Commit graph

3040 commits

Author SHA1 Message Date
Krrish Dholakia
5e85a5b208 fix(test_scheduler.py): simplify scheduler testing. fix race condition 2024-06-01 18:57:47 -07:00
Krrish Dholakia
7efac4d36c fix(azure.py): support dropping 'tool_choice=required' for older azure API versions
Closes https://github.com/BerriAI/litellm/issues/3876
2024-06-01 18:44:50 -07:00
Ishaan Jaff
054456c50e
Merge pull request #3963 from BerriAI/litellm_set_allowed_fail_policy
[FEAT]- set custom AllowedFailsPolicy on litellm.Router
2024-06-01 17:57:11 -07:00
Ishaan Jaff
fb49d036fb
Merge pull request #3962 from BerriAI/litellm_return_num_rets_max_exceptions
[Feat] return `num_retries` and `max_retries` in exceptions
2024-06-01 17:48:38 -07:00
Ishaan Jaff
4eaeec2a2d feat - set allowed fails policy 2024-06-01 17:39:44 -07:00
Ishaan Jaff
3caa9dfec6 add test 2024-06-01 17:03:53 -07:00
Krrish Dholakia
2245ee1cc8 test(test_scheduler.py): fix testing 2024-06-01 16:21:02 -07:00
Krrish Dholakia
7715267989 fix(router.py): simplify scheduler
move the scheduler poll queuing logic into the router class, making it easier to use
2024-06-01 16:09:57 -07:00
Krrish Dholakia
d7160eb3ea fix(test_scheduler.py): fix test 2024-06-01 15:11:13 -07:00
Krrish Dholakia
c6559753c7 fix(test_scheduler.py): fix test 2024-06-01 11:30:26 -07:00
Krish Dholakia
8375e9621c
Merge pull request #3954 from BerriAI/litellm_simple_request_prioritization
feat(scheduler.py): add request prioritization scheduler
2024-05-31 23:29:09 -07:00
Krrish Dholakia
183dd81087 fix(router.py): fix should_retry logic 2024-05-31 23:27:43 -07:00
Krish Dholakia
e7ff3adc26
Merge pull request #3944 from BerriAI/litellm_fix_parallel_streaming
fix: fix streaming with httpx client
2024-05-31 21:42:37 -07:00
Krrish Dholakia
7523f803d2 fix(utils.py): support get_max_tokens() call with same model_name as completion
Closes https://github.com/BerriAI/litellm/issues/3921
2024-05-31 21:37:51 -07:00
Krrish Dholakia
e49325b234 fix(router.py): fix cooldown logic for usage-based-routing-v2 pre-call-checks 2024-05-31 21:32:01 -07:00
Krrish Dholakia
f8d4be710e docs(scheduler.md): add request prioritization to docs 2024-05-31 19:35:47 -07:00
Ishaan Jaff
b8df5d1a01 (ci/cd) run again 2024-05-31 19:05:51 -07:00
Krrish Dholakia
79287a7584 feat(scheduler.py): add request prioritization scheduler
allow user to set priority for a request
2024-05-31 18:51:13 -07:00
Krish Dholakia
08bae3185a
Merge pull request #3936 from BerriAI/litellm_assistants_api_proxy
feat(proxy_server.py): add assistants api endpoints to proxy server
2024-05-31 18:43:22 -07:00
Ishaan Jaff
a049a52fde
Merge pull request #3942 from BerriAI/litellm_send_email_user_new
feat - `send_invite_email`  on /user/new
2024-05-31 17:28:32 -07:00
Ishaan Jaff
83aa9151af fix test 2024-05-31 12:49:38 -07:00
Krrish Dholakia
93c3635b64 fix: fix streaming with httpx client
prevent overwriting streams in parallel streaming calls
2024-05-31 10:55:18 -07:00
Ishaan Jaff
16f7bfde8b
Merge pull request #3688 from Manouchehri/oidc-bedrock-3578
Add OIDC + unit test for bedrock httpx
2024-05-31 09:42:30 -07:00
Ishaan Jaff
d3baf1f569
Merge pull request #3943 from lj-wego/fix-pydantic-typo
Update model config definition to use v2 style
2024-05-31 09:09:27 -07:00
Ishaan Jaff
f6d33a8998 ci/cd clarifai is an unstable provider, retry reqs 2024-05-31 09:03:28 -07:00
lj
d6c1282f88
Update model config definition to use v2 style 2024-05-31 23:55:28 +08:00
Ishaan Jaff
3d3502e15b fix - test - config 2024-05-31 08:46:31 -07:00
Ishaan Jaff
beffa4e398 ci/cd bump python v 2024-05-31 08:31:21 -07:00
Ishaan Jaff
becae4ba1f ci/cd bump python v 2024-05-31 08:25:11 -07:00
Ishaan Jaff
3408035ed6 ci/cd run again 2024-05-31 08:23:02 -07:00
Ishaan Jaff
49952983e1 ci/cd bump python v 2024-05-31 08:10:47 -07:00
Ishaan Jaff
5002804d87 (ci/cd) run again 2024-05-31 07:58:11 -07:00
Ishaan Jaff
903528a3e2 (ci/cd) run again 2024-05-31 07:49:25 -07:00
David Manouchehri
d70d484e10
Fix: Use David's AWS account to pass unit tests. 2024-05-31 13:50:49 +00:00
David Manouchehri
eb57b2c6d7
Fix OIDC tests. This should always work, even without IAM set up . 2024-05-31 13:48:52 +00:00
David Manouchehri
08ee4519b6
Add unit test for bedrock httpx oidc auth. 2024-05-31 12:44:53 +00:00
Krish Dholakia
deb87f71e3
Merge pull request #3670 from lj-wego/fix-pydantic-warnings-again
Fix warnings from pydantic
2024-05-30 22:57:21 -07:00
Krrish Dholakia
e2b34165e7 feat(proxy_server.py): add assistants api endpoints to proxy server 2024-05-30 22:44:43 -07:00
Ishaan Jaff
22f88de60b (ci/cd) run again 2024-05-30 21:00:53 -07:00
lj
27ed72405b
Merge branch 'main' into fix-pydantic-warnings-again 2024-05-31 11:35:42 +08:00
Krish Dholakia
d3a247bf20
Merge pull request #3928 from BerriAI/litellm_audio_speech_endpoint
feat(main.py): support openai tts endpoint
2024-05-30 17:30:42 -07:00
Krrish Dholakia
93166cdabf fix(openai.py): fix openai response for /audio/speech endpoint 2024-05-30 16:41:06 -07:00
Ishaan Jaff
21831905ba fix test_generate_and_call_with_valid_key 2024-05-30 15:10:16 -07:00
Ishaan Jaff
a4b6a959d8 fix literal usage 2024-05-30 14:28:53 -07:00
Krrish Dholakia
a67cbf47f6 feat(main.py): support openai tts endpoint
Closes https://github.com/BerriAI/litellm/issues/3094
2024-05-30 14:28:28 -07:00
Ishaan Jaff
6166381579 fix migrate to LitellmUserRoles 2024-05-30 13:57:50 -07:00
Krish Dholakia
76b5fccdc2
Merge pull request #3909 from nirga/revert-3908-revert-3846-revert-3831-revert-3780-traceloop-failures
Revert "Revert "fix: Log errors in Traceloop Integration (reverts previous revert)""
2024-05-29 21:14:14 -07:00
Ishaan Jaff
6f063156be fix test_call_with_end_user_over_budget 2024-05-29 20:48:29 -07:00
Ishaan Jaff
3e9410ffd6 fix - test budget exceeded prisma 2024-05-29 20:31:55 -07:00
Nir Gazit
b8d97c688c Revert "Revert "fix: Log errors in Traceloop Integration (reverts previous revert)"" 2024-05-30 04:06:45 +03:00