ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
23,118 Commits 9 Branches 7 Tags 935 MiB
4b3b4f8dff
Commit Graph

23118 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ishaan Jaff
e9eead2f25 test - size of callbacks, alerts 2024-05-03 14:22:15 -07:00
Ishaan Jaff
e99edaf4e1
Merge pull request #3426 from BerriAI/litellm_set_db_exceptions_on_ui 
UI - set DB Exceptions webhook_url on UI
 2024-05-03 14:05:37 -07:00
Ishaan Jaff
776f541f6c fix bug where slack would get inserting several times 2024-05-03 14:04:38 -07:00
Ishaan Jaff
fdc9856652 UI - set DB Exceptions webhook_url 2024-05-03 13:33:43 -07:00
Ishaan Jaff
34bf0b37f5
Merge pull request #3423 from BerriAI/litellm_test_callbacks_proxy 
[Test] Assert num Callbacks on Proxy don't increase
 2024-05-03 12:44:56 -07:00
Krrish Dholakia
b2a0502383 bump: version 1.35.36 → 1.35.37 2024-05-03 12:42:20 -07:00
Krrish Dholakia
defc205348 test(test_alangfuse.py): fix test 2024-05-03 12:39:38 -07:00
frob
4adba181b2
Merge branch 'BerriAI:main' into ollama-image-handling 2024-05-03 20:56:10 +02:00
Lunik
9ba9b3891f
⚡️ perf: Remove test violation on each stream chunk 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-03 20:51:40 +02:00
Lunik
e7405f105c
✅ ci: Add tests 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-03 20:50:37 +02:00
Krish Dholakia
cb1872d7cb
Merge pull request #3422 from BerriAI/litellm_lowest_latency_fix 
fix(lowest_latency.py): fix the size of the latency list to 10 by default (can be modified)
 2024-05-03 10:14:50 -07:00
Krrish Dholakia
2dd9d2f704 test(test_amazing_vertex_completion.py): try-except api errors 2024-05-03 10:09:57 -07:00
Ishaan Jaff
9ba5685722 test active callbacks on proxy 2024-05-03 10:05:06 -07:00
Ishaan Jaff
fe6e465466 test - num callbacks on proxy should not increase 2024-05-03 09:59:59 -07:00
Vincelwt
508e53593b
Merge branch 'BerriAI:main' into main 2024-05-03 17:43:17 +01:00
Vince Loewe
3677d56e9e
Lunary: Fix tool calling 2024-05-03 17:42:50 +01:00
Ishaan Jaff
c6a9b460cd
Merge pull request #3419 from BerriAI/litellm_fix_lowest_latency_router 
[Fix] Ensure callbacks are not added to router when `store_model_in_db=True`
 2024-05-03 09:28:35 -07:00
Ishaan Jaff
23d334fe60 proxy - return num callbacks on /health/readiness 2024-05-03 09:14:32 -07:00
Ishaan Jaff
a1814a3e4c test - num callbacks on proxy 2024-05-03 09:13:37 -07:00
Krrish Dholakia
0b72904608 fix(lowest_latency.py): fix the size of the latency list to 10 by default (can be modified) 2024-05-03 09:00:32 -07:00
Ishaan Jaff
540a35ed5e fix update router logic 2024-05-03 08:48:11 -07:00
mogith-pn
723ef9963e Clarifai - Added streaming and async completion support 2024-05-03 14:03:38 +00:00
sumanth
3bc6b5d119 usage-based-routing-ttl-on-cache 2024-05-03 10:50:45 +05:30
mikey
de7fe98556
Merge branch 'BerriAI:main' into main 2024-05-03 11:30:03 +08:00
ffreemt
a7ec1772b1 Add litellm\tests\test_batch_completion_return_exceptions.py 2024-05-03 11:28:38 +08:00
Krrish Dholakia
91971fa9e0 feat(router.py): add 'get_model_info' helper function to get the model info for a specific model, based on it's id 2024-05-02 17:53:09 -07:00
Krrish Dholakia
fdc4fdb91a fix(proxy/utils.py): fix slack alerting to only raise alerts for llm api exceptions 
don't spam for bad user requests. Closes https://github.com/BerriAI/litellm/issues/3395
 2024-05-02 17:18:21 -07:00
Krrish Dholakia
5baeeec899 fix(openmeter.py): fix get from env 2024-05-02 16:34:22 -07:00
Krish Dholakia
2200900ca2
Merge pull request #3393 from Priva28/main 
Add Llama3 tokenizer and allow custom tokenizers.
 2024-05-02 16:32:41 -07:00
Ishaan Jaff
0b27f5b3dc
Merge pull request #3409 from BerriAI/litellm_revert_passing_langfuse_traces_alerts 
fix - revert init langfuse client on slack alerts
 2024-05-02 16:09:23 -07:00
Ishaan Jaff
9edf463c3b fix - revert init langfuse client on slack alerts 2024-05-02 16:02:52 -07:00
Marc Abramowitz
cdb39e90ce Improve mocking in test_proxy_exception_mapping 
Mock the calls to the backend and assert that the correct parameters are passed
to the backend.
 2024-05-02 15:16:20 -07:00
Ishaan Jaff
f893f8bc55
Merge pull request #3403 from msabramo/disambiguate-invalid-model-name-errors 
Disambiguate invalid model name errors
 2024-05-02 15:09:59 -07:00
Krish Dholakia
9e56472a81
Merge pull request #3406 from msabramo/test_proxy_server_mock_improvements 
Improve mocking in `test_proxy_server.py`
 2024-05-02 15:05:09 -07:00
Marc Abramowitz
6d154e2317 Update tests to reflect new error messages 2024-05-02 15:02:58 -07:00
Marc Abramowitz
988c37fda3 Disambiguate invalid model name errors 
because that error can be thrown in several different places, so
knowing the function it's being thrown from can be very useul for debugging.
 2024-05-02 15:02:54 -07:00
Krrish Dholakia
acda064be6 fix(proxy/utils.py): fix retry logic for generic data request 2024-05-02 14:50:50 -07:00
Lunik
406c9820d1
➕ feat: Add python requirements for Azure Content-Safety callback 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-02 23:28:21 +02:00
Lunik
6cec252b07
✨ feat: Add Azure Content-Safety Proxy hooks 
Signed-off-by: Lunik <lunik@tiwabbit.fr>
 2024-05-02 23:21:08 +02:00
Krish Dholakia
e26b39822c
Merge pull request #3405 from azohra/patch-1 
Vision for Claude 3 Family + Info for Azure/GPT-4-0409
 2024-05-02 13:42:01 -07:00
Marc Abramowitz
14e7c9b01c Improve mocking in test_proxy_server 
Mock the calls to the backend and assert that the correct parameters are passed
to the backend.
 2024-05-02 13:36:23 -07:00
Justin Watts
77098e31e4
Update model_prices_and_context_window.json 2024-05-02 13:21:36 -07:00
Justin Watts
39670cd84a
Add Vision Support for Claude 3 Family 
modified the model info table to add "supports_vision": true, for the claude 3 family (haiku, sonnet, and opus)
 2024-05-02 13:09:17 -07:00
Krish Dholakia
762a1fbd50
Merge pull request #3375 from msabramo/GH-3372 
Fix route `/openai/deployments/{model}/chat/completions` not working properly
 2024-05-02 13:00:25 -07:00
Marc Abramowitz
a79fd772f4 Simplify mock_patch_acompletion 2024-05-02 12:47:27 -07:00
Marc Abramowitz
6ec058711a Make unnecessary to pass extra arg for mock object 
Modify `mock_patch_acompletion` to be a context manager instead of a
function that returns a mock object. This way, the mock object is
created and yielded by the context manager, and the test function
doesn't need to pass the mock object as an argument.
 2024-05-02 12:41:30 -07:00
Marc Abramowitz
4dfadb0cf4 mock_patch_acompletion in test_proxy_server.py 2024-05-02 12:24:49 -07:00
Ishaan Jaff
7ffe410097
Merge pull request #3392 from BerriAI/litellm_fix_langfuse_reinitalized 
[Fix] bug where langfuse was reinitialized on every call
 2024-05-02 10:54:47 -07:00
Marc Abramowitz
152b5c8ceb Add test_openai_deployments_model_chat_completions_azure 2024-05-02 10:27:32 -07:00
Ishaan Jaff
e16ca10ea5
Merge pull request #3278 from greenscale-ai/main 
Fix Greenscale Documentation
 2024-05-02 08:26:12 -07:00