Commit graph

1357 commits

Author SHA1 Message Date
Krish Dholakia
b6ca4406b6
Merge branch 'main' into bedrock-llama3.1-405b 2024-07-25 19:29:10 -07:00
Ishaan Jaff
a0655b4192
Merge pull request #4884 from Manouchehri/add-mistral-large-2407-bedrock-1
Add mistral.mistral-large-2407-v1:0 on Amazon Bedrock
2024-07-25 19:22:46 -07:00
Krish Dholakia
c0c934d9cf
Merge pull request #4879 from fracapuano/main
Add Single-Token predictions support for Replicate
2024-07-25 19:10:57 -07:00
Krish Dholakia
a306b83b2d
Merge pull request #4887 from BerriAI/litellm_custom_llm
feat(custom_llm.py): Support Custom LLM Handlers
2024-07-25 19:05:29 -07:00
Krrish Dholakia
41abd51240 fix(custom_llm.py): pass input params to custom llm 2024-07-25 19:03:52 -07:00
Ishaan Jaff
f2443996d8 feat support audio health checks for azure 2024-07-25 17:30:15 -07:00
Ishaan Jaff
2432c90515 feat - support health check audio_speech 2024-07-25 17:26:14 -07:00
Ishaan Jaff
e3142b4294 fix whisper health check with litellm 2024-07-25 17:22:57 -07:00
Krrish Dholakia
060249c7e0 feat(utils.py): support async streaming for custom llm provider 2024-07-25 17:11:57 -07:00
Krrish Dholakia
b4e3a77ad0 feat(utils.py): support sync streaming for custom llm provider 2024-07-25 16:47:32 -07:00
Krrish Dholakia
9f97436308 fix(custom_llm.py): support async completion calls 2024-07-25 15:51:39 -07:00
Krrish Dholakia
6bf1b9353b 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
22c66991ed
Support tool calling for Llama 3.1 on Amazon bedrock. 2024-07-25 20:36:25 +00:00
David Manouchehri
5c4ee3ef3c
Add mistral.mistral-large-2407-v1:0 on Amazon Bedrock. 2024-07-25 20:04:03 +00:00
David Manouchehri
3293ad7458
Add Llama 3.1 405b for Bedrock 2024-07-25 19:30:13 +00:00
fracapuano
5553f84d51 fix: now supports single tokens prediction 2024-07-25 19:06:07 +02:00
Krrish Dholakia
99d8b0ad68 fix(bedrock_httpx.py): fix async client check 2024-07-24 12:43:52 -07:00
David Manouchehri
609075bd17
Add Llama 3.1 for Bedrock. 2024-07-24 05:48:23 +00:00
Krish Dholakia
6c580ac8dc
Merge pull request #4845 from BerriAI/litellm_vertex_ai_llama3_1_api
feat(vertex_ai_llama.py): vertex ai llama3.1 api support
2024-07-23 21:51:46 -07:00
Krrish Dholakia
fb0a13c8bb fix(anthropic.py): support openai system message being a list 2024-07-23 21:45:56 -07:00
Krrish Dholakia
7df94100e8 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
83ef52e180 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
Ishaan Jaff
a71b60d005 Pass litellm proxy specific metadata 2024-07-23 15:31:30 -07:00
Ishaan Jaff
aba600a892 fix triton linting 2024-07-23 11:03:34 -07:00
Ishaan Jaff
1355932bf4
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
Krrish Dholakia
f4a388f217 fix(openai.py): check if error body is a dictionary before indexing in 2024-07-22 18:12:04 -07:00
Krrish Dholakia
2f65c950fe fix(vertex_httpx.py): Change non-blocking vertex error to warning
Fixes https://github.com/BerriAI/litellm/issues/4825
2024-07-22 14:00:33 -07:00
Krish Dholakia
227f55f370
Revert "Fix: use Bedrock region from environment variables before other region definitions" 2024-07-22 07:40:24 -07:00
Ishaan Jaff
b901a65572 fix make_sync_openai_audio_transcriptions_request 2024-07-20 20:03:12 -07:00
Krish Dholakia
bb6b2c6872
Merge pull request #4613 from petermuller/main
Fix: use Bedrock region from environment variables before other region definitions
2024-07-20 19:19:05 -07:00
Ishaan Jaff
66c73e4425 fix merge conflicts 2024-07-20 19:14:20 -07:00
Ishaan Jaff
f6225623e9
Merge branch 'main' into litellm_return-response_headers 2024-07-20 19:05:56 -07:00
Ishaan Jaff
82764d2cec fix make_sync_openai_audio_transcriptions_request 2024-07-20 18:17:21 -07:00
Ishaan Jaff
5e4d291244 rename to _response_headers 2024-07-20 17:31:16 -07:00
Ishaan Jaff
5e52f50a82 return response headers 2024-07-20 15:26:44 -07:00
Krrish Dholakia
a27454b8e3 fix(openai.py): support completion, streaming, async_streaming 2024-07-20 15:23:42 -07:00
Krrish Dholakia
86c9e05c10 fix(openai.py): drop invalid params if drop_params: true for azure ai
Fixes https://github.com/BerriAI/litellm/issues/4800
2024-07-20 15:08:15 -07:00
Ishaan Jaff
3427838ce5 openai - return response headers 2024-07-20 15:04:27 -07:00
Ishaan Jaff
64dbe07593 openai return response headers 2024-07-20 14:07:41 -07:00
Krish Dholakia
156d445597
Merge pull request #4796 from BerriAI/litellm_refactor_requests_factory
fix(factory.py): refactor factory to use httpx client
2024-07-19 21:07:41 -07:00
Krrish Dholakia
335cf65452 fix(anthropic.py): fix streaming client 2024-07-19 18:55:00 -07:00
Krrish Dholakia
757dedd4c8 fix(factory.py): refactor factory to use httpx client 2024-07-19 15:35:05 -07:00
Krrish Dholakia
4c4f032a75 fix(factory.py): refactor factory to use httpx client 2024-07-19 15:32:01 -07:00
Krish Dholakia
f973bd8109
Merge branch 'main' into litellm_ai21_jamba 2024-07-19 15:11:55 -07:00
Sophia Loris
d779253949 resolve merge conflicts 2024-07-19 09:45:53 -05:00
Sophia Loris
d5c65c6be2 Add support for Triton streaming & triton async completions 2024-07-19 09:35:27 -05:00
Krish Dholakia
2ad1c0455a
Merge pull request #4773 from titusz/patch-1
Add missing `num_gpu` ollama configuration parameter
2024-07-18 22:47:39 -07:00
Krrish Dholakia
c56456be64 fix(anthropic.py): revert client to requests library 2024-07-18 22:45:41 -07:00
Krrish Dholakia
f2401d6d5e feat(vertex_ai_anthropic.py): support response_schema for vertex ai anthropic calls
allows passing response_schema for anthropic calls. supports schema validation.
2024-07-18 22:40:35 -07:00
Krish Dholakia
967964a51c
Merge branch 'main' into litellm_anthropic_response_schema_support 2024-07-18 20:40:16 -07:00