fta

.github/actions/setup-poetry/action.yml

@@ -1,36 +0,0 @@
-name: Setup Poetry and Python
-
-inputs:
-  python-version:
-    description: Python version to use and the Poetry installed with
-    required: true
-    default: '3.10'
-  poetry-version:
-    description: Poetry version to set up
-    required: true
-    default: '1.8.4'
-  poetry-lockfile:
-    description: Path to the Poetry lockfile to restore cache from
-    required: true
-    default: ''
-
-runs:
-  using: composite
-  steps:
-    - name: Set up Python ${{ inputs.python-version }}
-      uses: actions/setup-python@v5
-      with:
-        python-version: ${{ inputs.python-version }}
-        cache: pip
-
-    - name: Install Poetry
-      shell: bash
-      run: pip install poetry==${{ inputs.poetry-version }}
-
-    - name: Restore Poetry cache
-      if: ${{ inputs.poetry-lockfile != '' }}
-      uses: actions/setup-python@v5
-      with:
-        python-version: ${{ inputs.python-version }}
-        cache: poetry
-        cache-dependency-path: ${{ inputs.poetry-lockfile }}

.github/workflows/api-tests.yml

@@ -7,7 +7,6 @@ on:
     paths:
       - api/**
       - docker/**
-      - .github/workflows/api-tests.yml
 
 concurrency:
   group: api-tests-${{ github.head_ref || github.run_id }}
@@ -28,11 +27,16 @@ jobs:
       - name: Checkout code
         uses: actions/checkout@v4
 
-      - name: Setup Poetry and Python ${{ matrix.python-version }}
-        uses: ./.github/actions/setup-poetry
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
         with:
           python-version: ${{ matrix.python-version }}
-          poetry-lockfile: api/poetry.lock
+          cache-dependency-path: |
+            api/pyproject.toml
+            api/poetry.lock
+
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
 
       - name: Check Poetry lockfile
         run: |
@@ -63,7 +67,7 @@ jobs:
         run: sh .github/workflows/expose_service_ports.sh
 
       - name: Set up Sandbox
-        uses: hoverkraft-tech/compose-action@v2.0.2
+        uses: hoverkraft-tech/compose-action@v2.0.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml
@@ -73,3 +77,22 @@ 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, Couchbase)
+        uses: hoverkraft-tech/compose-action@v2.0.0
+        with:
+          compose-file: |
+            docker/docker-compose.yaml
+          services: |
+            weaviate
+            qdrant
+            couchbase-server
+            etcd
+            minio
+            milvus-standalone
+            pgvecto-rs
+            pgvector
+            chroma
+            elasticsearch
+      - name: Test Vector Stores
+        run: poetry run -C api bash dev/pytest/pytest_vdb.sh

.github/workflows/db-migration-test.yml

@@ -6,7 +6,6 @@ on:
       - main
     paths:
       - api/migrations/**
-      - .github/workflows/db-migration-test.yml
 
 concurrency:
   group: db-migration-test-${{ github.ref }}
@@ -15,15 +14,25 @@ concurrency:
 jobs:
   db-migration-test:
     runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python-version:
+          - "3.10"
 
     steps:
       - name: Checkout code
         uses: actions/checkout@v4
 
-      - name: Setup Poetry and Python
-        uses: ./.github/actions/setup-poetry
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v5
         with:
-          poetry-lockfile: api/poetry.lock
+          python-version: ${{ matrix.python-version }}
+          cache-dependency-path: |
+            api/pyproject.toml
+            api/poetry.lock
+
+      - name: Install Poetry
+        uses: abatilo/actions-poetry@v3
 
       - name: Install dependencies
         run: poetry install -C api
@@ -34,7 +43,7 @@ jobs:
           cp middleware.env.example middleware.env
 
       - name: Set up Middlewares
-        uses: hoverkraft-tech/compose-action@v2.0.2
+        uses: hoverkraft-tech/compose-action@v2.0.0
         with:
           compose-file: |
             docker/docker-compose.middleware.yaml

.github/workflows/style.yml

@@ -22,28 +22,34 @@ jobs:
         id: changed-files
         uses: tj-actions/changed-files@v45
         with:
-          files: |
-            api/**
-            .github/workflows/style.yml
+          files: api/**
 
-      - name: Setup Poetry and Python
+      - name: Set up Python
+        uses: actions/setup-python@v5
         if: steps.changed-files.outputs.any_changed == 'true'
-        uses: ./.github/actions/setup-poetry
+        with:
+          python-version: '3.10'
 
-      - name: Install dependencies
+      - name: Install Poetry
+        if: steps.changed-files.outputs.any_changed == 'true'
+        uses: abatilo/actions-poetry@v3
+
+      - name: Python dependencies
         if: steps.changed-files.outputs.any_changed == 'true'
         run: poetry install -C api --only lint
 
       - name: Ruff check
         if: steps.changed-files.outputs.any_changed == 'true'
-        run: |
-          poetry run -C api ruff check ./api
-          poetry run -C api ruff format --check ./api
+        run: poetry run -C api ruff check ./api
 
       - name: Dotenv check
         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."

.github/workflows/vdb-tests.yml

@@ -1,71 +0,0 @@
-name: Run VDB Tests
-
-on:
-  pull_request:
-    branches:
-      - main
-    paths:
-      - api/core/rag/datasource/**
-      - docker/**
-      - .github/workflows/vdb-tests.yml
-
-concurrency:
-  group: vdb-tests-${{ github.head_ref || github.run_id }}
-  cancel-in-progress: true
-
-jobs:
-  test:
-    name: VDB Tests
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        python-version:
-          - "3.10"
-          - "3.11"
-          - "3.12"
-
-    steps:
-      - name: Checkout code
-        uses: actions/checkout@v4
-
-      - name: Setup Poetry and Python ${{ matrix.python-version }}
-        uses: ./.github/actions/setup-poetry
-        with:
-          python-version: ${{ matrix.python-version }}
-          poetry-lockfile: api/poetry.lock
-
-      - name: Check Poetry lockfile
-        run: |
-          poetry check -C api --lock
-          poetry show -C api
-
-      - name: Install dependencies
-        run: poetry install -C api --with dev
-
-      - name: Set up dotenvs
-        run: |
-          cp docker/.env.example docker/.env
-          cp docker/middleware.env.example docker/middleware.env
-
-      - name: Expose Service Ports
-        run: sh .github/workflows/expose_service_ports.sh
-
-      - name: Set up Vector Stores (Weaviate, Qdrant, PGVector, Milvus, PgVecto-RS, Chroma, MyScale, ElasticSearch, Couchbase)
-        uses: hoverkraft-tech/compose-action@v2.0.2
-        with:
-          compose-file: |
-            docker/docker-compose.yaml
-          services: |
-            weaviate
-            qdrant
-            couchbase-server
-            etcd
-            minio
-            milvus-standalone
-            pgvecto-rs
-            pgvector
-            chroma
-            elasticsearch
-
-      - name: Test Vector Stores
-        run: poetry run -C api bash dev/pytest/pytest_vdb.sh

.gitignore

@@ -175,7 +175,6 @@ docker/volumes/pgvector/data/*
 docker/volumes/pgvecto_rs/data/*
 docker/volumes/couchbase/*
 docker/volumes/oceanbase/*
-!docker/volumes/oceanbase/init.d
 
 docker/nginx/conf.d/default.conf
 docker/nginx/ssl/*

README.md

@@ -46,18 +46,45 @@
 </p>
 
 
-Dify is an open-source LLM app development platform. Its intuitive interface combines agentic AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production. 
+## Table of Content
+0. [Quick-Start🚀](https://github.com/langgenius/dify?tab=readme-ov-file#quick-start)
+
+1. [Intro📖](https://github.com/langgenius/dify?tab=readme-ov-file#intro)
+
+2. [How to use🔧](https://github.com/langgenius/dify?tab=readme-ov-file#using-dify)
+
+3. [Stay Ahead🏃](https://github.com/langgenius/dify?tab=readme-ov-file#staying-ahead)
+
+4. [Next Steps🏹](https://github.com/langgenius/dify?tab=readme-ov-file#next-steps)
+
+5. [Contributing💪](https://github.com/langgenius/dify?tab=readme-ov-file#contributing)
+
+6. [Community and Contact🏠](https://github.com/langgenius/dify?tab=readme-ov-file#community--contact)
+
+7. [Star-History📈](https://github.com/langgenius/dify?tab=readme-ov-file#star-history)
+
+8. [Security🔒](https://github.com/langgenius/dify?tab=readme-ov-file#security-disclosure)
+
+9. [License🤝](https://github.com/langgenius/dify?tab=readme-ov-file#license)
+
+> Make sure you read through this README before you start utilizing Dify😊
+
 
 ## Quick start
+The quickest way to deploy Dify locally is to run our [docker-compose.yml](https://github.com/langgenius/dify/blob/main/docker/docker-compose.yaml). Follow the instructions to start in 5 minutes.
+
 > Before installing Dify, make sure your machine meets the following minimum system requirements:
 > 
 >- CPU >= 2 Core
 >- RAM >= 4 GiB
-
+>- Docker and Docker Compose Installed
 </br>
 
-The easiest way to start the Dify server is through [docker compose](docker/docker-compose.yaml). Before running Dify with the following commands, make sure that [Docker](https://docs.docker.com/get-docker/) and [Docker Compose](https://docs.docker.com/compose/install/) are installed on your machine:
-
+Run the following command in your terminal to clone the whole repo.
+```bash
+git clone https://github.com/langgenius/dify.git
+```
+After cloning,run the following command one by one.
 ```bash
 cd dify
 cd docker
@@ -65,14 +92,13 @@ cp .env.example .env
 docker compose up -d
 ```
 
-After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process.
+After running, you can access the Dify dashboard in your browser at [http://localhost/install](http://localhost/install) and start the initialization process. You will be asked to setup an admin account.
+For more info of quick setup, check [here](https://docs.dify.ai/getting-started/install-self-hosted/docker-compose)
 
-#### Seeking help
-Please refer to our [FAQ](https://docs.dify.ai/getting-started/install-self-hosted/faqs) if you encounter problems setting up Dify. Reach out to [the community and us](#community--contact) if you are still having issues.
+## Intro
+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>
 
-> If you'd like to contribute to Dify or do additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
-
-## Key features
 **1. Workflow**: 
   Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
 
@@ -123,8 +149,20 @@ Star Dify on GitHub and be instantly notified of new releases.
 
 ![star-us](https://github.com/langgenius/dify/assets/13230914/b823edc1-6388-4e25-ad45-2f6b187adbb4)
 
+## Next steps
 
-## Advanced Setup
+Go to [quick-start](https://github.com/langgenius/dify?tab=readme-ov-file#quick-start) to setup your Dify or setup by source code.
+
+#### If you......
+If you forget your admin account, you can refer to this [guide](https://docs.dify.ai/getting-started/install-self-hosted/faqs#id-4.-how-to-reset-the-password-of-the-admin-account) to reset the password.
+
+> Use docker compose up without "-d" to enable logs printing out in your terminal. This might be useful if you have encountered unknow problems when using Dify.
+
+If you encountered system error and would like to acquire help in Github issues, make sure you always paste logs of the error in the request to accerate the conversation. Go to [Community & contact](https://github.com/langgenius/dify?tab=readme-ov-file#community--contact) for more information.
+
+> Please read the [Dify Documentation](https://docs.dify.ai/) for detailed how-to-use guidance. Most of the potential problems are explained in the doc.
+
+> If you'd like to contribute to Dify or make additional development, refer to our [guide to deploying from source code](https://docs.dify.ai/getting-started/install-self-hosted/local-source-code)
 
 If you need to customize the configuration, please refer to the comments in our [.env.example](docker/.env.example) file and update the corresponding values in your `.env` file. Additionally, you might need to make adjustments to the `docker-compose.yaml` file itself, such as changing image versions, port mappings, or volume mounts, based on your specific deployment environment and requirements. After making any changes, please re-run `docker-compose up -d`. You can find the full list of available environment variables [here](https://docs.dify.ai/getting-started/install-self-hosted/environments).
 
@@ -152,18 +190,19 @@ At the same time, please consider supporting Dify by sharing it on social media
 
 > 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**
+
+<a href="https://github.com/langgenius/dify/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
+</a>
+
 ## 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.
 * [X(Twitter)](https://twitter.com/dify_ai). Best for: sharing your applications and hanging out with the community.
-
-**Contributors**
-
-<a href="https://github.com/langgenius/dify/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=langgenius/dify" />
-</a>
+* Make sure a log, if possible, is attached to an error reported to maximize solution efficiency.
 
 ## Star history
 
@@ -177,4 +216,3 @@ To protect your privacy, please avoid posting security issues on GitHub. Instead
 ## License
 
 This repository is available under the [Dify Open Source License](LICENSE), which is essentially Apache 2.0 with a few additional restrictions.
-

api/.env.example

@@ -121,7 +121,7 @@ WEB_API_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 CONSOLE_CORS_ALLOW_ORIGINS=http://127.0.0.1:3000,*
 
 
-# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm, oceanbase
+# Vector database configuration, support: weaviate, qdrant, milvus, myscale, relyt, pgvecto_rs, pgvector, pgvector, chroma, opensearch, tidb_vector, couchbase, vikingdb, upstash, lindorm
 VECTOR_STORE=weaviate
 
 # Weaviate configuration
@@ -273,7 +273,7 @@ LINDORM_PASSWORD=admin
 OCEANBASE_VECTOR_HOST=127.0.0.1
 OCEANBASE_VECTOR_PORT=2881
 OCEANBASE_VECTOR_USER=root@test
-OCEANBASE_VECTOR_PASSWORD=difyai123456
+OCEANBASE_VECTOR_PASSWORD=
 OCEANBASE_VECTOR_DATABASE=test
 OCEANBASE_MEMORY_LIMIT=6G
 
@@ -285,9 +285,8 @@ UPLOAD_IMAGE_FILE_SIZE_LIMIT=10
 UPLOAD_VIDEO_FILE_SIZE_LIMIT=100
 UPLOAD_AUDIO_FILE_SIZE_LIMIT=50
 
-# Model configuration
+# Model Configuration
 MULTIMODAL_SEND_IMAGE_FORMAT=base64
-MULTIMODAL_SEND_VIDEO_FORMAT=base64
 PROMPT_GENERATION_MAX_TOKENS=512
 CODE_GENERATION_MAX_TOKENS=1024
 
@@ -321,14 +320,9 @@ ETL_TYPE=dify
 UNSTRUCTURED_API_URL=
 UNSTRUCTURED_API_KEY=
 
-#ssrf
 SSRF_PROXY_HTTP_URL=
 SSRF_PROXY_HTTPS_URL=
 SSRF_DEFAULT_MAX_RETRIES=3
-SSRF_DEFAULT_TIME_OUT=5
-SSRF_DEFAULT_CONNECT_TIME_OUT=5
-SSRF_DEFAULT_READ_TIME_OUT=5
-SSRF_DEFAULT_WRITE_TIME_OUT=5
 
 BATCH_UPLOAD_LIMIT=10
 KEYWORD_DATA_SOURCE_TYPE=database
@@ -367,10 +361,6 @@ LOG_FILE=
 LOG_FILE_MAX_SIZE=20
 # Log file max backup count
 LOG_FILE_BACKUP_COUNT=5
-# Log dateformat
-LOG_DATEFORMAT=%Y-%m-%d %H:%M:%S
-# Log Timezone
-LOG_TZ=UTC
 
 # Indexing configuration
 INDEXING_MAX_SEGMENTATION_TOKENS_LENGTH=1000
@@ -400,5 +390,3 @@ POSITION_PROVIDER_EXCLUDES=
 
 # Reset password token expiry minutes
 RESET_PASSWORD_TOKEN_EXPIRY_MINUTES=5
-
-CREATE_TIDB_SERVICE_JOB_ENABLED=false

api/Dockerfile

@@ -4,7 +4,7 @@ FROM python:3.10-slim-bookworm AS base
 WORKDIR /app/api
 
 # Install Poetry
-ENV POETRY_VERSION=1.8.4
+ENV POETRY_VERSION=1.8.3
 
 # if you located in China, you can use aliyun mirror to speed up
 # RUN pip install --no-cache-dir poetry==${POETRY_VERSION} -i https://mirrors.aliyun.com/pypi/simple/
@@ -55,7 +55,7 @@ RUN apt-get update \
     && echo "deb http://deb.debian.org/debian testing main" > /etc/apt/sources.list \
     && apt-get update \
     # For Security
-    && apt-get install -y --no-install-recommends expat=2.6.3-2 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-7 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
+    && apt-get install -y --no-install-recommends expat=2.6.3-2 libldap-2.5-0=2.5.18+dfsg-3+b1 perl=5.40.0-6 libsqlite3-0=3.46.1-1 zlib1g=1:1.3.dfsg+really1.3.1-1+b1 \
     # install a chinese font to support the use of tools like matplotlib
     && apt-get install -y fonts-noto-cjk \
     && apt-get autoremove -y \

api/README.md

@@ -76,13 +76,13 @@
 1. Install dependencies for both the backend and the test environment
 
    ```bash
-   poetry install -C api --with dev
+   poetry install --with dev
    ```
 
 2. Run the tests locally with mocked system environment variables in `tool.pytest_env` section in `pyproject.toml`
 
    ```bash
+   cd ../
    poetry run -C api bash dev/pytest/pytest_all_tests.sh
    ```
 
-

api/app.py

@@ -1,9 +1,8 @@
 import os
-import sys
 
 from configs import dify_config
 
-if not dify_config.DEBUG:
+if os.environ.get("DEBUG", "false").lower() != "true":
     from gevent import monkey
 
     monkey.patch_all()
@@ -30,9 +29,6 @@ from models import account, dataset, model, source, task, tool, tools, web  # no
 
 # DO NOT REMOVE ABOVE
 
-if sys.version_info[:2] == (3, 10):
-    print("Warning: Python 3.10 will not be supported in the next version.")
-
 
 warnings.simplefilter("ignore", ResourceWarning)
 

api/app_factory.py

@@ -1,8 +1,6 @@
 import os
 
-from configs import dify_config
-
-if not dify_config.DEBUG:
+if os.environ.get("DEBUG", "false").lower() != "true":
     from gevent import monkey
 
     monkey.patch_all()

api/configs/feature/__init__.py

@@ -109,7 +109,7 @@ class CodeExecutionSandboxConfig(BaseSettings):
     )
 
     CODE_MAX_PRECISION: PositiveInt = Field(
-        description="Maximum number of decimal places for floating-point numbers in code execution",
+        description="mMaximum number of decimal places for floating-point numbers in code execution",
         default=20,
     )
 
@@ -276,16 +276,6 @@ class HttpConfig(BaseSettings):
         default=1 * 1024 * 1024,
     )
 
-    SSRF_DEFAULT_MAX_RETRIES: PositiveInt = Field(
-        description="Maximum number of retries for network requests (SSRF)",
-        default=3,
-    )
-
-    SSRF_PROXY_ALL_URL: Optional[str] = Field(
-        description="Proxy URL for HTTP or HTTPS requests to prevent Server-Side Request Forgery (SSRF)",
-        default=None,
-    )
-
     SSRF_PROXY_HTTP_URL: Optional[str] = Field(
         description="Proxy URL for HTTP requests to prevent Server-Side Request Forgery (SSRF)",
         default=None,
@@ -296,26 +286,6 @@ class HttpConfig(BaseSettings):
         default=None,
     )
 
-    SSRF_DEFAULT_TIME_OUT: PositiveFloat = Field(
-        description="The default timeout period used for network requests (SSRF)",
-        default=5,
-    )
-
-    SSRF_DEFAULT_CONNECT_TIME_OUT: PositiveFloat = Field(
-        description="The default connect timeout period used for network requests (SSRF)",
-        default=5,
-    )
-
-    SSRF_DEFAULT_READ_TIME_OUT: PositiveFloat = Field(
-        description="The default read timeout period used for network requests (SSRF)",
-        default=5,
-    )
-
-    SSRF_DEFAULT_WRITE_TIME_OUT: PositiveFloat = Field(
-        description="The default write timeout period used for network requests (SSRF)",
-        default=5,
-    )
-
     RESPECT_XFORWARD_HEADERS_ENABLED: bool = Field(
         description="Enable or disable the X-Forwarded-For Proxy Fix middleware from Werkzeug"
         " to respect X-* headers to redirect clients",
@@ -376,7 +346,7 @@ class LoggingConfig(BaseSettings):
 
     LOG_TZ: Optional[str] = Field(
         description="Timezone for log timestamps (e.g., 'America/New_York')",
-        default="UTC",
+        default=None,
     )
 
 
@@ -611,11 +581,6 @@ class DataSetConfig(BaseSettings):
         default=500,
     )
 
-    CREATE_TIDB_SERVICE_JOB_ENABLED: bool = Field(
-        description="Enable or disable create tidb service job",
-        default=False,
-    )
-
 
 class WorkspaceConfig(BaseSettings):
     """
@@ -639,17 +604,12 @@ class IndexingConfig(BaseSettings):
     )
 
 
-class VisionFormatConfig(BaseSettings):
+class ImageFormatConfig(BaseSettings):
     MULTIMODAL_SEND_IMAGE_FORMAT: Literal["base64", "url"] = Field(
         description="Format for sending images in multimodal contexts ('base64' or 'url'), default is base64",
         default="base64",
     )
 
-    MULTIMODAL_SEND_VIDEO_FORMAT: Literal["base64", "url"] = Field(
-        description="Format for sending videos in multimodal contexts ('base64' or 'url'), default is base64",
-        default="base64",
-    )
-
 
 class CeleryBeatConfig(BaseSettings):
     CELERY_BEAT_SCHEDULER_TIME: int = Field(
@@ -752,7 +712,7 @@ class FeatureConfig(
     FileAccessConfig,
     FileUploadConfig,
     HttpConfig,
-    VisionFormatConfig,
+    ImageFormatConfig,
     InnerAPIConfig,
     IndexingConfig,
     LoggingConfig,

api/configs/packaging/__init__.py

@@ -9,7 +9,7 @@ class PackagingInfo(BaseSettings):
 
     CURRENT_VERSION: str = Field(
         description="Dify version",
-        default="0.11.1",
+        default="0.10.2",
     )
 
     COMMIT_SHA: str = Field(

api/controllers/console/__init__.py

@@ -55,6 +55,7 @@ from .datasets import (
     datasets_document,
     datasets_segments,
     external,
+    fta_test,
     hit_testing,
     website,
 )

api/controllers/console/datasets/datasets_document.py

@@ -317,11 +317,8 @@ class DatasetInitApi(Resource):
                 raise ValueError("embedding model and embedding model provider are required for high quality indexing.")
             try:
                 model_manager = ModelManager()
-                model_manager.get_model_instance(
-                    tenant_id=current_user.current_tenant_id,
-                    provider=args["embedding_model_provider"],
-                    model_type=ModelType.TEXT_EMBEDDING,
-                    model=args["embedding_model"],
+                model_manager.get_default_model_instance(
+                    tenant_id=current_user.current_tenant_id, model_type=ModelType.TEXT_EMBEDDING
                 )
             except InvokeAuthorizationError:
                 raise ProviderNotInitializeError(
@@ -948,7 +945,7 @@ class DocumentRetryApi(DocumentResource):
                     raise DocumentAlreadyFinishedError()
                 retry_documents.append(document)
             except Exception as e:
-                logging.exception(f"Document {document_id} retry failed: {str(e)}")
+                logging.error(f"Document {document_id} retry failed: {str(e)}")
                 continue
         # retry document
         DocumentService.retry_document(dataset_id, retry_documents)

api/controllers/console/datasets/fta_test.py

@@ -0,0 +1,145 @@
+import json
+
+import requests
+from flask import Response
+from flask_restful import Resource, reqparse
+from sqlalchemy import text
+
+from controllers.console import api
+from extensions.ext_database import db
+from extensions.ext_storage import storage
+from models.fta import ComponentFailure, ComponentFailureStats
+
+
+class FATTestApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("log_process_data", nullable=False, required=True, type=str, location="args")
+        args = parser.parse_args()
+        print(args["log_process_data"])
+        # Extract the JSON string from the text field
+        json_str = args["log_process_data"].strip("```json\\n").strip("```").strip().replace("\\n", "")
+        log_data = json.loads(json_str)
+        db.session.query(ComponentFailure).delete()
+        for data in log_data:
+            if not isinstance(data, dict):
+                raise TypeError("Data must be a dictionary.")
+
+            required_keys = {"Date", "Component", "FailureMode", "Cause", "RepairAction", "Technician"}
+            if not required_keys.issubset(data.keys()):
+                raise ValueError(f"Data dictionary must contain the following keys: {required_keys}")
+
+            try:
+                # Clear existing stats
+                component_failure = ComponentFailure(
+                    Date=data["Date"],
+                    Component=data["Component"],
+                    FailureMode=data["FailureMode"],
+                    Cause=data["Cause"],
+                    RepairAction=data["RepairAction"],
+                    Technician=data["Technician"],
+                )
+                db.session.add(component_failure)
+                db.session.commit()
+            except Exception as e:
+                print(e)
+        # Clear existing stats
+        db.session.query(ComponentFailureStats).delete()
+
+        # Insert calculated statistics
+        try:
+            db.session.execute(
+                text("""
+                    INSERT INTO component_failure_stats ("Component", "FailureMode", "Cause", "PossibleAction", "Probability", "MTBF")
+                    SELECT 
+                        cf."Component",
+                        cf."FailureMode",
+                        cf."Cause",
+                        cf."RepairAction" as "PossibleAction",
+                        COUNT(*) * 1.0 / (SELECT COUNT(*) FROM component_failure WHERE "Component" = cf."Component") AS "Probability",
+                        COALESCE(AVG(EXTRACT(EPOCH FROM (next_failure_date::timestamp - cf."Date"::timestamp)) / 86400.0),0)AS "MTBF"
+                    FROM (
+                        SELECT 
+                            "Component",
+                            "FailureMode",
+                            "Cause",
+                            "RepairAction",
+                            "Date", 
+                            LEAD("Date") OVER (PARTITION BY "Component", "FailureMode", "Cause" ORDER BY "Date") AS next_failure_date
+                        FROM 
+                            component_failure
+                    ) cf
+                    GROUP BY 
+                        cf."Component", cf."FailureMode", cf."Cause", cf."RepairAction";
+            """)
+            )
+            db.session.commit()
+        except Exception as e:
+            db.session.rollback()
+            print(f"Error during stats calculation: {e}")
+        # output format
+        # [
+        #     (17, 'Hydraulic system', 'Leak', 'Hose rupture', 'Replaced hydraulic hose', 0.3333333333333333, None),
+        #     (18, 'Hydraulic system', 'Leak', 'Seal Wear', 'Replaced the faulty seal', 0.3333333333333333, None),
+        #     (19, 'Hydraulic system', 'Pressure drop', 'Fluid leak', 'Replaced hydraulic fluid and seals', 0.3333333333333333, None)
+        # ]
+
+        component_failure_stats = db.session.query(ComponentFailureStats).all()
+        # Convert stats to list of tuples format
+        stats_list = []
+        for stat in component_failure_stats:
+            stats_list.append(
+                (
+                    stat.StatID,
+                    stat.Component,
+                    stat.FailureMode,
+                    stat.Cause,
+                    stat.PossibleAction,
+                    stat.Probability,
+                    stat.MTBF,
+                )
+            )
+        return {"data": stats_list}, 200
+
+
+# generate-fault-tree
+class GenerateFaultTreeApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("llm_text", nullable=False, required=True, type=str, location="args")
+        args = parser.parse_args()
+        entities = args["llm_text"].replace("```", "").replace("\\n", "\n")
+        print(entities)
+        request_data = {"fault_tree_text": entities}
+        url = "https://fta.cognitech-dev.live/generate-fault-tree"
+        headers = {"accept": "application/json", "Content-Type": "application/json"}
+
+        response = requests.post(url, json=request_data, headers=headers)
+        print(response.json())
+        return {"data": response.json()}, 200
+
+
+class ExtractSVGApi(Resource):
+    def post(self):
+        parser = reqparse.RequestParser()
+        parser.add_argument("svg_text", nullable=False, required=True, type=str, location="args")
+        args = parser.parse_args()
+        # svg_text = ''.join(args["svg_text"].splitlines())
+        svg_text = args["svg_text"].replace("\n", "")
+        svg_text = svg_text.replace('"', '"')
+        print(svg_text)
+        svg_text_json = json.loads(svg_text)
+        svg_content = svg_text_json.get("data").get("svg_content")[0]
+        svg_content = svg_content.replace("\n", "").replace('"', '"')
+        file_key = "fta_svg/" + "fat.svg"
+        if storage.exists(file_key):
+            storage.delete(file_key)
+        storage.save(file_key, svg_content.encode("utf-8"))
+        generator = storage.load(file_key, stream=True)
+
+        return Response(generator, mimetype="image/svg+xml")
+
+
+api.add_resource(FATTestApi, "/fta/db-handler")
+api.add_resource(GenerateFaultTreeApi, "/fta/generate-fault-tree")
+api.add_resource(ExtractSVGApi, "/fta/extract-svg")

api/controllers/console/error.py

@@ -62,27 +62,3 @@ class EmailSendIpLimitError(BaseHTTPException):
     error_code = "email_send_ip_limit"
     description = "Too many emails have been sent from this IP address recently. Please try again later."
     code = 429
-
-
-class FileTooLargeError(BaseHTTPException):
-    error_code = "file_too_large"
-    description = "File size exceeded. {message}"
-    code = 413
-
-
-class UnsupportedFileTypeError(BaseHTTPException):
-    error_code = "unsupported_file_type"
-    description = "File type not allowed."
-    code = 415
-
-
-class TooManyFilesError(BaseHTTPException):
-    error_code = "too_many_files"
-    description = "Only one file is allowed."
-    code = 400
-
-
-class NoFileUploadedError(BaseHTTPException):
-    error_code = "no_file_uploaded"
-    description = "Please upload your file."
-    code = 400

api/controllers/console/files/__init__.py

@@ -15,7 +15,7 @@ from fields.file_fields import file_fields, upload_config_fields
 from libs.login import login_required
 from services.file_service import FileService
 
-from .error import (
+from .errors import (
     FileTooLargeError,
     NoFileUploadedError,
     TooManyFilesError,

api/controllers/console/files/errors.py

@@ -0,0 +1,25 @@
+from libs.exception import BaseHTTPException
+
+
+class FileTooLargeError(BaseHTTPException):
+    error_code = "file_too_large"
+    description = "File size exceeded. {message}"
+    code = 413
+
+
+class UnsupportedFileTypeError(BaseHTTPException):
+    error_code = "unsupported_file_type"
+    description = "File type not allowed."
+    code = 415
+
+
+class TooManyFilesError(BaseHTTPException):
+    error_code = "too_many_files"
+    description = "Only one file is allowed."
+    code = 400
+
+
+class NoFileUploadedError(BaseHTTPException):
+    error_code = "no_file_uploaded"
+    description = "Please upload your file."
+    code = 400

api/controllers/console/remote_files.py

@@ -1,11 +1,9 @@
 import urllib.parse
 from typing import cast
 
-import httpx
 from flask_login import current_user
 from flask_restful import Resource, marshal_with, reqparse
 
-import services
 from controllers.common import helpers
 from core.file import helpers as file_helpers
 from core.helper import ssrf_proxy
@@ -13,25 +11,19 @@ from fields.file_fields import file_fields_with_signed_url, remote_file_info_fie
 from models.account import Account
 from services.file_service import FileService
 
-from .error import (
-    FileTooLargeError,
-    UnsupportedFileTypeError,
-)
-
 
 class RemoteFileInfoApi(Resource):
     @marshal_with(remote_file_info_fields)
     def get(self, url):
         decoded_url = urllib.parse.unquote(url)
-        resp = ssrf_proxy.head(decoded_url)
-        if resp.status_code != httpx.codes.OK:
-            # failed back to get method
-            resp = ssrf_proxy.get(decoded_url, timeout=3)
-        resp.raise_for_status()
-        return {
-            "file_type": resp.headers.get("Content-Type", "application/octet-stream"),
-            "file_length": int(resp.headers.get("Content-Length", 0)),
-        }
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", 0)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
 
 
 class RemoteFileUploadApi(Resource):
@@ -43,17 +35,17 @@ class RemoteFileUploadApi(Resource):
 
         url = args["url"]
 
-        resp = ssrf_proxy.head(url=url)
-        if resp.status_code != httpx.codes.OK:
-            resp = ssrf_proxy.get(url=url, timeout=3)
-        resp.raise_for_status()
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
 
-        file_info = helpers.guess_file_info_from_response(resp)
+        file_info = helpers.guess_file_info_from_response(response)
 
         if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
-            raise FileTooLargeError
+            return {"error": "File size exceeded"}, 400
 
-        content = resp.content if resp.request.method == "GET" else ssrf_proxy.get(url).content
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
 
         try:
             user = cast(Account, current_user)
@@ -64,10 +56,8 @@ class RemoteFileUploadApi(Resource):
                 user=user,
                 source_url=url,
             )
-        except services.errors.file.FileTooLargeError as file_too_large_error:
-            raise FileTooLargeError(file_too_large_error.description)
-        except services.errors.file.UnsupportedFileTypeError:
-            raise UnsupportedFileTypeError()
+        except Exception as e:
+            return {"error": str(e)}, 400
 
         return {
             "id": upload_file.id,

api/controllers/service_api/app/conversation.py

@@ -7,11 +7,7 @@ from controllers.service_api import api
 from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from core.app.entities.app_invoke_entities import InvokeFrom
-from fields.conversation_fields import (
-    conversation_delete_fields,
-    conversation_infinite_scroll_pagination_fields,
-    simple_conversation_fields,
-)
+from fields.conversation_fields import conversation_infinite_scroll_pagination_fields, simple_conversation_fields
 from libs.helper import uuid_value
 from models.model import App, AppMode, EndUser
 from services.conversation_service import ConversationService
@@ -53,7 +49,7 @@ class ConversationApi(Resource):
 
 class ConversationDetailApi(Resource):
     @validate_app_token(fetch_user_arg=FetchUserArg(fetch_from=WhereisUserArg.JSON))
-    @marshal_with(conversation_delete_fields)
+    @marshal_with(simple_conversation_fields)
     def delete(self, app_model: App, end_user: EndUser, c_id):
         app_mode = AppMode.value_of(app_model.mode)
         if app_mode not in {AppMode.CHAT, AppMode.AGENT_CHAT, AppMode.ADVANCED_CHAT}:

api/controllers/service_api/app/file.py

@@ -41,6 +41,7 @@ class FileApi(Resource):
                 content=file.read(),
                 mimetype=file.mimetype,
                 user=end_user,
+                source="datasets",
             )
         except services.errors.file.FileTooLargeError as file_too_large_error:
             raise FileTooLargeError(file_too_large_error.description)

api/controllers/service_api/app/message.py

@@ -10,7 +10,6 @@ from controllers.service_api.app.error import NotChatAppError
 from controllers.service_api.wraps import FetchUserArg, WhereisUserArg, validate_app_token
 from core.app.entities.app_invoke_entities import InvokeFrom
 from fields.conversation_fields import message_file_fields
-from fields.raws import FilesContainedField
 from libs.helper import TimestampField, uuid_value
 from models.model import App, AppMode, EndUser
 from services.errors.message import SuggestedQuestionsAfterAnswerDisabledError
@@ -56,7 +55,7 @@ class MessageListApi(Resource):
         "id": fields.String,
         "conversation_id": fields.String,
         "parent_message_id": fields.String,
-        "inputs": FilesContainedField,
+        "inputs": fields.Raw,
         "query": fields.String,
         "answer": fields.String(attribute="re_sign_file_url_answer"),
         "message_files": fields.List(fields.Nested(message_file_fields)),

api/controllers/web/remote_files.py

@@ -1,9 +1,7 @@
 import urllib.parse
 
-import httpx
 from flask_restful import marshal_with, reqparse
 
-import services
 from controllers.common import helpers
 from controllers.web.wraps import WebApiResource
 from core.file import helpers as file_helpers
@@ -11,22 +9,19 @@ from core.helper import ssrf_proxy
 from fields.file_fields import file_fields_with_signed_url, remote_file_info_fields
 from services.file_service import FileService
 
-from .error import FileTooLargeError, UnsupportedFileTypeError
-
 
 class RemoteFileInfoApi(WebApiResource):
     @marshal_with(remote_file_info_fields)
-    def get(self, app_model, end_user, url):
+    def get(self, url):
         decoded_url = urllib.parse.unquote(url)
-        resp = ssrf_proxy.head(decoded_url)
-        if resp.status_code != httpx.codes.OK:
-            # failed back to get method
-            resp = ssrf_proxy.get(decoded_url, timeout=3)
-        resp.raise_for_status()
-        return {
-            "file_type": resp.headers.get("Content-Type", "application/octet-stream"),
-            "file_length": int(resp.headers.get("Content-Length", -1)),
-        }
+        try:
+            response = ssrf_proxy.head(decoded_url)
+            return {
+                "file_type": response.headers.get("Content-Type", "application/octet-stream"),
+                "file_length": int(response.headers.get("Content-Length", -1)),
+            }
+        except Exception as e:
+            return {"error": str(e)}, 400
 
 
 class RemoteFileUploadApi(WebApiResource):
@@ -38,30 +33,28 @@ class RemoteFileUploadApi(WebApiResource):
 
         url = args["url"]
 
-        resp = ssrf_proxy.head(url=url)
-        if resp.status_code != httpx.codes.OK:
-            resp = ssrf_proxy.get(url=url, timeout=3)
-        resp.raise_for_status()
+        response = ssrf_proxy.head(url)
+        response.raise_for_status()
 
-        file_info = helpers.guess_file_info_from_response(resp)
+        file_info = helpers.guess_file_info_from_response(response)
 
         if not FileService.is_file_size_within_limit(extension=file_info.extension, file_size=file_info.size):
-            raise FileTooLargeError
+            return {"error": "File size exceeded"}, 400
 
-        content = resp.content if resp.request.method == "GET" else ssrf_proxy.get(url).content
+        response = ssrf_proxy.get(url)
+        response.raise_for_status()
+        content = response.content
 
         try:
             upload_file = FileService.upload_file(
                 filename=file_info.filename,
                 content=content,
                 mimetype=file_info.mimetype,
-                user=end_user,
+                user=end_user,  # Use end_user instead of current_user
                 source_url=url,
             )
-        except services.errors.file.FileTooLargeError as file_too_large_error:
-            raise FileTooLargeError(file_too_large_error.description)
-        except services.errors.file.UnsupportedFileTypeError:
-            raise UnsupportedFileTypeError
+        except Exception as e:
+            return {"error": str(e)}, 400
 
         return {
             "id": upload_file.id,

api/core/agent/base_agent_runner.py

@@ -30,7 +30,6 @@ from core.model_runtime.entities import (
     ToolPromptMessage,
     UserPromptMessage,
 )
-from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.model_runtime.entities.model_entities import ModelFeature
 from core.model_runtime.model_providers.__base.large_language_model import LargeLanguageModel
 from core.model_runtime.utils.encoders import jsonable_encoder
@@ -66,7 +65,7 @@ class BaseAgentRunner(AppRunner):
         prompt_messages: Optional[list[PromptMessage]] = None,
         variables_pool: Optional[ToolRuntimeVariablePool] = None,
         db_variables: Optional[ToolConversationVariables] = None,
-        model_instance: ModelInstance | None = None,
+        model_instance: ModelInstance = None,
     ) -> None:
         self.tenant_id = tenant_id
         self.application_generate_entity = application_generate_entity
@@ -509,27 +508,24 @@ class BaseAgentRunner(AppRunner):
 
     def organize_agent_user_prompt(self, message: Message) -> UserPromptMessage:
         files = db.session.query(MessageFile).filter(MessageFile.message_id == message.id).all()
-        if not files:
-            return UserPromptMessage(content=message.query)
-        file_extra_config = FileUploadConfigManager.convert(message.app_model_config.to_dict())
-        if not file_extra_config:
-            return UserPromptMessage(content=message.query)
+        if files:
+            file_extra_config = FileUploadConfigManager.convert(message.app_model_config.to_dict())
 
-        image_detail_config = file_extra_config.image_config.detail if file_extra_config.image_config else None
-        image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
-
-        file_objs = file_factory.build_from_message_files(
-            message_files=files, tenant_id=self.tenant_id, config=file_extra_config
-        )
-        if not file_objs:
-            return UserPromptMessage(content=message.query)
-        prompt_message_contents: list[PromptMessageContent] = []
-        prompt_message_contents.append(TextPromptMessageContent(data=message.query))
-        for file in file_objs:
-            prompt_message_contents.append(
-                file_manager.to_prompt_message_content(
-                    file,
-                    image_detail_config=image_detail_config,
+            if file_extra_config:
+                file_objs = file_factory.build_from_message_files(
+                    message_files=files, tenant_id=self.tenant_id, config=file_extra_config
                 )
-            )
-        return UserPromptMessage(content=prompt_message_contents)
+            else:
+                file_objs = []
+
+            if not file_objs:
+                return UserPromptMessage(content=message.query)
+            else:
+                prompt_message_contents: list[PromptMessageContent] = []
+                prompt_message_contents.append(TextPromptMessageContent(data=message.query))
+                for file_obj in file_objs:
+                    prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
+
+                return UserPromptMessage(content=prompt_message_contents)
+        else:
+            return UserPromptMessage(content=message.query)

api/core/agent/cot_chat_agent_runner.py

@@ -10,7 +10,6 @@ from core.model_runtime.entities import (
     TextPromptMessageContent,
     UserPromptMessage,
 )
-from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.model_runtime.utils.encoders import jsonable_encoder
 
 
@@ -37,24 +36,8 @@ class CotChatAgentRunner(CotAgentRunner):
         if self.files:
             prompt_message_contents: list[PromptMessageContent] = []
             prompt_message_contents.append(TextPromptMessageContent(data=query))
-
-            # get image detail config
-            image_detail_config = (
-                self.application_generate_entity.file_upload_config.image_config.detail
-                if (
-                    self.application_generate_entity.file_upload_config
-                    and self.application_generate_entity.file_upload_config.image_config
-                )
-                else None
-            )
-            image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
-            for file in self.files:
-                prompt_message_contents.append(
-                    file_manager.to_prompt_message_content(
-                        file,
-                        image_detail_config=image_detail_config,
-                    )
-                )
+            for file_obj in self.files:
+                prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
 
             prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
         else:

api/core/agent/fc_agent_runner.py

@@ -22,7 +22,6 @@ from core.model_runtime.entities import (
     ToolPromptMessage,
     UserPromptMessage,
 )
-from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.prompt.agent_history_prompt_transform import AgentHistoryPromptTransform
 from core.tools.entities.tool_entities import ToolInvokeMeta
 from core.tools.tool_engine import ToolEngine
@@ -398,24 +397,8 @@ class FunctionCallAgentRunner(BaseAgentRunner):
         if self.files:
             prompt_message_contents: list[PromptMessageContent] = []
             prompt_message_contents.append(TextPromptMessageContent(data=query))
-
-            # get image detail config
-            image_detail_config = (
-                self.application_generate_entity.file_upload_config.image_config.detail
-                if (
-                    self.application_generate_entity.file_upload_config
-                    and self.application_generate_entity.file_upload_config.image_config
-                )
-                else None
-            )
-            image_detail_config = image_detail_config or ImagePromptMessageContent.DETAIL.LOW
-            for file in self.files:
-                prompt_message_contents.append(
-                    file_manager.to_prompt_message_content(
-                        file,
-                        image_detail_config=image_detail_config,
-                    )
-                )
+            for file_obj in self.files:
+                prompt_message_contents.append(file_manager.to_prompt_message_content(file_obj))
 
             prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
         else:

api/core/app/app_config/entities.py

@@ -4,7 +4,7 @@ from typing import Any, Optional
 
 from pydantic import BaseModel, Field, field_validator
 
-from core.file import FileTransferMethod, FileType, FileUploadConfig
+from core.file import FileExtraConfig, FileTransferMethod, FileType
 from core.model_runtime.entities.message_entities import PromptMessageRole
 from models.model import AppMode
 
@@ -211,7 +211,7 @@ class TracingConfigEntity(BaseModel):
 
 
 class AppAdditionalFeatures(BaseModel):
-    file_upload: Optional[FileUploadConfig] = None
+    file_upload: Optional[FileExtraConfig] = None
     opening_statement: Optional[str] = None
     suggested_questions: list[str] = []
     suggested_questions_after_answer: bool = False

api/core/app/app_config/features/file_upload/manager.py

@@ -1,7 +1,7 @@
 from collections.abc import Mapping
 from typing import Any
 
-from core.file import FileUploadConfig
+from core.file import FileExtraConfig
 
 
 class FileUploadConfigManager:
@@ -29,18 +29,19 @@ class FileUploadConfigManager:
                 if is_vision:
                     data["image_config"]["detail"] = file_upload_dict.get("image", {}).get("detail", "low")
 
-                return FileUploadConfig.model_validate(data)
+                return FileExtraConfig.model_validate(data)
 
     @classmethod
-    def validate_and_set_defaults(cls, config: dict) -> tuple[dict, list[str]]:
+    def validate_and_set_defaults(cls, config: dict, is_vision: bool = True) -> tuple[dict, list[str]]:
         """
         Validate and set defaults for file upload feature
 
         :param config: app model config args
+        :param is_vision: if True, the feature is vision feature
         """
         if not config.get("file_upload"):
             config["file_upload"] = {}
         else:
-            FileUploadConfig.model_validate(config["file_upload"])
+            FileExtraConfig.model_validate(config["file_upload"])
 
         return config, ["file_upload"]

api/core/app/apps/advanced_chat/app_config_manager.py

@@ -52,7 +52,9 @@ class AdvancedChatAppConfigManager(BaseAppConfigManager):
         related_config_keys = []
 
         # file upload validation
-        config, current_related_config_keys = FileUploadConfigManager.validate_and_set_defaults(config=config)
+        config, current_related_config_keys = FileUploadConfigManager.validate_and_set_defaults(
+            config=config, is_vision=False
+        )
         related_config_keys.extend(current_related_config_keys)
 
         # opening_statement

api/core/app/apps/advanced_chat/app_generator.py

@@ -1,5 +1,6 @@
 import contextvars
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -9,7 +10,6 @@ from flask import Flask, current_app
 from pydantic import ValidationError
 
 import contexts
-from configs import dify_config
 from constants import UUID_NIL
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.advanced_chat.app_config_manager import AdvancedChatAppConfigManager
@@ -26,6 +26,7 @@ from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
 from models.account import Account
+from models.enums import CreatedByRole
 from models.model import App, Conversation, EndUser, Message
 from models.workflow import Workflow
 
@@ -97,10 +98,13 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         # parse files
         files = args["files"] if args.get("files") else []
         file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
+        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
         if file_extra_config:
             file_objs = file_factory.build_from_mappings(
                 mappings=files,
                 tenant_id=app_model.tenant_id,
+                user_id=user.id,
+                role=role,
                 config=file_extra_config,
             )
         else:
@@ -123,11 +127,10 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
         application_generate_entity = AdvancedChatAppGenerateEntity(
             task_id=str(uuid.uuid4()),
             app_config=app_config,
-            file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
@@ -314,7 +317,7 @@ class AdvancedChatAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
-                if dify_config.DEBUG:
+                if os.environ.get("DEBUG", "false").lower() == "true":
                     logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except Exception as e:

api/core/app/apps/advanced_chat/generate_task_pipeline.py

@@ -242,7 +242,7 @@ class AdvancedChatAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCyc
                     start_listener_time = time.time()
                     yield MessageAudioStreamResponse(audio=audio_trunk.audio, task_id=task_id)
             except Exception as e:
-                logger.exception(e)
+                logger.error(e)
                 break
         if tts_publisher:
             yield MessageAudioEndStreamResponse(audio="", task_id=task_id)

api/core/app/apps/agent_chat/app_generator.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -7,7 +8,6 @@ from typing import Any, Literal, Union, overload
 from flask import Flask, current_app
 from pydantic import ValidationError
 
-from configs import dify_config
 from constants import UUID_NIL
 from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
@@ -23,6 +23,7 @@ from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
 from models import Account, App, EndUser
+from models.enums import CreatedByRole
 
 logger = logging.getLogger(__name__)
 
@@ -102,6 +103,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             # always enable retriever resource in debugger mode
             override_model_config_dict["retriever_resource"] = {"enabled": True}
 
+        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
+
         # parse files
         files = args.get("files") or []
         file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
@@ -109,6 +112,8 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             file_objs = file_factory.build_from_mappings(
                 mappings=files,
                 tenant_id=app_model.tenant_id,
+                user_id=user.id,
+                role=role,
                 config=file_extra_config,
             )
         else:
@@ -130,11 +135,10 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
             task_id=str(uuid.uuid4()),
             app_config=app_config,
             model_conf=ModelConfigConverter.convert(app_config),
-            file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
@@ -226,7 +230,7 @@ class AgentChatAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
-                if dify_config.DEBUG:
+                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:

api/core/app/apps/base_app_generator.py

@@ -2,11 +2,12 @@ from collections.abc import Mapping
 from typing import TYPE_CHECKING, Any, Optional
 
 from core.app.app_config.entities import VariableEntityType
-from core.file import File, FileUploadConfig
+from core.file import File, FileExtraConfig
 from factories import file_factory
 
 if TYPE_CHECKING:
     from core.app.app_config.entities import AppConfig, VariableEntity
+    from models.enums import CreatedByRole
 
 
 class BaseAppGenerator:
@@ -15,6 +16,8 @@ class BaseAppGenerator:
         *,
         user_inputs: Optional[Mapping[str, Any]],
         app_config: "AppConfig",
+        user_id: str,
+        role: "CreatedByRole",
     ) -> Mapping[str, Any]:
         user_inputs = user_inputs or {}
         # Filter input variables from form configuration, handle required fields, default values, and option values
@@ -31,7 +34,9 @@ class BaseAppGenerator:
             k: file_factory.build_from_mapping(
                 mapping=v,
                 tenant_id=app_config.tenant_id,
-                config=FileUploadConfig(
+                user_id=user_id,
+                role=role,
+                config=FileExtraConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
                     allowed_extensions=entity_dictionary[k].allowed_file_extensions,
                     allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,
@@ -45,7 +50,9 @@ class BaseAppGenerator:
             k: file_factory.build_from_mappings(
                 mappings=v,
                 tenant_id=app_config.tenant_id,
-                config=FileUploadConfig(
+                user_id=user_id,
+                role=role,
+                config=FileExtraConfig(
                     allowed_file_types=entity_dictionary[k].allowed_file_types,
                     allowed_extensions=entity_dictionary[k].allowed_file_extensions,
                     allowed_upload_methods=entity_dictionary[k].allowed_file_upload_methods,

api/core/app/apps/chat/app_generator.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -7,7 +8,6 @@ from typing import Any, Literal, Union, overload
 from flask import Flask, current_app
 from pydantic import ValidationError
 
-from configs import dify_config
 from constants import UUID_NIL
 from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
@@ -23,6 +23,7 @@ from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
 from models.account import Account
+from models.enums import CreatedByRole
 from models.model import App, EndUser
 
 logger = logging.getLogger(__name__)
@@ -100,6 +101,8 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             # always enable retriever resource in debugger mode
             override_model_config_dict["retriever_resource"] = {"enabled": True}
 
+        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
+
         # parse files
         files = args["files"] if args.get("files") else []
         file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
@@ -107,6 +110,8 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             file_objs = file_factory.build_from_mappings(
                 mappings=files,
                 tenant_id=app_model.tenant_id,
+                user_id=user.id,
+                role=role,
                 config=file_extra_config,
             )
         else:
@@ -128,11 +133,10 @@ class ChatAppGenerator(MessageBasedAppGenerator):
             task_id=str(uuid.uuid4()),
             app_config=app_config,
             model_conf=ModelConfigConverter.convert(app_config),
-            file_upload_config=file_extra_config,
             conversation_id=conversation.id if conversation else None,
             inputs=conversation.inputs
             if conversation
-            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            else self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
             parent_message_id=args.get("parent_message_id") if invoke_from != InvokeFrom.SERVICE_API else UUID_NIL,
@@ -223,7 +227,7 @@ class ChatAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
-                if dify_config.DEBUG:
+                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:

api/core/app/apps/completion/app_generator.py

@@ -1,4 +1,5 @@
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator
@@ -7,7 +8,6 @@ from typing import Any, Literal, Union, overload
 from flask import Flask, current_app
 from pydantic import ValidationError
 
-from configs import dify_config
 from core.app.app_config.easy_ui_based_app.model_config.converter import ModelConfigConverter
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedError, PublishFrom
@@ -22,6 +22,7 @@ from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
 from models import Account, App, EndUser, Message
+from models.enums import CreatedByRole
 from services.errors.app import MoreLikeThisDisabledError
 from services.errors.message import MessageNotExistsError
 
@@ -87,6 +88,8 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
                 tenant_id=app_model.tenant_id, config=args.get("model_config")
             )
 
+        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
+
         # parse files
         files = args["files"] if args.get("files") else []
         file_extra_config = FileUploadConfigManager.convert(override_model_config_dict or app_model_config.to_dict())
@@ -94,6 +97,8 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
             file_objs = file_factory.build_from_mappings(
                 mappings=files,
                 tenant_id=app_model.tenant_id,
+                user_id=user.id,
+                role=role,
                 config=file_extra_config,
             )
         else:
@@ -105,6 +110,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
         )
 
         # get tracing instance
+        user_id = user.id if isinstance(user, Account) else user.session_id
         trace_manager = TraceQueueManager(app_model.id)
 
         # init application generate entity
@@ -112,8 +118,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
             task_id=str(uuid.uuid4()),
             app_config=app_config,
             model_conf=ModelConfigConverter.convert(app_config),
-            file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             query=query,
             files=file_objs,
             user_id=user.id,
@@ -198,7 +203,7 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
-                if dify_config.DEBUG:
+                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:
@@ -254,11 +259,14 @@ class CompletionAppGenerator(MessageBasedAppGenerator):
         override_model_config_dict["model"] = model_dict
 
         # parse files
+        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
         file_extra_config = FileUploadConfigManager.convert(override_model_config_dict)
         if file_extra_config:
             file_objs = file_factory.build_from_mappings(
                 mappings=message.message_files,
                 tenant_id=app_model.tenant_id,
+                user_id=user.id,
+                role=role,
                 config=file_extra_config,
             )
         else:

api/core/app/apps/workflow/app_config_manager.py

@@ -46,7 +46,9 @@ class WorkflowAppConfigManager(BaseAppConfigManager):
         related_config_keys = []
 
         # file upload validation
-        config, current_related_config_keys = FileUploadConfigManager.validate_and_set_defaults(config=config)
+        config, current_related_config_keys = FileUploadConfigManager.validate_and_set_defaults(
+            config=config, is_vision=False
+        )
         related_config_keys.extend(current_related_config_keys)
 
         # text_to_speech

api/core/app/apps/workflow/app_generator.py

@@ -1,5 +1,6 @@
 import contextvars
 import logging
+import os
 import threading
 import uuid
 from collections.abc import Generator, Mapping, Sequence
@@ -9,7 +10,6 @@ from flask import Flask, current_app
 from pydantic import ValidationError
 
 import contexts
-from configs import dify_config
 from core.app.app_config.features.file_upload.manager import FileUploadConfigManager
 from core.app.apps.base_app_generator import BaseAppGenerator
 from core.app.apps.base_app_queue_manager import AppQueueManager, GenerateTaskStoppedError, PublishFrom
@@ -25,6 +25,7 @@ from core.ops.ops_trace_manager import TraceQueueManager
 from extensions.ext_database import db
 from factories import file_factory
 from models import Account, App, EndUser, Workflow
+from models.enums import CreatedByRole
 
 logger = logging.getLogger(__name__)
 
@@ -69,11 +70,15 @@ class WorkflowAppGenerator(BaseAppGenerator):
     ):
         files: Sequence[Mapping[str, Any]] = args.get("files") or []
 
+        role = CreatedByRole.ACCOUNT if isinstance(user, Account) else CreatedByRole.END_USER
+
         # parse files
         file_extra_config = FileUploadConfigManager.convert(workflow.features_dict, is_vision=False)
         system_files = file_factory.build_from_mappings(
             mappings=files,
             tenant_id=app_model.tenant_id,
+            user_id=user.id,
+            role=role,
             config=file_extra_config,
         )
 
@@ -95,8 +100,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
         application_generate_entity = WorkflowAppGenerateEntity(
             task_id=str(uuid.uuid4()),
             app_config=app_config,
-            file_upload_config=file_extra_config,
-            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config),
+            inputs=self._prepare_user_inputs(user_inputs=inputs, app_config=app_config, user_id=user.id, role=role),
             files=system_files,
             user_id=user.id,
             stream=stream,
@@ -257,7 +261,7 @@ class WorkflowAppGenerator(BaseAppGenerator):
                 logger.exception("Validation Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except (ValueError, InvokeError) as e:
-                if dify_config.DEBUG:
+                if os.environ.get("DEBUG") and os.environ.get("DEBUG", "false").lower() == "true":
                     logger.exception("Error when generating")
                 queue_manager.publish_error(e, PublishFrom.APPLICATION_MANAGER)
             except Exception as e:

api/core/app/apps/workflow/generate_task_pipeline.py

@@ -216,7 +216,7 @@ class WorkflowAppGenerateTaskPipeline(BasedGenerateTaskPipeline, WorkflowCycleMa
                 else:
                     yield MessageAudioStreamResponse(audio=audio_trunk.audio, task_id=task_id)
             except Exception as e:
-                logger.exception(e)
+                logger.error(e)
                 break
         if tts_publisher:
             yield MessageAudioEndStreamResponse(audio="", task_id=task_id)

api/core/app/apps/workflow_app_runner.py

@@ -361,7 +361,6 @@ class WorkflowBasedAppRunner(AppRunner):
                     node_run_index=workflow_entry.graph_engine.graph_runtime_state.node_run_steps,
                     output=event.pre_iteration_output,
                     parallel_mode_run_id=event.parallel_mode_run_id,
-                    duration=event.duration,
                 )
             )
         elif isinstance(event, (IterationRunSucceededEvent | IterationRunFailedEvent)):

api/core/app/entities/app_invoke_entities.py

@@ -7,7 +7,7 @@ from pydantic import BaseModel, ConfigDict, Field, ValidationInfo, field_validat
 from constants import UUID_NIL
 from core.app.app_config.entities import AppConfig, EasyUIBasedAppConfig, WorkflowUIBasedAppConfig
 from core.entities.provider_configuration import ProviderModelBundle
-from core.file import File, FileUploadConfig
+from core.file.models import File
 from core.model_runtime.entities.model_entities import AIModelEntity
 from core.ops.ops_trace_manager import TraceQueueManager
 
@@ -80,7 +80,6 @@ class AppGenerateEntity(BaseModel):
 
     # app config
     app_config: AppConfig
-    file_upload_config: Optional[FileUploadConfig] = None
 
     inputs: Mapping[str, Any]
     files: Sequence[File]

api/core/app/entities/queue_entities.py

@@ -111,7 +111,6 @@ class QueueIterationNextEvent(AppQueueEvent):
     """iteratoin run in parallel mode run id"""
     node_run_index: int
     output: Optional[Any] = None  # output for the current iteration
-    duration: Optional[float] = None
 
     @field_validator("output", mode="before")
     @classmethod
@@ -308,8 +307,6 @@ class QueueNodeSucceededEvent(AppQueueEvent):
     execution_metadata: Optional[dict[NodeRunMetadataKey, Any]] = None
 
     error: Optional[str] = None
-    """single iteration duration map"""
-    iteration_duration_map: Optional[dict[str, float]] = None
 
 
 class QueueNodeInIterationFailedEvent(AppQueueEvent):

api/core/app/entities/task_entities.py

@@ -434,7 +434,6 @@ class IterationNodeNextStreamResponse(StreamResponse):
         parallel_id: Optional[str] = None
         parallel_start_node_id: Optional[str] = None
         parallel_mode_run_id: Optional[str] = None
-        duration: Optional[float] = None
 
     event: StreamEvent = StreamEvent.ITERATION_NEXT
     workflow_run_id: str

api/core/app/task_pipeline/workflow_cycle_manage.py

@@ -624,7 +624,6 @@ class WorkflowCycleManage:
                 parallel_id=event.parallel_id,
                 parallel_start_node_id=event.parallel_start_node_id,
                 parallel_mode_run_id=event.parallel_mode_run_id,
-                duration=event.duration,
             ),
         )
 

api/core/file/__init__.py

@@ -2,13 +2,13 @@ from .constants import FILE_MODEL_IDENTITY
 from .enums import ArrayFileAttribute, FileAttribute, FileBelongsTo, FileTransferMethod, FileType
 from .models import (
     File,
-    FileUploadConfig,
+    FileExtraConfig,
     ImageConfig,
 )
 
 __all__ = [
     "FileType",
-    "FileUploadConfig",
+    "FileExtraConfig",
     "FileTransferMethod",
     "FileBelongsTo",
     "File",

api/core/file/file_manager.py

@@ -1,9 +1,11 @@
 import base64
+import tempfile
+from pathlib import Path
 
 from configs import dify_config
 from core.file import file_repository
 from core.helper import ssrf_proxy
-from core.model_runtime.entities import AudioPromptMessageContent, ImagePromptMessageContent, VideoPromptMessageContent
+from core.model_runtime.entities import AudioPromptMessageContent, ImagePromptMessageContent
 from extensions.ext_database import db
 from extensions.ext_storage import storage
 
@@ -33,28 +35,25 @@ def get_attr(*, file: File, attr: FileAttribute):
             raise ValueError(f"Invalid file attribute: {attr}")
 
 
-def to_prompt_message_content(
-    f: File,
-    /,
-    *,
-    image_detail_config: ImagePromptMessageContent.DETAIL = ImagePromptMessageContent.DETAIL.LOW,
-):
+def to_prompt_message_content(f: File, /):
     """
-    Convert a File object to an ImagePromptMessageContent or AudioPromptMessageContent object.
+    Convert a File object to an ImagePromptMessageContent object.
 
-    This function takes a File object and converts it to an appropriate PromptMessageContent
-    object, which can be used as a prompt for image or audio-based AI models.
+    This function takes a File object and converts it to an ImagePromptMessageContent
+    object, which can be used as a prompt for image-based AI models.
 
     Args:
-        f (File): The File object to convert.
-        detail (Optional[ImagePromptMessageContent.DETAIL]): The detail level for image prompts.
-            If not provided, defaults to ImagePromptMessageContent.DETAIL.LOW.
+        file (File): The File object to convert. Must be of type FileType.IMAGE.
 
     Returns:
-        Union[ImagePromptMessageContent, AudioPromptMessageContent]: An object containing the file data and detail level
+        ImagePromptMessageContent: An object containing the image data and detail level.
 
     Raises:
-        ValueError: If the file type is not supported or if required data is missing.
+        ValueError: If the file is not an image or if the file data is missing.
+
+    Note:
+        The detail level of the image prompt is determined by the file's extra_config.
+        If not specified, it defaults to ImagePromptMessageContent.DETAIL.LOW.
     """
     match f.type:
         case FileType.IMAGE:
@@ -63,20 +62,19 @@ def to_prompt_message_content(
             else:
                 data = _to_base64_data_string(f)
 
-            return ImagePromptMessageContent(data=data, detail=image_detail_config)
+            if f._extra_config and f._extra_config.image_config and f._extra_config.image_config.detail:
+                detail = f._extra_config.image_config.detail
+            else:
+                detail = ImagePromptMessageContent.DETAIL.LOW
+
+            return ImagePromptMessageContent(data=data, detail=detail)
         case FileType.AUDIO:
             encoded_string = _file_to_encoded_string(f)
             if f.extension is None:
                 raise ValueError("Missing file extension")
             return AudioPromptMessageContent(data=encoded_string, format=f.extension.lstrip("."))
-        case FileType.VIDEO:
-            if dify_config.MULTIMODAL_SEND_VIDEO_FORMAT == "url":
-                data = _to_url(f)
-            else:
-                data = _to_base64_data_string(f)
-            return VideoPromptMessageContent(data=data, format=f.extension.lstrip("."))
         case _:
-            raise ValueError("file type f.type is not supported")
+            raise ValueError(f"file type {f.type} is not supported")
 
 
 def download(f: File, /):
@@ -113,10 +111,42 @@ def _download_file_content(path: str, /):
     return data
 
 
+def download_to_target_path(f: File, temp_dir: str, /):
+    if f.transfer_method == FileTransferMethod.TOOL_FILE:
+        tool_file = file_repository.get_tool_file(session=db.session(), file=f)
+        suffix = Path(tool_file.file_key).suffix
+        target_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"
+        _download_file_to_target_path(tool_file.file_key, target_path)
+        return target_path
+    elif f.transfer_method == FileTransferMethod.LOCAL_FILE:
+        upload_file = file_repository.get_upload_file(session=db.session(), file=f)
+        suffix = Path(upload_file.key).suffix
+        target_path = f"{temp_dir}/{next(tempfile._get_candidate_names())}{suffix}"
+        _download_file_to_target_path(upload_file.key, target_path)
+        return target_path
+    else:
+        raise ValueError(f"Unsupported transfer method: {f.transfer_method}")
+
+
+def _download_file_to_target_path(path: str, target_path: str, /):
+    """
+    Download and return the contents of a file as bytes.
+
+    This function loads the file from storage and ensures it's in bytes format.
+
+    Args:
+        path (str): The path to the file in storage.
+        target_path (str): The path to the target file.
+    Raises:
+        ValueError: If the loaded file is not a bytes object.
+    """
+    storage.download(path, target_path)
+
+
 def _get_encoded_string(f: File, /):
     match f.transfer_method:
         case FileTransferMethod.REMOTE_URL:
-            response = ssrf_proxy.get(f.remote_url, follow_redirects=True)
+            response = ssrf_proxy.get(f.remote_url)
             response.raise_for_status()
             content = response.content
             encoded_string = base64.b64encode(content).decode("utf-8")
@@ -144,8 +174,6 @@ def _file_to_encoded_string(f: File, /):
     match f.type:
         case FileType.IMAGE:
             return _to_base64_data_string(f)
-        case FileType.VIDEO:
-            return _to_base64_data_string(f)
         case FileType.AUDIO:
             return _get_encoded_string(f)
         case _:

api/core/file/models.py

@@ -21,7 +21,7 @@ class ImageConfig(BaseModel):
     detail: ImagePromptMessageContent.DETAIL | None = None
 
 
-class FileUploadConfig(BaseModel):
+class FileExtraConfig(BaseModel):
     """
     File Upload Entity.
     """
@@ -46,6 +46,7 @@ class File(BaseModel):
     extension: Optional[str] = Field(default=None, description="File extension, should contains dot")
     mime_type: Optional[str] = None
     size: int = -1
+    _extra_config: FileExtraConfig | None = None
 
     def to_dict(self) -> Mapping[str, str | int | None]:
         data = self.model_dump(mode="json")
@@ -106,4 +107,34 @@ class File(BaseModel):
             case FileTransferMethod.TOOL_FILE:
                 if not self.related_id:
                     raise ValueError("Missing file related_id")
+
+        # Validate the extra config.
+        if not self._extra_config:
+            return self
+
+        if self._extra_config.allowed_file_types:
+            if self.type not in self._extra_config.allowed_file_types and self.type != FileType.CUSTOM:
+                raise ValueError(f"Invalid file type: {self.type}")
+
+        if self._extra_config.allowed_extensions and self.extension not in self._extra_config.allowed_extensions:
+            raise ValueError(f"Invalid file extension: {self.extension}")
+
+        if (
+            self._extra_config.allowed_upload_methods
+            and self.transfer_method not in self._extra_config.allowed_upload_methods
+        ):
+            raise ValueError(f"Invalid transfer method: {self.transfer_method}")
+
+        match self.type:
+            case FileType.IMAGE:
+                # NOTE: This part of validation is deprecated, but still used in app features "Image Upload".
+                if not self._extra_config.image_config:
+                    return self
+                # TODO: skip check if transfer_methods is empty, because many test cases are not setting this field
+                if (
+                    self._extra_config.image_config.transfer_methods
+                    and self.transfer_method not in self._extra_config.image_config.transfer_methods
+                ):
+                    raise ValueError(f"Invalid transfer method: {self.transfer_method}")
+
         return self

api/core/helper/code_executor/__init__.py

@@ -1,3 +0,0 @@
-from .code_executor import CodeExecutor, CodeLanguage
-
-__all__ = ["CodeExecutor", "CodeLanguage"]

api/core/helper/code_executor/code_executor.py

@@ -1,8 +1,7 @@
 import logging
-from collections.abc import Mapping
 from enum import Enum
 from threading import Lock
-from typing import Any, Optional
+from typing import Optional
 
 from httpx import Timeout, post
 from pydantic import BaseModel
@@ -118,7 +117,7 @@ class CodeExecutor:
         return response.data.stdout or ""
 
     @classmethod
-    def execute_workflow_code_template(cls, language: CodeLanguage, code: str, inputs: Mapping[str, Any]) -> dict:
+    def execute_workflow_code_template(cls, language: CodeLanguage, code: str, inputs: dict) -> dict:
         """
         Execute code
         :param language: code language

api/core/helper/code_executor/template_transformer.py

@@ -2,8 +2,6 @@ import json
 import re
 from abc import ABC, abstractmethod
 from base64 import b64encode
-from collections.abc import Mapping
-from typing import Any
 
 
 class TemplateTransformer(ABC):
@@ -12,7 +10,7 @@ class TemplateTransformer(ABC):
     _result_tag: str = "<<RESULT>>"
 
     @classmethod
-    def transform_caller(cls, code: str, inputs: Mapping[str, Any]) -> tuple[str, str]:
+    def transform_caller(cls, code: str, inputs: dict) -> tuple[str, str]:
         """
         Transform code to python runner
         :param code: code
@@ -50,13 +48,13 @@ class TemplateTransformer(ABC):
         pass
 
     @classmethod
-    def serialize_inputs(cls, inputs: Mapping[str, Any]) -> str:
+    def serialize_inputs(cls, inputs: dict) -> str:
         inputs_json_str = json.dumps(inputs, ensure_ascii=False).encode()
         input_base64_encoded = b64encode(inputs_json_str).decode("utf-8")
         return input_base64_encoded
 
     @classmethod
-    def assemble_runner_script(cls, code: str, inputs: Mapping[str, Any]) -> str:
+    def assemble_runner_script(cls, code: str, inputs: dict) -> str:
         # assemble runner script
         script = cls.get_runner_script()
         script = script.replace(cls._code_placeholder, code)

api/core/helper/ssrf_proxy.py

@@ -3,20 +3,22 @@ Proxy requests to avoid SSRF
 """
 
 import logging
+import os
 import time
 
 import httpx
 
-from configs import dify_config
-
-SSRF_DEFAULT_MAX_RETRIES = dify_config.SSRF_DEFAULT_MAX_RETRIES
+SSRF_PROXY_ALL_URL = os.getenv("SSRF_PROXY_ALL_URL", "")
+SSRF_PROXY_HTTP_URL = os.getenv("SSRF_PROXY_HTTP_URL", "")
+SSRF_PROXY_HTTPS_URL = os.getenv("SSRF_PROXY_HTTPS_URL", "")
+SSRF_DEFAULT_MAX_RETRIES = int(os.getenv("SSRF_DEFAULT_MAX_RETRIES", "3"))
 
 proxy_mounts = (
     {
-        "http://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTP_URL),
-        "https://": httpx.HTTPTransport(proxy=dify_config.SSRF_PROXY_HTTPS_URL),
+        "http://": httpx.HTTPTransport(proxy=SSRF_PROXY_HTTP_URL),
+        "https://": httpx.HTTPTransport(proxy=SSRF_PROXY_HTTPS_URL),
     }
-    if dify_config.SSRF_PROXY_HTTP_URL and dify_config.SSRF_PROXY_HTTPS_URL
+    if SSRF_PROXY_HTTP_URL and SSRF_PROXY_HTTPS_URL
     else None
 )
 
@@ -30,19 +32,11 @@ def make_request(method, url, max_retries=SSRF_DEFAULT_MAX_RETRIES, **kwargs):
         if "follow_redirects" not in kwargs:
             kwargs["follow_redirects"] = allow_redirects
 
-    if "timeout" not in kwargs:
-        kwargs["timeout"] = httpx.Timeout(
-            timeout=dify_config.SSRF_DEFAULT_TIME_OUT,
-            connect=dify_config.SSRF_DEFAULT_CONNECT_TIME_OUT,
-            read=dify_config.SSRF_DEFAULT_READ_TIME_OUT,
-            write=dify_config.SSRF_DEFAULT_WRITE_TIME_OUT,
-        )
-
     retries = 0
     while retries <= max_retries:
         try:
-            if dify_config.SSRF_PROXY_ALL_URL:
-                with httpx.Client(proxy=dify_config.SSRF_PROXY_ALL_URL) as client:
+            if SSRF_PROXY_ALL_URL:
+                with httpx.Client(proxy=SSRF_PROXY_ALL_URL) as client:
                     response = client.request(method=method, url=url, **kwargs)
             elif proxy_mounts:
                 with httpx.Client(mounts=proxy_mounts) as client:

api/core/memory/token_buffer_memory.py

@@ -81,18 +81,15 @@ class TokenBufferMemory:
                             db.session.query(WorkflowRun).filter(WorkflowRun.id == message.workflow_run_id).first()
                         )
 
-                        if workflow_run and workflow_run.workflow:
+                        if workflow_run:
                             file_extra_config = FileUploadConfigManager.convert(
                                 workflow_run.workflow.features_dict, is_vision=False
                             )
 
-                detail = ImagePromptMessageContent.DETAIL.LOW
                 if file_extra_config and app_record:
                     file_objs = file_factory.build_from_message_files(
                         message_files=files, tenant_id=app_record.tenant_id, config=file_extra_config
                     )
-                    if file_extra_config.image_config and file_extra_config.image_config.detail:
-                        detail = file_extra_config.image_config.detail
                 else:
                     file_objs = []
 
@@ -101,16 +98,12 @@ class TokenBufferMemory:
                 else:
                     prompt_message_contents: list[PromptMessageContent] = []
                     prompt_message_contents.append(TextPromptMessageContent(data=message.query))
-                    for file in file_objs:
-                        if file.type in {FileType.IMAGE, FileType.AUDIO}:
-                            prompt_message = file_manager.to_prompt_message_content(
-                                file,
-                                image_detail_config=detail,
-                            )
+                    for file_obj in file_objs:
+                        if file_obj.type in {FileType.IMAGE, FileType.AUDIO}:
+                            prompt_message = file_manager.to_prompt_message_content(file_obj)
                             prompt_message_contents.append(prompt_message)
 
                     prompt_messages.append(UserPromptMessage(content=prompt_message_contents))
-
             else:
                 prompt_messages.append(UserPromptMessage(content=message.query))
 

api/core/model_manager.py

@@ -1,8 +1,8 @@
 import logging
+import os
 from collections.abc import Callable, Generator, Iterable, Sequence
 from typing import IO, Any, Optional, Union, cast
 
-from configs import dify_config
 from core.entities.embedding_type import EmbeddingInputType
 from core.entities.provider_configuration import ProviderConfiguration, ProviderModelBundle
 from core.entities.provider_entities import ModelLoadBalancingConfiguration
@@ -473,7 +473,7 @@ class LBModelManager:
 
                 continue
 
-            if dify_config.DEBUG:
+            if bool(os.environ.get("DEBUG", "False").lower() == "true"):
                 logger.info(
                     f"Model LB\nid: {config.id}\nname:{config.name}\n"
                     f"tenant_id: {self._tenant_id}\nprovider: {self._provider}\n"

api/core/model_runtime/entities/__init__.py

@@ -12,13 +12,11 @@ from .message_entities import (
     TextPromptMessageContent,
     ToolPromptMessage,
     UserPromptMessage,
-    VideoPromptMessageContent,
 )
 from .model_entities import ModelPropertyKey
 
 __all__ = [
     "ImagePromptMessageContent",
-    "VideoPromptMessageContent",
     "PromptMessage",
     "PromptMessageRole",
     "LLMUsage",

api/core/model_runtime/entities/message_entities.py

@@ -56,7 +56,6 @@ class PromptMessageContentType(Enum):
     TEXT = "text"
     IMAGE = "image"
     AUDIO = "audio"
-    VIDEO = "video"
 
 
 class PromptMessageContent(BaseModel):
@@ -76,12 +75,6 @@ class TextPromptMessageContent(PromptMessageContent):
     type: PromptMessageContentType = PromptMessageContentType.TEXT
 
 
-class VideoPromptMessageContent(PromptMessageContent):
-    type: PromptMessageContentType = PromptMessageContentType.VIDEO
-    data: str = Field(..., description="Base64 encoded video data")
-    format: str = Field(..., description="Video format")
-
-
 class AudioPromptMessageContent(PromptMessageContent):
     type: PromptMessageContentType = PromptMessageContentType.AUDIO
     data: str = Field(..., description="Base64 encoded audio data")

api/core/model_runtime/model_providers/anthropic/llm/claude-3-5-haiku-20241022.yaml

@@ -4,6 +4,7 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - vision
   - tool-call
   - stream-tool-call
 model_properties:

api/core/model_runtime/model_providers/azure_ai_studio/rerank/rerank.py

@@ -47,9 +47,9 @@ class AzureRerankModel(RerankModel):
                 result = response.read()
                 return json.loads(result)
         except urllib.error.HTTPError as error:
-            logger.exception(f"The request failed with status code: {error.code}")
-            logger.exception(error.info())
-            logger.exception(error.read().decode("utf8", "ignore"))
+            logger.error(f"The request failed with status code: {error.code}")
+            logger.error(error.info())
+            logger.error(error.read().decode("utf8", "ignore"))
             raise
 
     def _invoke(

api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-5-haiku-v1.yaml

@@ -4,6 +4,7 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - vision
   - tool-call
   - stream-tool-call
 model_properties:

api/core/model_runtime/model_providers/bedrock/llm/anthropic.claude-3-sonnet-v2.yaml

@@ -16,9 +16,9 @@ parameter_rules:
     use_template: max_tokens
     required: true
     type: int
-    default: 8192
+    default: 4096
     min: 1
-    max: 8192
+    max: 4096
     help:
       zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
       en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.

api/core/model_runtime/model_providers/bedrock/llm/us.anthropic.claude-3-5-haiku-v1.yaml

@@ -4,6 +4,7 @@ label:
 model_type: llm
 features:
   - agent-thought
+  - vision
   - tool-call
   - stream-tool-call
 model_properties:

api/core/model_runtime/model_providers/jina/rerank/rerank.py

@@ -55,7 +55,6 @@ class JinaRerankModel(RerankModel):
                 base_url + "/rerank",
                 json={"model": model, "query": query, "documents": docs, "top_n": top_n},
                 headers={"Authorization": f"Bearer {credentials.get('api_key')}"},
-                timeout=20,
             )
             response.raise_for_status()
             results = response.json()

api/core/model_runtime/model_providers/openai/llm/llm.py

@@ -617,10 +617,6 @@ class OpenAILargeLanguageModel(_CommonOpenAI, LargeLanguageModel):
         # o1 compatibility
         block_as_stream = False
         if model.startswith("o1"):
-            if "max_tokens" in model_parameters:
-                model_parameters["max_completion_tokens"] = model_parameters["max_tokens"]
-                del model_parameters["max_tokens"]
-
             if stream:
                 block_as_stream = True
                 stream = False

api/core/model_runtime/model_providers/openrouter/llm/claude-3-5-haiku.yaml

@@ -1,38 +0,0 @@
-model: anthropic/claude-3-5-haiku
-label:
-  en_US: claude-3-5-haiku
-model_type: llm
-features:
-  - agent-thought
-  - tool-call
-  - stream-tool-call
-model_properties:
-  mode: chat
-  context_size: 200000
-parameter_rules:
-  - name: temperature
-    use_template: temperature
-  - name: top_p
-    use_template: top_p
-  - name: top_k
-    label:
-      zh_Hans: 取样数量
-      en_US: Top k
-    type: int
-    help:
-      zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
-      en_US: Only sample from the top K options for each subsequent token.
-    required: false
-  - name: max_tokens
-    use_template: max_tokens
-    required: true
-    default: 8192
-    min: 1
-    max: 8192
-  - name: response_format
-    use_template: response_format
-pricing:
-  input: "1"
-  output: "5"
-  unit: "0.000001"
-  currency: USD

api/core/model_runtime/model_providers/sagemaker/llm/llm.py

@@ -4,7 +4,10 @@ import re
 from collections.abc import Generator, Iterator
 from typing import Any, Optional, Union, cast
 
+# from openai.types.chat import ChatCompletion, ChatCompletionChunk
 import boto3
+from sagemaker import Predictor, serializers
+from sagemaker.session import Session
 
 from core.model_runtime.entities.llm_entities import LLMMode, LLMResult, LLMResultChunk, LLMResultChunkDelta
 from core.model_runtime.entities.message_entities import (
@@ -209,9 +212,6 @@ class SageMakerLargeLanguageModel(LargeLanguageModel):
         :param user: unique user id
         :return: full response or stream response chunk generator result
         """
-        from sagemaker import Predictor, serializers
-        from sagemaker.session import Session
-
         if not self.sagemaker_session:
             access_key = credentials.get("aws_access_key_id")
             secret_key = credentials.get("aws_secret_access_key")

api/core/model_runtime/model_providers/tongyi/llm/llm.py

@@ -29,7 +29,6 @@ from core.model_runtime.entities.message_entities import (
     TextPromptMessageContent,
     ToolPromptMessage,
     UserPromptMessage,
-    VideoPromptMessageContent,
 )
 from core.model_runtime.entities.model_entities import (
     AIModelEntity,
@@ -432,14 +431,6 @@ class TongyiLargeLanguageModel(LargeLanguageModel):
 
                             sub_message_dict = {"image": image_url}
                             sub_messages.append(sub_message_dict)
-                        elif message_content.type == PromptMessageContentType.VIDEO:
-                            message_content = cast(VideoPromptMessageContent, message_content)
-                            video_url = message_content.data
-                            if message_content.data.startswith("data:"):
-                                raise InvokeError("not support base64, please set MULTIMODAL_SEND_VIDEO_FORMAT to url")
-
-                            sub_message_dict = {"video": video_url}
-                            sub_messages.append(sub_message_dict)
 
                     # resort sub_messages to ensure text is always at last
                     sub_messages = sorted(sub_messages, key=lambda x: "text" in x)

api/core/model_runtime/model_providers/vertex_ai/llm/anthropic.claude-3.5-sonnet-v2.yaml

@@ -13,9 +13,9 @@ parameter_rules:
     use_template: max_tokens
     required: true
     type: int
-    default: 8192
+    default: 4096
     min: 1
-    max: 8192
+    max: 4096
     help:
       zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
       en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.

api/core/model_runtime/model_providers/vessl_ai/vessl_ai.yaml

@@ -1,6 +1,6 @@
 provider: vessl_ai
 label:
-  en_US: VESSL AI
+  en_US: vessl_ai
 icon_small:
   en_US: icon_s_en.svg
 icon_large:
@@ -20,28 +20,28 @@ model_credential_schema:
     label:
       en_US: Model Name
     placeholder:
-      en_US: Enter model name
+      en_US: Enter your model name
   credential_form_schemas:
     - variable: endpoint_url
       label:
-        en_US: Endpoint Url
+        en_US: endpoint url
       type: text-input
       required: true
       placeholder:
-        en_US: Enter VESSL AI service endpoint url
+        en_US: Enter the url of your endpoint url
     - variable: api_key
       required: true
       label:
         en_US: API Key
       type: secret-input
       placeholder:
-        en_US: Enter VESSL AI secret key
+        en_US: Enter your VESSL AI secret key
     - variable: mode
       show_on:
         - variable: __model_type
           value: llm
       label:
-        en_US: Completion Mode
+        en_US: Completion mode
       type: select
       required: false
       default: chat

api/core/model_runtime/model_providers/zhipuai/llm/llm.py

@@ -313,35 +313,21 @@ class ZhipuAILargeLanguageModel(_CommonZhipuaiAI, LargeLanguageModel):
         return params
 
     def _construct_glm_4v_messages(self, prompt_message: Union[str, list[PromptMessageContent]]) -> list[dict]:
-        if isinstance(prompt_message, list):
-            sub_messages = []
-            for item in prompt_message:
-                if item.type == PromptMessageContentType.IMAGE:
-                    sub_messages.append(
-                        {
-                            "type": "image_url",
-                            "image_url": {"url": self._remove_base64_header(item.data)},
-                        }
-                    )
-                elif item.type == PromptMessageContentType.VIDEO:
-                    sub_messages.append(
-                        {
-                            "type": "video_url",
-                            "video_url": {"url": self._remove_base64_header(item.data)},
-                        }
-                    )
-                else:
-                    sub_messages.append({"type": "text", "text": item.data})
-            return sub_messages
-        else:
+        if isinstance(prompt_message, str):
             return [{"type": "text", "text": prompt_message}]
 
-    def _remove_base64_header(self, file_content: str) -> str:
-        if file_content.startswith("data:"):
-            data_split = file_content.split(";base64,")
-            return data_split[1]
+        return [
+            {"type": "image_url", "image_url": {"url": self._remove_image_header(item.data)}}
+            if item.type == PromptMessageContentType.IMAGE
+            else {"type": "text", "text": item.data}
+            for item in prompt_message
+        ]
 
-        return file_content
+    def _remove_image_header(self, image: str) -> str:
+        if image.startswith("data:image"):
+            return image.split(",")[1]
+
+        return image
 
     def _handle_generate_response(
         self,

api/core/moderation/output_moderation.py

@@ -126,6 +126,6 @@ class OutputModeration(BaseModel):
             result: ModerationOutputsResult = moderation_factory.moderation_for_outputs(moderation_buffer)
             return result
         except Exception as e:
-            logger.exception("Moderation Output error: %s", e)
+            logger.error("Moderation Output error: %s", e)
 
         return None

api/core/ops/entities/config_entity.py

@@ -54,7 +54,3 @@ class LangSmithConfig(BaseTracingConfig):
             raise ValueError("endpoint must start with https://")
 
         return v
-
-
-OPS_FILE_PATH = "ops_trace/"
-OPS_TRACE_FAILED_KEY = "FAILED_OPS_TRACE"

api/core/ops/entities/trace_entity.py

@@ -23,11 +23,6 @@ class BaseTraceInfo(BaseModel):
             return v
         return ""
 
-    class Config:
-        json_encoders = {
-            datetime: lambda v: v.isoformat(),
-        }
-
 
 class WorkflowTraceInfo(BaseTraceInfo):
     workflow_data: Any
@@ -105,12 +100,6 @@ class GenerateNameTraceInfo(BaseTraceInfo):
     tenant_id: str
 
 
-class TaskData(BaseModel):
-    app_id: str
-    trace_info_type: str
-    trace_info: Any
-
-
 trace_info_info_map = {
     "WorkflowTraceInfo": WorkflowTraceInfo,
     "MessageTraceInfo": MessageTraceInfo,

api/core/ops/ops_trace_manager.py

@@ -6,13 +6,12 @@ import threading
 import time
 from datetime import timedelta
 from typing import Any, Optional, Union
-from uuid import UUID, uuid4
+from uuid import UUID
 
 from flask import current_app
 
 from core.helper.encrypter import decrypt_token, encrypt_token, obfuscated_token
 from core.ops.entities.config_entity import (
-    OPS_FILE_PATH,
     LangfuseConfig,
     LangSmithConfig,
     TracingProviderEnum,
@@ -23,7 +22,6 @@ from core.ops.entities.trace_entity import (
     MessageTraceInfo,
     ModerationTraceInfo,
     SuggestedQuestionTraceInfo,
-    TaskData,
     ToolTraceInfo,
     TraceTaskName,
     WorkflowTraceInfo,
@@ -32,7 +30,6 @@ from core.ops.langfuse_trace.langfuse_trace import LangFuseDataTrace
 from core.ops.langsmith_trace.langsmith_trace import LangSmithDataTrace
 from core.ops.utils import get_message_data
 from extensions.ext_database import db
-from extensions.ext_storage import storage
 from models.model import App, AppModelConfig, Conversation, Message, MessageAgentThought, MessageFile, TraceAppConfig
 from models.workflow import WorkflowAppLog, WorkflowRun
 from tasks.ops_trace_task import process_trace_tasks
@@ -711,7 +708,7 @@ class TraceQueueManager:
                 trace_task.app_id = self.app_id
                 trace_manager_queue.put(trace_task)
         except Exception as e:
-            logging.exception(f"Error adding trace task: {e}")
+            logging.error(f"Error adding trace task: {e}")
         finally:
             self.start_timer()
 
@@ -730,7 +727,7 @@ class TraceQueueManager:
             if tasks:
                 self.send_to_celery(tasks)
         except Exception as e:
-            logging.exception(f"Error processing trace tasks: {e}")
+            logging.error(f"Error processing trace tasks: {e}")
 
     def start_timer(self):
         global trace_manager_timer
@@ -743,17 +740,10 @@ class TraceQueueManager:
     def send_to_celery(self, tasks: list[TraceTask]):
         with self.flask_app.app_context():
             for task in tasks:
-                file_id = uuid4().hex
                 trace_info = task.execute()
-                task_data = TaskData(
-                    app_id=task.app_id,
-                    trace_info_type=type(trace_info).__name__,
-                    trace_info=trace_info.model_dump() if trace_info else None,
-                )
-                file_path = f"{OPS_FILE_PATH}{task.app_id}/{file_id}.json"
-                storage.save(file_path, task_data.model_dump_json().encode("utf-8"))
-                file_info = {
-                    "file_id": file_id,
+                task_data = {
                     "app_id": task.app_id,
+                    "trace_info_type": type(trace_info).__name__,
+                    "trace_info": trace_info.model_dump() if trace_info else {},
                 }
-                process_trace_tasks.delay(file_info)
+                process_trace_tasks.delay(task_data)

api/core/prompt/advanced_prompt_transform.py

@@ -15,7 +15,6 @@ from core.model_runtime.entities import (
     TextPromptMessageContent,
     UserPromptMessage,
 )
-from core.model_runtime.entities.message_entities import ImagePromptMessageContent
 from core.prompt.entities.advanced_prompt_entities import ChatModelMessage, CompletionModelPromptTemplate, MemoryConfig
 from core.prompt.prompt_transform import PromptTransform
 from core.prompt.utils.prompt_template_parser import PromptTemplateParser
@@ -27,13 +26,8 @@ class AdvancedPromptTransform(PromptTransform):
     Advanced Prompt Transform for Workflow LLM Node.
     """
 
-    def __init__(
-        self,
-        with_variable_tmpl: bool = False,
-        image_detail_config: ImagePromptMessageContent.DETAIL = ImagePromptMessageContent.DETAIL.LOW,
-    ) -> None:
+    def __init__(self, with_variable_tmpl: bool = False) -> None:
         self.with_variable_tmpl = with_variable_tmpl
-        self.image_detail_config = image_detail_config
 
     def get_prompt(
         self,

api/core/rag/datasource/vdb/couchbase/couchbase_vector.py

@@ -242,7 +242,7 @@ class CouchbaseVector(BaseVector):
         try:
             self._cluster.query(query, named_parameters={"doc_ids": ids}).execute()
         except Exception as e:
-            logger.exception(e)
+            logger.error(e)
 
     def delete_by_document_id(self, document_id: str):
         query = f"""

api/core/rag/datasource/vdb/lindorm/lindorm_vector.py

@@ -79,7 +79,7 @@ class LindormVectorStore(BaseVector):
                 existing_docs = self._client.mget(index=self._collection_name, body={"ids": batch_ids}, _source=False)
                 return {doc["_id"] for doc in existing_docs["docs"] if doc["found"]}
             except Exception as e:
-                logger.exception(f"Error fetching batch {batch_ids}: {e}")
+                logger.error(f"Error fetching batch {batch_ids}: {e}")
                 return set()
 
         @retry(stop=stop_after_attempt(3), wait=wait_fixed(60))
@@ -96,7 +96,7 @@ class LindormVectorStore(BaseVector):
                 )
                 return {doc["_id"] for doc in existing_docs["docs"] if doc["found"]}
             except Exception as e:
-                logger.exception(f"Error fetching batch {batch_ids}: {e}")
+                logger.error(f"Error fetching batch {batch_ids}: {e}")
                 return set()
 
         if ids is None:
@@ -177,7 +177,7 @@ class LindormVectorStore(BaseVector):
             else:
                 logger.warning(f"Index '{self._collection_name}' does not exist. No deletion performed.")
         except Exception as e:
-            logger.exception(f"Error occurred while deleting the index: {e}")
+            logger.error(f"Error occurred while deleting the index: {e}")
             raise e
 
     def text_exists(self, id: str) -> bool:
@@ -201,7 +201,7 @@ class LindormVectorStore(BaseVector):
         try:
             response = self._client.search(index=self._collection_name, body=query)
         except Exception as e:
-            logger.exception(f"Error executing search: {e}")
+            logger.error(f"Error executing search: {e}")
             raise
 
         docs_and_scores = []

api/core/rag/datasource/vdb/milvus/milvus_vector.py

@@ -86,7 +86,7 @@ class MilvusVector(BaseVector):
                 ids = self._client.insert(collection_name=self._collection_name, data=batch_insert_list)
                 pks.extend(ids)
             except MilvusException as e:
-                logger.exception("Failed to insert batch starting at entity: %s/%s", i, total_count)
+                logger.error("Failed to insert batch starting at entity: %s/%s", i, total_count)
                 raise e
         return pks
 

api/core/rag/datasource/vdb/myscale/myscale_vector.py

@@ -142,7 +142,7 @@ class MyScaleVector(BaseVector):
                 for r in self._client.query(sql).named_results()
             ]
         except Exception as e:
-            logging.exception(f"\033[91m\033[1m{type(e)}\033[0m \033[95m{str(e)}\033[0m")
+            logging.error(f"\033[91m\033[1m{type(e)}\033[0m \033[95m{str(e)}\033[0m")
             return []
 
     def delete(self) -> None:

api/core/rag/datasource/vdb/opensearch/opensearch_vector.py

@@ -129,7 +129,7 @@ class OpenSearchVector(BaseVector):
                     if status == 404:
                         logger.warning(f"Document not found for deletion: {doc_id}")
                     else:
-                        logger.exception(f"Error deleting document: {error}")
+                        logger.error(f"Error deleting document: {error}")
 
     def delete(self) -> None:
         self._client.indices.delete(index=self._collection_name.lower())
@@ -158,7 +158,7 @@ class OpenSearchVector(BaseVector):
         try:
             response = self._client.search(index=self._collection_name.lower(), body=query)
         except Exception as e:
-            logger.exception(f"Error executing search: {e}")
+            logger.error(f"Error executing search: {e}")
             raise
 
         docs = []

api/core/rag/embedding/cached_embedding.py

@@ -89,7 +89,7 @@ class CacheEmbedding(Embeddings):
                     db.session.rollback()
             except Exception as ex:
                 db.session.rollback()
-                logger.exception("Failed to embed documents: %s", ex)
+                logger.error("Failed to embed documents: %s", ex)
                 raise ex
 
         return text_embeddings

api/core/rag/extractor/word_extractor.py

@@ -28,6 +28,7 @@ logger = logging.getLogger(__name__)
 class WordExtractor(BaseExtractor):
     """Load docx files.
 
+
     Args:
         file_path: Path to the file to load.
     """
@@ -229,7 +230,7 @@ class WordExtractor(BaseExtractor):
                                 for i in url_pattern.findall(x.text):
                                     hyperlinks_url = str(i)
                     except Exception as e:
-                        logger.exception(e)
+                        logger.error(e)
 
         def parse_paragraph(paragraph):
             paragraph_content = []

api/core/tools/provider/_position.yaml

@@ -48,13 +48,6 @@
 - feishu_task
 - feishu_calendar
 - feishu_spreadsheet
-- lark_base
-- lark_document
-- lark_message_and_group
-- lark_wiki
-- lark_task
-- lark_calendar
-- lark_spreadsheet
 - slack
 - twilio
 - wecom

api/core/tools/provider/builtin/cogview/tools/cogvideo.py

@@ -1,24 +0,0 @@
-from typing import Any, Union
-
-from zhipuai import ZhipuAI
-
-from core.tools.entities.tool_entities import ToolInvokeMessage
-from core.tools.tool.builtin_tool import BuiltinTool
-
-
-class CogVideoTool(BuiltinTool):
-    def _invoke(
-        self, user_id: str, tool_parameters: dict[str, Any]
-    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
-        client = ZhipuAI(
-            base_url=self.runtime.credentials["zhipuai_base_url"],
-            api_key=self.runtime.credentials["zhipuai_api_key"],
-        )
-        if not tool_parameters.get("prompt") and not tool_parameters.get("image_url"):
-            return self.create_text_message("require at least one of prompt and image_url")
-
-        response = client.videos.generations(
-            model="cogvideox", prompt=tool_parameters.get("prompt"), image_url=tool_parameters.get("image_url")
-        )
-
-        return self.create_json_message(response.dict())

api/core/tools/provider/builtin/cogview/tools/cogvideo.yaml

@@ -1,32 +0,0 @@
-identity:
-  name: cogvideo
-  author: hjlarry
-  label:
-    en_US: CogVideo
-    zh_Hans: CogVideo 视频生成
-description:
-  human:
-    en_US: Use the CogVideox model provided by ZhipuAI to generate videos based on user prompts and images.
-    zh_Hans: 使用智谱cogvideox模型，根据用户输入的提示词和图片，生成视频。
-  llm: A tool for generating videos. The input is user's prompt or image url or both of them, the output is a task id. You can use another tool with this task id to check the status and get the video.
-parameters:
-  - name: prompt
-    type: string
-    label:
-      en_US: prompt
-      zh_Hans: 提示词
-    human_description:
-      en_US: The prompt text used to generate video.
-      zh_Hans: 用于生成视频的提示词。
-    llm_description: The prompt text used to generate video. Optional.
-    form: llm
-  - name: image_url
-    type: string
-    label:
-      en_US: image url
-      zh_Hans: 图片链接
-    human_description:
-      en_US: The image url used to generate video.
-      zh_Hans: 输入一个图片链接，生成的视频将基于该图片和提示词。
-    llm_description: The image url used to generate video. Optional.
-    form: llm

api/core/tools/provider/builtin/cogview/tools/cogvideo_job.py

@@ -1,30 +0,0 @@
-from typing import Any, Union
-
-import httpx
-from zhipuai import ZhipuAI
-
-from core.tools.entities.tool_entities import ToolInvokeMessage
-from core.tools.tool.builtin_tool import BuiltinTool
-
-
-class CogVideoJobTool(BuiltinTool):
-    def _invoke(
-        self, user_id: str, tool_parameters: dict[str, Any]
-    ) -> Union[ToolInvokeMessage, list[ToolInvokeMessage]]:
-        client = ZhipuAI(
-            api_key=self.runtime.credentials["zhipuai_api_key"],
-            base_url=self.runtime.credentials["zhipuai_base_url"],
-        )
-
-        response = client.videos.retrieve_videos_result(id=tool_parameters.get("id"))
-        result = [self.create_json_message(response.dict())]
-        if response.task_status == "SUCCESS":
-            for item in response.video_result:
-                video_cover_image = self.create_image_message(item.cover_image_url)
-                result.append(video_cover_image)
-                video = self.create_blob_message(
-                    blob=httpx.get(item.url).content, meta={"mime_type": "video/mp4"}, save_as=self.VariableKey.VIDEO
-                )
-                result.append(video)
-
-        return result

api/core/tools/provider/builtin/cogview/tools/cogvideo_job.yaml

@@ -1,21 +0,0 @@
-identity:
-  name: cogvideo_job
-  author: hjlarry
-  label:
-    en_US: CogVideo Result
-    zh_Hans: CogVideo 结果获取
-description:
-  human:
-    en_US: Get the result of CogVideo tool generation.
-    zh_Hans: 根据 CogVideo 工具返回的 id 获取视频生成结果。
-  llm: Get the result of CogVideo tool generation. The input is the id which is returned by the CogVideo tool. The output is the url of video and video cover image.
-parameters:
-  - name: id
-    type: string
-    label:
-      en_US: id
-    human_description:
-      en_US: The id returned by the CogVideo.
-      zh_Hans: CogVideo 工具返回的 id。
-    llm_description: The id returned by the cogvideo.
-    form: llm

api/core/tools/provider/builtin/comfyui/tools/comfyui_client.py

@@ -48,6 +48,7 @@ class ComfyUiClient:
         prompt = origin_prompt.copy()
         id_to_class_type = {id: details["class_type"] for id, details in prompt.items()}
         k_sampler = [key for key, value in id_to_class_type.items() if value == "KSampler"][0]
+        prompt.get(k_sampler)["inputs"]["seed"] = random.randint(10**14, 10**15 - 1)
         positive_input_id = prompt.get(k_sampler)["inputs"]["positive"][0]
         prompt.get(positive_input_id)["inputs"]["text"] = positive_prompt
 
@@ -71,18 +72,6 @@ class ComfyUiClient:
             prompt.get(load_image)["inputs"]["image"] = image_name
         return prompt
 
-    def set_prompt_seed_by_id(self, origin_prompt: dict, seed_id: str) -> dict:
-        prompt = origin_prompt.copy()
-        if seed_id not in prompt:
-            raise Exception("Not a valid seed node")
-        if "seed" in prompt[seed_id]["inputs"]:
-            prompt[seed_id]["inputs"]["seed"] = random.randint(10**14, 10**15 - 1)
-        elif "noise_seed" in prompt[seed_id]["inputs"]:
-            prompt[seed_id]["inputs"]["noise_seed"] = random.randint(10**14, 10**15 - 1)
-        else:
-            raise Exception("Not a valid seed node")
-        return prompt
-
     def track_progress(self, prompt: dict, ws: WebSocket, prompt_id: str):
         node_ids = list(prompt.keys())
         finished_nodes = []

api/core/tools/provider/builtin/comfyui/tools/comfyui_workflow.py

@@ -8,20 +8,6 @@ from core.tools.provider.builtin.comfyui.tools.comfyui_client import ComfyUiClie
 from core.tools.tool.builtin_tool import BuiltinTool
 
 
-def sanitize_json_string(s):
-    escape_dict = {
-        "\n": "\\n",
-        "\r": "\\r",
-        "\t": "\\t",
-        "\b": "\\b",
-        "\f": "\\f",
-    }
-    for char, escaped in escape_dict.items():
-        s = s.replace(char, escaped)
-
-    return s
-
-
 class ComfyUIWorkflowTool(BuiltinTool):
     def _invoke(self, user_id: str, tool_parameters: dict[str, Any]) -> ToolInvokeMessage | list[ToolInvokeMessage]:
         comfyui = ComfyUiClient(self.runtime.credentials["base_url"])
@@ -40,17 +26,13 @@ class ComfyUIWorkflowTool(BuiltinTool):
         set_prompt_with_ksampler = True
         if "{{positive_prompt}}" in workflow:
             set_prompt_with_ksampler = False
-            workflow = workflow.replace("{{positive_prompt}}", positive_prompt.replace('"', "'"))
-            workflow = workflow.replace("{{negative_prompt}}", negative_prompt.replace('"', "'"))
+            workflow = workflow.replace("{{positive_prompt}}", positive_prompt)
+            workflow = workflow.replace("{{negative_prompt}}", negative_prompt)
 
         try:
             prompt = json.loads(workflow)
-        except json.JSONDecodeError:
-            cleaned_string = sanitize_json_string(workflow)
-            try:
-                prompt = json.loads(cleaned_string)
-            except:
-                return self.create_text_message("the Workflow JSON is not correct")
+        except:
+            return self.create_text_message("the Workflow JSON is not correct")
 
         if set_prompt_with_ksampler:
             try:
@@ -70,9 +52,6 @@ class ComfyUIWorkflowTool(BuiltinTool):
             else:
                 prompt = comfyui.set_prompt_images_by_default(prompt, image_names)
 
-        if seed_id := tool_parameters.get("seed_id"):
-            prompt = comfyui.set_prompt_seed_by_id(prompt, seed_id)
-
         images = comfyui.generate_image_by_prompt(prompt)
         result = []
         for img in images:

api/core/tools/provider/builtin/comfyui/tools/comfyui_workflow.yaml

@@ -52,12 +52,3 @@ parameters:
       en_US: When the workflow has multiple image nodes, enter the ID list of these nodes, and the images will be passed to ComfyUI in the order of the list.
       zh_Hans: 当工作流有多个图片节点时，输入这些节点的ID列表，图片将按列表顺序传给ComfyUI
     form: form
-  - name: seed_id
-    type: string
-    label:
-      en_US: Seed Node Id
-      zh_Hans: 种子节点ID
-    human_description:
-      en_US: If you need to generate different images each time, you need to enter the ID of the seed node.
-      zh_Hans: 如果需要每次生成时使用不同的种子，需要输入包含种子的节点的ID
-    form: form

api/core/tools/provider/builtin/feishu_base/tools/list_tables.yaml

@@ -34,7 +34,7 @@ parameters:
         Page size, default value: 20, maximum value: 100.
       zh_Hans: 分页大小，默认值：20，最大值：100。
     llm_description: 分页大小，默认值：20，最大值：100。
-    form: form
+    form: llm
 
   - name: page_token
     type: string

api/core/tools/provider/builtin/feishu_base/tools/search_records.yaml

@@ -147,7 +147,7 @@ parameters:
         Page size, default value: 20, maximum value: 500.
       zh_Hans: 分页大小，默认值：20，最大值：500。
     llm_description: 分页大小，默认值：20，最大值：500。
-    form: form
+    form: llm
 
   - name: page_token
     type: string

api/core/tools/provider/builtin/feishu_calendar/tools/list_events.yaml

@@ -47,7 +47,7 @@ parameters:
       en_US: The page size, i.e., the number of data entries returned in a single request. The default value is 50, and the value range is [50,1000].
       zh_Hans: 分页大小，即单次请求所返回的数据条目数。默认值为 50，取值范围为 [50,1000]。
     llm_description: 分页大小，即单次请求所返回的数据条目数。默认值为 50，取值范围为 [50,1000]。
-    form: form
+    form: llm
 
   - name: page_token
     type: string

api/core/tools/provider/builtin/feishu_calendar/tools/search_events.yaml

@@ -85,7 +85,7 @@ parameters:
       en_US: The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [10,100].
       zh_Hans: 分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [10,100]。
     llm_description: 分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [10,100]。
-    form: form
+    form: llm
 
   - name: page_token
     type: string

api/core/tools/provider/builtin/feishu_document/tools/list_document_blocks.yaml

@@ -59,7 +59,7 @@ parameters:
       en_US: Paging size, the default and maximum value is 500.
       zh_Hans: 分页大小, 默认值和最大值为 500。
     llm_description: 分页大小, 表示一次请求最多返回多少条数据，默认值和最大值为 500。
-    form: form
+    form: llm
 
   - name: page_token
     type: string

api/core/tools/provider/builtin/feishu_message/tools/get_chat_messages.yaml

@@ -81,7 +81,7 @@ parameters:
       en_US: The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [1,50].
       zh_Hans: 分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。
     llm_description: 分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。
-    form: form
+    form: llm
 
   - name: page_token
     type: string

api/core/tools/provider/builtin/feishu_message/tools/get_thread_messages.yaml

@@ -57,7 +57,7 @@ parameters:
       en_US: The page size, i.e., the number of data entries returned in a single request. The default value is 20, and the value range is [1,50].
       zh_Hans: 分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。
     llm_description: 分页大小，即单次请求所返回的数据条目数。默认值为 20，取值范围为 [1,50]。
-    form: form
+    form: llm
 
   - name: page_token
     type: string

api/core/tools/provider/builtin/feishu_spreadsheet/tools/add_cols.yaml

@@ -56,7 +56,7 @@ parameters:
       en_US: Number of columns to add, range (0-5000].
       zh_Hans: 要增加的列数，范围(0-5000]。
     llm_description: 要增加的列数，范围(0-5000]。
-    form: form
+    form: llm
 
   - name: values
     type: string

api/core/tools/provider/builtin/feishu_spreadsheet/tools/add_rows.yaml

@@ -56,7 +56,7 @@ parameters:
       en_US: Number of rows to add, range (0-5000].
       zh_Hans: 要增加行数，范围(0-5000]。
     llm_description: 要增加行数，范围(0-5000]。
-    form: form
+    form: llm
 
   - name: values
     type: string

api/core/tools/provider/builtin/feishu_spreadsheet/tools/read_cols.yaml

@@ -82,7 +82,7 @@ parameters:
       en_US: Starting column number, starting from 1.
       zh_Hans: 起始列号，从 1 开始。
     llm_description: 起始列号，从 1 开始。
-    form: form
+    form: llm
 
   - name: num_cols
     type: number
@@ -94,4 +94,4 @@ parameters:
       en_US: Number of columns to read.
       zh_Hans: 读取列数
     llm_description: 读取列数
-    form: form
+    form: llm

api/core/tools/provider/builtin/feishu_spreadsheet/tools/read_rows.yaml

@@ -82,7 +82,7 @@ parameters:
       en_US: Starting row number, starting from 1.
       zh_Hans: 起始行号，从 1 开始。
     llm_description: 起始行号，从 1 开始。
-    form: form
+    form: llm
 
   - name: num_rows
     type: number
@@ -94,4 +94,4 @@ parameters:
       en_US: Number of rows to read.
       zh_Hans: 读取行数
     llm_description: 读取行数
-    form: form
+    form: llm