phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-28 04:04:31 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
12854 commits 2497 branches 898 tags 558 MiB
Commit graph

1503 commits

Author SHA1 Message Date
Krrish Dholakia
ab747c8fe9 fix(utils.py): fix replicate completion cost calculation 2024-05-17 22:18:57 -07:00
Ishaan Jaff
cdfa9c9232 fix - cooldown based on exception header 2024-05-17 18:52:45 -07:00
Krish Dholakia
60615f46c4 Merge branch 'main' into litellm_bedrock_anthropic_fix 2024-05-17 17:47:32 -07:00
Krrish Dholakia
b20f4f65b4 fix(bedrock_httpx.py): raise better timeout exception 2024-05-17 17:16:36 -07:00
Krrish Dholakia
54b4e24427 fix(utils.py): exception map bedrock error 2024-05-17 16:18:25 -07:00
Krrish Dholakia
9ab2389b7e feat(proxy_server.py): enable custom branding + routes on openapi docs 
Allows user to add their branding + show only openai routes on docs
 2024-05-17 15:21:29 -07:00
Krrish Dholakia
963b207473 fix(utils.py): support openrouter function calling 2024-05-17 08:02:24 -07:00
Mikkel Gravgaard
13b7dba006 Merge branch 'main' into patch-1 2024-05-17 10:26:14 +02:00
Krrish Dholakia
13e4196e3e fix(bedrock_httpx.py): add async support for bedrock amazon, meta, mistral models 2024-05-16 22:39:25 -07:00
Krrish Dholakia
8409b39f0d fix(bedrock_httpx.py): move bedrock ai21 calls to being async 2024-05-16 22:21:30 -07:00
Krrish Dholakia
118fc4ffac fix(bedrock_httpx.py): move anthropic bedrock calls to httpx 
Fixing https://github.com/BerriAI/litellm/issues/2921
 2024-05-16 21:51:55 -07:00
lj
eee9be353a Removed config dict type definition 2024-05-17 10:39:00 +08:00
Ishaan Jaff
b722dfd0ce Merge pull request #3705 from BerriAI/litellm_add_cost_tracking_for_ft_models 
[FEAT] add cost tracking for Fine Tuned OpenAI `ft:davinci-002` and `ft:babbage-002`
 2024-05-16 17:37:35 -07:00
Ishaan Jaff
b9cda67bb8 fix add cost tracking for OpenAI ft models 2024-05-16 17:31:19 -07:00
Krrish Dholakia
e41897808d fix(replicate.py): move replicate calls to being completely async 
Closes https://github.com/BerriAI/litellm/issues/3128
 2024-05-16 17:24:08 -07:00
Krrish Dholakia
782b44818c fix(utils.py): allow passing in custom pricing to completion_cost as params 2024-05-16 16:24:44 -07:00
Krrish Dholakia
dc00b4a7ed fix(utils.py): update completion_cost docstring 2024-05-16 15:47:40 -07:00
Krrish Dholakia
1f99fa7411 fix(utils.py): fix logging level of error message 2024-05-16 15:44:08 -07:00
Ishaan Jaff
3a52073b48 Merge pull request #3682 from BerriAI/litellm_token_counter_endpoint 
[Feat] `token_counter` endpoint
 2024-05-16 13:39:23 -07:00
Ishaan Jaff
a3763c8608 feat - try using hf tokenizer 2024-05-16 10:59:29 -07:00
Krrish Dholakia
d167a9ea99 feat(lago.py): adding support for usage-based billing with lago 
Closes https://github.com/BerriAI/litellm/issues/3639
 2024-05-16 10:54:18 -07:00
lj
3620c6fc1a Update model config in utils.py 2024-05-16 16:39:37 +08:00
Ishaan Jaff
c6e91daad7 Merge pull request #3543 from kmheckel/main 
Updated Ollama cost models to include LLaMa3 and Mistral/Mixtral Instruct series
 2024-05-15 20:50:50 -07:00
Ishaan Jaff
5597efa587 Merge pull request #3662 from BerriAI/litellm_feat_predibase_exceptions 
[Fix] Mask API Keys from Predibase AuthenticationErrors
 2024-05-15 20:45:40 -07:00
Krish Dholakia
d294e26fdb Merge pull request #3660 from BerriAI/litellm_proxy_ui_general_settings 
feat(proxy_server.py): Enabling Admin to control general settings on proxy ui
 2024-05-15 20:36:42 -07:00
Krrish Dholakia
3f339cb694 fix(parallel_request_limiter.py): fix max parallel request limiter on retries 2024-05-15 20:16:11 -07:00
Ishaan Jaff
d399e09655 fix utils.py 2024-05-15 19:54:52 -07:00
Ishaan Jaff
9782d7060e feat - predibase exceptions 2024-05-15 16:52:33 -07:00
Ishaan Jaff
b645d8dcf9 fix - show litellm_debug_info 2024-05-15 13:07:04 -07:00
Krrish Dholakia
c098ad0a60 fix(alerting.py): fix datetime comparison logic 2024-05-14 22:10:09 -07:00
Krrish Dholakia
7ab7e81aed fix(utils.py): default claude-3 to tiktoken (0.8s faster than hf tokenizer) 2024-05-14 18:37:14 -07:00
Krish Dholakia
8e59bbd573 Revert "Logfire Integration" 2024-05-14 17:38:47 -07:00
Krrish Dholakia
c6ca76e265 fix(utils.py): fix pydantic v1 error 2024-05-14 17:17:20 -07:00
Krrish Dholakia
d220cd8626 fix(utils.py): add lru-cache logic to _select_tokenizer 
speed up tokenizer load times
 2024-05-14 16:39:50 -07:00
alisalim17
2ddcb9bfd9 Merge remote-tracking branch 'upstream/main' 2024-05-14 22:32:57 +04:00
Krrish Dholakia
6c7c9c4aef fix(utils.py): fix python 3.8 linting error 2024-05-14 11:25:36 -07:00
alisalim17
25518fb995 refactor: logging class to use continue instead of break for streaming logging 2024-05-14 21:21:21 +04:00
alisalim17
f2a4398a39 chore: fix typo 2024-05-14 21:18:00 +04:00
alisalim17
bac6b3beb7 Merge remote-tracking branch 'upstream/main' 2024-05-14 18:42:20 +04:00
Krish Dholakia
bef8a7f1d9 Merge pull request #3600 from msabramo/msabramo/fix-pydantic-warnings 
Update pydantic code to fix warnings
 2024-05-13 22:00:39 -07:00
Krish Dholakia
3645c89fb5 Merge pull request #3602 from msabramo/msabramo/fix_pkg_resources_warning 
Fix `pkg_resources` warning
 2024-05-13 21:59:52 -07:00
Krrish Dholakia
f8e1b1db2e refactor(utils.py): trigger local_testing 2024-05-13 18:18:22 -07:00
Krrish Dholakia
ace5ce0b78 fix(utils.py): fix watsonx exception mapping 2024-05-13 18:13:13 -07:00
Krrish Dholakia
bf8d3be791 fix(utils.py): watsonx ai exception mapping fix 2024-05-13 17:11:33 -07:00
Krrish Dholakia
ca641d0a24 fix(utils.py): handle api assistant returning 'null' role 
Fixes https://github.com/BerriAI/litellm/issues/3621
 2024-05-13 16:46:07 -07:00
Krrish Dholakia
8d94665842 fix(utils.py): fix custom pricing when litellm model != response obj model name 2024-05-13 15:25:35 -07:00
Krrish Dholakia
96336cdd49 fix(openai.py): creat MistralConfig with response_format mapping for mistral api 2024-05-13 13:29:58 -07:00
Krrish Dholakia
a907247033 fix(utils.py): fix vertex ai function calling + streaming 
Completes https://github.com/BerriAI/litellm/issues/3147
 2024-05-13 12:32:39 -07:00
Marc Abramowitz
b61cc97771 Merge branch 'msabramo/pydantic_replace_root_validator_with_model_validator' into msabramo/fix-pydantic-warnings 2024-05-13 11:25:55 -07:00
Marc Abramowitz
09829c7c78 Fix pkg_resources warning 
by trying to use `importlib.resources` first and falling back to
`pkg_resources` if that fails.

With this and the changes in GH-3600 and GH-3601, the tests pass with **zero
warnings**!! 🎉 🎉

```shell
abramowi at marcs-mbp-3 in ~/Code/OpenSource/litellm (msabramo/fix-pydantic-warnings●●)
$ env -i PATH=$PATH poetry run pytest litellm/tests/test_proxy_server.py
====================================== test session starts ======================================
platform darwin -- Python 3.12.3, pytest-7.4.4, pluggy-1.5.0
rootdir: /Users/abramowi/Code/OpenSource/litellm
plugins: anyio-4.3.0, mock-3.14.0
collected 12 items

litellm/tests/test_proxy_server.py s..........s                                           [100%]

================================= 10 passed, 2 skipped in 9.24s =================================
```
 2024-05-12 12:46:24 -07:00