Commit graph

175 commits

Author SHA1 Message Date
Krrish Dholakia
b38c09c87f fix(utils.py): fix azure streaming logic 2024-04-18 07:08:36 -07:00
Krrish Dholakia
15ae7a8314 fix(utils.py): fix streaming special character flushing logic 2024-04-17 18:03:40 -07:00
Krrish Dholakia
7d0086d742 fix(utils.py): ensure streaming output parsing only applied for hf / sagemaker models
selectively applies the <s>
</s> checking
2024-04-17 17:43:41 -07:00
Ishaan Jaff
5393930701 fix function calling prompt - ask llm to respond in fahrenheit 2024-04-16 21:09:53 -07:00
Krrish Dholakia
26286a54b8 fix(anthropic_text.py): add support for async text completion calls 2024-04-15 08:15:00 -07:00
Ishaan Jaff
a5aef6ec00
Merge pull request #2879 from BerriAI/litellm_async_anthropic_api
[Feat] Async Anthropic API 97.5% lower median latency
2024-04-07 09:56:52 -07:00
Ishaan Jaff
d51e853b60 undo adding next-asyncio 2024-04-06 19:28:51 -07:00
Krrish Dholakia
5f910c1811 test(test_streaming.py): fix vertex project name 2024-04-06 18:45:17 -07:00
Ishaan Jaff
f08486448c fix - test streaming 2024-04-06 18:28:07 -07:00
Ishaan Jaff
2622f0351b (ci/cd) run again 2024-04-06 18:26:52 -07:00
Ishaan Jaff
4512510d37 Revert "fix test streaming"
This reverts commit f10aba1007.
2024-04-06 18:24:00 -07:00
Ishaan Jaff
f10aba1007 fix test streaming 2024-04-06 18:23:10 -07:00
Ishaan Jaff
9be6b7ec7c ci/cd run again 2024-04-06 18:07:41 -07:00
Ishaan Jaff
548b2b6861 test - async claude streaming 2024-04-06 17:55:26 -07:00
Ishaan Jaff
83580dc00a (ci/cd) run again 2024-04-05 20:44:51 -07:00
Ishaan Jaff
122dff007b fix gemini test 2024-04-05 20:38:28 -07:00
Ishaan Jaff
3b2c34d587 ci/cd - skip 429 errors from google gemini 2024-04-05 13:36:29 -07:00
Krrish Dholakia
109cd93a39 fix(sagemaker.py): support model_id consistently. support dynamic args for async calls 2024-03-29 09:05:00 -07:00
Krrish Dholakia
cd53291b62 fix(utils.py): support bedrock mistral streaming 2024-03-29 07:56:10 -07:00
Krrish Dholakia
3a82ff2ef2 fix(utils.py): don't send subsequent chunks if last chunk sent
prevents multiple empty finish chunks from being sent
2024-03-26 13:49:42 -07:00
Krrish Dholakia
2dd2b8a8e3 test(test_streaming.py): add unit testing for custom stream wrapper 2024-03-26 08:57:44 -07:00
Krrish Dholakia
4d85387b5a test(test_azure_astreaming_and_function_calling): fix test to handle caching 2024-03-25 19:33:57 -07:00
Krrish Dholakia
9e1e97528d fix(utils.py): ensure last chunk is always empty delta w/ finish reason
makes sure we're openai-compatible with our streaming. Adds stricter tests for this as well
2024-03-25 16:33:41 -07:00
Krrish Dholakia
42a7588b04 fix(anthropic.py): support async claude 3 tool calling + streaming
https://github.com/BerriAI/litellm/issues/2644
2024-03-22 19:57:01 -07:00
Krrish Dholakia
b6f094c5ec test(test_streaming.py): fix test 2024-03-18 22:06:29 -07:00
ishaan-jaff
ebfefe61ea (fix-ci-cd) skip deep infra 429 errors 2024-03-13 22:05:16 -07:00
Krrish Dholakia
e342ecd873 test: set verbose for test 2024-03-12 12:56:38 -07:00
Krrish Dholakia
86ed0aaba8 fix(anthropic.py): support streaming with function calling 2024-03-12 09:52:11 -07:00
Krrish Dholakia
8b24ddcbbd fix(bedrock.py): enable claude-3 streaming 2024-03-09 14:02:27 -08:00
ishaan-jaff
eb53136448 (ci/cd) run again 2024-03-08 22:05:39 -08:00
Krrish Dholakia
5f225e3a88 test(test_streaming.py): skip flaky test 2024-03-04 22:33:45 -08:00
Krrish Dholakia
b2eef61679 fix(test_streaming.py): skip flaky test 2024-03-04 20:46:21 -08:00
Krrish Dholakia
478307d4cf fix(bedrock.py): support anthropic messages api on bedrock (claude-3) 2024-03-04 17:15:47 -08:00
ishaan-jaff
3e8cecc03b (fix) test streaming 2024-03-04 08:29:16 -08:00
Krish Dholakia
0633eecdb8
Merge pull request #2236 from BerriAI/litellm_faster_usage_logs_pg_db
fix(proxy_server.py): introduces a beta endpoint for admin to view global spend
2024-02-28 17:08:55 -08:00
Krrish Dholakia
4c951d20bc test: removing aws tests - account suspended - pending their approval 2024-02-28 13:46:20 -08:00
ishaan-jaff
4bd15985b4 (test) hugging face test - their endpoint is unstable 2024-02-28 12:11:29 -08:00
Krrish Dholakia
6b14c6287b test(test_streaming.py): add more logging 2024-02-26 21:44:28 -08:00
Krrish Dholakia
5b06627c09 fix(utils.py): fix streaming 2024-02-26 12:52:53 -08:00
Krrish Dholakia
dfb1d34e26 fix(utils.py): support returning caching streaming response for function calling streaming calls 2024-02-26 12:31:00 -08:00
Krrish Dholakia
97b9d570a6 fix(utils.py): stricter azure function calling tests 2024-02-23 20:55:32 -08:00
Krish Dholakia
dd4439b6a8
Merge branch 'main' into litellm_fix_azure_function_calling_streaming 2024-02-22 22:36:38 -08:00
Krrish Dholakia
ca03c57277 test(test_streaming.py): fix openai streaming function calling test 2024-02-22 21:50:14 -08:00
Krrish Dholakia
e07cf33cba test(test_streaming.py): add exception mapping for palm timeout error 2024-02-22 21:36:57 -08:00
Krrish Dholakia
b6017115e3 fix(utils.py): ensure argument is always a string 2024-02-22 15:15:56 -08:00
Krrish Dholakia
f6e52ac771 test: handle api errors for gemini/palm testing 2024-02-21 21:44:08 -08:00
Krrish Dholakia
c9c6547ef9 test(test_streaming.py): handle gemini 500 error 2024-02-21 21:32:03 -08:00
Krrish Dholakia
1d3bef2e9c fix(gemini.py): implement custom streamer 2024-02-20 17:10:51 -08:00
Krrish Dholakia
45eb4a5fcc fix(gemini.py): fix async streaming + add native async completions 2024-02-19 22:41:36 -08:00
Krrish Dholakia
5f9e141d1e fix(huggingface_restapi.py): return streamed response correctly 2024-02-16 13:25:13 -08:00