phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 03:34:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
11200 commits 2497 branches 897 tags 550 MiB
Commit graph

2596 commits

Author SHA1 Message Date
Krrish Dholakia
18e3cf8bff fix(utils.py): support azure mistral function calling 2024-04-17 19:10:26 -07:00
Krrish Dholakia
0d2b400e91 test(test_function_calling.py): handle for when model returns a text response 2024-04-17 18:32:34 -07:00
Krrish Dholakia
fabc398acd test(test_function_calling.py): fix test to check if tool call in response 2024-04-17 18:28:59 -07:00
Krrish Dholakia
c613a47c66 test(test_max_tpm_rpm_limiter.py): fix test to use hashed api key in cache check 2024-04-17 18:10:18 -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
Krrish Dholakia
473e667bdf test: refactor testing to handle the hash token fix 2024-04-17 17:31:39 -07:00
Krrish Dholakia
bafb008b44 fix(_types.py): hash api key, if given 
fixes https://github.com/BerriAI/litellm/issues/2114
 2024-04-17 16:43:35 -07:00
Krrish Dholakia
53df916f69 fix(utils.py): accept {custom_llm_provider}/{model_name} in get_model_info 
fixes https://github.com/BerriAI/litellm/issues/3100
 2024-04-17 16:38:53 -07:00
Ishaan Jaff
409bd5b4ab ci/cd run again 2024-04-17 08:01:39 -07:00
Ishaan Jaff
5e955fb52c fix - azure test - don't pop api key 2024-04-17 07:54:16 -07:00
Krish Dholakia
8febe2f573
Merge pull request #3062 from cwang/cwang/trim-messages-fix 
Use `max_input_token` for `trim_messages`
 2024-04-16 22:29:45 -07:00
Krrish Dholakia
f68a6b6e13 test(test_amazing_vertex_completion.py): handle api errors 2024-04-16 21:47:02 -07:00
Ishaan Jaff
70f1dc2bb9 (ci/cd) run again 2024-04-16 21:44:11 -07:00
Ishaan Jaff
860d97c342 fix test_key_name_null 2024-04-16 21:37:31 -07:00
Ishaan Jaff
5393930701 fix function calling prompt - ask llm to respond in fahrenheit 2024-04-16 21:09:53 -07:00
Ishaan Jaff
6498bbbd09 fix - gemini function calling 2024-04-16 20:54:22 -07:00
Ishaan Jaff
9db529b2f8 test vertex ai exception mapping 2024-04-16 20:00:32 -07:00
Ishaan Jaff
7e99854d05
Merge pull request #3079 from BerriAI/litellm_router_save_settings_ui 
UI - Save / Edit router settings UI
 2024-04-16 16:57:42 -07:00
Krrish Dholakia
13cd252f3e fix(proxy_server.py): ensure id used in delete deployment matches id used in litellm Router 2024-04-16 15:17:18 -07:00
Ishaan Jaff
e271ce8030 router - get settings 2024-04-16 14:22:54 -07:00
Ishaan Jaff
2ad2d6cf9f return correct response from user/new 2024-04-16 08:17:45 -07:00
Krish Dholakia
2837b6b2f3
Merge pull request #3019 from ligaz/fix-anthropic-system-msg-handling 
Fix Anthropic system message handling
 2024-04-16 07:18:47 -07:00
Chen Wang
ebc889d77a
Use max_input_token for trim_messages 2024-04-16 13:36:25 +01:00
Krrish Dholakia
40d9167cae test(test_amazing_vertex_completion.py): fix vertex anthropic streaming text 2024-04-15 14:37:22 -07:00
Krrish Dholakia
1ec7118e1f fix(vertex_ai_anthropic.py): set vertex_credentials for vertex ai anthropic calls 
allows setting vertex credentials as a json string for vertex ai anthropic calls
 2024-04-15 14:16:28 -07:00
Krrish Dholakia
50081479f9 fix(main.py): accept vertex service account credentials as json string 
allows us to dynamically set vertex ai credentials
 2024-04-15 13:28:59 -07:00
Krish Dholakia
72b54eaad7
Merge pull request #3028 from BerriAI/litellm_anthropic_text_completion_fix 
fix(anthropic_text.py): add support for async text completion calls
 2024-04-15 09:26:28 -07:00
Ishaan Jaff
c8832489d6 test groq tool calling 2024-04-15 08:41:53 -07:00
Ishaan Jaff
ea575ef62d fix test groq function call 2024-04-15 08:40:39 -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
017127a704 test - groq tool calling 2024-04-15 08:13:05 -07:00
Stefan Dobrev
1cfea955aa
Fix Anthropic system message handling 2024-04-14 16:23:59 +03:00
Krrish Dholakia
bef24cd4ab fix(caching.py): don't decode a string 2024-04-13 18:48:03 -07:00
Krrish Dholakia
4e81acf2c6 feat(prometheus_services.py): monitor health of proxy adjacent services (redis / postgres / etc.) 2024-04-13 18:15:02 -07:00
Ishaan Jaff
5856ec03c6 (ci/cd) run again 2024-04-12 20:48:26 -07:00
Ishaan Jaff
f617f5ebb5 fix - test caching atext_completion 2024-04-12 20:37:56 -07:00
Ishaan Jaff
11cd1ec6cf test - atext_completion + caching 2024-04-12 12:32:21 -07:00
Krrish Dholakia
77097f8e7d test(test_jwt.py): add testing to make sure user api key auth returns the expected values 2024-04-11 20:18:55 -07:00
Krrish Dholakia
84d43484c6 fix(router.py): make sure pre call rpm check runs even when model not in model cost map 2024-04-11 09:27:46 -07:00
Krish Dholakia
83e7ed94ce
Merge pull request #2942 from BerriAI/litellm_fix_router_loading 
Router Async Improvements
 2024-04-10 20:16:53 -07:00
Ishaan Jaff
8bc02b34c2 test -base64 cache hits 2024-04-10 16:46:56 -07:00
Krrish Dholakia
a47a719caa fix(router.py): generate consistent model id's 
having the same id for a deployment, lets redis usage caching work across multiple instances
 2024-04-10 15:23:57 -07:00
Krrish Dholakia
a311788f0d test(test_completion.py): handle api instability 2024-04-09 21:58:48 -07:00
Krrish Dholakia
a6b004f10b test(test_completion.py): change model 2024-04-09 21:38:17 -07:00
Krish Dholakia
2fa47cf416
Merge pull request #2924 from BerriAI/litellm_text_completion_response 
fix(main.py): handle translating text completion openai to chat completion for async requests
 2024-04-09 21:13:30 -07:00
Krrish Dholakia
8857c9b978 test(test_key_generate_prisma.py): add better unit testing for spend logs on proxy server 2024-04-09 17:58:18 -07:00
Krrish Dholakia
855e7ed9d2 fix(main.py): handle translating text completion openai to chat completion for async requests 
also adds testing for this, to prevent future regressions
 2024-04-09 16:47:49 -07:00
Krrish Dholakia
4495f6c058 test(test_key_generate_prisma.py): fix check for raising error if key generate max budget > key upperbound 2024-04-09 13:07:57 -07:00
Krrish Dholakia
ef4c85522c test(test_llm_guard.py): fix test 2024-04-08 21:55:35 -07:00