ishaan-jaff
|
e7b6ef8f50
|
(fix) hf don't fail when logprob is None
|
2023-11-06 14:22:09 -08:00 |
|
Krrish Dholakia
|
9baafd7dbf
|
fix(huggingface_restapi.py): output parsing chat template models
|
2023-11-06 11:43:12 -08:00 |
|
Krrish Dholakia
|
d53a0d9663
|
refactor(bedrock.py): better exception mapping for bedrock + huggingface
|
2023-11-04 16:12:12 -07:00 |
|
Krrish Dholakia
|
b1dcd0f1b9
|
fix(timeout.py): import errors
|
2023-11-04 16:05:14 -07:00 |
|
Krrish Dholakia
|
f7c5595a0d
|
fix(main.py): fixing print_verbose
|
2023-11-04 14:41:34 -07:00 |
|
Krrish Dholakia
|
d0b23a2722
|
refactor(all-files): removing all print statements; adding pre-commit + flake8 to prevent future regressions
|
2023-11-04 12:50:15 -07:00 |
|
Krrish Dholakia
|
64b6b0155d
|
fix(bedrock.py): add exception mapping coverage for authentication scenarios
|
2023-11-03 18:25:34 -07:00 |
|
Krrish Dholakia
|
8bf8464fc2
|
fix(bedrock.py): fix bedrock exception mapping
|
2023-11-03 18:14:12 -07:00 |
|
ishaan-jaff
|
10f72f0f4a
|
(fix) bedrock: remove check for - if "error" in outputText
|
2023-11-03 18:06:23 -07:00 |
|
ishaan-jaff
|
d278417682
|
(fix) hf calculating usage non blocking
|
2023-11-03 18:03:19 -07:00 |
|
Krrish Dholakia
|
fa24a61976
|
refactor(proxy_server.py): print statement showing how to add debug for logs
|
2023-11-03 17:41:14 -07:00 |
|
ishaan-jaff
|
ee60c04251
|
(fix) remove errant print statements
|
2023-11-03 13:02:52 -07:00 |
|
ishaan-jaff
|
838e261ab9
|
(fix) remove errant tg ai print statements
|
2023-11-03 12:59:23 -07:00 |
|
ishaan-jaff
|
fbd5117a6d
|
(fix) vertex ai streaming
|
2023-11-03 12:54:36 -07:00 |
|
Krrish Dholakia
|
127972a80b
|
build(litellm_server/utils.py): add support for general settings + num retries as a module variable
|
2023-11-02 20:56:41 -07:00 |
|
Krrish Dholakia
|
33c1118080
|
feat(completion()): enable setting prompt templates via completion()
|
2023-11-02 16:24:01 -07:00 |
|
ishaan-jaff
|
36a2266382
|
(feat) add setting input_type for cohere
|
2023-11-02 10:16:35 -07:00 |
|
ishaan-jaff
|
d100bfdc2e
|
(fix) improve cohere error handling
|
2023-11-02 10:07:11 -07:00 |
|
Krrish Dholakia
|
8475772daa
|
fix(huggingface_restapi.py): fix linting issue
|
2023-11-01 16:43:35 -07:00 |
|
Krrish Dholakia
|
80cb421e02
|
fix(huggingface_restapi.py): fix embeddings for sentence-transformer models
|
2023-11-01 16:36:46 -07:00 |
|
ishaan-jaff
|
0668d8d81e
|
(feat) embedding() add bedrock/amazon.titan-embed-text-v1
|
2023-11-01 13:55:28 -07:00 |
|
ishaan-jaff
|
c6229b7113
|
(feat) add bedrock.cohere streaming
|
2023-10-31 22:26:43 -07:00 |
|
ishaan-jaff
|
525e5476f6
|
(feat) textcompletion - transform hf log probs to openai text completion
|
2023-10-31 17:15:35 -07:00 |
|
Krish Dholakia
|
ed8f1ab5dc
|
Merge pull request #717 from canada4663/main
support for custom bedrock runtime endpoint
|
2023-10-31 16:47:33 -07:00 |
|
Krrish Dholakia
|
147d69f230
|
feat(main.py): add support for maritalk api
|
2023-10-30 17:36:51 -07:00 |
|
canada4663
|
49033bbe27
|
add ability to use custom AWS Bedrock Runtime endpoint via environment or .env variable AWS_BEDROCK_RUNTIME_ENDPOINT or as a parameter to init_bedrock_client
|
2023-10-28 22:25:45 -07:00 |
|
canada4663
|
46ef5a94b9
|
add in ability to read AWS boto3 default AWS Region name if litellm .env config AWS_REGION_NAME not available
|
2023-10-28 21:43:48 -07:00 |
|
ishaan-jaff
|
75d45c27c1
|
(fix) bedrock region name defaults to None
|
2023-10-27 10:17:45 -07:00 |
|
ishaan-jaff
|
485a7ff136
|
(feat) use usage class for model responses for cohere, hf, tg ai, cohere
|
2023-10-27 09:58:47 -07:00 |
|
ishaan-jaff
|
194b6263c7
|
(feat) add model_response.usage.completion_tokens for bedrock, palm, petals, sagemaker
|
2023-10-27 09:51:50 -07:00 |
|
ishaan-jaff
|
66e934b0ad
|
(feat) use usage class for vertex ai
|
2023-10-27 09:38:37 -07:00 |
|
ishaan-jaff
|
a9331edfd9
|
(feat) use usage class for anthropic
|
2023-10-27 09:32:25 -07:00 |
|
Krrish Dholakia
|
98c25b08cd
|
fix(vertex_ai.py): fix output parsing
|
2023-10-24 12:08:22 -07:00 |
|
Krrish Dholakia
|
5e83c34913
|
fix(vertex_ai.py): parse out text response from response object
|
2023-10-24 08:53:22 -07:00 |
|
Krrish Dholakia
|
2f9e112c14
|
fix(anthropic.py-+-bedrock.py): anthropic prompt format
|
2023-10-20 10:56:15 -07:00 |
|
Krrish Dholakia
|
18a6facdb3
|
fix: allow api base to be set for all providers
enables proxy use cases
|
2023-10-19 19:07:42 -07:00 |
|
Krrish Dholakia
|
a415c79b8b
|
fix(anthropic.py): enable api base to be customized
|
2023-10-19 18:45:29 -07:00 |
|
Krrish Dholakia
|
44cafb5bac
|
docs(proxy_server.md): update proxy server docs to include multi-agent autogen tutorial
|
2023-10-17 09:22:34 -07:00 |
|
Krrish Dholakia
|
e5279ef99d
|
style: fix linting errors
|
2023-10-16 17:35:08 -07:00 |
|
Krrish Dholakia
|
5f9dd0b21f
|
bump: version 0.8.4 → 0.8.5
|
2023-10-14 16:43:06 -07:00 |
|
Krrish Dholakia
|
2a694c4410
|
fix(openai.py): fix linting errors
|
2023-10-13 22:24:58 -07:00 |
|
Krrish Dholakia
|
ec5e7aa4a9
|
fix(openai.p): adding support for exception mapping for openai-compatible apis via http calls
|
2023-10-13 21:56:51 -07:00 |
|
ishaan-jaff
|
3fe21a7cf3
|
(fix) fix linting errors
|
2023-10-13 21:23:00 -07:00 |
|
Krrish Dholakia
|
d0b4dfd26c
|
feat(proxy_server): adds create-proxy feature
|
2023-10-12 18:27:07 -07:00 |
|
ishaan-jaff
|
960481a540
|
(feat) ollama raise Exceptions + use LiteLLM stream wrapper
|
2023-10-11 17:00:39 -07:00 |
|
Krrish Dholakia
|
5b4311eaa7
|
fix(openai-py): fix linting errors
|
2023-10-10 21:56:14 -07:00 |
|
Krrish Dholakia
|
127d406963
|
fix(openai-py): fix linting issues
|
2023-10-10 21:49:14 -07:00 |
|
Krrish Dholakia
|
75c811837d
|
fix(openai.py): fix linting errors
|
2023-10-10 21:04:13 -07:00 |
|
Krrish Dholakia
|
70bfa022a4
|
fix(init.py): expose complete client session
|
2023-10-10 15:16:10 -07:00 |
|
Krrish Dholakia
|
67b3e792ff
|
fix(openai.py): enable custom proxy to pass in ca_bundle_path
|
2023-10-10 13:23:27 -07:00 |
|