Commit graph

260 commits

Author SHA1 Message Date
Krrish Dholakia
3a1b3227d8 fix(utils.py): ignore none chunk in stream infinite loop check
Fixes https://github.com/BerriAI/litellm/issues/5158#issuecomment-2287156946
2024-08-13 15:06:44 -07:00
Krrish Dholakia
fdd9a07051 fix(utils.py): Break out of infinite streaming loop
Fixes https://github.com/BerriAI/litellm/issues/5158
2024-08-12 14:00:43 -07:00
Krrish Dholakia
3cf9148a4a test: add vertex claude to streaming valid json str test 2024-08-07 10:18:17 -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
Krrish Dholakia
4919cc4d25 fix(anthropic.py): handle scenario where anthropic returns invalid json string for tool call while streaming
Fixes https://github.com/BerriAI/litellm/issues/5063
2024-08-07 09:24:11 -07:00
Krrish Dholakia
ca0a0bed46 fix(utils.py): fix anthropic streaming usage calculation
Fixes https://github.com/BerriAI/litellm/issues/4965
2024-08-01 14:45:54 -07:00
Ishaan Jaff
dce8e3efb8 testing fix - skip rate limit errors from anthropic api 2024-08-01 12:12:50 -07:00
Ishaan Jaff
54e1f18832 use timeouts for predibase - never use them in prod ! 2024-07-30 22:54:01 -07:00
Ishaan Jaff
19ab0614c4 fix predibase tests 2024-07-30 22:49:33 -07:00
Krrish Dholakia
24395492aa test: cleanup duplicate tests + add error handling for backend api errors 2024-07-30 21:47:52 -07:00
Krrish Dholakia
eecd93c81d test(test_streaming.py): fix streaming test 2024-07-30 20:36:19 -07:00
Ishaan Jaff
6c0506a144 handle predibase failing streaming tests 2024-07-30 17:53:27 -07:00
Krrish Dholakia
84513c0254 test(test_streaming.py): move to mock implementation for sagemaker streaming tests 2024-07-30 15:34:27 -07:00
Krrish Dholakia
e1cbb397fe test(test_streaming.py): handle predibase instability 2024-07-30 15:32:36 -07:00
Krrish Dholakia
a2fd8459fc 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
Krrish Dholakia
f64a3309d1 fix(utils.py): support raw response headers for streaming requests 2024-07-23 11:58:58 -07:00
Krrish Dholakia
a27454b8e3 fix(openai.py): support completion, streaming, async_streaming 2024-07-20 15:23:42 -07:00
Krrish Dholakia
96471c145e fix(bedrock_httpx.py): support jamba streaming 2024-07-18 19:36:50 -07:00
Ishaan Jaff
3110abc832 shorten predibase streaming test 2024-07-17 17:50:42 -07:00
Krrish Dholakia
b2e46086dd fix(utils.py): fix recreating model response object when stream usage is true 2024-07-11 21:01:12 -07:00
Ishaan Jaff
7efe9beac5 fix test_bedrock_httpx_streaming 2024-07-10 17:14:53 -07:00
Krish Dholakia
65bee737c5
Merge branch 'main' into litellm_gemini_stream_tool_calling 2024-07-06 19:07:31 -07:00
Ishaan Jaff
482913c2e9 test had "assert False" for some reason ? 2024-07-06 15:46:28 -07:00
Krrish Dholakia
faa88a1ab1 fix(vertex_httpx.py): support tool calling w/ streaming for vertex ai + gemini 2024-07-06 14:02:25 -07:00
Krrish Dholakia
f2dabc65be fix(anthropic.py): fix anthropic tool calling + streaming
Fixes https://github.com/BerriAI/litellm/issues/4537
2024-07-04 16:30:24 -07:00
Krrish Dholakia
2e5a81f280 fix(utils.py): stream_options working across all providers 2024-07-03 20:40:46 -07:00
Krrish Dholakia
344268e053 fix(anthropic.py): support *real* anthropic tool calling + streaming
Parses each chunk and translates to openai format
2024-07-03 19:48:35 -07:00
Krrish Dholakia
d18dc2648c fix(replicate.py): correctly handly invalid replicate response 2024-07-03 10:09:46 -07:00
Ishaan Jaff
03dbc29c85 fix test_completion_replicate_llama3_streaming 2024-06-29 19:51:07 -07:00
Krrish Dholakia
831745e710 test(test_streaming.py): try-except replicate api instability 2024-06-28 22:19:44 -07:00
Krrish Dholakia
0001683036 fix(cost_calculator.py): handle unexpected error in cost_calculator.py 2024-06-28 14:53:00 -07:00
Krrish Dholakia
a7122f91a1 fix(support-'alt=sse'-param): Fixes https://github.com/BerriAI/litellm/issues/4459 2024-06-28 10:40:47 -07:00
Krrish Dholakia
0fd9033502 fix(vertex_httpx.py): flush remaining chunks from stream 2024-06-22 20:33:54 -07:00
Krrish Dholakia
73254987da fix(vertex_httpx.py): ignore vertex finish reason - wait for stream to end
Fixes https://github.com/BerriAI/litellm/issues/4339
2024-06-22 20:21:01 -07:00
Krrish Dholakia
1b215d704d test: cleanup tests 2024-06-17 16:33:58 -07:00
Krrish Dholakia
c5df662e0f test(test_streaming.py): reduce vertex tests to avoid exhausting limits 2024-06-13 07:30:53 -07:00
Krish Dholakia
05e21441a6
Merge branch 'main' into litellm_vertex_completion_httpx 2024-06-12 21:19:22 -07:00
Ishaan Jaff
29e5e3c265 ci/cd predibase is an unstable provider 2024-06-12 21:10:30 -07:00
Krrish Dholakia
3955b058ed fix(vertex_httpx.py): support streaming via httpx client 2024-06-12 19:55:14 -07:00
Ishaan Jaff
5ebeb4d067 ci/cd fix predibase 500 errors 2024-06-11 23:15:48 -07:00
Krrish Dholakia
65baa83928 fix(bedrock_httpx.py): returning correct finish reason on streaming completion 2024-06-10 14:47:49 -07:00
Krrish Dholakia
84652dd946 fix(bedrock_httpx.py): fix tool calling for anthropic bedrock calls w/ streaming
Fixes https://github.com/BerriAI/litellm/issues/4091
2024-06-10 14:20:25 -07:00
Krrish Dholakia
35e4323095 refactor(main.py): only route anthropic calls through converse api
v0 scope let's move function calling to converse api
2024-06-07 08:47:51 -07:00
Krrish Dholakia
51ba5652a0 feat(bedrock_httpx.py): working bedrock converse api streaming 2024-06-06 22:13:21 -07:00
Krish Dholakia
c544ba3654
Merge pull request #4009 from BerriAI/litellm_fix_streaming_cost_cal
fix(utils.py): fix cost calculation for openai-compatible streaming object
2024-06-04 21:00:22 -07:00
Krrish Dholakia
43af5575c8 fix(utils.py): fix 2024-06-04 19:41:20 -07:00
Krrish Dholakia
54dacfdf61 feat(utils.py): support 'stream_options' param across all providers
Closes https://github.com/BerriAI/litellm/issues/3553
2024-06-04 19:03:26 -07:00
Krrish Dholakia
9aa29854de fix(utils.py): fix stream options to return consistent response object 2024-06-04 18:17:45 -07:00
Krrish Dholakia
52a2f5150c fix(utils.py): fix cost calculation for openai-compatible streaming object 2024-06-04 10:36:25 -07:00
Ishaan Jaff
2f9dac6238 test - test gpt-3.5-turbo on test_parallel_streaming_requests 2024-06-01 20:56:33 -07:00