phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
14321 commits 2484 branches 894 tags 536 MiB
Commit graph

162 commits

Author SHA1 Message Date
Krish Dholakia
b3ef1ac18c
Merge branch 'main' into litellm_proxy_tts_pricing 2024-07-06 14:56:16 -07:00
Ishaan Jaff
80a31c5dab allow async_only_mode on rotuer 2024-07-06 12:50:57 -07:00
Krrish Dholakia
6e43cdcb17 feat(litellm_logging.py): support cost tracking for tts calls 2024-07-05 22:09:08 -07:00
Krrish Dholakia
7618ec43b3 fix(proxy_server.py): support langfuse logging for rejected requests on /v1/chat/completions 2024-07-05 13:07:09 -07:00
Krrish Dholakia
015a398713 fix(vertex_httpx.py): fix assumptions on usagemetadata 2024-07-05 11:01:51 -07:00
Krish Dholakia
0721e95b0b
Merge branch 'main' into feature/return-output-vector-size-in-modelinfo 2024-07-04 17:03:31 -07:00
Krrish Dholakia
86632f6da0 fix(types/router.py): add custom pricing info to 'model_info' 
Fixes https://github.com/BerriAI/litellm/issues/4542
 2024-07-04 16:07:58 -07:00
Krrish Dholakia
a8e181369d fix(cohere.py): fix message parsing to handle tool calling correctly 2024-07-04 11:13:07 -07:00
Krish Dholakia
5e47970eed
Merge branch 'main' into litellm_anthropic_tool_calling_streaming_fix 2024-07-03 20:43:51 -07:00
Krrish Dholakia
344268e053 fix(anthropic.py): support *real* anthropic tool calling + streaming 
Parses each chunk and translates to openai format
 2024-07-03 19:48:35 -07:00
Ishaan Jaff
a2b6baab16 add new GuardrailItem type 2024-07-03 14:03:34 -07:00
Krrish Dholakia
589c1c6280 refactor(azure.py): replaces the custom transport logic for just using our httpx client 
Done to fix all the http/https proxy issues people are facing with proxy.
 2024-07-02 15:32:53 -07:00
Krrish Dholakia
4b1e85f54e fix(vertex_ai_anthropic.py): support pre-filling "{" for json mode 2024-06-29 18:54:10 -07:00
Krrish Dholakia
5718d1e205 fix(utils.py): new helper function to check if provider/model supports 'response_schema' param 2024-06-29 12:40:29 -07:00
Krrish Dholakia
010b55e6db fix(utils.py): handle arguments being None 
Fixes https://github.com/BerriAI/litellm/issues/4440
 2024-06-27 08:56:52 -07:00
Ishaan Jaff
90b0bd93a8 Revert "Add return type annotations to util types" 
This reverts commit faef56fe69.
 2024-06-26 15:59:38 -07:00
Josh Learn
faef56fe69 Add return type annotations to util types 2024-06-26 12:46:59 -04:00
Krrish Dholakia
1ff0129a94 fix(vertex_httpx.py): cover gemini content violation (on prompt) 2024-06-24 19:13:56 -07:00
Krish Dholakia
0454c0781a
Merge branch 'main' into litellm_azure_content_filter_fallbacks 2024-06-22 21:28:29 -07:00
Krrish Dholakia
2c7a80d08d fix(router.py): check if azure returns 'content_filter' response + fallback available -> fallback 
Exception maps azure content filter response exceptions
 2024-06-22 19:10:15 -07:00
Krrish Dholakia
2545da777b feat(dynamic_rate_limiter.py): initial commit for dynamic rate limiting 
Closes https://github.com/BerriAI/litellm/issues/4124
 2024-06-21 18:41:31 -07:00
Ishaan Jaff
cdc1e952ac router - add doc string 2024-06-20 14:36:51 -07:00
Ishaan Jaff
b6066d1ece feat - set custom routing strategy 2024-06-20 13:49:44 -07:00
Krrish Dholakia
7a141ff7f0 fix(types/utils.py): fix linting error 2024-06-19 18:58:12 -07:00
Krrish Dholakia
16da21e839 feat(llm_cost_calc/google.py): do character based cost calculation for vertex ai 
Calculate cost for vertex ai responses using characters in query/response

 Closes https://github.com/BerriAI/litellm/issues/4165
 2024-06-19 17:18:42 -07:00
Tom Usher
17482ded74 Return output_vector_size in get_model_info 2024-06-19 14:09:20 +01:00
Krish Dholakia
0c2c02ba8d
Merge pull request #4266 from BerriAI/litellm_gemini_image_url 
Support 'image url' to vertex ai / google ai studio gemini models
 2024-06-18 20:39:25 -07:00
Krrish Dholakia
b79e21a81a fix(types/utils.py): fix linting errors 2024-06-18 20:19:06 -07:00
Krish Dholakia
308fa6f4a0
Merge pull request #4258 from nejch/fix/typing 
fix: add more type hints to init methods
 2024-06-18 20:04:05 -07:00
Krrish Dholakia
14b66c3daa fix(router.py): support multiple orgs in 1 model definition 
Closes https://github.com/BerriAI/litellm/issues/3949
 2024-06-18 19:36:58 -07:00
Krrish Dholakia
71f4bf3bb4 fix(vertex_httpx.py): support safety settings on vertex ai 
Fixes https://github.com/BerriAI/litellm/issues/4267
 2024-06-18 11:43:07 -07:00
Krrish Dholakia
3f7252c422 fix(support-passing-image-url-to-gemini-via-vertex-ai): Closes https://github.com/BerriAI/litellm/issues/4262 2024-06-18 10:55:58 -07:00
Nejc Habjan
2ecd614a73
fix: add more type hints to init methods 2024-06-18 12:09:39 +02:00
Krish Dholakia
63216f42b8
Merge branch 'main' into litellm_gemini_refactoring 2024-06-17 19:50:56 -07:00
Krish Dholakia
48a0635a37
Merge pull request #4182 from UsableMachines/fix-type-uppercase 
Fix file type handling of uppercase extensions
 2024-06-17 17:54:20 -07:00
Krrish Dholakia
3d9ef689e7 fix(vertex_httpx.py): check if model supports system messages before sending separately 2024-06-17 17:32:38 -07:00
Krrish Dholakia
f597aa432b feat(cost_calculator.py): add cost calculating for dynamic context window (vertex ai / google ai studio) 2024-06-17 12:38:10 -07:00
Krrish Dholakia
115adc7c30 fix(init.py): fix imports 2024-06-15 11:31:09 -07:00
Krrish Dholakia
d7bed031bc fix(types/utils.py): fix import 2024-06-15 11:04:15 -07:00
Krrish Dholakia
4f91205530 refactor(utils.py): refactor Logging to it's own class. Cut down utils.py to <10k lines. 
Easier debugging

 Reference: https://github.com/BerriAI/litellm/issues/4206
 2024-06-15 10:57:20 -07:00
nick-rackauckas
25ce49770a Fix file type handling of uppercase extensions 2024-06-13 15:00:16 -07:00
Krrish Dholakia
42f326a164 fix(vertex_httpx.py): support json schema 2024-06-12 21:46:43 -07:00
Krrish Dholakia
c426d75e91 fix(vertex_httpx.py): add function calling support to httpx route 2024-06-12 21:11:00 -07:00
Krrish Dholakia
3955b058ed fix(vertex_httpx.py): support streaming via httpx client 2024-06-12 19:55:14 -07:00
Krrish Dholakia
3b913443fe feat(vertex_httpx.py): Moving to call vertex ai via httpx (instead of their sdk). Allows us to support all their api updates. 2024-06-12 16:47:00 -07:00
Krrish Dholakia
84652dd946 fix(bedrock_httpx.py): fix tool calling for anthropic bedrock calls w/ streaming 
Fixes https://github.com/BerriAI/litellm/issues/4091
 2024-06-10 14:20:25 -07:00
Krrish Dholakia
6306914e56 fix(types/router.py): modelgroupinfo to handle mode being None and supported_openai_params not being a list 2024-06-08 20:13:45 -07:00
Krrish Dholakia
af1ae80277 fix(litellm_pre_call_utils.py): add support for key level caching params 2024-06-07 22:09:14 -07:00
Ishaan Jaff
e1f722b83b linting fix 2024-06-07 17:23:05 -07:00
Ishaan Jaff
718b547646
Merge branch 'main' into litellm_security_fix 2024-06-07 16:52:25 -07:00