Commit graph

3256 commits

Author SHA1 Message Date
ishaan-jaff
e6a7212d10 (fix) counting streaming prompt tokens - azure 2023-12-29 16:13:52 +05:30
ishaan-jaff
8c03be59a8 (fix) token_counter for tool calling 2023-12-29 15:54:03 +05:30
ishaan-jaff
73f60b7315 (test) stream chunk builder - azure prompt tokens 2023-12-29 15:45:41 +05:30
ishaan-jaff
b1077ebc38 (test) test_token_counter_azure 2023-12-29 15:37:46 +05:30
ishaan-jaff
037dcbbe10 (fix) use openai token counter for azure llms 2023-12-29 15:37:46 +05:30
Krrish Dholakia
cbdfae1267 fix(router.py): support wait_for for async completion calls 2023-12-29 15:27:20 +05:30
Krrish Dholakia
4882325c35 feat(router.py): support 'retry_after' param, to set min timeout before retrying a failed request (default 0) 2023-12-29 15:18:28 +05:30
ishaan-jaff
4a028d012a (test) token_counter - prompt tokens == tokens from API 2023-12-29 15:15:39 +05:30
ishaan-jaff
a300ab9152 (feat) azure stream - count correct prompt tokens 2023-12-29 15:15:39 +05:30
Krrish Dholakia
1e07f0fce8 fix(caching.py): hash the cache key to prevent key too long errors 2023-12-29 15:03:33 +05:30
Krrish Dholakia
6e68cd1125 docs(load_test.md): add litellm load test script to docs 2023-12-29 13:41:44 +05:30
ishaan-jaff
3973b9c8e4 (feat) cloudflare - add exception mapping 2023-12-29 12:31:10 +05:30
ishaan-jaff
243ad31e90 (test) async + stream clooudflare 2023-12-29 12:03:29 +05:30
ishaan-jaff
ee682be093 (feat) add cloudflare streaming 2023-12-29 12:01:26 +05:30
ishaan-jaff
a999e80b46 (test) async cloudflare 2023-12-29 11:50:09 +05:30
ishaan-jaff
dde6bc4fb6 (feat) cloudflare - add optional params 2023-12-29 11:50:09 +05:30
Krrish Dholakia
e06840b571 refactor: move async text completion testing to test_text_completion.py 2023-12-29 11:46:40 +05:30
ishaan-jaff
5fc9524a46 (test) test cloudflare completion 2023-12-29 11:34:58 +05:30
ishaan-jaff
8fcfb7df22 (feat) cloudflare ai workers - add completion support 2023-12-29 11:34:58 +05:30
Krrish Dholakia
6f2734100f fix(main.py): fix async text completion streaming + add new tests 2023-12-29 11:33:42 +05:30
ishaan-jaff
2b8e2bd937 (ci/cd) set num retries for HF test 2023-12-29 10:52:45 +05:30
ishaan-jaff
367e9913dc (feat) v0 adding cloudflare 2023-12-29 09:32:29 +05:30
ishaan-jaff
daf32f3bd4 (fix) tg AI cost tracking - zero-one-ai/Yi-34B-Chat 2023-12-29 09:14:07 +05:30
ishaan-jaff
d79df3a1e9 (fix) together_ai cost tracking 2023-12-28 22:11:08 +05:30
Krrish Dholakia
86403cd14e fix(vertex_ai.py): support function calling for gemini 2023-12-28 19:07:04 +05:30
ishaan-jaff
95e6d2fbba (feat) add voyage ai embeddings 2023-12-28 17:10:15 +05:30
Krrish Dholakia
cbcf406fd0 feat(admin_ui.py): support creating keys on admin ui 2023-12-28 16:59:11 +05:30
ishaan-jaff
41d5dceaec (test) mistral-embed 2023-12-28 16:42:36 +05:30
ishaan-jaff
78f0c0228b (feat) add mistral api embeddings 2023-12-28 16:41:55 +05:30
Krrish Dholakia
71a8b95710 refactor(proxy_server.py): make print statements into print_verbose 2023-12-28 15:08:23 +05:30
Krrish Dholakia
e5a287379a refactor(proxy_server.py): move admin ui to be locally hosted within proxy 2023-12-28 15:06:32 +05:30
ishaan-jaff
3919710823 (docs) proxy - swagger docs, add tags for model/info 2023-12-28 13:13:04 +05:30
ishaan-jaff
ab90b547d8 (fix) proxy - raise error when user missing litellm[proxy] 2023-12-28 13:07:44 +05:30
Krrish Dholakia
4db138facc test(test_proxy_custom_logger.py): fix testing to handle [done] chunks 2023-12-28 11:37:57 +05:30
Krrish Dholakia
bf4c4426e5 fix(proxy_server.py): return [DONE] end of stream chunk 2023-12-28 11:30:49 +05:30
Krrish Dholakia
c4fc28ab0d fix(utils.py): use local tiktoken copy 2023-12-28 11:22:33 +05:30
ishaan-jaff
7751b83100 (ci/cd) run render deploy 2023-12-28 11:16:58 +05:30
Krrish Dholakia
5089753925 test(test_health_check.py): fix azure embedding health check test 2023-12-28 10:48:31 +05:30
Krrish Dholakia
3b1685e7c6 feat(health_check.py): more detailed health check calls 2023-12-28 09:12:57 +05:30
ishaan-jaff
b071157df5 (test) proxy - debug /health 2023-12-27 19:18:41 +05:30
ishaan-jaff
ca8b87915f (test) langfuse - mark beta test 2023-12-27 18:43:49 +05:30
ishaan-jaff
a16411cf1d (ci/cd) move langfuse test early 2023-12-27 17:50:44 +05:30
ishaan-jaff
d7646669f2 (test) langfuse logging 2023-12-27 17:50:05 +05:30
ishaan-jaff
c1a8e30b01 (feat) proxy - remove appdirs 2023-12-27 17:40:05 +05:30
ishaan-jaff
07ea2e26f4 (fix) proxy - remove bloat - deprecated log_input_output 2023-12-27 17:36:53 +05:30
ishaan-jaff
74ea0832ca (feat) proxy remove appdirs as a dep 2023-12-27 17:33:47 +05:30
ishaan-jaff
af15e49948 (feat) proxy - remove subprocess install 2023-12-27 17:28:03 +05:30
Krrish Dholakia
e516cfe9f5 fix(utils.py): allow text completion input to be either model or engine 2023-12-27 17:24:16 +05:30
ishaan-jaff
7864d9a027 (fix) openai + stream - logprobs check 2023-12-27 16:59:56 +05:30
Krrish Dholakia
10a74d02c1 test(test_router_fallbacks.py): fix test to check previous models in pre_api_call not on success 2023-12-27 16:34:40 +05:30