ishaan-jaff
|
6c82abf5bf
|
(fix) vertex ai streaming
|
2023-11-03 12:54:36 -07:00 |
|
Krrish Dholakia
|
6b3671b593
|
fix(proxy_server.py): accept config.yaml
|
2023-11-03 12:50:52 -07:00 |
|
ishaan-jaff
|
e09b4cb01a
|
bump: version 0.12.11 → 0.12.12
|
2023-11-03 10:04:14 -07:00 |
|
ishaan-jaff
|
539bdae364
|
(fix) remove errant print statements
|
2023-11-03 08:20:14 -07:00 |
|
ishaan-jaff
|
8b389e9e8a
|
(fix) proxy correctly handle reading data using ast, fallback to json.loads if ast parse fails
|
2023-11-02 21:14:08 -07:00 |
|
ishaan-jaff
|
4d82c81531
|
(fix) proxy cli tests
|
2023-11-02 21:14:08 -07:00 |
|
ishaan-jaff
|
104239dbe7
|
(fix) proxy server - verbose = False always
|
2023-11-02 21:14:08 -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
|
3f1b4c0759
|
(fix) linting fix
|
2023-11-02 17:28:45 -07:00 |
|
ishaan-jaff
|
7c87d613ed
|
(testing) test_function_call_non_openai_model
|
2023-11-02 17:26:30 -07:00 |
|
ishaan-jaff
|
e040df8989
|
bump: version 0.12.10 → 0.12.11
|
2023-11-02 17:15:38 -07:00 |
|
ishaan-jaff
|
bb832e38b9
|
(fix) litellm utils
|
2023-11-02 17:03:46 -07:00 |
|
ishaan-jaff
|
9d090db2d4
|
(test) vertex llms
|
2023-11-02 16:31:13 -07:00 |
|
ishaan-jaff
|
81f608dd34
|
(fix) vertexai detect code_chat and code_text llms as vertex
|
2023-11-02 16:31:13 -07:00 |
|
Krrish Dholakia
|
512a1637eb
|
feat(completion()): enable setting prompt templates via completion()
|
2023-11-02 16:24:01 -07:00 |
|
ishaan-jaff
|
1fc726d5dd
|
(fix) cleanup
|
2023-11-02 14:52:33 -07:00 |
|
ishaan-jaff
|
9484d19920
|
(docs) caching
|
2023-11-02 14:51:07 -07:00 |
|
ishaan-jaff
|
764ba41224
|
(docs) embedding
|
2023-11-02 10:57:57 -07:00 |
|
ishaan-jaff
|
f24e1cb133
|
(docs) embedding cohere
|
2023-11-02 10:56:24 -07:00 |
|
ishaan-jaff
|
4dfefc475d
|
(docs) cohere embedding
|
2023-11-02 10:45:56 -07:00 |
|
ishaan-jaff
|
fdc88cc0ee
|
(docs) cohere embedding models
|
2023-11-02 10:35:46 -07:00 |
|
ishaan-jaff
|
8ea2270058
|
(feat) cohere embedding
|
2023-11-02 10:26:02 -07:00 |
|
ishaan-jaff
|
33350c7c41
|
(docs) cohere
|
2023-11-02 10:23:52 -07:00 |
|
ishaan-jaff
|
5a471caf16
|
(test) add cohere embedding v3
|
2023-11-02 10:17:40 -07:00 |
|
ishaan-jaff
|
03860984eb
|
(feat) add setting input_type for cohere
|
2023-11-02 10:16:35 -07:00 |
|
ishaan-jaff
|
724e169f32
|
(fix) improve cohere error handling
|
2023-11-02 10:07:11 -07:00 |
|
ishaan-jaff
|
744e69f01f
|
(feat) add embed-english-v3.0
|
2023-11-02 10:05:22 -07:00 |
|
ishaan-jaff
|
d09486f93b
|
(feat) model context window.json add ollama/mistral, ollama/codellama, ollama/orca-mini, ollama/vicuna
|
2023-11-02 09:18:26 -07:00 |
|
ishaan-jaff
|
6b7b66aa96
|
bump: version 0.12.9 → 0.12.10
|
2023-11-02 08:50:43 -07:00 |
|
ishaan-jaff
|
76c007d542
|
(test) promptlayer logger
|
2023-11-02 08:18:00 -07:00 |
|
ishaan-jaff
|
2c18f7d374
|
(fix) logging callbacks - promptlayer
|
2023-11-02 08:18:00 -07:00 |
|
Krrish Dholakia
|
1bef2c62a6
|
fix(proxy_server.py): fix linting issues
|
2023-11-02 08:07:20 -07:00 |
|
Krrish Dholakia
|
740460f390
|
fix(main.py): expose custom llm provider for text completions
|
2023-11-02 07:55:54 -07:00 |
|
Krrish Dholakia
|
cb20554c79
|
fix(proxy_server.py): accept single quote json body
|
2023-11-02 07:07:38 -07:00 |
|
Krrish Dholakia
|
a12d0508c4
|
fix(proxy_server.py): fix v1/models get request
|
2023-11-02 06:51:47 -07:00 |
|
ishaan-jaff
|
7a389489b7
|
bump: version 0.12.8 → 0.12.9
|
2023-11-01 18:33:16 -07:00 |
|
ishaan-jaff
|
0a41443c3e
|
(test) hf text_completion
|
2023-11-01 18:25:13 -07:00 |
|
ishaan-jaff
|
8b5ee89d82
|
(feat) add transform_logprobs for text_completion
|
2023-11-01 18:25:13 -07:00 |
|
ishaan-jaff
|
8ca7af3a63
|
(feat) text completion set top_n_tokens for tgi
|
2023-11-01 18:25:13 -07:00 |
|
ishaan-jaff
|
19737f95c5
|
(feat) proxy add testing for openai.Completion.create
|
2023-11-01 18:25:13 -07:00 |
|
ishaan-jaff
|
bc61c81cc6
|
(feat) proxy server add route ngines/{model:path}/completions
|
2023-11-01 18:25:13 -07:00 |
|
ishaan-jaff
|
700fcfa5fb
|
(feat) text_completion add transform_logprobs
|
2023-11-01 18:25:13 -07:00 |
|
ishaan-jaff
|
1d0ce77baf
|
(fix) improve litellm.set_verbose=True logging
|
2023-11-01 18:25:13 -07:00 |
|
Krrish Dholakia
|
73cd0f3778
|
docs(proxy_server.md): cleanup
|
2023-11-01 18:13:22 -07:00 |
|
Krrish Dholakia
|
82065716de
|
docs(lm_evaluation_harness.md): adding github link to docs
|
2023-11-01 17:46:21 -07:00 |
|
Krrish Dholakia
|
9afd3c8bfa
|
docs(lm_evaluation_harness.md): tutorial showing how to use lm evaluation harness with tgi
|
2023-11-01 17:45:16 -07:00 |
|
Krrish Dholakia
|
b305492a0b
|
fix(huggingface_restapi.py): fix linting issue
|
2023-11-01 16:43:35 -07:00 |
|
Krrish Dholakia
|
aaa2a0dfb5
|
bump: version 0.12.7 → 0.12.8
|
2023-11-01 16:39:50 -07:00 |
|
Krrish Dholakia
|
2c4cb76ce5
|
fix(huggingface_restapi.py): fix embeddings for sentence-transformer models
|
2023-11-01 16:36:46 -07:00 |
|
Krrish Dholakia
|
ab0a29e160
|
fix(proxy_server.py): return all locally available ollama models
|
2023-11-01 16:20:26 -07:00 |
|