ishaan-jaff
|
cfd30bb152
|
(feat) proxy server add /routes to see available routes
|
2023-11-22 13:20:21 -08:00 |
|
Krrish Dholakia
|
57e894ad5e
|
fix(proxy_server.py): If master key is set, only master key can be used to generate new keys
|
2023-11-22 10:18:28 -08:00 |
|
Krrish Dholakia
|
9bb2c7ee0f
|
fix(utils.py): add param mapping for perplexity, anyscale, deepinfra
n
n
|
2023-11-22 10:04:27 -08:00 |
|
Krrish Dholakia
|
2a681e578c
|
fix(proxy_server): fix linting issues
|
2023-11-22 08:47:59 -08:00 |
|
Krrish Dholakia
|
73d70ef01c
|
feat(router.py): adding latency-based routing strategy
|
2023-11-21 21:19:27 -08:00 |
|
ishaan-jaff
|
12c2d1411a
|
(test) load test with api.litellm.ai
|
2023-11-21 21:07:27 -08:00 |
|
ishaan-jaff
|
bd5c89aab9
|
(test) load test proxy
|
2023-11-21 21:04:46 -08:00 |
|
ishaan-jaff
|
4ccee2e1a6
|
(test) load test q
|
2023-11-21 20:48:56 -08:00 |
|
ishaan-jaff
|
67b7aba40f
|
(test) load test q
|
2023-11-21 20:48:56 -08:00 |
|
ishaan-jaff
|
97a8177dfc
|
(fix) caching config
|
2023-11-21 20:48:56 -08:00 |
|
ishaan-jaff
|
4db51c6eae
|
(fix) cache configs
|
2023-11-21 20:48:56 -08:00 |
|
Krrish Dholakia
|
e96bb8868d
|
fix(proxy_server.py): fix /models endpoint
|
2023-11-21 20:15:43 -08:00 |
|
Krrish Dholakia
|
9a0a24259c
|
fix(celery_app.py): add retries to worker
|
2023-11-21 20:07:16 -08:00 |
|
Krrish Dholakia
|
efc2bfe295
|
fix(utils.py): add response ms for async calls
|
2023-11-21 19:59:00 -08:00 |
|
ishaan-jaff
|
5bf5bdf73a
|
(test) test q
|
2023-11-21 19:45:46 -08:00 |
|
ishaan-jaff
|
fd3462fb4f
|
(fix) proxy server set model list through headers
|
2023-11-21 19:33:48 -08:00 |
|
Krrish Dholakia
|
550ddb4a6b
|
docs(routing.md): update routing docs
|
2023-11-21 19:32:50 -08:00 |
|
ishaan-jaff
|
466e5c2a86
|
(test) test q
|
2023-11-21 18:15:00 -08:00 |
|
ishaan-jaff
|
e8b2c64255
|
(test) refactor test
|
2023-11-21 18:02:49 -08:00 |
|
Krrish Dholakia
|
9205f70b0f
|
docs(routing.md): add queueing to docs
|
2023-11-21 18:01:02 -08:00 |
|
ishaan-jaff
|
70af870005
|
(fix) explicitly run prisma generate
|
2023-11-21 17:42:42 -08:00 |
|
ishaan-jaff
|
3f442d85a4
|
(fix) prisma
|
2023-11-21 17:38:34 -08:00 |
|
ishaan-jaff
|
e4b7040500
|
(fix) prisma always installed on deploys
|
2023-11-21 17:27:07 -08:00 |
|
ishaan-jaff
|
5e62b8fdce
|
(docs) example hosted litellm yaml
|
2023-11-21 16:59:33 -08:00 |
|
ishaan-jaff
|
7ec9dbc94e
|
(test) add test for testing queuing
|
2023-11-21 16:59:33 -08:00 |
|
ishaan-jaff
|
0f80ae46a0
|
(test) move test file dir
|
2023-11-21 16:59:33 -08:00 |
|
Krrish Dholakia
|
7fb3a71b47
|
refactor(proxy_server.py): using celery workers instead of rq for concurrency
|
2023-11-21 16:31:56 -08:00 |
|
ishaan-jaff
|
cfafdb3463
|
(feat)proxy: readon config per request
|
2023-11-21 16:26:05 -08:00 |
|
ishaan-jaff
|
c3ff9cd433
|
(feat) proxy: add config col to prisma config
|
2023-11-21 16:22:26 -08:00 |
|
ishaan-jaff
|
0c5cfe5d1e
|
(docs) proxy queue config yaml
|
2023-11-21 16:22:00 -08:00 |
|
Krish Dholakia
|
1e99ebfec3
|
Merge pull request #845 from canada4663/upstream-main
Added support for multiple embeddings via Bedrock
|
2023-11-21 14:00:06 -08:00 |
|
Krrish Dholakia
|
5c3ea2a97e
|
refactor(rq_worker.py): put rq worker behind function call (prevent default import)
|
2023-11-21 13:51:42 -08:00 |
|
Krrish Dholakia
|
68c955409d
|
refactor(proxy_server.py): refactoring background rq worker
|
2023-11-21 13:47:09 -08:00 |
|
ishaan-jaff
|
760a465bd2
|
(test) catch streaming + timeout exceptions
|
2023-11-21 13:46:21 -08:00 |
|
ishaan-jaff
|
3e57b14cc6
|
(test) timeout error
|
2023-11-21 13:37:12 -08:00 |
|
ishaan-jaff
|
20ecef8664
|
(fix) request_timeout mapped to timeout for openai
|
2023-11-21 13:22:21 -08:00 |
|
Krrish Dholakia
|
7fb25ef2dd
|
fix(proxy_server.py): defaulting status to queued
|
2023-11-21 12:40:30 -08:00 |
|
Krrish Dholakia
|
8a77885c1c
|
refactor(proxy_server.py): experimental endpoint - defined job status
|
2023-11-21 12:37:00 -08:00 |
|
Krrish Dholakia
|
0b0e931e21
|
refactor(proxy_server.py): refactoring experimental endpoint names
|
2023-11-21 12:12:15 -08:00 |
|
Krrish Dholakia
|
b8e62f3d0c
|
feat(proxy_server.py): EXPERIMENTAL: adding queuing endpoints to openai proxy server
|
2023-11-21 12:06:23 -08:00 |
|
Krrish Dholakia
|
f763666cf1
|
test(test_completion.py): fix replicate streaming test
|
2023-11-21 10:38:05 -08:00 |
|
Krrish Dholakia
|
aad17a5479
|
fix(huggingface_restapi.pyu): fix linting errors
|
2023-11-21 10:05:35 -08:00 |
|
Krrish Dholakia
|
6e3a54cba9
|
test(test_rules.py): refactor testing
|
2023-11-21 10:01:06 -08:00 |
|
Krrish Dholakia
|
a1c342c3ad
|
feat(factory.py): add support for anthropic system prompts for claude 2.1
|
2023-11-21 09:57:26 -08:00 |
|
Krrish Dholakia
|
53d71c229f
|
fix(huggingface_restapi.py): fixing formatting
|
2023-11-21 09:57:26 -08:00 |
|
Krrish Dholakia
|
c48e775908
|
fix(huggingface_restapi.py): fix huggingface response format
|
2023-11-21 09:57:26 -08:00 |
|
Krrish Dholakia
|
c425fb7eeb
|
fix(huggingface_restapi.py): handle generate text output
|
2023-11-21 09:57:26 -08:00 |
|
ishaan-jaff
|
a7596ae30b
|
(test) add claude-2.1
|
2023-11-21 09:53:47 -08:00 |
|
ishaan-jaff
|
05f9ff6351
|
(fix) proxy server LiteLLM warning
|
2023-11-21 08:50:31 -08:00 |
|
ishaan-jaff
|
8ab13122d3
|
(docs) proxy starting config.yaml
|
2023-11-21 08:36:34 -08:00 |
|