Krrish Dholakia
|
3291de9e11
|
fix(proxy_server.py): setup depedencies on server startup
|
2023-12-16 11:56:11 -08:00 |
|
Krrish Dholakia
|
4e828ff541
|
fix(health.md): add background health check details to docs
|
2023-12-16 10:31:59 -08:00 |
|
ishaan-jaff
|
abd7e48dee
|
(ci/cd) run again
|
2023-12-16 22:34:10 +05:30 |
|
ishaan-jaff
|
5ee6b87f2e
|
(fix) vertexai - gemini
|
2023-12-16 22:15:41 +05:30 |
|
ishaan-jaff
|
a5fce3b2de
|
(test) gemini vision
|
2023-12-16 19:16:32 +05:30 |
|
ishaan-jaff
|
4af13e44df
|
(test) vertex ai: stop running 4 requests / test
|
2023-12-16 19:01:12 +05:30 |
|
ishaan-jaff
|
e527137bee
|
(test) gemini-pro-vision
|
2023-12-16 18:58:31 +05:30 |
|
ishaan-jaff
|
764f31c970
|
(feat) add async, async+stream for gemini
|
2023-12-16 18:58:12 +05:30 |
|
ishaan-jaff
|
efe8b75200
|
(fix) use litellm.vertex_vision_models
|
2023-12-16 18:39:40 +05:30 |
|
ishaan-jaff
|
f3ebfb0517
|
(test) gemini vision test
|
2023-12-16 18:38:36 +05:30 |
|
ishaan-jaff
|
0bf29a14e8
|
init vertex_vision_models
|
2023-12-16 18:37:00 +05:30 |
|
ishaan-jaff
|
db188507b9
|
(test) gemini pro vision
|
2023-12-16 18:31:55 +05:30 |
|
ishaan-jaff
|
774a725ccb
|
(feat) add vertex ai gemini-pro-vision
|
2023-12-16 18:31:03 +05:30 |
|
ishaan-jaff
|
ed0b5d29b0
|
(test) proxy - cache config
|
2023-12-16 14:45:06 +05:30 |
|
ishaan-jaff
|
6b7d0eada4
|
(feat) proxy - set cache configs on proxy
|
2023-12-16 14:44:39 +05:30 |
|
ishaan-jaff
|
20b5505476
|
(feat) show POST request for HF embeddings
|
2023-12-16 13:09:49 +05:30 |
|
ishaan-jaff
|
37bf94dcdf
|
(fix) proxy remove errant print
|
2023-12-16 12:26:02 +05:30 |
|
Krrish Dholakia
|
5b4ca42de6
|
docs(routing.md): add docs on using caching groups across deployments
|
2023-12-15 21:51:59 -08:00 |
|
Krrish Dholakia
|
84ad9f441e
|
feat(router.py): support caching groups
|
2023-12-15 21:45:51 -08:00 |
|
ishaan-jaff
|
a7822b8772
|
(test) ollama-local, add llava test
|
2023-12-16 10:35:43 +05:30 |
|
ishaan-jaff
|
287633887e
|
(feat) add ollama/llava
|
2023-12-16 10:35:27 +05:30 |
|
Krrish Dholakia
|
add153d110
|
fix(huggingface_restapi.py): add support for additional hf embedding formats
|
2023-12-15 21:02:41 -08:00 |
|
Krrish Dholakia
|
5fe5149070
|
refactor(test_router_caching.py): add tests for router caching
|
2023-12-15 20:38:51 -08:00 |
|
Krrish Dholakia
|
4d8376a8e9
|
fix(router.py): init clients for azure/openai on set_model_list
|
2023-12-15 20:23:29 -08:00 |
|
Krrish Dholakia
|
4791dda66f
|
feat(proxy_server.py): enable infinite retries on rate limited requests
|
2023-12-15 20:03:41 -08:00 |
|
Krrish Dholakia
|
e5268fa6bc
|
fix(router.py): support openai-compatible endpoints
|
2023-12-15 14:47:54 -08:00 |
|
Krrish Dholakia
|
d2e9798de9
|
fix(router.py): adding mistral to list of openai-compatible endpoints
|
2023-12-15 14:24:43 -08:00 |
|
Krrish Dholakia
|
edb88e31e4
|
fix(together_ai.py): return empty tgai responses
|
2023-12-15 10:46:35 -08:00 |
|
Krrish Dholakia
|
a09a6f24a4
|
fix(together_ai.py): additional logging for together ai encoding prompt
|
2023-12-15 10:39:23 -08:00 |
|
Krrish Dholakia
|
cab870f73a
|
fix(ollama.py): fix ollama async streaming for /completions calls
|
2023-12-15 09:28:32 -08:00 |
|
ishaan-jaff
|
c9fb4ba88c
|
(feat) proxy - use async langfuse logger
|
2023-12-15 21:57:12 +05:30 |
|
ishaan-jaff
|
7915a5a120
|
(feat) langfuse add _async_log_event
|
2023-12-15 21:46:32 +05:30 |
|
ishaan-jaff
|
003cf92af3
|
(test) dynamodb set table name
|
2023-12-15 21:39:03 +05:30 |
|
ishaan-jaff
|
9bdd6e73bb
|
(feat) proxy logs: dynamodb - set table name
|
2023-12-15 21:38:44 +05:30 |
|
ishaan-jaff
|
99c505dba6
|
(fix) make dynamo logger async for proxy
|
2023-12-15 18:52:09 +05:30 |
|
ishaan-jaff
|
fa57a6d1f8
|
(fix) async + stream +sync logging
|
2023-12-15 18:31:36 +05:30 |
|
ishaan-jaff
|
6af3e73495
|
(fix) async+stream logger - building complete resp
|
2023-12-15 18:13:29 +05:30 |
|
ishaan-jaff
|
6c58fe65ff
|
(feat) dynamo db - log call_type
|
2023-12-15 17:27:48 +05:30 |
|
ishaan-jaff
|
cec7fcee2c
|
(test) dynamo logger
|
2023-12-15 17:22:21 +05:30 |
|
ishaan-jaff
|
8cfa233b74
|
(test) dynamo logger
|
2023-12-15 17:22:07 +05:30 |
|
ishaan-jaff
|
e35f0cbbdc
|
(feat) dynamo logger - all payload vals are str
|
2023-12-15 17:00:38 +05:30 |
|
ishaan-jaff
|
15b1e758ab
|
(test) dynamo db writes
|
2023-12-15 16:43:33 +05:30 |
|
ishaan-jaff
|
6b0f61f29b
|
(fix) dynamo.py spelling
|
2023-12-15 16:07:42 +05:30 |
|
ishaan-jaff
|
8b75d30a77
|
(test) dynamo db logger
|
2023-12-15 15:36:29 +05:30 |
|
ishaan-jaff
|
dacc95614c
|
(utils) add dynamoDB logger
|
2023-12-15 15:36:00 +05:30 |
|
ishaan-jaff
|
98662d1f59
|
(feat) add dynamoDB logger
|
2023-12-15 15:35:35 +05:30 |
|
ishaan-jaff
|
4413ef6dd2
|
(test) proxy - AuthError Exception mapping
|
2023-12-15 14:10:42 +05:30 |
|
ishaan-jaff
|
33afbd6ff5
|
(fix) raise openai.NotFoundError
|
2023-12-15 14:03:50 +05:30 |
|
ishaan-jaff
|
0b4f1dee42
|
(feat) proxy: embeddings-add OpenAI exception mapping
|
2023-12-15 14:02:24 +05:30 |
|
ishaan-jaff
|
d797bb100f
|
(test) proxy - exception mapping openai.NotFoundError
|
2023-12-15 13:34:51 +05:30 |
|