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
Krish Dholakia
0fc50a69ee Merge branch 'main' into litellm_fix_streaming_usage_calc 2024-08-01 21:29:04 -07:00
Krish Dholakia
375a4049aa Merge branch 'main' into litellm_response_cost_logging 2024-08-01 21:28:22 -07:00
Krrish Dholakia
cb9b19e887 feat(vertex_ai_partner.py): add vertex ai codestral FIM support 
Closes https://github.com/BerriAI/litellm/issues/4984
 2024-08-01 17:10:27 -07:00
Krrish Dholakia
71aada78d6 fix(utils.py): fix togetherai streaming cost calculation 2024-08-01 15:03:08 -07:00
Krrish Dholakia
a502914f13 fix(utils.py): fix anthropic streaming usage calculation 
Fixes https://github.com/BerriAI/litellm/issues/4965
 2024-08-01 14:45:54 -07:00
Krrish Dholakia
08541d056c fix(litellm_logging.py): use 1 cost calc function across response headers + logging integrations 
Ensures consistent cost calculation when azure base models are used
 2024-08-01 10:26:59 -07:00
Krrish Dholakia
ac6bca2320 fix(utils.py): fix special keys list for provider-specific items in response object 2024-07-31 18:30:49 -07:00
Krrish Dholakia
1206b7626a fix(utils.py): return additional kwargs from openai-like response body 
Closes https://github.com/BerriAI/litellm/issues/4981
 2024-07-31 15:37:03 -07:00
Krrish Dholakia
b95feb16f1 fix(utils.py): map cohere timeout error 2024-07-31 15:15:18 -07:00
Krrish Dholakia
dc58b9f33e fix(utils.py): fix linting errors 2024-07-30 18:38:10 -07:00
Krrish Dholakia
0bcfdafc58 fix(utils.py): fix model registeration to model cost map 
Fixes https://github.com/BerriAI/litellm/issues/4972
 2024-07-30 18:15:00 -07:00
Krrish Dholakia
802e39b606 fix(utils.py): fix cost tracking for vertex ai partner models 2024-07-30 14:20:52 -07:00
Krish Dholakia
14c2aabf63 Merge pull request #4948 from dleen/response 
fixes: #4947 Bedrock context exception does not have a response
 2024-07-29 15:03:40 -07:00
David Leen
55cc3adbec fixes: #4947 Bedrock context exception does not have a response 2024-07-29 14:23:56 -07:00
Krrish Dholakia
00dde68001 fix(utils.py): fix trim_messages to handle tool calling 
Fixes https://github.com/BerriAI/litellm/issues/4931
 2024-07-29 13:04:41 -07:00
Krrish Dholakia
708b427a04 fix(utils.py): correctly re-raise azure api connection error 
'
 2024-07-29 12:28:25 -07:00
Krrish Dholakia
2a705dbb49 fix(utils.py): check if tools is iterable before indexing into it 
Fixes https://github.com/BerriAI/litellm/issues/4933
 2024-07-29 09:01:32 -07:00
Ravi N
5cf0667d38 Allow zero temperature for Sagemaker models based on config 
Since Sagemaker can host any kind of model, some models allow
zero temperature. However, this is not enabled by default and
only allowed based on config
 2024-07-28 21:55:53 -04:00
Krrish Dholakia
dc7df00581 fix: utils.py 
fix supported openai params
 2024-07-27 22:03:40 -07:00
Krish Dholakia
1c50339580 Merge pull request #4925 from BerriAI/litellm_vertex_mistral 
feat(vertex_ai_partner.py): Vertex AI Mistral Support
 2024-07-27 21:51:26 -07:00
Krish Dholakia
0525fb75f3 Merge branch 'main' into litellm_vertex_migration 2024-07-27 20:25:12 -07:00
Krrish Dholakia
fcac9bd2fa fix(utils.py): support fireworks ai finetuned models 
Fixes https://github.com/BerriAI/litellm/issues/4923
 2024-07-27 15:38:27 -07:00
Krrish Dholakia
70b281c0aa fix(utils.py): support fireworks ai finetuned models 
Fixes https://github.com/BerriAI/litellm/issues/4923
 2024-07-27 15:37:28 -07:00
Krrish Dholakia
56ba0c62f3 feat(utils.py): fix openai-like streaming 2024-07-27 15:32:57 -07:00
Krrish Dholakia
089539e21e fix(utils.py): add exception mapping for databricks errors 2024-07-27 13:13:31 -07:00
Krrish Dholakia
ce7257ec5e feat(vertex_ai_partner.py): initial working commit for calling vertex ai mistral 
Closes https://github.com/BerriAI/litellm/issues/4874
 2024-07-27 12:54:14 -07:00
Krrish Dholakia
3a1eedfbf3 feat(ollama_chat.py): support ollama tool calling 
Closes https://github.com/BerriAI/litellm/issues/4812
 2024-07-26 21:51:54 -07:00
Krrish Dholakia
1562cba823 fix(utils.py): fix cache hits for streaming 
Fixes https://github.com/BerriAI/litellm/issues/4109
 2024-07-26 19:04:08 -07:00
Krrish Dholakia
d3ff21181c fix(litellm_cost_calc/google.py): support meta llama vertex ai cost tracking 2024-07-25 22:12:07 -07:00
Ishaan Jaff
1103c614a0 Merge branch 'main' into litellm_proxy_support_all_providers 2024-07-25 20:15:37 -07:00
Krrish Dholakia
e7744177cb fix(utils.py): don't raise error on openai content filter during streaming - return as is 
Fixes issue where we would raise an error vs. openai who return the chunk with finish reason as 'content_filter'
 2024-07-25 19:50:52 -07:00
Krish Dholakia
a5cea7929d Merge branch 'main' into bedrock-llama3.1-405b 2024-07-25 19:29:10 -07:00
Ishaan Jaff
422b4d7e0f support using */* 2024-07-25 18:48:56 -07:00
Krrish Dholakia
9b1c7066b7 feat(utils.py): support async streaming for custom llm provider 2024-07-25 17:11:57 -07:00
Krrish Dholakia
bf23aac11d feat(utils.py): support sync streaming for custom llm provider 2024-07-25 16:47:32 -07:00
Krrish Dholakia
54e1ca29b7 feat(custom_llm.py): initial working commit for writing your own custom LLM handler 
Fixes https://github.com/BerriAI/litellm/issues/4675

 Also Addresses https://github.com/BerriAI/litellm/discussions/4677
 2024-07-25 15:33:05 -07:00
David Manouchehri
5a7be22038 Check for converse support first. 2024-07-25 21:16:23 +00:00
Krrish Dholakia
5945da4a66 fix(main.py): fix calling openai gpt-3.5-turbo-instruct via /completions 
Fixes https://github.com/BerriAI/litellm/issues/749
 2024-07-25 09:57:19 -07:00
wslee
c2efb260c1 support dynamic api base 2024-07-25 11:14:38 +09:00
wslee
e7fbb7e40a add support for friendli dedicated endpoint 2024-07-25 11:14:35 +09:00
Ishaan Jaff
1e65173b88 add UnsupportedParamsError to litellm exceptions 2024-07-24 12:20:14 -07:00
Krrish Dholakia
23a3be184b build(model_prices_and_context_window.json): add model pricing for vertex ai llama 3.1 api 2024-07-23 17:36:07 -07:00
Krrish Dholakia
778afcee31 feat(vertex_ai_llama.py): vertex ai llama3.1 api support 
Initial working commit for vertex ai llama 3.1 api support
 2024-07-23 17:07:30 -07:00
Krrish Dholakia
271407400a fix(utils.py): support raw response headers for streaming requests 2024-07-23 11:58:58 -07:00
Krrish Dholakia
d55b516f3c feat(utils.py): support passing openai response headers to client, if enabled 
Allows openai/openai-compatible provider response headers to be sent to client, if 'return_response_headers' is enabled
 2024-07-23 11:30:52 -07:00
Ishaan Jaff
71c755d9a2 Merge pull request #3905 from giritatavarty-8451/litellm_triton_chatcompletion_support 
Litellm triton chatcompletion support - Resubmit of #3895
 2024-07-23 10:30:26 -07:00
Ishaan Jaff
8ae98008b3 fix raise correct provider on content policy violation 2024-07-22 16:03:15 -07:00
Ishaan Jaff
3bbb4e8f1d fix checking if _known_custom_logger_compatible_callbacks 2024-07-22 15:43:43 -07:00
Krrish Dholakia
98382a465a fix(utils.py): allow dropping extra_body in additional_drop_params 
Fixes https://github.com/BerriAI/litellm/issues/4769
 2024-07-20 19:12:58 -07:00
Ishaan Jaff
2dcbd5c534 rename to _response_headers 2024-07-20 17:31:16 -07:00