mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
* fix(cost_calculator.py): move to using `.get_model_info()` for cost per token calculations ensures cost tracking is reliable - handles edge cases of parsing model cost map * build(model_prices_and_context_window.json): add 'supports_response_schema' for select tgai models Fixes https://github.com/BerriAI/litellm/pull/7037#discussion_r1872157329 * build(model_prices_and_context_window.json): remove 'pdf input' and 'vision' support from nova micro in model map Bedrock docs indicate no support for micro - https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference-supported-models-features.html * fix(converse_transformation.py): support amazon nova tool use * fix(opentelemetry): Add missing LLM request type attribute to spans (#7041) * feat(opentelemetry): add LLM request type attribute to spans * lint * fix: curl usage (#7038) curl -d, --data <data> is lowercase d curl -D, --dump-header <filename> is uppercase D references: https://curl.se/docs/manpage.html#-d https://curl.se/docs/manpage.html#-D * fix(spend_tracking.py): handle empty 'id' in model response - when creating spend log Fixes https://github.com/BerriAI/litellm/issues/7023 * fix(streaming_chunk_builder.py): handle initial id being empty string Fixes https://github.com/BerriAI/litellm/issues/7023 * fix(anthropic_passthrough_logging_handler.py): add end user cost tracking for anthropic pass through endpoint * docs(pass_through/): refactor docs location + add table on supported features for pass through endpoints * feat(anthropic_passthrough_logging_handler.py): support end user cost tracking via anthropic sdk * docs(anthropic_completion.md): add docs on passing end user param for cost tracking on anthropic sdk * fix(litellm_logging.py): use standard logging payload if present in kwargs prevent datadog logging error for pass through endpoints * docs(bedrock.md): add rerank api usage example to docs * bugfix/change dummy tool name format (#7053) * fix viewing keys (#7042) * ui new build * build(model_prices_and_context_window.json): add bedrock region models to model cost map (#7044) * bye (#6982) * (fix) litellm router.aspeech (#6962) * doc Migrating Databases * fix aspeech on router * test_audio_speech_router * test_audio_speech_router * docs show supported providers on batches api doc * change dummy tool name format --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com> Co-authored-by: yujonglee <yujonglee.dev@gmail.com> * fix: fix linting errors * test: update test * fix(litellm_logging.py): fix pass through check * fix(test_otel_logging.py): fix test * fix(cost_calculator.py): update handling for cost per second * fix(cost_calculator.py): fix cost check * test: fix test * (fix) adding public routes when using custom header (#7045) * get_api_key_from_custom_header * add test_get_api_key_from_custom_header * fix testing use 1 file for test user api key auth * fix test user api key auth * test_custom_api_key_header_name * build: update ui build --------- Co-authored-by: Doron Kopit <83537683+doronkopit5@users.noreply.github.com> Co-authored-by: lloydchang <lloydchang@gmail.com> Co-authored-by: hgulersen <haymigulersen@gmail.com> Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: yujonglee <yujonglee.dev@gmail.com>
128 lines
4.4 KiB
Python
128 lines
4.4 KiB
Python
import json
|
|
import re
|
|
import threading
|
|
from datetime import datetime
|
|
from typing import Optional, Union
|
|
|
|
import httpx
|
|
|
|
import litellm
|
|
from litellm._logging import verbose_proxy_logger
|
|
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
|
|
from litellm.litellm_core_utils.litellm_logging import (
|
|
get_standard_logging_object_payload,
|
|
)
|
|
from litellm.llms.vertex_ai_and_google_ai_studio.gemini.vertex_and_google_ai_studio_gemini import (
|
|
VertexLLM,
|
|
)
|
|
from litellm.proxy._types import PassThroughEndpointLoggingResultValues
|
|
from litellm.proxy.auth.user_api_key_auth import user_api_key_auth
|
|
from litellm.types.utils import StandardPassThroughResponseObject
|
|
from litellm.utils import executor as thread_pool_executor
|
|
|
|
from .llm_provider_handlers.anthropic_passthrough_logging_handler import (
|
|
AnthropicPassthroughLoggingHandler,
|
|
)
|
|
from .llm_provider_handlers.vertex_passthrough_logging_handler import (
|
|
VertexPassthroughLoggingHandler,
|
|
)
|
|
|
|
|
|
class PassThroughEndpointLogging:
|
|
def __init__(self):
|
|
self.TRACKED_VERTEX_ROUTES = [
|
|
"generateContent",
|
|
"streamGenerateContent",
|
|
"predict",
|
|
]
|
|
|
|
# Anthropic
|
|
self.TRACKED_ANTHROPIC_ROUTES = ["/messages"]
|
|
|
|
async def pass_through_async_success_handler(
|
|
self,
|
|
httpx_response: httpx.Response,
|
|
response_body: Optional[dict],
|
|
logging_obj: LiteLLMLoggingObj,
|
|
url_route: str,
|
|
result: str,
|
|
start_time: datetime,
|
|
end_time: datetime,
|
|
cache_hit: bool,
|
|
**kwargs,
|
|
):
|
|
standard_logging_response_object: Optional[
|
|
PassThroughEndpointLoggingResultValues
|
|
] = None
|
|
if self.is_vertex_route(url_route):
|
|
vertex_passthrough_logging_handler_result = (
|
|
VertexPassthroughLoggingHandler.vertex_passthrough_handler(
|
|
httpx_response=httpx_response,
|
|
logging_obj=logging_obj,
|
|
url_route=url_route,
|
|
result=result,
|
|
start_time=start_time,
|
|
end_time=end_time,
|
|
cache_hit=cache_hit,
|
|
**kwargs,
|
|
)
|
|
)
|
|
standard_logging_response_object = (
|
|
vertex_passthrough_logging_handler_result["result"]
|
|
)
|
|
kwargs = vertex_passthrough_logging_handler_result["kwargs"]
|
|
elif self.is_anthropic_route(url_route):
|
|
anthropic_passthrough_logging_handler_result = (
|
|
AnthropicPassthroughLoggingHandler.anthropic_passthrough_handler(
|
|
httpx_response=httpx_response,
|
|
response_body=response_body or {},
|
|
logging_obj=logging_obj,
|
|
url_route=url_route,
|
|
result=result,
|
|
start_time=start_time,
|
|
end_time=end_time,
|
|
cache_hit=cache_hit,
|
|
**kwargs,
|
|
)
|
|
)
|
|
|
|
standard_logging_response_object = (
|
|
anthropic_passthrough_logging_handler_result["result"]
|
|
)
|
|
kwargs = anthropic_passthrough_logging_handler_result["kwargs"]
|
|
if standard_logging_response_object is None:
|
|
standard_logging_response_object = StandardPassThroughResponseObject(
|
|
response=httpx_response.text
|
|
)
|
|
thread_pool_executor.submit(
|
|
logging_obj.success_handler,
|
|
standard_logging_response_object, # Positional argument 1
|
|
start_time, # Positional argument 2
|
|
end_time, # Positional argument 3
|
|
cache_hit, # Positional argument 4
|
|
**kwargs, # Unpacked keyword arguments
|
|
)
|
|
|
|
await logging_obj.async_success_handler(
|
|
result=(
|
|
json.dumps(result)
|
|
if isinstance(result, dict)
|
|
else standard_logging_response_object
|
|
),
|
|
start_time=start_time,
|
|
end_time=end_time,
|
|
cache_hit=False,
|
|
**kwargs,
|
|
)
|
|
|
|
def is_vertex_route(self, url_route: str):
|
|
for route in self.TRACKED_VERTEX_ROUTES:
|
|
if route in url_route:
|
|
return True
|
|
return False
|
|
|
|
def is_anthropic_route(self, url_route: str):
|
|
for route in self.TRACKED_ANTHROPIC_ROUTES:
|
|
if route in url_route:
|
|
return True
|
|
return False
|