3222 commits

Author	SHA1	Message	Date
Krrish Dholakia	88d498a54a	fix(ollama.py): use tiktoken as backup for prompt token counting	2024-01-09 09:47:18 +05:30
Krrish Dholakia	a5147f9e06	feat(lowest_latency.py): support expanded time window for latency based routing ... uses a 1hr avg. of latency for deployments, to determine which to route to https://github.com/BerriAI/litellm/issues/1361	2024-01-09 09:38:04 +05:30
Mateo Cámara	3bc8a03150	Merge remote-tracking branch 'origin/main' ... # Conflicts: # litellm/main.py	2024-01-08 18:51:46 +01:00
ishaan-jaff	6263103680	(ci/cd) run again	2024-01-08 22:42:31 +05:30
Krrish Dholakia	8edd3fe651	test(test_proxy_startup.py): fix gunicorn test	2024-01-08 19:55:18 +05:30
Krish Dholakia	e949a2ada3	Merge pull request #1367 from BerriAI/litellm_proxy_startup ... fix(proxy_server.py): add support for passing in config file via worker_config directly + testing	2024-01-08 19:46:48 +05:30
Krrish Dholakia	e305dcf0a6	test(test_proxy_startup.py): separate tests	2024-01-08 17:58:37 +05:30
Krrish Dholakia	2bcfe28ee9	fix(proxy_server.py): improve /health/readiness endpoint to give more details on connected services	2024-01-08 17:45:00 +05:30
Krrish Dholakia	8f8f961941	fix(proxy_server.py): add support for passing in config file via worker_config directly + testing	2024-01-08 16:47:15 +05:30
ishaan-jaff	fa74831d79	(docs) control proxy debug using env vars	2024-01-08 16:15:33 +05:30
ishaan-jaff	5d7646b30a	(fix) proxy - show detailed_debug logs	2024-01-08 15:34:24 +05:30
Krrish Dholakia	dd78782133	fix(utils.py): error handling for litellm --model mistral edge case	2024-01-08 15:09:01 +05:30
Krrish Dholakia	1ca7747371	fix(router.py): azure client init fix	2024-01-08 14:56:57 +05:30
Krrish Dholakia	1a480b3bd2	refactor: trigger dockerbuild	2024-01-08 14:42:28 +05:30
Ishaan Jaff	a70626d6e9	Merge pull request #1356 from BerriAI/litellm_improve_proxy_logs ... [Feat] Improve Proxy Logging	2024-01-08 14:41:01 +05:30
Krrish Dholakia	ec83243521	fix(router.py): increasing connection pool limits for azure router	2024-01-08 14:39:49 +05:30
ishaan-jaff	96e8c2b4cf	(test) tg - ai - set max_tokens=5, fast test	2024-01-08 14:03:31 +05:30
ishaan-jaff	bf30e8fdb2	(test) router- verbose logs with fallbacks	2024-01-08 14:00:12 +05:30
ishaan-jaff	6786e4f343	(feat) allow users to opt into detailed debug on proxy	2024-01-08 12:53:41 +05:30
Krrish Dholakia	6333fbfe56	fix(main.py): support cost calculation for text completion streaming object	2024-01-08 12:41:43 +05:30
ishaan-jaff	b4d9754dc2	(feat) verbose logs + fallbacks - working well	2024-01-08 12:33:09 +05:30
Krrish Dholakia	9b46412279	fix(utils.py): fix logging for text completion streaming	2024-01-08 12:05:28 +05:30
Krrish Dholakia	3d0ea08f77	refactor(gemini.py): fix linting issue	2024-01-08 11:43:33 +05:30
Krrish Dholakia	b1fd0a164b	fix(huggingface_restapi.py): support timeouts for huggingface + openai text completions ... https://github.com/BerriAI/litellm/issues/1334	2024-01-08 11:40:56 +05:30
Krrish Dholakia	c720870f80	docs(gemini.md,-deploy.md): doc updates	2024-01-08 11:02:12 +05:30
Krish Dholakia	4ea3e778f7	Merge pull request #1315 from spdustin/feature_allow_claude_prefill ... Adds "pre-fill" support for Claude	2024-01-08 10:48:15 +05:30
ishaan-jaff	f63f9d02cc	(feat) use '-debug' with proxy logger	2024-01-08 10:35:49 +05:30
Ishaan Jaff	5cfcd42763	Merge pull request #1311 from Manouchehri/patch-5 ... (caching) improve s3 backend	2024-01-08 09:47:57 +05:30
ishaan-jaff	7e4f5e5fbd	(feat) log what model is being used as a fallback	2024-01-08 09:41:24 +05:30
ishaan-jaff	f9d75233de	(feat) move litellm router - to use logging.debug, logging.info	2024-01-08 09:31:29 +05:30
ishaan-jaff	119ff2fe05	(docs) show fallbacks on proxy_config	2024-01-08 08:54:10 +05:30
ishaan-jaff	ccd100fab3	(fix) improve logging when no fallbacks found	2024-01-08 08:53:40 +05:30
ishaan-jaff	7742950c57	v0 proxy logger	2024-01-08 08:25:04 +05:30
Krrish Dholakia	c04fa54d19	fix(utils.py): fix exception raised	2024-01-08 07:42:17 +05:30
Krrish Dholakia	3469b5b911	fix(utils.py): map optional params for gemini	2024-01-08 07:38:55 +05:30
Krrish Dholakia	79264b0dab	fix(gemini.py): better error handling	2024-01-08 07:32:26 +05:30
Krrish Dholakia	75177c2a15	bump: version 1.16.16 → 1.16.17	2024-01-08 07:16:37 +05:30
David Manouchehri	56b03732ae	(caching) Set Content-Disposition header and Content-Language	2024-01-07 12:21:15 -05:00
Krrish Dholakia	888e21e8e7	test(test_google_ai_studio_gemini.py): use an image url that will work on ci/cd	2024-01-06 22:58:37 +05:30
Krrish Dholakia	1507217725	fix(factory.py): more logging around the image loading for gemini	2024-01-06 22:50:44 +05:30
Krish Dholakia	439ee3bafc	Merge pull request #1344 from BerriAI/litellm_speed_improvements ... Litellm speed improvements	2024-01-06 22:38:10 +05:30
Krrish Dholakia	5fd2f945f3	fix(factory.py): support gemini-pro-vision on google ai studio ... https://github.com/BerriAI/litellm/issues/1329	2024-01-06 22:36:22 +05:30
Krrish Dholakia	3577857ed1	fix(sagemaker.py): fix the post-call logging logic	2024-01-06 21:52:58 +05:30
Krrish Dholakia	f2ad13af65	fix(openai.py): fix image generation model dump	2024-01-06 17:55:32 +05:30
Krrish Dholakia	2d8d7e3569	perf(router.py): don't use asyncio.wait for - just pass it to the completion call for timeouts	2024-01-06 17:05:55 +05:30
Krrish Dholakia	712f89b4f1	fix(utils.py): handle original_response being a json	2024-01-06 17:02:50 +05:30
Krrish Dholakia	a7245dba07	build(Dockerfile): fixes the build time setup	2024-01-06 16:41:37 +05:30
ishaan-jaff	edac4130bb	(fix) s3 + os.environ/ cache test	2024-01-06 16:33:29 +05:30
ishaan-jaff	c222c0bfb8	(fix) proxy + cache - os.environ/ vars	2024-01-06 16:15:53 +05:30
ishaan-jaff	174248fc71	(test) add back test for counting stream completion tokens	2024-01-06 16:08:32 +05:30