Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

refactor wenxin rerank #9486

Merged
merged 2 commits into from
Oct 21, 2024
Merged

refactor wenxin rerank #9486

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dc3b558
wenxin:remove unused code and refactor error mapping
Oct 18, 2024
c5312dc
format rerank.py
Oct 18, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 8 additions & 33 deletions api/core/model_runtime/model_providers/wenxin/rerank/rerank.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,20 +2,15 @@

import httpx

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.invoke import InvokeError
from core.model_runtime.errors.validate import CredentialsValidateFailedError
from core.model_runtime.model_providers.__base.rerank_model import RerankModel
from core.model_runtime.model_providers.wenxin._common import _CommonWenxin
from core.model_runtime.model_providers.wenxin.wenxin_errors import (
InternalServerError,
invoke_error_mapping,
)


class WenxinRerank(_CommonWenxin):
Expand All @@ -32,7 +27,7 @@ def rerank(self, model: str, query: str, docs: list[str], top_n: Optional[int] =
response.raise_for_status()
return response.json()
except httpx.HTTPStatusError as e:
raise InvokeServerUnavailableError(str(e))
raise InternalServerError(str(e))


class WenxinRerankModel(RerankModel):
Expand Down Expand Up @@ -93,7 +88,7 @@ def _invoke(

return RerankResult(model=model, docs=rerank_documents)
except httpx.HTTPStatusError as e:
raise InvokeServerUnavailableError(str(e))
raise InternalServerError(str(e))

def validate_credentials(self, model: str, credentials: dict) -> None:
"""
Expand Down Expand Up @@ -124,24 +119,4 @@ 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
return invoke_error_mapping()