942 commits

Author	SHA1	Message	Date
Krrish Dholakia	c37aad50ea	fix(utils.py): add more exception mapping for huggingface	2024-02-15 21:26:22 -08:00
Krrish Dholakia	aa78f55dff	fix(utils.py): add try-except around the tiktoken local import	2024-02-15 17:57:31 -08:00
Krrish Dholakia	3a5d40f4b9	fix(utils.py): fix local tiktoken package import	2024-02-15 16:18:54 -08:00
Krish Dholakia	78bff46d4a	Merge pull request #1947 from sorokine/main ... Update utils.py: switched from pkg_resources to importlib.resources for `filename` stored in the `os.environ(TIKTOKEN_CACHE_DIR)`	2024-02-14 22:02:35 -08:00
Krish Dholakia	57654f4533	Merge branch 'main' into litellm_aioboto3_sagemaker	2024-02-14 21:46:58 -08:00
ishaan-jaff	693efc8e84	(feat) add moderation on router	2024-02-14 11:00:09 -08:00
Krrish Dholakia	afad40b4f8	fix(utils.py): fix streaming rule calling	2024-02-12 22:36:32 -08:00
Krrish Dholakia	7600c8f41d	feat(utils.py): enable post call rules for streaming	2024-02-12 22:08:04 -08:00
Krrish Dholakia	b1bc30ee16	feat(sagemaker.py): aioboto3 streaming support	2024-02-12 21:18:34 -08:00
Alexandre Sorokine	36360c62ac	Update utils.py: switched from pkg_resources to importlib.resources for filename stored in the os/environ(TIKTOKEN_CACHE_DIR)	2024-02-12 16:28:38 -05:00
ishaan-jaff	e36f1af389	(feat) fix litellm verbose logger	2024-02-09 19:01:21 -08:00
ishaan-jaff	6dc7ded1a6	(bedrock) raise timeout error	2024-02-09 14:37:34 -08:00
Krrish Dholakia	b9393fb769	fix(test_parallel_request_limiter.py): use mock responses for streaming	2024-02-08 21:45:38 -08:00
Ishaan Jaff	59465bd612	Merge pull request #1892 from BerriAI/litellm_speed_up_s3_logging ... [FEAT] 76 % Faster s3 logging Proxy / litellm.acompletion / router.acompletion 🚀	2024-02-08 11:48:36 -08:00
ishaan-jaff	ac4d9a7542	(feat) speed up s3 logging	2024-02-08 10:59:54 -08:00
ishaan-jaff	9a23317461	(feat) fix s3 cache	2024-02-08 10:01:56 -08:00
ishaan-jaff	6969b25946	(fix) azure cost calc	2024-02-07 17:33:10 -08:00
ishaan-jaff	bb469278c6	(fix) cost tracking	2024-02-07 17:06:05 -08:00
ishaan-jaff	0764af4392	(feat) use base_model for azure response_cost	2024-02-07 16:33:07 -08:00
Krrish Dholakia	655fcd4d79	fix(utils.py): fix ollama stop sequence mapping	2024-02-07 13:14:03 -08:00
ishaan-jaff	ef32a5da1b	(feat) redis-semantic cache	2024-02-06 13:30:55 -08:00
Krrish Dholakia	67dce555ec	fix(utils.py): round max tokens to be int always	2024-02-06 13:17:26 -08:00
Krrish Dholakia	3afa5230d6	fix(utils.py): return finish reason for last vertex ai chunk	2024-02-06 09:21:03 -08:00
Krrish Dholakia	c2a523b954	fix(utils.py): use print_verbose for statements, so debug can be seen when running sdk	2024-02-06 07:30:26 -08:00
Krrish Dholakia	2e3748e6eb	fix(ollama_chat.py): fix ollama chat completion token counting	2024-02-06 07:30:26 -08:00
Krrish Dholakia	a1bbb16ab2	fix(langfuse.py): support logging failed llm api calls to langfuse	2024-02-05 16:16:15 -08:00
Krrish Dholakia	77fe71ee08	fix(utils.py): support together ai function calling	2024-02-05 15:30:44 -08:00
Krrish Dholakia	1bdb332454	fix(utils.py): handle count response tokens false case token counting	2024-02-05 08:47:10 -08:00
Krish Dholakia	640572647a	Merge pull request #1805 from BerriAI/litellm_cost_tracking_image_gen ... feat(utils.py): support cost tracking for openai/azure image gen models	2024-02-03 22:23:22 -08:00
Krrish Dholakia	25a0e15727	fix(utils.py): support time based pricing for openai-compatible together ai	2024-02-03 19:59:32 -08:00
Krrish Dholakia	efb6123d28	fix(utils.py): support get_secret("TOGETHER_AI_TOKEN")	2024-02-03 19:35:09 -08:00
Krrish Dholakia	c49c88c8e5	fix(utils.py): route together ai calls to openai client ... together ai is now openai-compatible n	2024-02-03 19:22:48 -08:00
Krrish Dholakia	c2f674ebe0	fix(utils.py): fix conditional check	2024-02-03 18:58:58 -08:00
Krish Dholakia	9ab59045a3	Merge branch 'main' into litellm_embedding_caching_updates	2024-02-03 18:08:47 -08:00
Krrish Dholakia	ef0171e063	feat(utils.py): support cost tracking for openai/azure image gen models	2024-02-03 17:09:54 -08:00
Krish Dholakia	1d241b4001	Merge pull request #1802 from BerriAI/litellm_vertex_ai_high_traffic_fix ... fix(vertex_ai.py): treat vertex ai high-traffic error as a rate limit error - allows user-controlled backoff logic to work here	2024-02-03 15:37:05 -08:00
Krish Dholakia	6408af11b6	Merge pull request #1799 from BerriAI/litellm_bedrock_stable_diffusion_support ... feat(bedrock.py): add stable diffusion image generation support	2024-02-03 12:59:00 -08:00
Krrish Dholakia	e617ef981d	fix(vertex_ai.py): treat vertex ai high-traffic error as a rate limit error - allows backoff logic to work here	2024-02-03 12:58:16 -08:00
Krrish Dholakia	36416360c4	feat(bedrock.py): add stable diffusion image generation support	2024-02-03 12:08:38 -08:00
Krrish Dholakia	d9ba8668f4	feat(vertex_ai.py): vertex ai gecko text embedding support	2024-02-03 09:48:29 -08:00
Krrish Dholakia	1ed6842009	fix(utils.py): fix cost tracking for cache hits (should be 0)	2024-02-02 17:33:39 -08:00
ishaan-jaff	d69edac11b	(feat) use same id to log on s3, langfuse	2024-02-02 16:26:59 -08:00
Krrish Dholakia	31b19a420f	fix(helicone.py): fix logging	2024-02-02 14:30:01 -08:00
Krrish Dholakia	a11b505721	fix(utils.py): dynamic switch langfuse client based on keys	2024-02-02 14:03:46 -08:00
Krish Dholakia	93fb0134e5	Merge pull request #1761 from BerriAI/litellm_fix_dynamic_callbacks ... fix(utils.py): override default success callbacks with dynamic callbacks if set	2024-02-02 13:06:55 -08:00
ishaan-jaff	aae54e0305	(feat) improve exceptions for OpenAI compatible -	2024-02-02 10:14:26 -08:00
Krrish Dholakia	127db122ef	test(test_keys.py): add more logging	2024-02-02 10:08:02 -08:00
ishaan-jaff	a55e0a9689	(feat) show correct provider in exceptions	2024-02-02 08:37:42 -08:00
Krrish Dholakia	61576fa6a9	fix(utils.py): logging fixes	2024-02-02 08:31:17 -08:00
Krrish Dholakia	5f9ea8a94f	fix(utils.py): add track cost callback to callback list for team id callbacks	2024-02-02 08:18:06 -08:00