scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-21 00:21:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 74
15656 commits 2565 branches 1413 tags 3.2 GiB
Commit graph

15656 commits

This branch
This branch
All branches
Author SHA1 Message Date
Joe Cheng
b7be609d6e Use correct key name 2024-08-03 11:58:46 -07:00
Joe Cheng
1fbfc09b44 Add unit test 2024-08-02 20:51:08 -07:00
Joe Cheng
33f4411f17 Fix tool call coalescing 
The previous code seemed to assume that the tool call index property
started at 0, but Anthropic sometimes returns them starting at 1.
This was causing an extra null-ish tool call to be materialized.
 2024-08-02 13:05:23 -07:00
Joe Cheng
90dd60fa71 fix(main.py): Handle bedrock tool calling in stream_chunk_builder 
Fixes #5022.

The streaming chunks from Anthropic seem to violate an assumption
that is implicit in the stream_chunk_builder implementation: that
only tool_calls OR function_calls OR content will appear in a
streamed response. The repro in #5022 shows that you can get
content followed by tool calls.

These changes properly handle these combinations by building
separate lists of each type of chunk (note that in theory a chunk
could appear in multiple lists, e.g. both delta.tool_calls and
delta.content being present on one chunk).
 2024-08-02 12:41:13 -07:00
Krrish Dholakia
cd073d5ad3 test: handle anthropic rate limit error 2024-08-02 08:57:09 -07:00
Ishaan Jaff
48419ca8bc add step to ghcr deploy 2024-08-02 08:06:09 -07:00
Krrish Dholakia
fe7e68adc8 fix(utils.py): fix codestral streaming 2024-08-02 07:38:06 -07:00
Ishaan Jaff
75fba18c9f fix langfuse hardcoded public key 2024-08-02 07:21:02 -07:00
Krrish Dholakia
4c2ef8ea64 fix(bedrock_httpx.py): fix ai21 streaming 2024-08-01 22:03:24 -07:00
Krrish Dholakia
57e3044974 bump: version 1.42.9 → 1.42.10 2024-08-01 21:29:36 -07:00
Krish Dholakia
13337bca57
Merge pull request #5001 from BerriAI/litellm_fix_streaming_usage_calc 
fix(utils.py): Add streaming token usage in hidden params
 2024-08-01 21:29:10 -07:00
Krish Dholakia
25ac9c2d75
Merge branch 'main' into litellm_fix_streaming_usage_calc 2024-08-01 21:29:04 -07:00
Krish Dholakia
6bdc443157
Merge pull request #4996 from BerriAI/litellm_response_cost_logging 
fix(litellm_logging.py): Fix azure base model cost calc in response headers
 2024-08-01 21:28:34 -07:00
Krish Dholakia
e7f83602d8
Merge branch 'main' into litellm_response_cost_logging 2024-08-01 21:28:22 -07:00
Krrish Dholakia
d096c6c0ee fix(langfuse.py): cleanup 2024-08-01 21:24:41 -07:00
Krish Dholakia
d8778380d8
Merge pull request #5004 from BerriAI/litellm_codestral_fim_support 
feat(vertex_ai_partner.py): add vertex ai codestral FIM support
 2024-08-01 21:24:12 -07:00
Ishaan Jaff
f5b8ecbcc3 docs spend tracking enteprrise 2024-08-01 20:52:23 -07:00
Krrish Dholakia
4355e923e5 fix(langfuse.py): cleanup 2024-08-01 20:46:29 -07:00
Ishaan Jaff
7f93fa01e9 ci/cd run again 2024-08-01 19:55:12 -07:00
Ishaan Jaff
85ced920a0 fix test traceloop.py 2024-08-01 19:49:53 -07:00
Krrish Dholakia
f506eb341b feat(litellm_logging.py): log exception response headers to langfuse 2024-08-01 18:07:47 -07:00
Ishaan Jaff
17d007d6da Update prompt_injection.md 2024-08-01 18:07:38 -07:00
Ishaan Jaff
c09d95d3d3 ci/cd - anyscale discontinued their API endoints - skip test 2024-08-01 18:07:38 -07:00
Ishaan Jaff
69d58b08eb fix model prices formatting 2024-08-01 18:07:38 -07:00
David Manouchehri
6bf2166f93 Add new model for gemini-1.5-pro-exp-0801. 2024-08-01 18:07:38 -07:00
Ishaan Jaff
3d1cdd5374 bump: version 1.42.8 → 1.42.9 2024-08-01 18:07:38 -07:00
Ishaan Jaff
673a991da2 fix test_traceparent_not_added_by_default 2024-08-01 18:07:38 -07:00
Ishaan Jaff
2029e0607c docs dbrx 2024-08-01 18:07:38 -07:00
Ishaan Jaff
f89a0427df docs add new dbrx models 2024-08-01 18:07:38 -07:00
Ishaan Jaff
42bf2bb551 add correct context window 2024-08-01 18:07:38 -07:00
Ishaan Jaff
ff27e5813b add new dbrx models 2024-08-01 18:07:38 -07:00
Ishaan Jaff
ee9b9623ab docs gcs buckets 2024-08-01 18:07:38 -07:00
lowjiansheng
f02325bf76 update helm chart 2024-08-01 18:07:38 -07:00
Ishaan Jaff
026e380b92 enforce premium user cheks on gcs bucket 2024-08-01 18:07:38 -07:00
Ishaan Jaff
950f803035 docs logging to GCS 2024-08-01 18:07:38 -07:00
Ishaan Jaff
7f3dd3072c docs setting service accounts 2024-08-01 18:07:38 -07:00
Ishaan Jaff
6c899ced28 init gcs using gcs_bucket 2024-08-01 18:07:38 -07:00
Ishaan Jaff
1595dc4dc6 docs using gcs 2024-08-01 18:07:38 -07:00
Ishaan Jaff
781bfd1517 fix type errors 2024-08-01 18:07:38 -07:00
Ishaan Jaff
fc447dee5e delete object from gcs 2024-08-01 18:07:38 -07:00
Ishaan Jaff
ba74d71c31 test writing logs to GCS bucket 2024-08-01 18:07:38 -07:00
Ishaan Jaff
357a1b87df feat gcs bucket log payload 2024-08-01 18:07:38 -07:00
Ishaan Jaff
92a34f9dcd add better debugging statements for vertex logging 2024-08-01 18:07:38 -07:00
Ishaan Jaff
a18f2f7626 basic gcs logging test 2024-08-01 18:07:38 -07:00
Krrish Dholakia
35de167550 fix(vertex_ai_partner.py): add /chat/completion codestral support 
Closes https://github.com/BerriAI/litellm/issues/4984
 2024-08-01 18:07:38 -07:00
Krrish Dholakia
7404373e93 fix(google.py): fix cost tracking for vertex ai mistral models 2024-08-01 18:07:38 -07:00
Krrish Dholakia
d350c9194f build(model_prices_and_context_window.json): add mistral nemo latest to model cost map 2024-08-01 18:07:38 -07:00
Krrish Dholakia
5acb2236af fix(databricks.py): fix error handling 2024-08-01 18:07:38 -07:00
Krrish Dholakia
db65a5a70f fix: add type hints for APIError and AnthropicError status codes 
Fixes https://github.com/BerriAI/litellm/issues/5000
 2024-08-01 18:07:38 -07:00
Krrish Dholakia
186dabebcb fix(cost_calculator.py): respect litellm.suppress_debug_info for cost calc 
Fixes https://github.com/BerriAI/litellm/issues/4818#issuecomment-2263795765
 2024-08-01 18:07:38 -07:00