feat: support siliconflow rerank (#7337)

This commit is contained in:
Weaxs 2024-08-16 20:21:41 +08:00 committed by GitHub
parent 7d4a0a417a
commit 3a33062405
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
6 changed files with 146 additions and 1 deletions

View File

@ -0,0 +1,4 @@
model: netease-youdao/bce-reranker-base_v1
model_type: rerank
model_properties:
context_size: 512

View File

@ -0,0 +1,4 @@
model: BAAI/bge-reranker-v2-m3
model_type: rerank
model_properties:
context_size: 8192

View File

@ -0,0 +1,87 @@
from typing import Optional
import httpx
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 SiliconflowRerankModel(RerankModel):
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:
if len(docs) == 0:
return RerankResult(model=model, docs=[])
base_url = credentials.get('base_url', 'https://api.siliconflow.cn/v1')
if base_url.endswith('/'):
base_url = base_url[:-1]
try:
response = httpx.post(
base_url + '/rerank',
json={
"model": model,
"query": query,
"documents": docs,
"top_n": top_n,
"return_documents": True
},
headers={"Authorization": f"Bearer {credentials.get('api_key')}"}
)
response.raise_for_status()
results = response.json()
rerank_documents = []
for result in results['results']:
rerank_document = RerankDocument(
index=result['index'],
text=result['document']['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:
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]
}

View File

@ -12,10 +12,11 @@ help:
en_US: Get your API Key from SiliconFlow
zh_Hans: 从 SiliconFlow 获取 API Key
url:
en_US: https://cloud.siliconflow.cn/keys
en_US: https://cloud.siliconflow.cn/account/ak
supported_model_types:
- llm
- text-embedding
- rerank
- speech2text
configurate_methods:
- predefined-model

View File

@ -0,0 +1,49 @@
import os
import pytest
from core.model_runtime.entities.rerank_entities import RerankResult
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.siliconflow.rerank.rerank import SiliconflowRerankModel
def test_validate_credentials():
model = SiliconflowRerankModel()
with pytest.raises(CredentialsValidateFailedError):
model.validate_credentials(
model="BAAI/bge-reranker-v2-m3",
credentials={
"api_key": "invalid_key"
},
)
model.validate_credentials(
model="BAAI/bge-reranker-v2-m3",
credentials={
"api_key": os.environ.get("API_KEY"),
},
)
def test_invoke_model():
model = SiliconflowRerankModel()
result = model.invoke(
model='BAAI/bge-reranker-v2-m3',
credentials={
"api_key": os.environ.get("API_KEY"),
},
query="Who is Kasumi?",
docs=[
"Kasumi is a girl's name of Japanese origin meaning \"mist\".",
"Her music is a kawaii bass, a mix of future bass, pop, and kawaii music ",
"and she leads a team named PopiParty."
],
score_threshold=0.8
)
assert isinstance(result, RerankResult)
assert len(result.docs) == 1
assert result.docs[0].index == 0
assert result.docs[0].score >= 0.8