Krrish Dholakia
|
10fe16c965
|
fix(utils.py): add param mapping for perplexity, anyscale, deepinfra
n
n
|
2023-11-22 10:04:27 -08:00 |
|
Krrish Dholakia
|
b16646e584
|
refactor(proxy_server.py): using celery workers instead of rq for concurrency
|
2023-11-21 16:31:56 -08:00 |
|
Krrish Dholakia
|
a1f6b9b531
|
refactor(proxy_server.py): refactoring background rq worker
|
2023-11-21 13:47:09 -08:00 |
|
Krrish Dholakia
|
c6a4744947
|
feat(proxy_server.py): EXPERIMENTAL: adding queuing endpoints to openai proxy server
|
2023-11-21 12:06:23 -08:00 |
|
Krrish Dholakia
|
855964ed45
|
fix(utils.py): adding support for rules + mythomax/alpaca prompt template
|
2023-11-20 18:58:15 -08:00 |
|
Krrish Dholakia
|
e75c07f726
|
fix(init.py): exposing apiconnectionerror
|
2023-11-20 08:12:29 -08:00 |
|
ishaan-jaff
|
bd82559553
|
(v1.0+ breaking change) get_max_tokens -> return int
|
2023-11-17 10:38:50 -08:00 |
|
Krrish Dholakia
|
a23c0a2599
|
fix(openai.py): fix linting issues
|
2023-11-16 11:01:28 -08:00 |
|
Krrish Dholakia
|
fc8b54eb73
|
fix(openai.py): switch back to using requests instead of httpx
|
2023-11-15 18:25:21 -08:00 |
|
Krrish Dholakia
|
9fd7c5b343
|
test: set request timeout at request level
|
2023-11-15 17:42:31 -08:00 |
|
ishaan-jaff
|
2a81cc567d
|
(chore) removing bloat
|
2023-11-15 17:11:56 -08:00 |
|
Krrish Dholakia
|
1a705bfbcb
|
refactor(huggingface_restapi.py): moving async completion + streaming to real async calls
|
2023-11-15 15:14:21 -08:00 |
|
Krrish Dholakia
|
33d823a18d
|
docs(routing.md): add contributor s/o
|
2023-11-15 13:20:02 -08:00 |
|
Krrish Dholakia
|
59eaeba92a
|
fix(router.py): enabling retrying with expo backoff (without tenacity) for router
|
2023-11-14 20:57:51 -08:00 |
|
Krrish Dholakia
|
a7222f257c
|
fix(main.py): keep client consistent across calls + exponential backoff retry on ratelimit errors
|
2023-11-14 16:26:05 -08:00 |
|
Krrish Dholakia
|
39c2597c33
|
refactor(azure.py): working azure completion calls with openai v1 sdk
|
2023-11-11 16:44:39 -08:00 |
|
Krrish Dholakia
|
d3323ba637
|
refactor(openai.py): making it compatible for openai v1
BREAKING CHANGE:
|
2023-11-11 15:33:02 -08:00 |
|
ishaan-jaff
|
59c76db34e
|
(fix) add APIError to litellm module
|
2023-11-11 11:33:02 -08:00 |
|
Krrish Dholakia
|
53abc31c27
|
refactor(azure.py): moving azure openai calls to http calls
|
2023-11-08 16:52:18 -08:00 |
|
Krrish Dholakia
|
21ae940992
|
bump: version 0.13.1 → 0.13.2.dev1
|
2023-11-05 21:12:13 -08:00 |
|
Krrish Dholakia
|
3a4370ae20
|
bump: version 0.13.1.dev2 → 0.13.1.dev3
|
2023-11-04 22:31:53 -07:00 |
|
Krrish Dholakia
|
c3916a7754
|
feat(utils.py): adding additional states for custom logging
|
2023-11-04 17:07:20 -07:00 |
|
Krrish Dholakia
|
5bd6d6ff4c
|
test(test_completion.py): num retries 3
|
2023-11-04 15:55:56 -07:00 |
|
Krrish Dholakia
|
4e1885734a
|
refactor(proxy_server.py): print statement showing how to add debug for logs
|
2023-11-03 17:41:14 -07:00 |
|
Krrish Dholakia
|
e3a1c58dd9
|
build(litellm_server/utils.py): add support for general settings + num retries as a module variable
|
2023-11-02 20:56:41 -07:00 |
|
ishaan-jaff
|
744e69f01f
|
(feat) add embed-english-v3.0
|
2023-11-02 10:05:22 -07:00 |
|
ishaan-jaff
|
9cfd218101
|
(feat) detect amazon.titan-embed-text-v1 as bedrock embedding model
|
2023-11-01 14:46:33 -07:00 |
|
Krrish Dholakia
|
0ed3917b09
|
feat(main.py): add support for maritalk api
|
2023-10-30 17:36:51 -07:00 |
|
ishaan-jaff
|
d5e6777973
|
(fix) remove bloat completion_with_split_tests
|
2023-10-27 18:13:30 -07:00 |
|
Krrish Dholakia
|
c1b2553827
|
fix(utils.py): adding support for anyscale models
|
2023-10-25 09:08:10 -07:00 |
|
Krrish Dholakia
|
f967d6af5e
|
fix(init.py): fix linting errors
|
2023-10-24 15:54:21 -07:00 |
|
Krrish Dholakia
|
5c8a4f51d5
|
fix(utils.py): allow url to be passed to model cost map
|
2023-10-24 15:38:05 -07:00 |
|
ishaan-jaff
|
1bd41ab636
|
(feat) add perplexity llms
|
2023-10-20 14:39:29 -07:00 |
|
ishaan-jaff
|
114d8fda65
|
(feat) native perplexity support
|
2023-10-20 14:29:07 -07:00 |
|
Krrish Dholakia
|
4eeadd284a
|
feat(utils.py): adding encode and decode functions
|
2023-10-20 11:59:47 -07:00 |
|
Iskren Chernev
|
629fe3c6ba
|
Load deepinfra models from json
|
2023-10-20 11:34:17 +03:00 |
|
Krrish Dholakia
|
8dda69e216
|
feat(utils.py): add register model helper function
|
2023-10-19 18:26:36 -07:00 |
|
Krrish Dholakia
|
50a3c9768b
|
test(init.py): improving testing for get_model_cost_map
b69449a811
|
2023-10-18 14:55:36 -07:00 |
|
Krrish Dholakia
|
b69449a811
|
fix(init.py): adding local cached copy of model mapping for fallbacks
|
2023-10-18 13:59:12 -07:00 |
|
Krrish Dholakia
|
b20cf3171b
|
feat(router.py): add routing capabilities for multiple deployments
|
2023-10-17 22:28:31 -07:00 |
|
canada4663
|
98abecf124
|
remove duplicate entry for bedrock in provider list
|
2023-10-14 21:44:16 -07:00 |
|
canada4663
|
4411fd3872
|
Update __init__.py model_list to include bedrock models
|
2023-10-14 16:29:18 -07:00 |
|
Krrish Dholakia
|
4d4f8bfa5d
|
feat(proxy_server): adding model fallbacks and default model to toml
|
2023-10-13 15:31:17 -07:00 |
|
Krrish Dholakia
|
8dc009255b
|
fix(init.py): fix linting errors
|
2023-10-12 21:31:53 -07:00 |
|
Krrish Dholakia
|
d280a8c434
|
fix(proxy_cli-and-utils.py): fixing how config file is read + infering llm_provider for known openai endpoints
|
2023-10-10 20:53:02 -07:00 |
|
Krrish Dholakia
|
0e7b83785b
|
fix(init.py): expose complete client session
|
2023-10-10 15:16:10 -07:00 |
|
Krrish Dholakia
|
b50013386f
|
fix(openai.py): enable custom proxy to pass in ca_bundle_path
|
2023-10-10 13:23:27 -07:00 |
|
Krrish Dholakia
|
0d863f00ad
|
refactor(bedrock.py): take model names from model cost dict
|
2023-10-10 07:35:03 -07:00 |
|
Krrish Dholakia
|
704be9dcd1
|
feat(factory.py): option to add function details to prompt, if model doesn't support functions param
|
2023-10-09 09:53:53 -07:00 |
|
Kyle
|
22525d9333
|
Add custom_openai type in provider list
|
2023-10-08 21:20:10 -07:00 |
|