phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
16595 commits 2497 branches 897 tags 550 MiB
Commit graph

1509 commits

Author SHA1 Message Date
Krrish Dholakia
04d69464e2 fix(ollama.py): fix ollama embeddings - pass optional params 
Fixes https://github.com/BerriAI/litellm/issues/5267
 2024-08-19 08:45:26 -07:00
Krrish Dholakia
cc42f96d6a fix(ollama_chat.py): fix sync tool calling 
Fixes https://github.com/BerriAI/litellm/issues/5245
 2024-08-19 08:31:46 -07:00
Krrish Dholakia
db54b66457 style(vertex_httpx.py): make vertex error string more helpful 2024-08-17 15:09:55 -07:00
Krish Dholakia
be37310e94
Merge pull request #5232 from Penagwin/fix_anthropic_tool_streaming_index 
Fixes the `tool_use` indexes not being correctly mapped
 2024-08-17 14:33:50 -07:00
Krish Dholakia
a8dd2b6910
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
Ishaan Jaff
5d1fcc545b fix predictions image generation response 2024-08-16 15:06:12 -07:00
Krrish Dholakia
61f4b71ef7 refactor: replace .error() with .exception() logging for better debugging on sentry 2024-08-16 09:22:47 -07:00
Ishaan Jaff
89ba7b3e11 pass trace through for bedrock guardrails 2024-08-16 09:10:56 -07:00
Paul Lang
b0d13f42ed Merge remote-tracking branch 'origin/main' into fix_anthropic_tool_streaming_index 2024-08-16 09:26:04 -04:00
Ishaan Jaff
e1839c8da2 allow index to not exist in sagemaker chunks 2024-08-15 19:45:59 -07:00
Ishaan Jaff
b93152e978 assume index is not always in stream chunk 2024-08-15 19:42:03 -07:00
Ishaan Jaff
fa569aaf6f feat add support for aws_region_name 2024-08-15 19:32:59 -07:00
Ishaan Jaff
b4ba12e22c show bedrock, sagemaker creds in verbose mode 2024-08-15 19:10:11 -07:00
Ishaan Jaff
0d374fb7c0 fix sagemaker test 2024-08-15 18:23:41 -07:00
Ishaan Jaff
df4ea8fba6 refactor sagemaker to be async 2024-08-15 18:18:02 -07:00
Ishaan Jaff
e217eda303 use BaseAWSLLM for bedrock getcredentials 2024-08-15 13:58:47 -07:00
Paul Lang
97fce022e4 Fixes the tool_use chunk mapping 2024-08-15 15:44:09 -04:00
Ishaan Jaff
1f631606a5
Merge pull request #5210 from BerriAI/litellm_add_prompt_caching_support 
[Feat] Add Anthropic API Prompt Caching Support
 2024-08-14 17:43:01 -07:00
Ishaan Jaff
78a2013e51 add test for large context in system message for anthropic 2024-08-14 17:03:10 -07:00
Krrish Dholakia
6333b04be3 fix(factory.py): handle assistant null content 2024-08-14 15:44:38 -07:00
Ishaan Jaff
54102a660d pass cache_control in tool call 2024-08-14 15:18:11 -07:00
Ishaan Jaff
96f9655a02 test test_anthropic_api_prompt_caching_basic 2024-08-14 15:06:10 -07:00
Ishaan Jaff
b0651bd481 add anthropic cache controls 2024-08-14 14:56:49 -07:00
Krrish Dholakia
9b46ec05b0 fix(factory.py): support assistant messages as a list of dictionaries - cohere messages api 
Fixes https://github.com/BerriAI/litellm/pull/5121
 2024-08-14 14:19:59 -07:00
Krish Dholakia
eb5f0a8da2
Merge pull request #5148 from fabceolin/main 
Enable follow redirects in ollama_chat
 2024-08-14 14:08:45 -07:00
Ishaan Jaff
209c91ac03 feat - anthropic api context caching v0 2024-08-14 13:08:03 -07:00
Krish Dholakia
a6bf763dd9
Merge pull request #5116 from thiswillbeyourgithub/fix_ollama_argument_order 
fix: wrong order of arguments for ollama
 2024-08-14 08:36:14 -07:00
Krish Dholakia
c8f4cd373d
Merge pull request #5189 from ArtyomZemlyak/patch-1 
Fix not sended json_data_for_triton
 2024-08-13 20:44:26 -07:00
Krrish Dholakia
c1279ed809 fix(bedrock_httpx.py): fix error code for not found provider/model combo to be 404 2024-08-13 20:36:12 -07:00
Artem Zemliak
5290490106
Fix not sended json_data_for_triton 2024-08-14 09:57:48 +07:00
Krrish Dholakia
66d77f177f fix(bedrock_httpx.py): raise bad request error if invalid bedrock model given 2024-08-13 19:27:06 -07:00
Krrish Dholakia
526b196f83 fix(bedrock_httpx.py): handle empty stop string 2024-08-13 07:30:30 -07:00
Krrish Dholakia
6e8d2856b0 fix(bedrock_httpx.py): handle bedrock empty system message 2024-08-13 07:17:17 -07:00
Krrish Dholakia
96d4466a8f fix(azure.py): return response headers acompletion + acompletion w/ streaming 
Fixes https://github.com/BerriAI/litellm/issues/2440#issuecomment-2283259187
 2024-08-12 11:29:49 -07:00
Krrish Dholakia
dd2ea72cb4 fix(openai.py): fix position of invalid_params param 2024-08-10 09:52:27 -07:00
Fabrício Ceolin
936b76662f Follow redirects 2024-08-10 12:12:55 -03:00
Ishaan Jaff
d445f3967d correctly add modified tool names to cache 2024-08-09 17:39:49 -07:00
Ishaan Jaff
43ff70348d init bedrock_tool_name_mappings 2024-08-09 17:09:19 -07:00
Ishaan Jaff
8b98193a51 bedrock make_valid_bedrock_tool_name 2024-08-09 13:16:38 -07:00
Krrish Dholakia
0cf81eba62 fix(huggingface_restapi.py): support passing 'wait_for_model' param on completion calls 2024-08-09 09:25:19 -07:00
Krrish Dholakia
466dc9f32a fix(huggingface_restapi.py): fix hf embeddings optional param processing 2024-08-09 09:10:56 -07:00
Krrish Dholakia
d471f7e840 feat(vertex_httpx.py): return vertex grounding, citation, and safety results 2024-08-09 08:54:55 -07:00
Krrish Dholakia
51ccfa9e77 fix(huggingface_restapi.py): fixes issue where 'wait_for_model' was not being passed as expected 2024-08-09 08:36:35 -07:00
Krrish Dholakia
9839a7858c fix(anthropic.py): fix translation 2024-08-08 17:33:48 -07:00
Krrish Dholakia
da0413f0a4 fix(factory.py): handle openai function message having tool call id 2024-08-08 17:06:50 -07:00
Ishaan Jaff
e671ae58e3
Merge pull request #5119 from BerriAI/litellm_add_gemini_context_caching_litellm 
[Feat-Proxy] Add Support for VertexAI context caching
 2024-08-08 16:08:58 -07:00
Ishaan Jaff
cae941f4c0 auto update the model in cachedContents request 2024-08-08 15:56:46 -07:00
Krrish Dholakia
1bf8af5cb1 fix(anthropic.py): fix translation from /v1/messages format to openai format 2024-08-08 15:55:01 -07:00
Ishaan Jaff
0d662368ac add native cachedContents endpoint 2024-08-08 15:32:07 -07:00
Ishaan Jaff
d237e625ca use v1beta1 when using cached_content 2024-08-08 11:09:31 -07:00