||
data = {
|
||||
'language': running_language,
|
||||
}
|
||||
|
||||
try:
|
||||
response = get(str(url), params=data, headers=headers, timeout=CODE_EXECUTION_TIMEOUT)
|
||||
if response.status_code != 200:
|
||||
raise Exception(f'Failed to list dependencies, got status code {response.status_code}, please check if the sandbox service is running')
|
||||
response = response.json()
|
||||
dependencies = response.get('data', {}).get('dependencies', [])
|
||||
return [
|
||||
CodeDependency(**dependency) for dependency in dependencies
|
||||
if dependency.get('name') not in Python3TemplateTransformer.get_standard_packages()
|
||||
]
|
||||
except Exception as e:
|
||||
logger.exception(f'Failed to list dependencies: {e}')
|
||||
return []
|
||||
@ -2,6 +2,8 @@ from abc import abstractmethod
|
||||
|
||||
from pydantic import BaseModel
|
||||
|
||||
from core.helper.code_executor.code_executor import CodeExecutor
|
||||
|
||||
|
||||
class CodeNodeProvider(BaseModel):
|
||||
@staticmethod
|
||||
@ -21,6 +23,10 @@ class CodeNodeProvider(BaseModel):
|
||||
"""
|
||||
pass
|
||||
|
||||
@classmethod
|
||||
def get_default_available_packages(cls) -> list[dict]:
|
||||
return [p.model_dump() for p in CodeExecutor.list_dependencies(cls.get_language())]
|
||||
|
||||
@classmethod
|
||||
def get_default_config(cls) -> dict:
|
||||
return {
|
||||
@ -44,5 +50,6 @@ class CodeNodeProvider(BaseModel):
|
||||
"children": None
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"available_dependencies": cls.get_default_available_packages(),
|
||||
}
|
||||
|
||||
6
api/core/helper/code_executor/entities.py
Normal file
6
api/core/helper/code_executor/entities.py
Normal file
@ -0,0 +1,6 @@
|
||||
from pydantic import BaseModel
|
||||
|
||||
|
||||
class CodeDependency(BaseModel):
|
||||
name: str
|
||||
version: str
|
||||
@ -3,7 +3,7 @@ from core.helper.code_executor.code_executor import CodeExecutor, CodeLanguage
|
||||
|
||||
class Jinja2Formatter:
|
||||
@classmethod
|
||||
def format(cls, template: str, inputs: dict) -> str:
|
||||
def format(cls, template: str, inputs: str) -> str:
|
||||
"""
|
||||
Format template
|
||||
:param template: template
|
||||
|
||||
@ -1,9 +1,14 @@
|
||||
from textwrap import dedent
|
||||
|
||||
from core.helper.code_executor.python3.python3_transformer import Python3TemplateTransformer
|
||||
from core.helper.code_executor.template_transformer import TemplateTransformer
|
||||
|
||||
|
||||
class Jinja2TemplateTransformer(TemplateTransformer):
|
||||
@classmethod
|
||||
def get_standard_packages(cls) -> set[str]:
|
||||
return {'jinja2'} | Python3TemplateTransformer.get_standard_packages()
|
||||
|
||||
@classmethod
|
||||
def transform_response(cls, response: str) -> dict:
|
||||
"""
|
||||
|
||||
@ -13,7 +13,7 @@ class Python3CodeProvider(CodeNodeProvider):
|
||||
def get_default_code(cls) -> str:
|
||||
return dedent(
|
||||
"""
|
||||
def main(arg1: str, arg2: str) -> dict:
|
||||
def main(arg1: int, arg2: int) -> dict:
|
||||
return {
|
||||
"result": arg1 + arg2,
|
||||
}
|
||||
|
||||
@ -4,6 +4,30 @@ from core.helper.code_executor.template_transformer import TemplateTransformer
|
||||
|
||||
|
||||
class Python3TemplateTransformer(TemplateTransformer):
|
||||
@classmethod
|
||||
def get_standard_packages(cls) -> set[str]:
|
||||
return {
|
||||
'base64',
|
||||
'binascii',
|
||||
'collections',
|
||||
'datetime',
|
||||
'functools',
|
||||
'hashlib',
|
||||
'hmac',
|
||||
'itertools',
|
||||
'json',
|
||||
'math',
|
||||
'operator',
|
||||
'os',
|
||||
'random',
|
||||
're',
|
||||
'string',
|
||||
'sys',
|
||||
'time',
|
||||
'traceback',
|
||||
'uuid',
|
||||
}
|
||||
|
||||
@classmethod
|
||||
def get_runner_script(cls) -> str:
|
||||
runner_script = dedent(f"""
|
||||
|
||||
@ -2,6 +2,9 @@ import json
|
||||
import re
|
||||
from abc import ABC, abstractmethod
|
||||
from base64 import b64encode
|
||||
from typing import Optional
|
||||
|
||||
from core.helper.code_executor.entities import CodeDependency
|
||||
|
||||
|
||||
class TemplateTransformer(ABC):
|
||||
@ -10,7 +13,12 @@ class TemplateTransformer(ABC):
|
||||
_result_tag: str = '<<RESULT>>'
|
||||
|
||||
@classmethod
|
||||
def transform_caller(cls, code: str, inputs: dict) -> tuple[str, str]:
|
||||
def get_standard_packages(cls) -> set[str]:
|
||||
return set()
|
||||
|
||||
@classmethod
|
||||
def transform_caller(cls, code: str, inputs: dict,
|
||||
dependencies: Optional[list[CodeDependency]] = None) -> tuple[str, str, list[CodeDependency]]:
|
||||
"""
|
||||
Transform code to python runner
|
||||
:param code: code
|
||||
@ -20,7 +28,14 @@ class TemplateTransformer(ABC):
|
||||
runner_script = cls.assemble_runner_script(code, inputs)
|
||||
preload_script = cls.get_preload_script()
|
||||
|
||||
return runner_script, preload_script
|
||||
packages = dependencies or []
|
||||
standard_packages = cls.get_standard_packages()
|
||||
for package in standard_packages:
|
||||
if package not in packages:
|
||||
packages.append(CodeDependency(name=package, version=''))
|
||||
packages = list({dep.name: dep for dep in packages if dep.name}.values())
|
||||
|
||||
return runner_script, preload_script, packages
|
||||
|
||||
@classmethod
|
||||
def extract_result_str_from_response(cls, response: str) -> str:
|
||||
|
||||
@ -2,6 +2,7 @@ import base64
|
||||
|
||||
from extensions.ext_database import db
|
||||
from libs import rsa
|
||||
from models.account import Tenant
|
||||
|
||||
|
||||
def obfuscated_token(token: str):
|
||||
@ -13,7 +14,6 @@ def obfuscated_token(token: str):
|
||||
|
||||
|
||||
def encrypt_token(tenant_id: str, token: str):
|
||||
from models.account import Tenant
|
||||
if not (tenant := db.session.query(Tenant).filter(Tenant.id == tenant_id).first()):
|
||||
raise ValueError(f'Tenant with id {tenant_id} not found')
|
||||
encrypted_token = rsa.encrypt(token, tenant.encrypt_public_key)
|
||||
|
||||
@ -3,7 +3,6 @@ from collections import OrderedDict
|
||||
from collections.abc import Callable
|
||||
from typing import Any
|
||||
|
||||
from configs import dify_config
|
||||
from core.tools.utils.yaml_utils import load_yaml_file
|
||||
|
||||
|
||||
@ -20,87 +19,6 @@ def get_position_map(folder_path: str, *, file_name: str = "_position.yaml") ->
|
||||
return {name: index for index, name in enumerate(positions)}
|
||||
|
||||
|
||||
def get_tool_position_map(folder_path: str, file_name: str = "_position.yaml") -> dict[str, int]:
|
||||
"""
|
||||
Get the mapping for tools from name to index from a YAML file.
|
||||
:param folder_path:
|
||||
:param file_name: the YAML file name, default to '_position.yaml'
|
||||
:return: a dict with name as key and index as value
|
||||
"""
|
||||
position_map = get_position_map(folder_path, file_name=file_name)
|
||||
|
||||
return pin_position_map(
|
||||
position_map,
|
||||
pin_list=dify_config.POSITION_TOOL_PINS_LIST,
|
||||
)
|
||||
|
||||
|
||||
def get_provider_position_map(folder_path: str, file_name: str = "_position.yaml") -> dict[str, int]:
|
||||
"""
|
||||
Get the mapping for providers from name to index from a YAML file.
|
||||
:param folder_path:
|
||||
:param file_name: the YAML file name, default to '_position.yaml'
|
||||
:return: a dict with name as key and index as value
|
||||
"""
|
||||
position_map = get_position_map(folder_path, file_name=file_name)
|
||||
return pin_position_map(
|
||||
position_map,
|
||||
pin_list=dify_config.POSITION_PROVIDER_PINS_LIST,
|
||||
)
|
||||
|
||||
|
||||
def pin_position_map(original_position_map: dict[str, int], pin_list: list[str]) -> dict[str, int]:
|
||||
"""
|
||||
Pin the items in the pin list to the beginning of the position map.
|
||||
Overall logic: exclude > include > pin
|
||||
:param position_map: the position map to be sorted and filtered
|
||||
:param pin_list: the list of pins to be put at the beginning
|
||||
:return: the sorted position map
|
||||
"""
|
||||
positions = sorted(original_position_map.keys(), key=lambda x: original_position_map[x])
|
||||
|
||||
# Add pins to position map
|
||||
position_map = {name: idx for idx, name in enumerate(pin_list)}
|
||||
|
||||
# Add remaining positions to position map
|
||||
start_idx = len(position_map)
|
||||
for name in positions:
|
||||
if name not in position_map:
|
||||
position_map[name] = start_idx
|
||||
start_idx += 1
|
||||
|
||||
return position_map
|
||||
|
||||
|
||||
def is_filtered(
|
||||
include_set: set[str],
|
||||
exclude_set: set[str],
|
||||
data: Any,
|
||||
name_func: Callable[[Any], str],
|
||||
) -> bool:
|
||||
"""
|
||||
Chcek if the object should be filtered out.
|
||||
Overall logic: exclude > include > pin
|
||||
:param include_set: the set of names to be included
|
||||
:param exclude_set: the set of names to be excluded
|
||||
:param name_func: the function to get the name of the object
|
||||
:param data: the data to be filtered
|
||||
:return: True if the object should be filtered out, False otherwise
|
||||
"""
|
||||
if not data:
|
||||
return False
|
||||
if not include_set and not exclude_set:
|
||||
return False
|
||||
|
||||
name = name_func(data)
|
||||
|
||||
if name in exclude_set: # exclude_set is prioritized
|
||||
return True
|
||||
if include_set and name not in include_set: # filter out only if include_set is not empty
|
||||
return True
|
||||
return False
|
||||
|
||||
|
||||
def sort_by_position_map(
|
||||
position_map: dict[str, int],
|
||||
data: list[Any],
|
||||
|
||||
@ -700,7 +700,6 @@ class IndexingRunner:
|
||||
DatasetDocument.tokens: tokens,
|
||||
DatasetDocument.completed_at: datetime.datetime.now(datetime.timezone.utc).replace(tzinfo=None),
|
||||
DatasetDocument.indexing_latency: indexing_end_at - indexing_start_at,
|
||||
DatasetDocument.error: None,
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
@ -271,8 +271,9 @@ class ModelInstance:
|
||||
|
||||
:param content_text: text content to be translated
|
||||
:param tenant_id: user tenant id
|
||||
:param voice: model timbre
|
||||
:param user: unique user id
|
||||
:param voice: model timbre
|
||||
:param streaming: output is streaming
|
||||
:return: text for given audio file
|
||||
"""
|
||||
if not isinstance(self.model_type_instance, TTSModel):
|
||||
@ -368,15 +369,6 @@ class ModelManager:
|
||||
|
||||
return ModelInstance(provider_model_bundle, model)
|
||||
|
||||
def get_default_provider_model_name(self, tenant_id: str, model_type: ModelType) -> tuple[str, str]:
|
||||
"""
|
||||
Return first provider and the first model in the provider
|
||||
:param tenant_id: tenant id
|
||||
:param model_type: model type
|
||||
:return: provider name, model name
|
||||
"""
|
||||
return self._provider_manager.get_first_provider_first_model(tenant_id, model_type)
|
||||
|
||||
def get_default_model_instance(self, tenant_id: str, model_type: ModelType) -> ModelInstance:
|
||||
"""
|
||||
Get default model instance
|
||||
@ -409,10 +401,6 @@ class LBModelManager:
|
||||
managed_credentials: Optional[dict] = None) -> None:
|
||||
"""
|
||||
Load balancing model manager
|
||||
:param tenant_id: tenant_id
|
||||
:param provider: provider
|
||||
:param model_type: model_type
|
||||
:param model: model name
|
||||
:param load_balancing_configs: all load balancing configurations
|
||||
:param managed_credentials: credentials if load balancing configuration name is __inherit__
|
||||
"""
|
||||
@ -511,6 +499,7 @@ class LBModelManager:
|
||||
config.id
|
||||
)
|
||||
|
||||
|
||||
res = redis_client.exists(cooldown_cache_key)
|
||||
res = cast(bool, res)
|
||||
return res
|
||||
|
||||
@ -1,3 +1,4 @@
|
||||
|
||||
from core.model_runtime.entities.model_entities import DefaultParameterName
|
||||
|
||||
PARAMETER_RULE_TEMPLATE: dict[DefaultParameterName, dict] = {
|
||||
@ -93,16 +94,5 @@ PARAMETER_RULE_TEMPLATE: dict[DefaultParameterName, dict] = {
|
||||
},
|
||||
'required': False,
|
||||
'options': ['JSON', 'XML'],
|
||||
},
|
||||
DefaultParameterName.JSON_SCHEMA: {
|
||||
'label': {
|
||||
'en_US': 'JSON Schema',
|
||||
},
|
||||
'type': 'text',
|
||||
'help': {
|
||||
'en_US': 'Set a response json schema will ensure LLM to adhere it.',
|
||||
'zh_Hans': '设置返回的json schema，llm将按照它返回',
|
||||
},
|
||||
'required': False,
|
||||
},
|
||||
}
|
||||
}
|
||||
}
|
||||
@ -95,7 +95,6 @@ class DefaultParameterName(Enum):
|
||||
FREQUENCY_PENALTY = "frequency_penalty"
|
||||
MAX_TOKENS = "max_tokens"
|
||||
RESPONSE_FORMAT = "response_format"
|
||||
JSON_SCHEMA = "json_schema"
|
||||
|
||||
@classmethod
|
||||
def value_of(cls, value: Any) -> 'DefaultParameterName':
|
||||
@ -119,7 +118,6 @@ class ParameterType(Enum):
|
||||
INT = "int"
|
||||
STRING = "string"
|
||||
BOOLEAN = "boolean"
|
||||
TEXT = "text"
|
||||
|
||||
|
||||
class ModelPropertyKey(Enum):
|
||||
|
||||
@ -151,9 +151,9 @@ class AIModel(ABC):
|
||||
os.path.join(provider_model_type_path, model_schema_yaml)
|
||||
for model_schema_yaml in os.listdir(provider_model_type_path)
|
||||
if not model_schema_yaml.startswith('__')
|
||||
and not model_schema_yaml.startswith('_')
|
||||
and os.path.isfile(os.path.join(provider_model_type_path, model_schema_yaml))
|
||||
and model_schema_yaml.endswith('.yaml')
|
||||
and not model_schema_yaml.startswith('_')
|
||||
and os.path.isfile(os.path.join(provider_model_type_path, model_schema_yaml))
|
||||
and model_schema_yaml.endswith('.yaml')
|
||||
]
|
||||
|
||||
# get _position.yaml file path
|
||||
|
||||
@ -185,7 +185,7 @@ if you are not sure about the structure.
|
||||
stream=stream,
|
||||
user=user
|
||||
)
|
||||
|
||||
|
||||
model_parameters.pop("response_format")
|
||||
stop = stop or []
|
||||
stop.extend(["\n```", "```\n"])
|
||||
@ -249,10 +249,10 @@ if you are not sure about the structure.
|
||||
prompt_messages=prompt_messages,
|
||||
input_generator=new_generator()
|
||||
)
|
||||
|
||||
|
||||
return response
|
||||
|
||||
def _code_block_mode_stream_processor(self, model: str, prompt_messages: list[PromptMessage],
|
||||
def _code_block_mode_stream_processor(self, model: str, prompt_messages: list[PromptMessage],
|
||||
input_generator: Generator[LLMResultChunk, None, None]
|
||||
) -> Generator[LLMResultChunk, None, None]:
|
||||
"""
|
||||
@ -310,7 +310,7 @@ if you are not sure about the structure.
|
||||
)
|
||||
)
|
||||
|
||||
def _code_block_mode_stream_processor_with_backtick(self, model: str, prompt_messages: list,
|
||||
def _code_block_mode_stream_processor_with_backtick(self, model: str, prompt_messages: list,
|
||||
input_generator: Generator[LLMResultChunk, None, None]) \
|
||||
-> Generator[LLMResultChunk, None, None]:
|
||||
"""
|
||||
@ -470,7 +470,7 @@ if you are not sure about the structure.
|
||||
:return: full response or stream response chunk generator result
|
||||
"""
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
@abstractmethod
|
||||
def get_num_tokens(self, model: str, credentials: dict, prompt_messages: list[PromptMessage],
|
||||
tools: Optional[list[PromptMessageTool]] = None) -> int:
|
||||
@ -792,13 +792,6 @@ if you are not sure about the structure.
|
||||
if not isinstance(parameter_value, str):
|
||||
raise ValueError(f"Model Parameter {parameter_name} should be string.")
|
||||
|
||||
# validate options
|
||||
if parameter_rule.options and parameter_value not in parameter_rule.options:
|
||||
raise ValueError(f"Model Parameter {parameter_name} should be one of {parameter_rule.options}.")
|
||||
elif parameter_rule.type == ParameterType.TEXT:
|
||||
if not isinstance(parameter_value, str):
|
||||
raise ValueError(f"Model Parameter {parameter_name} should be text.")
|
||||
|
||||
# validate options
|
||||
if parameter_rule.options and parameter_value not in parameter_rule.options:
|
||||
raise ValueError(f"Model Parameter {parameter_name} should be one of {parameter_rule.options}.")
|
||||
|
||||
@ -70,7 +70,7 @@ class AzureOpenAIText2SpeechModel(_CommonAzureOpenAI, TTSModel):
|
||||
# doc: https://platform.openai.com/docs/guides/text-to-speech
|
||||
credentials_kwargs = self._to_credential_kwargs(credentials)
|
||||
client = AzureOpenAI(**credentials_kwargs)
|
||||
# max length is 4096 characters, there is 3500 limit for each request
|
||||
# max font is 4096,there is 3500 limit for each request
|
||||
max_length = 3500
|
||||
if len(content_text) > max_length:
|
||||
sentences = self._split_text_into_sentences(content_text, max_length=max_length)
|
||||
|
||||
@ -6,7 +6,7 @@ from typing import Optional
|
||||
from pydantic import BaseModel, ConfigDict
|
||||
|
||||
from core.helper.module_import_helper import load_single_subclass_from_source
|
||||
from core.helper.position_helper import get_provider_position_map, sort_to_dict_by_position_map
|
||||
from core.helper.position_helper import get_position_map, sort_to_dict_by_position_map
|
||||
from core.model_runtime.entities.model_entities import ModelType
|
||||
from core.model_runtime.entities.provider_entities import ProviderConfig, ProviderEntity, SimpleProviderEntity
|
||||
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
|
||||
@ -234,7 +234,7 @@ class ModelProviderFactory:
|
||||
]
|
||||
|
||||
# get _position.yaml file path
|
||||
position_map = get_provider_position_map(model_providers_path)
|
||||
position_map = get_position_map(model_providers_path)
|
||||
|
||||
# traverse all model_provider_dir_paths
|
||||
model_providers: list[ModelProviderExtension] = []
|
||||
|
||||
@ -84,8 +84,7 @@ class MoonshotLargeLanguageModel(OAIAPICompatLargeLanguageModel):
|
||||
|
||||
def _add_custom_parameters(self, credentials: dict) -> None:
|
||||
credentials['mode'] = 'chat'
|
||||
if 'endpoint_url' not in credentials or credentials['endpoint_url'] == "":
|
||||
credentials['endpoint_url'] = 'https://api.moonshot.cn/v1'
|
||||
credentials['endpoint_url'] = 'https://api.moonshot.cn/v1'
|
||||
|
||||
def _add_function_call(self, model: str, credentials: dict) -> None:
|
||||
model_schema = self.get_model_schema(model, credentials)
|
||||
|
||||
@ -31,14 +31,6 @@ provider_credential_schema:
|
||||
placeholder:
|
||||
zh_Hans: 在此输入您的 API Key
|
||||
en_US: Enter your API Key
|
||||
- variable: endpoint_url
|
||||
label:
|
||||
en_US: API Base
|
||||
type: text-input
|
||||
required: false
|
||||
placeholder:
|
||||
zh_Hans: Base URL, 如：https://api.moonshot.cn/v1
|
||||
en_US: Base URL, e.g. https://api.moonshot.cn/v1
|
||||
model_credential_schema:
|
||||
model:
|
||||
label:
|
||||
|
||||
@ -2,7 +2,6 @@
|
||||
- gpt-4o
|
||||
- gpt-4o-2024-05-13
|
||||
- gpt-4o-2024-08-06
|
||||
- chatgpt-4o-latest
|
||||
- gpt-4o-mini
|
||||
- gpt-4o-mini-2024-07-18
|
||||
- gpt-4-turbo
|
||||
|
||||
@ -1,44 +0,0 @@
|
||||
model: chatgpt-4o-latest
|
||||
label:
|
||||
zh_Hans: chatgpt-4o-latest
|
||||
en_US: chatgpt-4o-latest
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 16384
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '2.50'
|
||||
output: '10.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@ -37,9 +37,6 @@ parameter_rules:
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
- json_schema
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '2.50'
|
||||
output: '10.00'
|
||||
|
||||
@ -37,9 +37,6 @@ parameter_rules:
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
- json_schema
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.15'
|
||||
output: '0.60'
|
||||
|
||||
@ -37,9 +37,6 @@ parameter_rules:
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
- json_schema
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.15'
|
||||
output: '0.60'
|
||||
|
||||
@ -1,4 +1,3 @@
|
||||
import json
|
||||
import logging
|
||||
from collections.abc import Generator
|
||||
from typing import Optional, Union, cast
|
||||
@ -545,18 +544,13 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
|
||||
|
||||
response_format = model_parameters.get("response_format")
|
||||
if response_format:
|
||||
if response_format == "json_schema":
|
||||
json_schema = model_parameters.get("json_schema")
|
||||
if not json_schema:
|
||||
raise ValueError("Must define JSON Schema when the response format is json_schema")
|
||||
try:
|
||||
schema = json.loads(json_schema)
|
||||
except:
|
||||
raise ValueError(f"not currect json_schema format: {json_schema}")
|
||||
model_parameters.pop("json_schema")
|
||||
model_parameters["response_format"] = {"type": "json_schema", "json_schema": schema}
|
||||
if response_format == "json_object":
|
||||
response_format = {"type": "json_object"}
|
||||
else:
|
||||
model_parameters["response_format"] = {"type": response_format}
|
||||
response_format = {"type": "text"}
|
||||
|
||||
model_parameters["response_format"] = response_format
|
||||
|
||||
|
||||
extra_model_kwargs = {}
|
||||
|
||||
@ -928,14 +922,11 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
|
||||
tools: Optional[list[PromptMessageTool]] = None) -> int:
|
||||
"""Calculate num tokens for gpt-3.5-turbo and gpt-4 with tiktoken package.
|
||||
|
||||
Official documentation: https://github.com/openai/openai-cookbook/blob/main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
|
||||
Official documentation: https://github.com/openai/openai-cookbook/blob/
|
||||
main/examples/How_to_format_inputs_to_ChatGPT_models.ipynb"""
|
||||
if model.startswith('ft:'):
|
||||
model = model.split(':')[1]
|
||||
|
||||
# Currently, we can use gpt4o to calculate chatgpt-4o-latest's token.
|
||||
if model == "chatgpt-4o-latest":
|
||||
model = "gpt-4o"
|
||||
|
||||
try:
|
||||
encoding = tiktoken.encoding_for_model(model)
|
||||
except KeyError:
|
||||
@ -955,7 +946,7 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
|
||||
raise NotImplementedError(
|
||||
f"get_num_tokens_from_messages() is not presently implemented "
|
||||
f"for model {model}."
|
||||
"See https://platform.openai.com/docs/advanced-usage/managing-tokens for "
|
||||
"See https://github.com/openai/openai-python/blob/main/chatml.md for "
|
||||
"information on how messages are converted to tokens."
|
||||
)
|
||||
num_tokens = 0
|
||||
|
||||
@ -428,7 +428,7 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
|
||||
if new_tool_call.function.arguments:
|
||||
tool_call.function.arguments += new_tool_call.function.arguments
|
||||
|
||||
finish_reason = None # The default value of finish_reason is None
|
||||
finish_reason = 'Unknown'
|
||||
|
||||
for chunk in response.iter_lines(decode_unicode=True, delimiter=delimiter):
|
||||
chunk = chunk.strip()
|
||||
@ -437,8 +437,6 @@ class OAIAPICompatLargeLanguageModel(_CommonOAI_API_Compat, LargeLanguageModel):
|
||||
if chunk.startswith(':'):
|
||||
continue
|
||||
decoded_chunk = chunk.strip().lstrip('data: ').lstrip()
|
||||
if decoded_chunk == '[DONE]': # Some provider returns "data: [DONE]"
|
||||
continue
|
||||
|
||||
try:
|
||||
chunk_json = json.loads(decoded_chunk)
|
||||
|
||||
@ -7,7 +7,6 @@ description:
|
||||
supported_model_types:
|
||||
- llm
|
||||
- text-embedding
|
||||
- speech2text
|
||||
configurate_methods:
|
||||
- customizable-model
|
||||
model_credential_schema:
|
||||
@ -62,22 +61,6 @@ model_credential_schema:
|
||||
zh_Hans: 模型上下文长度
|
||||
en_US: Model context size
|
||||
required: true
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
type: text-input
|
||||
default: '4096'
|
||||
placeholder:
|
||||
zh_Hans: 在此输入您的模型上下文长度
|
||||
en_US: Enter your Model context size
|
||||
- variable: context_size
|
||||
label:
|
||||
zh_Hans: 模型上下文长度
|
||||
en_US: Model context size
|
||||
required: true
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: text-embedding
|
||||
type: text-input
|
||||
default: '4096'
|
||||
placeholder:
|
||||
|
||||
@ -1,63 +0,0 @@
|
||||
from typing import IO, Optional
|
||||
from urllib.parse import urljoin
|
||||
|
||||
import requests
|
||||
|
||||
from core.model_runtime.errors.invoke import InvokeBadRequestError
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.speech2text_model import Speech2TextModel
|
||||
from core.model_runtime.model_providers.openai_api_compatible._common import _CommonOAI_API_Compat
|
||||
|
||||
|
||||
class OAICompatSpeech2TextModel(_CommonOAI_API_Compat, Speech2TextModel):
|
||||
"""
|
||||
Model class for OpenAI Compatible Speech to text model.
|
||||
"""
|
||||
|
||||
def _invoke(
|
||||
self, model: str, credentials: dict, file: IO[bytes], user: Optional[str] = None
|
||||
) -> str:
|
||||
"""
|
||||
Invoke speech2text model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param file: audio file
|
||||
:param user: unique user id
|
||||
:return: text for given audio file
|
||||
"""
|
||||
headers = {}
|
||||
|
||||
api_key = credentials.get("api_key")
|
||||
if api_key:
|
||||
headers["Authorization"] = f"Bearer {api_key}"
|
||||
|
||||
endpoint_url = credentials.get("endpoint_url")
|
||||
if not endpoint_url.endswith("/"):
|
||||
endpoint_url += "/"
|
||||
endpoint_url = urljoin(endpoint_url, "audio/transcriptions")
|
||||
|
||||
payload = {"model": model}
|
||||
files = [("file", file)]
|
||||
response = requests.post(endpoint_url, headers=headers, data=payload, files=files)
|
||||
|
||||
if response.status_code != 200:
|
||||
raise InvokeBadRequestError(response.text)
|
||||
response_data = response.json()
|
||||
return response_data["text"]
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return:
|
||||
"""
|
||||
try:
|
||||
audio_file_path = self._get_demo_file_path()
|
||||
|
||||
with open(audio_file_path, "rb") as audio_file:
|
||||
self._invoke(model, credentials, audio_file)
|
||||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
@ -1,44 +0,0 @@
|
||||
model: gpt-4o-2024-08-06
|
||||
label:
|
||||
zh_Hans: gpt-4o-2024-08-06
|
||||
en_US: gpt-4o-2024-08-06
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 16384
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '2.50'
|
||||
output: '10.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@ -1,61 +0,0 @@
|
||||
model: Llama3-Chinese_v2
|
||||
label:
|
||||
en_US: Llama3-Chinese_v2
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
|
||||
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 600
|
||||
min: 1
|
||||
max: 1248
|
||||
help:
|
||||
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
|
||||
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
type: float
|
||||
default: 0.8
|
||||
min: 0.1
|
||||
max: 0.9
|
||||
help:
|
||||
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
|
||||
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
|
||||
- name: top_k
|
||||
type: int
|
||||
min: 0
|
||||
max: 99
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
help:
|
||||
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
|
||||
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
|
||||
- name: repetition_penalty
|
||||
required: false
|
||||
type: float
|
||||
default: 1.1
|
||||
label:
|
||||
en_US: Repetition penalty
|
||||
help:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
currency: RMB
|
||||
@ -1,61 +0,0 @@
|
||||
model: Meta-Llama-3-70B-Instruct-GPTQ-Int4
|
||||
label:
|
||||
en_US: Meta-Llama-3-70B-Instruct-GPTQ-Int4
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1024
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
|
||||
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 600
|
||||
min: 1
|
||||
max: 1248
|
||||
help:
|
||||
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
|
||||
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
type: float
|
||||
default: 0.8
|
||||
min: 0.1
|
||||
max: 0.9
|
||||
help:
|
||||
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
|
||||
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
|
||||
- name: top_k
|
||||
type: int
|
||||
min: 0
|
||||
max: 99
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
help:
|
||||
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
|
||||
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
|
||||
- name: repetition_penalty
|
||||
required: false
|
||||
type: float
|
||||
default: 1.1
|
||||
label:
|
||||
en_US: Repetition penalty
|
||||
help:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
currency: RMB
|
||||
@ -1,61 +0,0 @@
|
||||
model: Meta-Llama-3-8B-Instruct
|
||||
label:
|
||||
en_US: Meta-Llama-3-8B-Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
|
||||
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 600
|
||||
min: 1
|
||||
max: 1248
|
||||
help:
|
||||
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
|
||||
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
type: float
|
||||
default: 0.8
|
||||
min: 0.1
|
||||
max: 0.9
|
||||
help:
|
||||
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
|
||||
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
|
||||
- name: top_k
|
||||
type: int
|
||||
min: 0
|
||||
max: 99
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
help:
|
||||
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
|
||||
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
|
||||
- name: repetition_penalty
|
||||
required: false
|
||||
type: float
|
||||
default: 1.1
|
||||
label:
|
||||
en_US: Repetition penalty
|
||||
help:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
currency: RMB
|
||||
@ -1,61 +0,0 @@
|
||||
model: Meta-Llama-3.1-405B-Instruct-AWQ-INT4
|
||||
label:
|
||||
en_US: Meta-Llama-3.1-405B-Instruct-AWQ-INT4
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 410960
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
|
||||
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 600
|
||||
min: 1
|
||||
max: 1248
|
||||
help:
|
||||
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
|
||||
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
type: float
|
||||
default: 0.8
|
||||
min: 0.1
|
||||
max: 0.9
|
||||
help:
|
||||
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
|
||||
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
|
||||
- name: top_k
|
||||
type: int
|
||||
min: 0
|
||||
max: 99
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
help:
|
||||
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
|
||||
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
|
||||
- name: repetition_penalty
|
||||
required: false
|
||||
type: float
|
||||
default: 1.1
|
||||
label:
|
||||
en_US: Repetition penalty
|
||||
help:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
currency: RMB
|
||||
@ -1,61 +0,0 @@
|
||||
model: Meta-Llama-3.1-8B-Instruct
|
||||
label:
|
||||
en_US: Meta-Llama-3.1-8B-Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 4096
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 0.1
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
|
||||
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 600
|
||||
min: 1
|
||||
max: 1248
|
||||
help:
|
||||
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
|
||||
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
type: float
|
||||
default: 0.8
|
||||
min: 0.1
|
||||
max: 0.9
|
||||
help:
|
||||
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
|
||||
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
|
||||
- name: top_k
|
||||
type: int
|
||||
min: 0
|
||||
max: 99
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
help:
|
||||
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
|
||||
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
|
||||
- name: repetition_penalty
|
||||
required: false
|
||||
type: float
|
||||
default: 1.1
|
||||
label:
|
||||
en_US: Repetition penalty
|
||||
help:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
currency: RMB
|
||||
@ -55,8 +55,7 @@ parameter_rules:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
input: '0.000'
|
||||
output: '0.000'
|
||||
unit: '0.000'
|
||||
currency: RMB
|
||||
deprecated: true
|
||||
|
||||
@ -55,8 +55,7 @@ parameter_rules:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
input: '0.000'
|
||||
output: '0.000'
|
||||
unit: '0.000'
|
||||
currency: RMB
|
||||
deprecated: true
|
||||
|
||||
@ -6,7 +6,7 @@ features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 2048
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
@ -55,7 +55,7 @@ parameter_rules:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
input: '0.000'
|
||||
output: '0.000'
|
||||
unit: '0.000'
|
||||
currency: RMB
|
||||
|
||||
@ -6,7 +6,7 @@ features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 32768
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
@ -55,7 +55,7 @@ parameter_rules:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
input: '0.000'
|
||||
output: '0.000'
|
||||
unit: '0.000'
|
||||
currency: RMB
|
||||
|
||||
@ -8,12 +8,12 @@ features:
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 2048
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 0.7
|
||||
default: 0.3
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
@ -57,7 +57,7 @@ parameter_rules:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
input: '0.000'
|
||||
output: '0.000'
|
||||
unit: '0.000'
|
||||
currency: RMB
|
||||
|
||||
@ -1,61 +0,0 @@
|
||||
model: Qwen2-72B-Instruct
|
||||
label:
|
||||
en_US: Qwen2-72B-Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 用于控制随机性和多样性的程度。具体来说，temperature值控制了生成文本时对每个候选词的概率分布进行平滑的程度。较高的temperature值会降低概率分布的峰值，使得更多的低概率词被选择，生成结果更加多样化；而较低的temperature值则会增强概率分布的峰值，使得高概率词更容易被选择，生成结果更加确定。
|
||||
en_US: Used to control the degree of randomness and diversity. Specifically, the temperature value controls the degree to which the probability distribution of each candidate word is smoothed when generating text. A higher temperature value will reduce the peak value of the probability distribution, allowing more low-probability words to be selected, and the generated results will be more diverse; while a lower temperature value will enhance the peak value of the probability distribution, making it easier for high-probability words to be selected. , the generated results are more certain.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 600
|
||||
min: 1
|
||||
max: 1248
|
||||
help:
|
||||
zh_Hans: 用于指定模型在生成内容时token的最大数量，它定义了生成的上限，但不保证每次都会生成到这个数量。
|
||||
en_US: It is used to specify the maximum number of tokens when the model generates content. It defines the upper limit of generation, but does not guarantee that this number will be generated every time.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
type: float
|
||||
default: 0.8
|
||||
min: 0.1
|
||||
max: 0.9
|
||||
help:
|
||||
zh_Hans: 生成过程中核采样方法概率阈值，例如，取值为0.8时，仅保留概率加起来大于等于0.8的最可能token的最小集合作为候选集。取值范围为（0,1.0)，取值越大，生成的随机性越高；取值越低，生成的确定性越高。
|
||||
en_US: The probability threshold of the kernel sampling method during the generation process. For example, when the value is 0.8, only the smallest set of the most likely tokens with a sum of probabilities greater than or equal to 0.8 is retained as the candidate set. The value range is (0,1.0). The larger the value, the higher the randomness generated; the lower the value, the higher the certainty generated.
|
||||
- name: top_k
|
||||
type: int
|
||||
min: 0
|
||||
max: 99
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
help:
|
||||
zh_Hans: 生成时，采样候选集的大小。例如，取值为50时，仅将单次生成中得分最高的50个token组成随机采样的候选集。取值越大，生成的随机性越高；取值越小，生成的确定性越高。
|
||||
en_US: The size of the sample candidate set when generated. For example, when the value is 50, only the 50 highest-scoring tokens in a single generation form a randomly sampled candidate set. The larger the value, the higher the randomness generated; the smaller the value, the higher the certainty generated.
|
||||
- name: repetition_penalty
|
||||
required: false
|
||||
type: float
|
||||
default: 1.1
|
||||
label:
|
||||
en_US: Repetition penalty
|
||||
help:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
currency: RMB
|
||||
@ -8,7 +8,7 @@ features:
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 32768
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
@ -57,7 +57,7 @@ parameter_rules:
|
||||
zh_Hans: 用于控制模型生成时的重复度。提高repetition_penalty时可以降低模型生成的重复度。1.0表示不做惩罚。
|
||||
en_US: Used to control the repeatability when generating models. Increasing repetition_penalty can reduce the duplication of model generation. 1.0 means no punishment.
|
||||
pricing:
|
||||
input: "0.000"
|
||||
output: "0.000"
|
||||
unit: "0.000"
|
||||
input: '0.000'
|
||||
output: '0.000'
|
||||
unit: '0.000'
|
||||
currency: RMB
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user