mirror of
https://github.com/langgenius/dify.git
synced 2026-05-05 09:58:04 +08:00
Merge branch 'main' into fix/chore-fix
This commit is contained in:
Yeuoly
@ -1,6 +1,6 @@
|
||||
import logging
|
||||
import time
|
||||
from collections.abc import Generator
|
||||
from collections.abc import Generator, Sequence
|
||||
from typing import Optional, Union
|
||||
|
||||
from pydantic import ConfigDict
|
||||
@ -41,7 +41,7 @@ class LargeLanguageModel(AIModel):
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: Optional[dict] = None,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stop: Optional[Sequence[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
@ -96,7 +96,7 @@ class LargeLanguageModel(AIModel):
|
||||
model_parameters=model_parameters,
|
||||
prompt_messages=prompt_messages,
|
||||
tools=tools,
|
||||
stop=stop,
|
||||
stop=list(stop) if stop else None,
|
||||
stream=stream,
|
||||
)
|
||||
|
||||
@ -176,7 +176,7 @@ class LargeLanguageModel(AIModel):
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stop: Optional[Sequence[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
@ -318,7 +318,7 @@ class LargeLanguageModel(AIModel):
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stop: Optional[Sequence[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
@ -364,7 +364,7 @@ class LargeLanguageModel(AIModel):
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stop: Optional[Sequence[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
@ -411,7 +411,7 @@ class LargeLanguageModel(AIModel):
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stop: Optional[Sequence[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
@ -459,7 +459,7 @@ class LargeLanguageModel(AIModel):
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stop: Optional[Sequence[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
callbacks: Optional[list[Callback]] = None,
|
||||
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 277 KiB |
@ -1,15 +0,0 @@
|
||||
<svg width="68" height="24" viewBox="0 0 68 24" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<g id="Gemini">
|
||||
<path id="Union" fill-rule="evenodd" clip-rule="evenodd" d="M50.6875 4.37014C48.3498 4.59292 46.5349 6.41319 46.3337 8.72764C46.1446 6.44662 44.2677 4.56074 41.9805 4.3737C44.2762 4.1997 46.152 2.28299 46.3373 0C46.4882 2.28911 48.405 4.20047 50.6875 4.37014ZM15.4567 9.41141L13.9579 10.9076C9.92941 6.64892 2.69298 9.97287 3.17317 15.8112C3.22394 23.108 14.5012 24.4317 15.3628 16.8809H9.52096L9.50061 14.9149H17.3595C18.8163 23.1364 8.44367 27.0292 3.19453 21.238C0.847044 18.7556 0.363651 14.7682 1.83717 11.7212C4.1129 6.62089 11.6505 5.29845 15.4567 9.41141ZM45.5915 23.5989H47.6945C47.6944 22.9155 47.6945 22.2307 47.6946 21.5452V21.5325C47.6948 19.8907 47.695 18.2453 47.6924 16.6072C47.6914 15.9407 47.6161 15.2823 47.4024 14.647C46.4188 11.2828 41.4255 11.4067 39.8332 14.214C38.5637 11.4171 34.4009 11.5236 32.8538 14.0084L32.8082 13.9976V12.4806L32.4233 12.4804H32.4224C31.8687 12.4801 31.3324 12.4798 30.7949 12.4811V23.5848L32.8977 23.5672C32.8981 22.9411 32.8979 22.3122 32.8977 21.6822V21.6812V21.6802V21.6791V21.6781V21.6771V21.676V21.676V21.6759V21.6758V21.6757V21.6757V21.6756C32.8973 20.204 32.8969 18.7261 32.904 17.2614C32.8889 15.3646 34.5674 13.5687 36.5358 14.124C37.7794 14.3298 38.1851 15.6148 38.1761 16.7257C38.1821 17.7019 38.18 18.6824 38.178 19.6633V19.6638C38.1752 20.9756 38.1724 22.2881 38.1891 23.5919L40.2846 23.5731C40.2929 22.7511 40.2881 21.9245 40.2832 21.0966C40.2753 19.7402 40.2674 18.3805 40.317 17.0328C40.4418 15.2122 42.0141 13.6186 43.9064 14.1168C45.2685 14.3231 45.6136 15.7748 45.5882 16.9545C45.5938 18.4959 45.5929 20.0492 45.5921 21.5968V21.5991V21.6014V21.6037V21.606V21.6083V21.6106C45.5917 22.2749 45.5913 22.9382 45.5915 23.5989ZM20.6167 18.4408C20.5625 21.9486 25.2121 23.6996 27.2993 20.0558L29.1566 20.9592C27.8157 23.7067 24.2337 24.7424 21.5381 23.4213C18.0052 21.7253 17.41 16.5007 20.0334 13.7517C21.4609 12.1752 23.7291 11.7901 25.7206 12.3653C28.3408 13.1257 29.4974 15.8937 29.326 18.4399C27.5547 18.4415 25.7971 18.4412 24.0364 18.4409C22.8993 18.4407 21.7609 18.4405 20.6167 18.4408ZM27.1041 16.6957C26.7048 13.1033 21.2867 13.2256 20.7494 16.6957H27.1041ZM53.543 23.5999H55.6206L55.6206 22.4361C55.6205 20.7877 55.6205 19.1443 55.6207 17.4939C55.6208 16.8853 55.7234 16.297 56.0063 15.7531C56.6115 14.3862 58.1745 13.7002 59.5927 14.1774C60.7512 14.4455 61.2852 15.6069 61.2762 16.7154C61.2774 18.3497 61.2771 19.9826 61.2769 21.6162V21.6166V21.617V21.6174V21.6179L61.2766 23.6007H63.3698C63.3913 22.0924 63.3869 20.584 63.3826 19.0755V19.0754V19.0753V19.0753V19.0752C63.3799 18.1682 63.3773 17.2612 63.3803 16.3541C63.3796 15.8622 63.3103 15.3765 63.1698 14.9052C62.3248 11.5142 57.3558 11.2385 55.5828 14.0038L55.5336 13.9905V12.4917H53.539C53.4898 12.7313 53.4934 23.4113 53.543 23.5999ZM49.6211 12.4944H51.7065V23.5994H49.6211V12.4944ZM65.1035 23.5991H67.1831C67.2367 23.2198 67.2133 12.6566 67.1634 12.4983H65.1035V23.5991ZM52.1504 8.67829C52.1709 10.4847 49.2418 10.7058 49.1816 8.65714C49.2189 6.5948 52.2437 6.81331 52.1504 8.67829ZM66.1387 10.1324C64.2712 10.1609 64.1316 7.19881 66.1559 7.17114C68.1709 7.19817 68.0215 10.2087 66.1387 10.1324Z" fill="url(#paint0_linear_14286_118464)"/>
|
||||
</g>
|
||||
<defs>
|
||||
<linearGradient id="paint0_linear_14286_118464" x1="-2" y1="0.999998" x2="67.9999" y2="27.5002" gradientUnits="userSpaceOnUse">
|
||||
<stop stop-color="#7798E0"/>
|
||||
<stop offset="0.210002" stop-color="#086FFF"/>
|
||||
<stop offset="0.345945" stop-color="#086FFF"/>
|
||||
<stop offset="0.591777" stop-color="#479AFF"/>
|
||||
<stop offset="0.895892" stop-color="#B7C4FA"/>
|
||||
<stop offset="1" stop-color="#B5C5F9"/>
|
||||
</linearGradient>
|
||||
</defs>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 3.6 KiB |
Binary file not shown.
|
Before Width: | Height: | Size: 57 KiB |
@ -1,11 +0,0 @@
|
||||
<svg width="24" height="24" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<rect width="24" height="24" rx="6" fill="url(#paint0_linear_7301_16076)"/>
|
||||
<path d="M20 12.0116C15.7043 12.42 12.3692 15.757 11.9995 20C11.652 15.8183 8.20301 12.361 4 12.0181C8.21855 11.6991 11.6656 8.1853 12.006 4C12.2833 8.19653 15.8057 11.7005 20 12.0116Z" fill="white" fill-opacity="0.88"/>
|
||||
<defs>
|
||||
<linearGradient id="paint0_linear_7301_16076" x1="-9" y1="29.5" x2="19.4387" y2="1.43791" gradientUnits="userSpaceOnUse">
|
||||
<stop offset="0.192878" stop-color="#1C7DFF"/>
|
||||
<stop offset="0.520213" stop-color="#1C69FF"/>
|
||||
<stop offset="1" stop-color="#F0DCD6"/>
|
||||
</linearGradient>
|
||||
</defs>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 689 B |
@ -1,10 +0,0 @@
|
||||
import logging
|
||||
|
||||
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class GPUStackProvider(ModelProvider):
|
||||
def validate_provider_credentials(self, credentials: dict) -> None:
|
||||
pass
|
||||
@ -1,120 +0,0 @@
|
||||
provider: gpustack
|
||||
label:
|
||||
en_US: GPUStack
|
||||
icon_small:
|
||||
en_US: icon_s_en.png
|
||||
icon_large:
|
||||
en_US: icon_l_en.png
|
||||
supported_model_types:
|
||||
- llm
|
||||
- text-embedding
|
||||
- rerank
|
||||
configurate_methods:
|
||||
- customizable-model
|
||||
model_credential_schema:
|
||||
model:
|
||||
label:
|
||||
en_US: Model Name
|
||||
zh_Hans: 模型名称
|
||||
placeholder:
|
||||
en_US: Enter your model name
|
||||
zh_Hans: 输入模型名称
|
||||
credential_form_schemas:
|
||||
- variable: endpoint_url
|
||||
label:
|
||||
zh_Hans: 服务器地址
|
||||
en_US: Server URL
|
||||
type: text-input
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 输入 GPUStack 的服务器地址，如 http://192.168.1.100
|
||||
en_US: Enter the GPUStack server URL, e.g. http://192.168.1.100
|
||||
- variable: api_key
|
||||
label:
|
||||
en_US: API Key
|
||||
type: secret-input
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 输入您的 API Key
|
||||
en_US: Enter your API Key
|
||||
- variable: mode
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
label:
|
||||
en_US: Completion mode
|
||||
type: select
|
||||
required: false
|
||||
default: chat
|
||||
placeholder:
|
||||
zh_Hans: 选择补全类型
|
||||
en_US: Select completion type
|
||||
options:
|
||||
- value: completion
|
||||
label:
|
||||
en_US: Completion
|
||||
zh_Hans: 补全
|
||||
- value: chat
|
||||
label:
|
||||
en_US: Chat
|
||||
zh_Hans: 对话
|
||||
- variable: context_size
|
||||
label:
|
||||
zh_Hans: 模型上下文长度
|
||||
en_US: Model context size
|
||||
required: true
|
||||
type: text-input
|
||||
default: "8192"
|
||||
placeholder:
|
||||
zh_Hans: 输入您的模型上下文长度
|
||||
en_US: Enter your Model context size
|
||||
- variable: max_tokens_to_sample
|
||||
label:
|
||||
zh_Hans: 最大 token 上限
|
||||
en_US: Upper bound for max tokens
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
default: "8192"
|
||||
type: text-input
|
||||
- variable: function_calling_type
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
label:
|
||||
en_US: Function calling
|
||||
type: select
|
||||
required: false
|
||||
default: no_call
|
||||
options:
|
||||
- value: function_call
|
||||
label:
|
||||
en_US: Function Call
|
||||
zh_Hans: Function Call
|
||||
- value: tool_call
|
||||
label:
|
||||
en_US: Tool Call
|
||||
zh_Hans: Tool Call
|
||||
- value: no_call
|
||||
label:
|
||||
en_US: Not Support
|
||||
zh_Hans: 不支持
|
||||
- variable: vision_support
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
label:
|
||||
zh_Hans: Vision 支持
|
||||
en_US: Vision Support
|
||||
type: select
|
||||
required: false
|
||||
default: no_support
|
||||
options:
|
||||
- value: support
|
||||
label:
|
||||
en_US: Support
|
||||
zh_Hans: 支持
|
||||
- value: no_support
|
||||
label:
|
||||
en_US: Not Support
|
||||
zh_Hans: 不支持
|
||||
@ -1,45 +0,0 @@
|
||||
from collections.abc import Generator
|
||||
|
||||
from yarl import URL
|
||||
|
||||
from core.model_runtime.entities.llm_entities import LLMResult
|
||||
from core.model_runtime.entities.message_entities import (
|
||||
PromptMessage,
|
||||
PromptMessageTool,
|
||||
)
|
||||
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import (
|
||||
OAIAPICompatLargeLanguageModel,
|
||||
)
|
||||
|
||||
|
||||
class GPUStackLanguageModel(OAIAPICompatLargeLanguageModel):
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: list[PromptMessageTool] | None = None,
|
||||
stop: list[str] | None = None,
|
||||
stream: bool = True,
|
||||
user: str | None = None,
|
||||
) -> LLMResult | Generator:
|
||||
return super()._invoke(
|
||||
model,
|
||||
credentials,
|
||||
prompt_messages,
|
||||
model_parameters,
|
||||
tools,
|
||||
stop,
|
||||
stream,
|
||||
user,
|
||||
)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
self._add_custom_parameters(credentials)
|
||||
super().validate_credentials(model, credentials)
|
||||
|
||||
@staticmethod
|
||||
def _add_custom_parameters(credentials: dict) -> None:
|
||||
credentials["endpoint_url"] = str(URL(credentials["endpoint_url"]) / "v1-openai")
|
||||
credentials["mode"] = "chat"
|
||||
@ -1,146 +0,0 @@
|
||||
from json import dumps
|
||||
from typing import Optional
|
||||
|
||||
import httpx
|
||||
from requests import post
|
||||
from yarl import URL
|
||||
|
||||
from core.model_runtime.entities.common_entities import I18nObject
|
||||
from core.model_runtime.entities.model_entities import (
|
||||
AIModelEntity,
|
||||
FetchFrom,
|
||||
ModelPropertyKey,
|
||||
ModelType,
|
||||
)
|
||||
from core.model_runtime.entities.rerank_entities import RerankDocument, RerankResult
|
||||
from core.model_runtime.errors.invoke import (
|
||||
InvokeAuthorizationError,
|
||||
InvokeBadRequestError,
|
||||
InvokeConnectionError,
|
||||
InvokeError,
|
||||
InvokeRateLimitError,
|
||||
InvokeServerUnavailableError,
|
||||
)
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.rerank_model import RerankModel
|
||||
|
||||
|
||||
class GPUStackRerankModel(RerankModel):
|
||||
"""
|
||||
Model class for GPUStack rerank model.
|
||||
"""
|
||||
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
query: str,
|
||||
docs: list[str],
|
||||
score_threshold: Optional[float] = None,
|
||||
top_n: Optional[int] = None,
|
||||
user: Optional[str] = None,
|
||||
) -> RerankResult:
|
||||
"""
|
||||
Invoke rerank model
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:param query: search query
|
||||
:param docs: docs for reranking
|
||||
:param score_threshold: score threshold
|
||||
:param top_n: top n documents to return
|
||||
:param user: unique user id
|
||||
:return: rerank result
|
||||
"""
|
||||
if len(docs) == 0:
|
||||
return RerankResult(model=model, docs=[])
|
||||
|
||||
endpoint_url = credentials["endpoint_url"]
|
||||
headers = {
|
||||
"Authorization": f"Bearer {credentials.get('api_key')}",
|
||||
"Content-Type": "application/json",
|
||||
}
|
||||
|
||||
data = {"model": model, "query": query, "documents": docs, "top_n": top_n}
|
||||
|
||||
try:
|
||||
response = post(
|
||||
str(URL(endpoint_url) / "v1" / "rerank"),
|
||||
headers=headers,
|
||||
data=dumps(data),
|
||||
timeout=10,
|
||||
)
|
||||
response.raise_for_status()
|
||||
results = response.json()
|
||||
|
||||
rerank_documents = []
|
||||
for result in results["results"]:
|
||||
index = result["index"]
|
||||
if "document" in result:
|
||||
text = result["document"]["text"]
|
||||
else:
|
||||
text = docs[index]
|
||||
|
||||
rerank_document = RerankDocument(
|
||||
index=index,
|
||||
text=text,
|
||||
score=result["relevance_score"],
|
||||
)
|
||||
|
||||
if score_threshold is None or result["relevance_score"] >= score_threshold:
|
||||
rerank_documents.append(rerank_document)
|
||||
|
||||
return RerankResult(model=model, docs=rerank_documents)
|
||||
except httpx.HTTPStatusError as e:
|
||||
raise InvokeServerUnavailableError(str(e))
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
"""
|
||||
Validate model credentials
|
||||
|
||||
:param model: model name
|
||||
:param credentials: model credentials
|
||||
:return:
|
||||
"""
|
||||
try:
|
||||
self._invoke(
|
||||
model=model,
|
||||
credentials=credentials,
|
||||
query="What is the capital of the United States?",
|
||||
docs=[
|
||||
"Carson City is the capital city of the American state of Nevada. At the 2010 United States "
|
||||
"Census, Carson City had a population of 55,274.",
|
||||
"The Commonwealth of the Northern Mariana Islands is a group of islands in the Pacific Ocean that "
|
||||
"are a political division controlled by the United States. Its capital is Saipan.",
|
||||
],
|
||||
score_threshold=0.8,
|
||||
)
|
||||
except Exception as ex:
|
||||
raise CredentialsValidateFailedError(str(ex))
|
||||
|
||||
@property
|
||||
def _invoke_error_mapping(self) -> dict[type[InvokeError], list[type[Exception]]]:
|
||||
"""
|
||||
Map model invoke error to unified error
|
||||
"""
|
||||
return {
|
||||
InvokeConnectionError: [httpx.ConnectError],
|
||||
InvokeServerUnavailableError: [httpx.RemoteProtocolError],
|
||||
InvokeRateLimitError: [],
|
||||
InvokeAuthorizationError: [httpx.HTTPStatusError],
|
||||
InvokeBadRequestError: [httpx.RequestError],
|
||||
}
|
||||
|
||||
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
|
||||
"""
|
||||
generate custom model entities from credentials
|
||||
"""
|
||||
entity = AIModelEntity(
|
||||
model=model,
|
||||
label=I18nObject(en_US=model),
|
||||
model_type=ModelType.RERANK,
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
model_properties={ModelPropertyKey.CONTEXT_SIZE: int(credentials.get("context_size"))},
|
||||
)
|
||||
|
||||
return entity
|
||||
@ -1,35 +0,0 @@
|
||||
from typing import Optional
|
||||
|
||||
from yarl import URL
|
||||
|
||||
from core.entities.embedding_type import EmbeddingInputType
|
||||
from core.model_runtime.entities.text_embedding_entities import (
|
||||
TextEmbeddingResult,
|
||||
)
|
||||
from core.model_runtime.model_providers.openai_api_compatible.text_embedding.text_embedding import (
|
||||
OAICompatEmbeddingModel,
|
||||
)
|
||||
|
||||
|
||||
class GPUStackTextEmbeddingModel(OAICompatEmbeddingModel):
|
||||
"""
|
||||
Model class for GPUStack text embedding model.
|
||||
"""
|
||||
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
texts: list[str],
|
||||
user: Optional[str] = None,
|
||||
input_type: EmbeddingInputType = EmbeddingInputType.DOCUMENT,
|
||||
) -> TextEmbeddingResult:
|
||||
return super()._invoke(model, credentials, texts, user, input_type)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
self._add_custom_parameters(credentials)
|
||||
super().validate_credentials(model, credentials)
|
||||
|
||||
@staticmethod
|
||||
def _add_custom_parameters(credentials: dict) -> None:
|
||||
credentials["endpoint_url"] = str(URL(credentials["endpoint_url"]) / "v1-openai")
|
||||
@ -1,55 +0,0 @@
|
||||
model: claude-3-5-sonnet-v2@20241022
|
||||
label:
|
||||
en_US: Claude 3.5 Sonnet v2
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
type: int
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
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.
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
pricing:
|
||||
input: '0.003'
|
||||
output: '0.015'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 11 KiB |
@ -1,3 +0,0 @@
|
||||
<svg width="1200" height="925" viewBox="0 0 1200 925" fill="none" xmlns="http://www.w3.org/2000/svg">
|
||||
<path d="M780.152 250.999L907.882 462.174C907.882 462.174 880.925 510.854 867.43 535.21C834.845 594.039 764.171 612.49 710.442 508.333L420.376 0H0L459.926 803.307C552.303 964.663 787.366 964.663 879.743 803.307C989.874 610.952 1089.87 441.97 1200 249.646L1052.28 0H639.519L780.152 250.999Z" fill="#3366FF"/>
|
||||
</svg>
|
||||
|
Before Width: | Height: | Size: 417 B |
@ -1,83 +0,0 @@
|
||||
from decimal import Decimal
|
||||
|
||||
from core.model_runtime.entities.common_entities import I18nObject
|
||||
from core.model_runtime.entities.llm_entities import LLMMode
|
||||
from core.model_runtime.entities.model_entities import (
|
||||
AIModelEntity,
|
||||
DefaultParameterName,
|
||||
FetchFrom,
|
||||
ModelPropertyKey,
|
||||
ModelType,
|
||||
ParameterRule,
|
||||
ParameterType,
|
||||
PriceConfig,
|
||||
)
|
||||
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
|
||||
|
||||
|
||||
class VesslAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
|
||||
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
|
||||
features = []
|
||||
|
||||
entity = AIModelEntity(
|
||||
model=model,
|
||||
label=I18nObject(en_US=model),
|
||||
model_type=ModelType.LLM,
|
||||
fetch_from=FetchFrom.CUSTOMIZABLE_MODEL,
|
||||
features=features,
|
||||
model_properties={
|
||||
ModelPropertyKey.MODE: credentials.get("mode"),
|
||||
},
|
||||
parameter_rules=[
|
||||
ParameterRule(
|
||||
name=DefaultParameterName.TEMPERATURE.value,
|
||||
label=I18nObject(en_US="Temperature"),
|
||||
type=ParameterType.FLOAT,
|
||||
default=float(credentials.get("temperature", 0.7)),
|
||||
min=0,
|
||||
max=2,
|
||||
precision=2,
|
||||
),
|
||||
ParameterRule(
|
||||
name=DefaultParameterName.TOP_P.value,
|
||||
label=I18nObject(en_US="Top P"),
|
||||
type=ParameterType.FLOAT,
|
||||
default=float(credentials.get("top_p", 1)),
|
||||
min=0,
|
||||
max=1,
|
||||
precision=2,
|
||||
),
|
||||
ParameterRule(
|
||||
name=DefaultParameterName.TOP_K.value,
|
||||
label=I18nObject(en_US="Top K"),
|
||||
type=ParameterType.INT,
|
||||
default=int(credentials.get("top_k", 50)),
|
||||
min=-2147483647,
|
||||
max=2147483647,
|
||||
precision=0,
|
||||
),
|
||||
ParameterRule(
|
||||
name=DefaultParameterName.MAX_TOKENS.value,
|
||||
label=I18nObject(en_US="Max Tokens"),
|
||||
type=ParameterType.INT,
|
||||
default=512,
|
||||
min=1,
|
||||
max=int(credentials.get("max_tokens_to_sample", 4096)),
|
||||
),
|
||||
],
|
||||
pricing=PriceConfig(
|
||||
input=Decimal(credentials.get("input_price", 0)),
|
||||
output=Decimal(credentials.get("output_price", 0)),
|
||||
unit=Decimal(credentials.get("unit", 0)),
|
||||
currency=credentials.get("currency", "USD"),
|
||||
),
|
||||
)
|
||||
|
||||
if credentials["mode"] == "chat":
|
||||
entity.model_properties[ModelPropertyKey.MODE] = LLMMode.CHAT.value
|
||||
elif credentials["mode"] == "completion":
|
||||
entity.model_properties[ModelPropertyKey.MODE] = LLMMode.COMPLETION.value
|
||||
else:
|
||||
raise ValueError(f"Unknown completion type {credentials['completion_type']}")
|
||||
|
||||
return entity
|
||||
@ -1,10 +0,0 @@
|
||||
import logging
|
||||
|
||||
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class VesslAIProvider(ModelProvider):
|
||||
def validate_provider_credentials(self, credentials: dict) -> None:
|
||||
pass
|
||||
@ -1,56 +0,0 @@
|
||||
provider: vessl_ai
|
||||
label:
|
||||
en_US: VESSL AI
|
||||
icon_small:
|
||||
en_US: icon_s_en.svg
|
||||
icon_large:
|
||||
en_US: icon_l_en.png
|
||||
background: "#F1EFED"
|
||||
help:
|
||||
title:
|
||||
en_US: How to deploy VESSL AI LLM Model Endpoint
|
||||
url:
|
||||
en_US: https://docs.vessl.ai/guides/get-started/llama3-deployment
|
||||
supported_model_types:
|
||||
- llm
|
||||
configurate_methods:
|
||||
- customizable-model
|
||||
model_credential_schema:
|
||||
model:
|
||||
label:
|
||||
en_US: Model Name
|
||||
placeholder:
|
||||
en_US: Enter model name
|
||||
credential_form_schemas:
|
||||
- variable: endpoint_url
|
||||
label:
|
||||
en_US: Endpoint Url
|
||||
type: text-input
|
||||
required: true
|
||||
placeholder:
|
||||
en_US: Enter VESSL AI service endpoint url
|
||||
- variable: api_key
|
||||
required: true
|
||||
label:
|
||||
en_US: API Key
|
||||
type: secret-input
|
||||
placeholder:
|
||||
en_US: Enter VESSL AI secret key
|
||||
- variable: mode
|
||||
show_on:
|
||||
- variable: __model_type
|
||||
value: llm
|
||||
label:
|
||||
en_US: Completion Mode
|
||||
type: select
|
||||
required: false
|
||||
default: chat
|
||||
placeholder:
|
||||
en_US: Select completion mode
|
||||
options:
|
||||
- value: completion
|
||||
label:
|
||||
en_US: Completion
|
||||
- value: chat
|
||||
label:
|
||||
en_US: Chat
|
||||
@ -1 +0,0 @@
|
||||
<svg xmlns="http://www.w3.org/2000/svg" fill="currentColor" viewBox="0 0 24 24" aria-hidden="true" class="" focusable="false" style="fill:currentColor;height:28px;width:28px"><path d="m3.005 8.858 8.783 12.544h3.904L6.908 8.858zM6.905 15.825 3 21.402h3.907l1.951-2.788zM16.585 2l-6.75 9.64 1.953 2.79L20.492 2zM17.292 7.965v13.437h3.2V3.395z"></path></svg>
|
||||
|
Before Width: | Height: | Size: 356 B |
@ -1,63 +0,0 @@
|
||||
model: grok-beta
|
||||
label:
|
||||
en_US: Grok beta
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
label:
|
||||
en_US: "Temperature"
|
||||
zh_Hans: "采样温度"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The randomness of the sampling temperature control output. The temperature value is within the range of [0.0, 1.0]. The higher the value, the more random and creative the output; the lower the value, the more stable it is. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样温度控制输出的随机性。温度值在 [0.0, 1.0] 范围内，值越高，输出越随机和创造性；值越低，输出越稳定。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: top_p
|
||||
label:
|
||||
en_US: "Top P"
|
||||
zh_Hans: "Top P"
|
||||
type: float
|
||||
default: 0.7
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
precision: 1
|
||||
required: true
|
||||
help:
|
||||
en_US: "The value range of the sampling method is [0.0, 1.0]. The top_p value determines that the model selects tokens from the top p% of candidate words with the highest probability; when top_p is 0, this parameter is invalid. It is recommended to adjust either top_p or temperature parameters according to your needs to avoid adjusting both at the same time."
|
||||
zh_Hans: "采样方法的取值范围为 [0.0,1.0]。top_p 值确定模型从概率最高的前p%的候选词中选取 tokens；当 top_p 为 0 时，此参数无效。建议根据需求调整 top_p 或 temperature 参数，避免同时调整两者。"
|
||||
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
label:
|
||||
en_US: "Frequency Penalty"
|
||||
zh_Hans: "频率惩罚"
|
||||
type: float
|
||||
default: 0
|
||||
min: 0
|
||||
max: 2.0
|
||||
precision: 1
|
||||
required: false
|
||||
help:
|
||||
en_US: "Number between 0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim."
|
||||
zh_Hans: "介于0和2.0之间的数字。正值会根据新标记在文本中迄今为止的现有频率来惩罚它们，从而降低模型一字不差地重复同一句话的可能性。"
|
||||
|
||||
- name: user
|
||||
use_template: text
|
||||
label:
|
||||
en_US: "User"
|
||||
zh_Hans: "用户"
|
||||
type: string
|
||||
required: false
|
||||
help:
|
||||
en_US: "Used to track and differentiate conversation requests from different users."
|
||||
zh_Hans: "用于追踪和区分不同用户的对话请求。"
|
||||
@ -1,37 +0,0 @@
|
||||
from collections.abc import Generator
|
||||
from typing import Optional, Union
|
||||
|
||||
from yarl import URL
|
||||
|
||||
from core.model_runtime.entities.llm_entities import LLMMode, LLMResult
|
||||
from core.model_runtime.entities.message_entities import (
|
||||
PromptMessage,
|
||||
PromptMessageTool,
|
||||
)
|
||||
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
|
||||
|
||||
|
||||
class XAILargeLanguageModel(OAIAPICompatLargeLanguageModel):
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
) -> Union[LLMResult, Generator]:
|
||||
self._add_custom_parameters(credentials)
|
||||
return super()._invoke(model, credentials, prompt_messages, model_parameters, tools, stop, stream)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
self._add_custom_parameters(credentials)
|
||||
super().validate_credentials(model, credentials)
|
||||
|
||||
@staticmethod
|
||||
def _add_custom_parameters(credentials) -> None:
|
||||
credentials["endpoint_url"] = str(URL(credentials["endpoint_url"])) or "https://api.x.ai/v1"
|
||||
credentials["mode"] = LLMMode.CHAT.value
|
||||
credentials["function_calling_type"] = "tool_call"
|
||||
@ -1,25 +0,0 @@
|
||||
import logging
|
||||
|
||||
from core.model_runtime.entities.model_entities import ModelType
|
||||
from core.model_runtime.errors.validate import CredentialsValidateFailedError
|
||||
from core.model_runtime.model_providers.__base.model_provider import ModelProvider
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class XAIProvider(ModelProvider):
|
||||
def validate_provider_credentials(self, credentials: dict) -> None:
|
||||
"""
|
||||
Validate provider credentials
|
||||
if validate failed, raise exception
|
||||
|
||||
:param credentials: provider credentials, credentials form defined in `provider_credential_schema`.
|
||||
"""
|
||||
try:
|
||||
model_instance = self.get_model_instance(ModelType.LLM)
|
||||
model_instance.validate_credentials(model="grok-beta", credentials=credentials)
|
||||
except CredentialsValidateFailedError as ex:
|
||||
raise ex
|
||||
except Exception as ex:
|
||||
logger.exception(f"{self.get_provider_schema().provider} credentials validate failed")
|
||||
raise ex
|
||||
@ -1,38 +0,0 @@
|
||||
provider: x
|
||||
label:
|
||||
en_US: xAI
|
||||
description:
|
||||
en_US: xAI is a company working on building artificial intelligence to accelerate human scientific discovery. We are guided by our mission to advance our collective understanding of the universe.
|
||||
icon_small:
|
||||
en_US: x-ai-logo.svg
|
||||
icon_large:
|
||||
en_US: x-ai-logo.svg
|
||||
help:
|
||||
title:
|
||||
en_US: Get your token from xAI
|
||||
zh_Hans: 从 xAI 获取 token
|
||||
url:
|
||||
en_US: https://x.ai/api
|
||||
supported_model_types:
|
||||
- llm
|
||||
configurate_methods:
|
||||
- predefined-model
|
||||
provider_credential_schema:
|
||||
credential_form_schemas:
|
||||
- variable: api_key
|
||||
label:
|
||||
en_US: API Key
|
||||
type: secret-input
|
||||
required: true
|
||||
placeholder:
|
||||
zh_Hans: 在此输入您的 API Key
|
||||
en_US: Enter your API Key
|
||||
- variable: endpoint_url
|
||||
label:
|
||||
en_US: API Base
|
||||
type: text-input
|
||||
required: false
|
||||
default: https://api.x.ai/v1
|
||||
placeholder:
|
||||
zh_Hans: 在此输入您的 API Base
|
||||
en_US: Enter your API Base
|
||||
Reference in New Issue
Block a user