Commit graph

3109 commits

Author SHA1 Message Date
Ishaan Jaff
2501b4eccd feat link to model cost map on swagger 2024-07-26 21:34:42 -07:00
Ishaan Jaff
548adea8cf add litellm_header_name endpoint 2024-07-26 21:04:31 -07:00
Ishaan Jaff
a7f964b869
Merge pull request #4913 from BerriAI/litellm_fix_error_limit
[Proxy-Fix] - raise more descriptive errors when crossing tpm / rpm limits on keys, user, global limits
2024-07-26 20:25:28 -07:00
Ishaan Jaff
3c463ccbe6
Merge pull request #4914 from BerriAI/litellm_fix_batches
[Proxy-Fix + Test] - /batches endpoint
2024-07-26 20:12:03 -07:00
Krrish Dholakia
fe0b55f2ca fix(utils.py): fix cache hits for streaming
Fixes https://github.com/BerriAI/litellm/issues/4109
2024-07-26 19:04:08 -07:00
Ishaan Jaff
f627fa9b40 fix for GET /v1/batches{batch_id:path} 2024-07-26 18:23:15 -07:00
Ishaan Jaff
56ce7e892d fix batches inserting metadata 2024-07-26 18:08:54 -07:00
Ishaan Jaff
159a880dcc fix /v1/batches POST 2024-07-26 18:06:00 -07:00
Ishaan Jaff
c4e4b4675c fix raise better error when crossing tpm / rpm limits 2024-07-26 17:35:08 -07:00
Krrish Dholakia
9943c6d607 fix(proxy_server.py): fix get secret for environment_variables 2024-07-26 13:33:02 -07:00
Krrish Dholakia
84482703b8 docs(config.md): update wildcard docs 2024-07-26 08:59:53 -07:00
Krrish Dholakia
1d6c39a607 feat(proxy_server.py): handle pydantic mockselvar error
Fixes https://github.com/BerriAI/litellm/issues/4898#issuecomment-2252105485
2024-07-26 08:38:51 -07:00
Krrish Dholakia
2f773d9cb6 fix(litellm_cost_calc/google.py): support meta llama vertex ai cost tracking 2024-07-25 22:12:07 -07:00
Ishaan Jaff
079a41fbe1
Merge branch 'main' into litellm_proxy_support_all_providers 2024-07-25 20:15:37 -07:00
Ishaan Jaff
68e94f0976 example mistral sdk 2024-07-25 19:48:54 -07:00
Ishaan Jaff
693bcfac39 fix using pass_through_all_models 2024-07-25 19:32:49 -07:00
Krish Dholakia
c2086300b7
Merge branch 'main' into litellm_redis_team_object 2024-07-25 19:31:52 -07:00
Krish Dholakia
a306b83b2d
Merge pull request #4887 from BerriAI/litellm_custom_llm
feat(custom_llm.py): Support Custom LLM Handlers
2024-07-25 19:05:29 -07:00
Ishaan Jaff
9863520376 support using */* 2024-07-25 18:48:56 -07:00
Ishaan Jaff
8f4c5437b8 router support setting pass_through_all_models 2024-07-25 18:34:12 -07:00
Krrish Dholakia
bd7af04a72 feat(proxy_server.py): support custom llm handler on proxy 2024-07-25 17:56:34 -07:00
Ishaan Jaff
2432c90515 feat - support health check audio_speech 2024-07-25 17:26:14 -07:00
Krrish Dholakia
bfdda089c8 fix(proxy_server.py): check if input list > 0 before indexing into it
resolves 'list index out of range' error
2024-07-25 14:23:07 -07:00
Krrish Dholakia
4e51f712f3 fix(main.py): fix calling openai gpt-3.5-turbo-instruct via /completions
Fixes https://github.com/BerriAI/litellm/issues/749
2024-07-25 09:57:19 -07:00
Krrish Dholakia
b376ee71b0 fix(internal_user_endpoints.py): support updating budgets for /user/update 2024-07-24 21:51:46 -07:00
Krrish Dholakia
6ab2527fdc feat(auth_check.py): support using redis cache for team objects
Allows team update / check logic to work across instances instantly
2024-07-24 18:14:49 -07:00
Krrish Dholakia
b5c5ed2209 fix(key_management_endpoints.py): if budget duration set, set budget_reset_at 2024-07-24 15:02:22 -07:00
Krrish Dholakia
99d8b0ad68 fix(bedrock_httpx.py): fix async client check 2024-07-24 12:43:52 -07:00
Marc Abramowitz
642f1a7bcc Check existence of multiple views in 1 query
instead of multiple queries. This is more efficient because it lets us check for
all views in one query instead of multiple queries.
2024-07-23 21:55:02 -07:00
Krrish Dholakia
fb0a13c8bb fix(anthropic.py): support openai system message being a list 2024-07-23 21:45:56 -07:00
Ishaan Jaff
92708a2737
Merge pull request #4841 from BerriAI/litellm_anthropic_cost_tracking
[Feat] - /v1/messages support usage tracking on spendLogs
2024-07-23 16:37:42 -07:00
Ishaan Jaff
78eb5164df fix DB accept null values for api_base, user, etc 2024-07-23 16:33:04 -07:00
Ishaan Jaff
a71b60d005 Pass litellm proxy specific metadata 2024-07-23 15:31:30 -07:00
Ishaan Jaff
4c1ee1e282 fix add better debugging _PROXY_track_cost_callback 2024-07-23 15:25:46 -07:00
Krrish Dholakia
f64a3309d1 fix(utils.py): support raw response headers for streaming requests 2024-07-23 11:58:58 -07:00
Krrish Dholakia
dcb974dd1e feat(utils.py): support passing openai response headers to client, if enabled
Allows openai/openai-compatible provider response headers to be sent to client, if 'return_response_headers' is enabled
2024-07-23 11:30:52 -07:00
Ishaan Jaff
b137207ae6 doc alert_to_webhook_url 2024-07-23 11:04:15 -07:00
Ishaan Jaff
0ec2e9aa27 feat alert_to_webhook_url 2024-07-23 10:09:24 -07:00
Ishaan Jaff
d116ff280e feat - set alert_to_webhook_url 2024-07-23 10:08:21 -07:00
Ishaan Jaff
c1593c0cd1 update alert_to_webhook_url 2024-07-23 10:07:08 -07:00
Ishaan Jaff
69091f31df feat - add success_Callback per request 2024-07-23 08:43:01 -07:00
Ishaan Jaff
24ae0119d1 add debug logging for team callback settings 2024-07-23 08:41:05 -07:00
Ishaan Jaff
1a33c40713 add endpoint to disable logging for a team 2024-07-23 08:38:23 -07:00
Krish Dholakia
e770ac48a2
Merge branch 'main' into litellm_braintrust_integration 2024-07-22 22:40:39 -07:00
Krish Dholakia
c4db6aa15e
Merge pull request #4810 from BerriAI/litellm_team_modify_guardrails
feat(auth_checks.py): Allow admin to disable team from turning on/off guardrails
2024-07-22 22:32:24 -07:00
Krrish Dholakia
1a83935aa4 fix(proxy/utils.py): add stronger typing for litellm params in failure call logging 2024-07-22 21:31:39 -07:00
Ishaan Jaff
290628d66b
Merge pull request #4831 from BerriAI/litellm_api_control_team_logging
[Feat] - API Endpoints to control logging callbacks per Team
2024-07-22 21:22:14 -07:00
Krrish Dholakia
548e4f53f8 feat(redact_messages.py): allow remove sensitive key information before passing to logging integration 2024-07-22 20:58:02 -07:00
Ishaan Jaff
2e5da5ea18 GET endpoint to get team callbacks 2024-07-22 20:46:20 -07:00
Ishaan Jaff
447bab4d46 only allow unique callbacks for team callbacks 2024-07-22 20:43:42 -07:00