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
17231 commits 2484 branches 894 tags 537 MiB
Commit graph

81 commits

Author SHA1 Message Date
Krish Dholakia
37f9705d6e
Bedrock Embeddings refactor + model support (#5462) 
* refactor(bedrock): initial commit to refactor bedrock to a folder

Improve code readability + maintainability

* refactor: more refactor work

* fix: fix imports

* feat(bedrock/embeddings.py): support translating embedding into amazon embedding formats

* fix: fix linting errors

* test: skip test on end of life model

* fix(cohere/embed.py): fix linting error

* fix(cohere/embed.py): fix typing

* fix(cohere/embed.py): fix post-call logging for cohere embedding call

* test(test_embeddings.py): fix error message assertion in test
 2024-09-01 13:29:58 -07:00
Krish Dholakia
dd7b008161
fix: Minor LiteLLM Fixes + Improvements (29/08/2024) (#5436) 
* fix(model_checks.py): support returning wildcard models on `/v1/models`

Fixes https://github.com/BerriAI/litellm/issues/4903

* fix(bedrock_httpx.py): support calling bedrock via api_base

Closes https://github.com/BerriAI/litellm/pull/4587

* fix(litellm_logging.py): only leave last 4 char of gemini key unmasked

Fixes https://github.com/BerriAI/litellm/issues/5433

* feat(router.py): support setting 'weight' param for models on router

Closes https://github.com/BerriAI/litellm/issues/5410

* test(test_bedrock_completion.py): add unit test for custom api base

* fix(model_checks.py): handle no "/" in model
 2024-08-29 22:40:25 -07:00
David Manouchehri
19db80ffeb
(bedrock): Add new cross-region inference support for Bedrock. 2024-08-29 17:49:16 +00:00
Krrish Dholakia
6431af0678 fix(bedrock_httpx.py): support 'Auth' header as extra_header 
Fixes https://github.com/BerriAI/litellm/issues/5389#issuecomment-2313677977
 2024-08-27 16:08:54 -07:00
Krrish Dholakia
70bf8bd4f4 feat(factory.py): enable 'user_continue_message' for interweaving user/assistant messages when provider requires it 
allows bedrock to be used with autogen
 2024-08-22 11:03:33 -07:00
Ishaan Jaff
89ba7b3e11 pass trace through for bedrock guardrails 2024-08-16 09:10:56 -07:00
Ishaan Jaff
e217eda303 use BaseAWSLLM for bedrock getcredentials 2024-08-15 13:58:47 -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
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
Ishaan Jaff
43ff70348d init bedrock_tool_name_mappings 2024-08-09 17:09:19 -07:00
Krrish Dholakia
2ccb5a48b7 fix(bedrock_httpx.py): handle empty arguments returned during tool calling streaming 2024-08-07 09:54:50 -07:00
Krish Dholakia
fa82b2a412
Merge pull request #4982 from Manouchehri/bedrock-sts-custom-1 
Allow Bedrock to set custom STS endpoint for OIDC flow
 2024-08-02 23:42:38 -07:00
Krrish Dholakia
4c2ef8ea64 fix(bedrock_httpx.py): fix ai21 streaming 2024-08-01 22:03:24 -07:00
David Manouchehri
ffbe1845ef
(bedrock_httpx.py) - Add support for custom STS endpoints, e.g. for FIPS. 2024-07-31 16:51:52 +00:00
Ishaan Jaff
5154ec51a3 feat - support guardrailConfig 2024-07-29 14:10:09 -07:00
Krrish Dholakia
9a6ed8cabb fix(bedrock_httpx.py): fix streaming error message 
Fixes https://github.com/BerriAI/litellm/issues/4900
 2024-07-26 10:42:47 -07:00
Krish Dholakia
b6ca4406b6
Merge branch 'main' into bedrock-llama3.1-405b 2024-07-25 19:29:10 -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
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
Krrish Dholakia
96471c145e fix(bedrock_httpx.py): support jamba streaming 2024-07-18 19:36:50 -07:00
Krrish Dholakia
cece76c4ee feat(bedrock_httpx.py): add ai21 jamba instruct as converse model 
initial commit for adding ai21 jamba instruct support through bedrock converse
 2024-07-18 18:24:06 -07:00
Krrish Dholakia
e3ca2789df fix(bedrock_httpx.py): cache response stream shape 
Fixes https://github.com/BerriAI/litellm/issues/4774
 2024-07-18 17:41:31 -07:00
Ishaan Jaff
03933de775 fix exception raised in factory.py 2024-07-13 09:54:32 -07:00
Krrish Dholakia
88eb25da5c fix(bedrock_httpx.py): handle user error - malformed system prompt 
if user passes in system prompt as a list of content blocks, handle that
 2024-07-12 08:28:50 -07:00
Krrish Dholakia
6e9f048618 fix: move to using pydantic obj for setting values 2024-07-11 13:18:36 -07:00
Ishaan Jaff
7efe9beac5 fix test_bedrock_httpx_streaming 2024-07-10 17:14:53 -07:00
Ishaan Jaff
78e67f36e7 fix bedrock better debugging for credentials 2024-07-09 22:02:17 -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
David Manouchehri
9a74364baa
fix(bedrock_httpx.py): Add anthropic.claude-3-5-sonnet-20240620-v1:0 to the converse list. 2024-07-01 14:18:23 +00:00
Ishaan Jaff
46698ae01f fix param mapping for bedrock claude 2024-06-29 19:33:51 -07:00
Ishaan Jaff
f9ba3cf668 fix bedrock claude test 2024-06-29 18:46:06 -07:00
Brian Schultheiss
632b7ce17d Resolve merge conflicts 2024-06-29 15:53:02 -07:00
Krrish Dholakia
151d19960e fix(bedrock_httpx.py): Fix https://github.com/BerriAI/litellm/issues/4415 2024-06-26 16:19:46 -07:00
Brian Schultheiss
3fbb25f903 Updated more references to AWS session token 2024-06-23 13:37:38 -07:00
Brian Schultheiss
8ad1ae73e5 Support aws_session_token for bedrock client. https://github.com/BerriAI/litellm/issues/4346 2024-06-23 12:51:25 -07:00
Krrish Dholakia
cea630022e fix(add-exception-mapping-+-langfuse-exception-logging-for-streaming-exceptions): add exception mapping + langfuse exception logging for streaming exceptions 
Fixes https://github.com/BerriAI/litellm/issues/4338
 2024-06-22 21:26:15 -07:00
Krish Dholakia
f2b3770869
Merge pull request #4216 from BerriAI/litellm_refactor_logging 
refactor(utils.py): Cut down utils.py to <10k lines.
 2024-06-15 15:19:42 -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
Ishaan Jaff
38995def54 refactor to use _get_async_httpx_client 2024-06-14 21:30:42 -07:00
Ishaan Jaff
5ea6fbbe1e fix cached httpx client 2024-06-14 21:23:13 -07:00
Ishaan Jaff
ec095a814d fix async client 2024-06-14 21:12:32 -07:00
David Manouchehri
844f15f8b0
fix(bedrock_httpx.py): Add IAM caching for converse flow. 2024-06-11 17:00:18 +00:00
David Manouchehri
9aee0b4a0f
fix(bedrock_httpx.py): Fix STS region endpoint for converse flow. 2024-06-11 16:35:03 +00:00
David Manouchehri
7faf0b9586
fix(bedrock_httpx.py): Fix STS region endpoint. 2024-06-11 15:43:33 +00:00
David Manouchehri
cd21c80a15
feat(bedrock_httpx.py): Add AWS IAM cred caching for OIDC flow. 2024-06-11 15:43:15 +00:00