phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
21359 commits 2484 branches 894 tags 537 MiB
Commit graph

2105 commits

Author SHA1 Message Date
Krrish Dholakia
cf1a1605a6 feat(cost_calculator.py): only override base model if custom pricing is set 2024-08-19 16:05:49 -07:00
Krrish Dholakia
c5d1899940 feat(Support-pass-through-for-bedrock-endpoints): Allows pass-through support for bedrock endpoints 2024-08-17 17:57:43 -07:00
Krrish Dholakia
afcebac8ed feat(azure.py): support 'json_schema' for older models 
Converts the json schema input to a tool call, allows the call to still work on older azure models
 2024-08-17 16:31:13 -07:00
Krish Dholakia
0916197c9d Merge pull request #5244 from BerriAI/litellm_better_error_logging_sentry 
refactor: replace .error() with .exception() logging for better debugging on sentry
 2024-08-16 19:16:20 -07:00
Krish Dholakia
1844e01133 Merge pull request #5251 from Manouchehri/oidc-improvements-20240816 
(oidc): Add support for loading tokens via a file, env var, and path in env var
 2024-08-16 19:15:31 -07:00
Krish Dholakia
6fe21d6dd4 Merge pull request #5255 from BerriAI/litellm_fix_token_counter 
fix(utils.py): fix get_image_dimensions to handle more image types
 2024-08-16 17:27:27 -07:00
Ishaan Jaff
937471223a fix databricks streaming test 2024-08-16 16:56:08 -07:00
Ishaan Jaff
6de7785442 Merge pull request #5243 from BerriAI/litellm_add_bedrock_traces_in_response 
[Feat] Add bedrock Guardrail `traces ` in response when trace=enabled
 2024-08-16 14:49:20 -07:00
David Manouchehri
f24e986534 (oidc): Add support for loading tokens via a file, environment variable, and from a file path set in an env var. 2024-08-16 20:13:07 +00:00
Krrish Dholakia
3e42ee1bbb fix(utils.py): fix get_image_dimensions to handle more image types 
Fixes https://github.com/BerriAI/litellm/issues/5205
 2024-08-16 12:00:04 -07:00
Ishaan Jaff
262bf14917 return traces in bedrock guardrails when enabled 2024-08-16 11:35:43 -07:00
Krrish Dholakia
2874b94fb1 refactor: replace .error() with .exception() logging for better debugging on sentry 2024-08-16 09:22:47 -07:00
Ishaan Jaff
98c9191f84 pass trace through for bedrock guardrails 2024-08-16 09:10:56 -07:00
Ishaan Jaff
15334cfae3 Merge pull request #5173 from gitravin/rn/sagemaker-zero-temp 
Allow zero temperature for Sagemaker models based on config
 2024-08-16 08:45:44 -07:00
Ishaan Jaff
953a67ba4c refactor sagemaker to be async 2024-08-15 18:18:02 -07:00
Krrish Dholakia
43b90c0b86 fix(utils.py): fix is_azure_openai_model helper function 2024-08-14 14:04:39 -07:00
Krrish Dholakia
3026e69926 fix(utils.py): support calling openai models via azure_ai/ 2024-08-14 13:41:04 -07:00
Krrish Dholakia
ec3bf3eda6 fix(utils.py): ignore none chunk in stream infinite loop check 
Fixes https://github.com/BerriAI/litellm/issues/5158#issuecomment-2287156946
 2024-08-13 15:06:44 -07:00
Ravi N
7e12f3f02f remove aws_sagemaker_allow_zero_temp from the parameters passed to inference 2024-08-12 21:09:50 -04:00
Krrish Dholakia
7620ef0628 fix(utils.py): if openai model, don't check hf tokenizers 2024-08-12 16:28:22 -07:00
Krrish Dholakia
f4c984878d fix(utils.py): Break out of infinite streaming loop 
Fixes https://github.com/BerriAI/litellm/issues/5158
 2024-08-12 14:00:43 -07:00
Krrish Dholakia
4e5d5354c2 build(model_prices_and_context_window.json): add 'supports_assistant_prefill' to model info map 
Closes https://github.com/BerriAI/litellm/issues/4881
 2024-08-10 14:15:12 -07:00
Krrish Dholakia
5ad72419d2 docs(prefix.md): add prefix support to docs 2024-08-10 13:55:47 -07:00
Krrish Dholakia
3fd02a1587 fix(main.py): safely fail stream_chunk_builder calls 2024-08-10 10:22:26 -07:00
Krrish Dholakia
7c8484ac15 fix(utils.py): handle anthropic overloaded error 2024-08-08 17:18:19 -07:00
Ishaan Jaff
c6799e8aad fix use get_file_check_sum 2024-08-08 08:03:08 -07:00
Krrish Dholakia
94fb5c093e fix(vertex_ai_partner.py): pass model for llama3 param mapping 2024-08-07 18:07:14 -07:00
Krrish Dholakia
82eb418c86 fix(utils.py): fix linting error for python3.8 2024-08-07 13:14:29 -07:00
Krish Dholakia
77a33baabb Merge branch 'main' into litellm_add_pydantic_model_support 2024-08-07 13:07:46 -07:00
Krrish Dholakia
788b06a33c fix(utils.py): support deepseek tool calling 
Fixes https://github.com/BerriAI/litellm/issues/5081
 2024-08-07 11:14:05 -07:00
Krrish Dholakia
8b028d41aa feat(utils.py): support validating json schema client-side if user opts in 2024-08-06 19:35:33 -07:00
Krrish Dholakia
831dc1b886 feat: Translate openai 'response_format' json_schema to 'response_schema' for vertex ai + google ai studio 
Closes https://github.com/BerriAI/litellm/issues/5074
 2024-08-06 19:06:14 -07:00
Krrish Dholakia
2b132c6bef feat(utils.py): support passing response_format as pydantic model 
Related issue - https://github.com/BerriAI/litellm/issues/5074
 2024-08-06 18:16:07 -07:00
Ishaan Jaff
ff9fe47989 use file size _ name to get file check sum 2024-08-06 15:18:50 -07:00
Ishaan Jaff
75cbdda714 use file_checksum 2024-08-06 13:55:22 -07:00
Krrish Dholakia
152e7ebc51 fix(utils.py): fix dynamic api base 2024-08-06 11:27:39 -07:00
Krrish Dholakia
3a3381387f feat(utils.py): check env var for api base for openai-compatible endpoints 
Closes https://github.com/BerriAI/litellm/issues/5066
 2024-08-06 08:32:44 -07:00
Krrish Dholakia
8500f6d087 feat(caching.py): enable caching on provider-specific optional params 
Closes https://github.com/BerriAI/litellm/issues/5049
 2024-08-05 11:18:59 -07:00
Krrish Dholakia
bbc56f7202 fix(utils.py): parse out aws specific params from openai call 
Fixes https://github.com/BerriAI/litellm/issues/5009
 2024-08-03 12:04:44 -07:00
Krrish Dholakia
acbc2917b8 feat(utils.py): Add github as a provider 
Closes https://github.com/BerriAI/litellm/issues/4922#issuecomment-2266564469
 2024-08-03 09:11:22 -07:00
Krish Dholakia
95175b0b34 Merge pull request #5029 from BerriAI/litellm_azure_ui_fix 
fix(utils.py): Fix adding azure models on ui
 2024-08-02 22:12:19 -07:00
Krrish Dholakia
e6bc7e938a fix(utils.py): handle scenario where model="azure/*" and custom_llm_provider="azure" 
Fixes https://github.com/BerriAI/litellm/issues/4912
 2024-08-02 17:48:53 -07:00
Ishaan Jaff
954dd95bdb Merge pull request #5026 from BerriAI/litellm_fix_whisper_caching 
[Fix] Whisper Caching - Use correct cache keys for checking request in cache
 2024-08-02 17:26:28 -07:00
Ishaan Jaff
8074d0d3f8 return cache hit True on cache hits 2024-08-02 15:07:05 -07:00
Ishaan Jaff
f5ec25248a log correct file name on langfuse 2024-08-02 14:49:25 -07:00
Krrish Dholakia
c1513bfe42 fix(types/utils.py): support passing prompt cache usage stats in usage object 
Passes deepseek prompt caching values through to end user
 2024-08-02 09:30:50 -07:00
Haadi Rakhangi
1adf7bc909 Merge branch 'BerriAI:main' into main 2024-08-02 21:08:48 +05:30
Haadi Rakhangi
a047df3825 qdrant semantic caching added 2024-08-02 21:07:19 +05:30
Krrish Dholakia
8204037975 fix(utils.py): fix codestral streaming 2024-08-02 07:38:06 -07:00
Krrish Dholakia
70afbafd94 fix(bedrock_httpx.py): fix ai21 streaming 2024-08-01 22:03:24 -07:00