Commit graph

920 commits

Author SHA1 Message Date
wslee
fe8d59f5eb add friendli_ai provider 2024-06-10 17:27:15 +09:00
Krrish Dholakia
1dafb1b3b7 fix(utils.py): improved predibase exception mapping
adds unit testing + better coverage for predibase errors
2024-06-08 14:32:43 -07:00
Ishaan Jaff
3ecc077507 fix mock_completion 2024-06-07 19:10:05 -07:00
Ishaan Jaff
718b547646
Merge branch 'main' into litellm_security_fix 2024-06-07 16:52:25 -07:00
Krrish Dholakia
f73b6033fd fix(test_custom_callbacks_input.py): unit tests for 'turn_off_message_logging'
ensure no raw request is logged either
2024-06-07 15:39:15 -07:00
Ishaan Jaff
d9dacc1f43
Merge pull request #4065 from BerriAI/litellm_use_common_func
[Refactor] - Refactor proxy_server.py to use common function for `add_litellm_data_to_request`
2024-06-07 14:02:17 -07:00
Ishaan Jaff
2cf3133669
Merge branch 'main' into litellm_svc_logger 2024-06-07 14:01:54 -07:00
Ishaan Jaff
7ef7bc8a9a fix simplify - pass litellm_parent_otel_span 2024-06-07 13:48:21 -07:00
Ishaan Jaff
54ac848bfb use litellm_parent_otel_span as litellm_param 2024-06-07 08:54:28 -07:00
Krish Dholakia
26993c067e
Merge branch 'main' into litellm_bedrock_converse_api 2024-06-07 08:49:52 -07:00
Krrish Dholakia
35e4323095 refactor(main.py): only route anthropic calls through converse api
v0 scope let's move function calling to converse api
2024-06-07 08:47:51 -07:00
Krrish Dholakia
44670d952d test(main.py): test cicd 2024-06-07 08:18:37 -07:00
Krrish Dholakia
b3bf93685a style(main.py): trigger new build 2024-06-07 08:10:28 -07:00
Krrish Dholakia
a995a0b172 fix(bedrock_httpx.py): working claude 3 function calling 2024-06-06 20:12:41 -07:00
Krrish Dholakia
6cca5612d2 refactor: replace 'traceback.print_exc()' with logging library
allows error logs to be in json format for otel logging
2024-06-06 13:47:43 -07:00
Krish Dholakia
c544ba3654
Merge pull request #4009 from BerriAI/litellm_fix_streaming_cost_cal
fix(utils.py): fix cost calculation for openai-compatible streaming object
2024-06-04 21:00:22 -07:00
Krrish Dholakia
9ff5b099b7 fix(main.py): check verify ssl on custom endpoint call 2024-06-04 17:12:42 -07:00
Krrish Dholakia
52a2f5150c fix(utils.py): fix cost calculation for openai-compatible streaming object 2024-06-04 10:36:25 -07:00
Krrish Dholakia
5d3674b63d fix(main.py): fix typing for image gen response 2024-06-04 08:29:30 -07:00
Krrish Dholakia
90f5aa7125 fix(main.py): fix ahealth_check to infer mode when custom_llm_provider/model_name used 2024-06-03 14:06:36 -07:00
Krrish Dholakia
9ef83126d7 fix(utils.py): correctly instrument passing through api version in optional param check 2024-06-01 19:31:52 -07:00
Krrish Dholakia
93c9ea160d fix(openai.py): fix client caching logic 2024-06-01 16:45:56 -07:00
Krrish Dholakia
a16a1c407a fix(http_handler.py): allow setting ca bundle path 2024-06-01 14:48:53 -07:00
Krrish Dholakia
a0fb301b18 docs(assistants.md): add assistants api to docs 2024-06-01 10:30:07 -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
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
93c3635b64 fix: fix streaming with httpx client
prevent overwriting streams in parallel streaming calls
2024-05-31 10:55:18 -07:00
Krrish Dholakia
d65b7fe01b fix(main.py): add logging to audio_transcription calls 2024-05-30 16:57:11 -07:00
Krrish Dholakia
93166cdabf fix(openai.py): fix openai response for /audio/speech endpoint 2024-05-30 16:41:06 -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
Krrish Dholakia
da56201e80 fix(main.py): pass api key and api base to openai.py for audio transcription call 2024-05-29 21:29:01 -07:00
Ishaan Jaff
99e506525c
Revert "Added support for Triton chat completion using trtlllm generate endpo…" 2024-05-29 13:42:49 -07:00
Ishaan Jaff
e8c1e87ac9
Merge pull request #3895 from giritatavarty-8451/litellm_triton_chatcompletion_support
Added support for Triton chat completion using trtlllm generate endpo…
2024-05-29 12:50:31 -07:00
Krrish Dholakia
f168e35629 build(config.yml): add pillow to ci/cd 2024-05-28 21:39:09 -07:00
Krrish Dholakia
20106715d5 feat(proxy_server.py): enable batch completion fastest response calls on proxy
introduces new `fastest_response` flag for enabling the call
2024-05-28 20:09:31 -07:00
Giri Tatavarty
a58dc68418 Added support for Triton chat completion using trtlllm generate endpoint and custom infer endpoint 2024-05-28 07:54:11 -07:00
Krrish Dholakia
6b50e656b8 fix(main.py): pass extra headers through for async calls 2024-05-27 19:11:40 -07:00
Krrish Dholakia
d2e14ca833 fix(bedrock_httpx.py): fix bedrock ptu model id str encoding
Fixes https://github.com/BerriAI/litellm/issues/3805
2024-05-25 10:54:01 -07:00
Krish Dholakia
d25ed9c4d3
Merge pull request #3828 from BerriAI/litellm_outage_alerting
fix(slack_alerting.py): support region based outage alerting
2024-05-24 19:13:17 -07:00
Krrish Dholakia
8dec87425e feat(slack_alerting.py): refactor region outage alerting to do model based alerting instead
Unable to extract azure region from api base, makes sense to start with model alerting and then move to region
2024-05-24 19:10:33 -07:00
Krrish Dholakia
f8350b9461 fix(slack_alerting.py): support region based outage alerting 2024-05-24 16:59:16 -07:00
Ishaan Jaff
466accd4f5
Merge pull request #3462 from ffreemt/main
Add return_exceptions to batch_completion (retry)
2024-05-24 09:19:10 -07:00
ffreemt
86d46308bf Make return-exceptions as default behavior in litellm.batch_completion 2024-05-24 11:09:11 +08:00
Krrish Dholakia
43353c28b3 feat(databricks.py): add embedding model support 2024-05-23 18:22:03 -07:00
Krrish Dholakia
d2229dcd21 feat(databricks.py): adds databricks support - completion, async, streaming
Closes https://github.com/BerriAI/litellm/issues/2160
2024-05-23 16:29:46 -07:00
Krrish Dholakia
f3d29a6b4a feat(anthropic.py): support anthropic 'tool_choice' param
Closes https://github.com/BerriAI/litellm/issues/3752
2024-05-21 17:50:44 -07:00
Ishaan Jaff
2519879e67 add ImageObject 2024-05-20 10:45:37 -07:00
Ishaan Jaff
24951d44a4 feat - working httpx requests vertex ai image gen 2024-05-20 09:51:15 -07:00
Krrish Dholakia
5d24a72b7e fix(bedrock_httpx.py): support mapping for bedrock cohere command r text 2024-05-17 16:13:49 -07:00
Krrish Dholakia
0258351c61 fix(main.py): fix async stream handling during bedrock error 2024-05-16 23:37:59 -07:00