phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-27 11:43:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
11293 commits 2497 branches 897 tags 550 MiB
Commit graph

1332 commits

Author SHA1 Message Date
Ishaan Jaff
41f9622f29 (docs) grafana / prometheus 2024-03-29 14:25:45 -07:00
Krrish Dholakia
ae3510c0d2 fix(utils.py): exception mapping on 'next()' streaming error 2024-03-29 09:18:41 -07:00
Krrish Dholakia
006c20a10f fix(utils.py): support bedrock mistral streaming 2024-03-29 07:56:10 -07:00
Krrish Dholakia
d98e040f36 fix(utils.py): don't add chatml tokens to a simple text token count 2024-03-28 13:48:48 -07:00
Krrish Dholakia
7fe02405e0 fix(proxy/utils.py): check cache before alerting user 2024-03-27 20:09:15 -07:00
Krrish Dholakia
62e557404c fix(utils.py): don't run post-call rules on a coroutine function 2024-03-27 13:16:27 -07:00
Krish Dholakia
d51f12ca44 Merge pull request #2704 from BerriAI/litellm_jwt_auth_improvements_3 
fix(handle_jwt.py): enable team-based jwt-auth access
 2024-03-26 16:06:56 -07:00
Krrish Dholakia
4028f935a5 fix(utils.py): check if item in list is pydantic object or dict before dereferencing 2024-03-26 14:39:16 -07:00
Krrish Dholakia
c21e954c6f test(test_batch_completions.py): handle anthropic overloaded error 2024-03-26 13:55:03 -07:00
Krrish Dholakia
05fddcb06b 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
Ishaan Jaff
f5f7e344c7 Merge branch 'main' into litellm_remove_litellm_telemetry 2024-03-26 11:35:02 -07:00
Ishaan Jaff
62c83d36a5 (fix) remove litellm.telemetry 2024-03-26 11:21:09 -07:00
Krrish Dholakia
44bc79aadb fix(utils.py): check if message is pydantic object or dict before dereferencing 2024-03-26 09:47:44 -07:00
Krrish Dholakia
1137264d99 test(test_streaming.py): add unit testing for custom stream wrapper 2024-03-26 08:57:44 -07:00
Krish Dholakia
3fef983439 Merge pull request #2656 from TashaSkyUp/patch-1 
fix for: when using ModelResponse.json() to save and then reconstruct a ModelResponse the choices field ends up empty
 2024-03-26 08:36:55 -07:00
Ishaan Jaff
ebdec4d262 (fix) cache control logic 2024-03-26 07:36:45 -07:00
Ishaan Jaff
7bf9cb3c54 (fix) cache control logic 2024-03-25 22:19:34 -07:00
Krrish Dholakia
f604a6155f fix(utils.py): persist system fingerprint across chunks 2024-03-25 19:24:09 -07:00
Krrish Dholakia
c5bd4d4233 fix(utils.py): log success event for streaming 2024-03-25 19:03:10 -07:00
Krrish Dholakia
cbf4c95e5f fix(utils.py): persist response id across chunks 2024-03-25 18:20:43 -07:00
Krrish Dholakia
ecc0cf5d9c fix(utils.py): fix text completion streaming 2024-03-25 16:47:17 -07:00
Krrish Dholakia
26dbb76d53 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
c667e437b9 fix(utils.py): allow user to disable streaming logging 
fixes event loop issue for litellm.disable_streaming_logging
 2024-03-25 14:28:46 -07:00
Max Deichmann
efa599b0ee push 2024-03-25 17:43:55 +01:00
Krrish Dholakia
4e70a3e09a feat(router.py): enable pre-call checks 
filter models outside of context window limits of a given message for a model group

 https://github.com/BerriAI/litellm/issues/872
 2024-03-23 18:03:30 -07:00
Tasha Upchurch
8814524473 Update utils.py 
fix for constructed from dict choices.message being a dict still instead of Message class.
 2024-03-23 00:12:24 -04:00
Ishaan Jaff
07067db5a1 (feat) remove litellm.telemetry 2024-03-22 20:58:14 -07:00
Tasha Upchurch
2c1fb7e881 Update utils.py 
Fix for creating an empty choices if no choices passed in
 2024-03-22 23:39:17 -04:00
Tasha Upchurch
541155c08d Update utils.py 
fix for #2655
 2024-03-22 23:13:24 -04:00
Krrish Dholakia
4dad400b57 fix(anthropic.py): handle multiple system prompts 2024-03-22 18:14:15 -07:00
Vincelwt
860f1b982d Merge branch 'main' into main 2024-03-22 00:52:42 +09:00
Ishaan Jaff
1d598581bb (fix) don't run .completion retries if using router / proxy 2024-03-21 08:32:42 -07:00
Krrish Dholakia
416cccdc6a fix(utils.py): support response_format param for ollama 
https://github.com/BerriAI/litellm/issues/2580
 2024-03-19 21:07:20 -07:00
Ishaan Jaff
a23746b776 (fix) add /metrics to utils.py 2024-03-19 17:28:33 -07:00
Vincelwt
e92db58204 Merge branch 'main' into main 2024-03-19 12:50:04 +09:00
Krish Dholakia
3e32a245ea Merge pull request #2577 from BerriAI/litellm_vertex_ai_streaming_func_call 
feat(vertex_ai.py): support gemini (vertex ai) function calling when streaming
 2024-03-18 20:10:00 -07:00
Ishaan Jaff
447bddc7f8 (feat) v0 datadog logger 2024-03-18 16:01:47 -07:00
Krrish Dholakia
f4443e21e0 feat(vertex_ai.py): support gemini (vertex ai) function calling when streaming 2024-03-18 11:47:27 -07:00
Krrish Dholakia
bad2327b88 fix(utils.py): fix aws secret manager + support key_management_settings 
fixes the aws secret manager implementation and allows the user to set which keys they want to check thr
ough it
 2024-03-16 16:47:50 -07:00
Krrish Dholakia
77cb4cdf9c fix(utils.py): initial commit for aws secret manager support 2024-03-16 14:37:46 -07:00
Krrish Dholakia
84430d0e29 fix(utils.py): async add to cache - for streaming 2024-03-15 18:25:40 -07:00
Krrish Dholakia
8d1c60bfdc feat(batch_redis_get.py): batch redis GET requests for a given key + call type 
reduces the number of GET requests we're making in high-throughput scenarios
 2024-03-15 14:40:11 -07:00
Krrish Dholakia
0783a3f247 feat(utils.py): add native fireworks ai support 
addresses - https://github.com/BerriAI/litellm/issues/777, https://github.com/BerriAI/litellm/issues/2486
 2024-03-15 09:09:59 -07:00
Krrish Dholakia
1e1190745f fix(utils.py): move to using litellm.modify_params to enable max output token trimming fix 2024-03-14 12:17:56 -07:00
Krrish Dholakia
5769bd22c3 feat(prompt_injection_detection.py): support simple heuristic similarity check for prompt injection attacks 2024-03-13 10:32:21 -07:00
Krish Dholakia
ce3c865adb Merge pull request #2472 from BerriAI/litellm_anthropic_streaming_tool_calling 
fix(anthropic.py): support claude-3 streaming with function calling
 2024-03-12 21:36:01 -07:00
Ishaan Jaff
2c4407bb04 Merge pull request #2479 from BerriAI/litellm_cohere_tool_call 
[FEAT Cohere/command-r tool calling
 2024-03-12 21:20:59 -07:00
Krrish Dholakia
c871d61218 fix(anthropic.py): bug fix 2024-03-12 19:32:42 -07:00
ishaan-jaff
9a2852c353 (fix) use cohere_chat optional params 2024-03-12 14:31:43 -07:00
Krish Dholakia
bf0adfc246 Merge pull request #2473 from BerriAI/litellm_fix_compatible_provider_model_name 
fix(openai.py): return model name with custom llm provider for openai-compatible endpoints (e.g. mistral, together ai, etc.)
 2024-03-12 12:58:29 -07:00