Commit graph

1706 commits

Author SHA1 Message Date
Krrish Dholakia
2ac804a42f feat(proxy_server.py): enable model aliases 2023-11-20 16:51:04 -08:00
Krrish Dholakia
22b86c532f fix(litellm_server): commenting out the code 2023-11-20 15:39:05 -08:00
Krrish Dholakia
7472be1529 fix(routing.py): update token usage on streaming 2023-11-20 14:19:25 -08:00
Krrish Dholakia
952dd61e0e fix(init.py): exposing apiconnectionerror 2023-11-20 08:12:29 -08:00
Krrish Dholakia
854b749535 fix(utils.py): expanding exception mapping coverage for vertex ai 2023-11-18 20:05:40 -08:00
Krrish Dholakia
5f4dca301b refactor(router.py): adding user support message 2023-11-18 19:05:45 -08:00
ishaan-jaff
7e6c37962b (test) update testing streaming for open ai v1.0.0+ 2023-11-18 19:04:41 -08:00
ishaan-jaff
0fabd4caf8 (fix) streaming completion azure 2023-11-18 19:04:41 -08:00
Krrish Dholakia
43c26f3382 docs(routing.md): updating docs for managing multiple deployments 2023-11-18 19:02:50 -08:00
Krrish Dholakia
1812b7ae37 fix(proxy_server.py): fix linting errors 2023-11-18 17:35:16 -08:00
Krrish Dholakia
59b547a65e docs(simple_proxy.md): adding token based auth to docs 2023-11-18 17:34:11 -08:00
ishaan-jaff
e276023462 (test) palm streaming test 2023-11-18 17:32:15 -08:00
ishaan-jaff
70dc8441f6 (fix) streaming ensure response obj is initialized 2023-11-18 17:31:58 -08:00
ishaan-jaff
9bea4044b0 (test) remove unused tests 2023-11-18 17:25:42 -08:00
ishaan-jaff
2f0304f100 (test) async for chunk 2023-11-18 17:17:39 -08:00
ishaan-jaff
903016ba2f (fix) stream chunk builder when content == None in chunk 2023-11-18 17:16:05 -08:00
ishaan-jaff
30fcc1f9a0 (test) do nothing if token==None in stream chunk 2023-11-18 17:13:16 -08:00
ishaan-jaff
e527a45ffc (feat) print_verbose Raw openai chunk 2023-11-18 17:12:49 -08:00
ishaan-jaff
2466d26301 (fix) linting 2023-11-18 17:05:46 -08:00
ishaan-jaff
b2f8f8ed45 (test) openai streaming + function calling 2023-11-18 17:01:46 -08:00
ishaan-jaff
8f402e04c9 (fix) streaming openai + function calling 2023-11-18 17:01:46 -08:00
Krrish Dholakia
6a1270ce5a fix(proxy_server.py): handle initializing prisma / db connection just once 2023-11-18 16:45:19 -08:00
ishaan-jaff
e10c2d0bda (test) tool/function calling + streaming 2023-11-18 16:23:29 -08:00
ishaan-jaff
edf98cabae (fix) streaming + function / tool calling 2023-11-18 16:23:29 -08:00
Krrish Dholakia
8e599ed4f8 feat(proxy_server.py): enable token based authentication for server endpoints 2023-11-18 16:13:53 -08:00
Krrish Dholakia
229e5ea083 fix(proxy_server.py): allow user to connect their proxy to a postgres db 2023-11-18 15:57:38 -08:00
ishaan-jaff
c9445db22f (fix) langfuse logging - dont fail when casting optional params 2023-11-18 15:36:12 -08:00
ishaan-jaff
b31368ac2f (test) function calling 2023-11-18 15:15:02 -08:00
ishaan-jaff
250c891750 (fix) langfuse logger for function calling / tools 2023-11-18 15:14:44 -08:00
Krrish Dholakia
34decba3cf fix(text_completion): allow either model or engine to be set 2023-11-17 18:25:21 -08:00
Krrish Dholakia
7ea80de2f1 test(test_async_fn.py): catch timeouts 2023-11-17 18:01:52 -08:00
Krrish Dholakia
cf0a9f591c fix(router.py): introducing usage-based-routing 2023-11-17 17:56:26 -08:00
ishaan-jaff
259c1c7616 (ci/cd) fix timeout error 2023-11-17 17:46:49 -08:00
ishaan-jaff
505a0c354c (docs) update readme proxy server 2023-11-17 17:40:44 -08:00
ishaan-jaff
bae94aced0 (docs) load balancer 2023-11-17 17:25:46 -08:00
ishaan-jaff
a9bb85489f (docs) add example load balancer 2023-11-17 17:25:12 -08:00
Krrish Dholakia
452946b2f8 refactor(router.py): code cleanup 2023-11-17 17:05:46 -08:00
Krrish Dholakia
7d70bf84a7 test(test_langfuse.py): handle timeouts 2023-11-17 17:05:46 -08:00
ishaan-jaff
1ba32368ef (test) parallel tool calling 2023-11-17 17:03:24 -08:00
Krrish Dholakia
29906f6320 test(test_completion.py): change tgai model 2023-11-17 16:06:42 -08:00
Krrish Dholakia
237e6a4c32 fix(test_router.py): catch timeouts 2023-11-17 15:56:06 -08:00
ishaan-jaff
6d3248e17f (test) parallel function calling 2023-11-17 15:51:27 -08:00
ishaan-jaff
0ba90475c9 (feat) support parallel function calling 2023-11-17 15:51:27 -08:00
ishaan-jaff
b494990045 (feat) openai improve logging post_call 2023-11-17 15:51:27 -08:00
ishaan-jaff
698f47c226 (feat) improve logging - show model_call_details 2023-11-17 15:51:27 -08:00
Krrish Dholakia
aa6e6865cd fix(main.py): fix linting issue 2023-11-17 15:45:00 -08:00
Krrish Dholakia
02ed97d0b2 fix(acompletion): support client side timeouts + raise exceptions correctly for async calls 2023-11-17 15:39:47 -08:00
ishaan-jaff
b3e36d0486 (test) test seed, response format, for gpt-3.5-turbo 2023-11-17 14:00:42 -08:00
ishaan-jaff
ef8d82a54c (feat) completion: add response_format, seed, tools, tool_choice 2023-11-17 13:59:57 -08:00
ishaan-jaff
e9f6741b0b (v1.0+ breaking change) get_max_tokens -> return int 2023-11-17 10:38:50 -08:00