mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
* fix(proxy_server.py): use default azure credentials to support azure non-client secret kms * fix(langsmith.py): raise error if credentials missing * feat(langsmith.py): support error logging for langsmith + standard logging payload Fixes https://github.com/BerriAI/litellm/issues/5738 * Fix hardcoding of schema in view check (#5749) * fix - deal with case when check view exists returns None (#5740) * Revert "fix - deal with case when check view exists returns None (#5740)" (#5741) This reverts commit535228159b
. * test(test_router_debug_logs.py): move to mock response * Fix hardcoding of schema --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Krrish Dholakia <krrishdholakia@gmail.com> * fix(proxy_server.py): allow admin to disable ui via `DISABLE_ADMIN_UI` flag * fix(router.py): fix default model name value Fixes55db19a1e4 (r1763712148)
* fix(utils.py): fix unbound variable error * feat(rerank/main.py): add azure ai rerank endpoints Closes https://github.com/BerriAI/litellm/issues/5667 * feat(secret_detection.py): Allow configuring secret detection params Allows admin to control what plugins to run for secret detection. Prevents overzealous secret detection. * docs(secret_detection.md): add secret detection guardrail docs * fix: fix linting errors * fix - deal with case when check view exists returns None (#5740) * Revert "fix - deal with case when check view exists returns None (#5740)" (#5741) This reverts commit535228159b
. * Litellm fix router testing (#5748) * test: fix testing - azure changed content policy error logic * test: fix tests to use mock responses * test(test_image_generation.py): handle api instability * test(test_image_generation.py): handle azure api instability * fix(utils.py): fix unbounded variable error * fix(utils.py): fix unbounded variable error * test: refactor test to use mock response * test: mark flaky azure tests * Bump next from 14.1.1 to 14.2.10 in /ui/litellm-dashboard (#5753) Bumps [next](https://github.com/vercel/next.js) from 14.1.1 to 14.2.10. - [Release notes](https://github.com/vercel/next.js/releases) - [Changelog](https://github.com/vercel/next.js/blob/canary/release.js) - [Commits](https://github.com/vercel/next.js/compare/v14.1.1...v14.2.10) --- updated-dependencies: - dependency-name: next dependency-type: direct:production ... Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> * [Fix] o1-mini causes pydantic warnings on `reasoning_tokens` (#5754) * add requester_metadata in standard logging payload * log requester_metadata in metadata * use StandardLoggingPayload for logging * docs StandardLoggingPayload * fix import * include standard logging object in failure * add test for requester metadata * handle completion_tokens_details * add test for completion_tokens_details * [Feat-Proxy-DataDog] Log Redis, Postgres Failure events on DataDog (#5750) * dd - start tracking redis status on dd * add async_service_succes_hook / failure hook in custom logger * add async_service_failure_hook * log service failures on dd * fix import error * add test for redis errors / warning * [Fix] Router/ Proxy - Tag Based routing, raise correct error when no deployments found and tag filtering is on (#5745) * fix tag routing - raise correct error when no model with tag based routing * fix error string from tag based routing * test router tag based routing * raise 401 error when no tags avialable for deploymen * linting fix * [Feat] Log Request metadata on gcs bucket logging (#5743) * add requester_metadata in standard logging payload * log requester_metadata in metadata * use StandardLoggingPayload for logging * docs StandardLoggingPayload * fix import * include standard logging object in failure * add test for requester metadata * fix(litellm_logging.py): fix logging message * fix(rerank_api/main.py): fix linting errors * fix(custom_guardrails.py): maintain backwards compatibility for older guardrails * fix(rerank_api/main.py): fix cost tracking for rerank endpoints --------- Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: steffen-sbt <148480574+steffen-sbt@users.noreply.github.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
from typing import Any, Dict, List, Optional, Union
|
|
|
|
import httpx
|
|
|
|
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
|
from litellm.llms.cohere.rerank import CohereRerank
|
|
from litellm.rerank_api.types import RerankResponse
|
|
|
|
|
|
class AzureAIRerank(CohereRerank):
|
|
def rerank(
|
|
self,
|
|
model: str,
|
|
api_key: str,
|
|
api_base: str,
|
|
query: str,
|
|
documents: List[Union[str, Dict[str, Any]]],
|
|
headers: Optional[dict],
|
|
litellm_logging_obj: LiteLLMLoggingObj,
|
|
top_n: Optional[int] = None,
|
|
rank_fields: Optional[List[str]] = None,
|
|
return_documents: Optional[bool] = True,
|
|
max_chunks_per_doc: Optional[int] = None,
|
|
_is_async: Optional[bool] = False,
|
|
) -> RerankResponse:
|
|
|
|
if headers is None:
|
|
headers = {"Authorization": "Bearer {}".format(api_key)}
|
|
else:
|
|
headers = {**headers, "Authorization": "Bearer {}".format(api_key)}
|
|
|
|
# Assuming api_base is a string representing the base URL
|
|
api_base_url = httpx.URL(api_base)
|
|
|
|
# Replace the path with '/v1/rerank' if it doesn't already end with it
|
|
if not api_base_url.path.endswith("/v1/rerank"):
|
|
api_base = str(api_base_url.copy_with(path="/v1/rerank"))
|
|
|
|
return super().rerank(
|
|
model=model,
|
|
api_key=api_key,
|
|
api_base=api_base,
|
|
query=query,
|
|
documents=documents,
|
|
top_n=top_n,
|
|
rank_fields=rank_fields,
|
|
return_documents=return_documents,
|
|
max_chunks_per_doc=max_chunks_per_doc,
|
|
_is_async=_is_async,
|
|
headers=headers,
|
|
litellm_logging_obj=litellm_logging_obj,
|
|
)
|