phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 11:14:04 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
15650 commits 2484 branches 894 tags 537 MiB
Commit graph

1753 commits

Author SHA1 Message Date
Krrish Dholakia
1cecdc4690 fix(utils.py): fix replicate completion cost calculation 2024-05-17 22:18:57 -07:00
Ishaan Jaff
f7a1675337 fix - cooldown based on exception header 2024-05-17 18:52:45 -07:00
Krish Dholakia
3a06fe2818
Merge branch 'main' into litellm_bedrock_anthropic_fix 2024-05-17 17:47:32 -07:00
Krrish Dholakia
4682802444 fix(bedrock_httpx.py): raise better timeout exception 2024-05-17 17:16:36 -07:00
Krrish Dholakia
b486bb1f8b fix(utils.py): exception map bedrock error 2024-05-17 16:18:25 -07:00
Krrish Dholakia
c0d62e94ae 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
26aefc7cd6 fix(utils.py): support openrouter function calling 2024-05-17 08:02:24 -07:00
Mikkel Gravgaard
80ef0f86d1
Merge branch 'main' into patch-1 2024-05-17 10:26:14 +02:00
Krrish Dholakia
92c2e2af6a fix(bedrock_httpx.py): add async support for bedrock amazon, meta, mistral models 2024-05-16 22:39:25 -07:00
Krrish Dholakia
0293f7766a fix(bedrock_httpx.py): move bedrock ai21 calls to being async 2024-05-16 22:21:30 -07:00
Krrish Dholakia
180bc46ca4 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
f3d0f003fb
Removed config dict type definition 2024-05-17 10:39:00 +08:00
Ishaan Jaff
4952e244d9
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
28ae8284df fix add cost tracking for OpenAI ft models 2024-05-16 17:31:19 -07:00
Krrish Dholakia
709373b15c 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
a2a5884df1 fix(utils.py): allow passing in custom pricing to completion_cost as params 2024-05-16 16:24:44 -07:00
Krrish Dholakia
bc23365acc fix(utils.py): update completion_cost docstring 2024-05-16 15:47:40 -07:00
Krrish Dholakia
ce4dffb7cb fix(utils.py): fix logging level of error message 2024-05-16 15:44:08 -07:00
Ishaan Jaff
0a816b2c45
Merge pull request #3682 from BerriAI/litellm_token_counter_endpoint 
[Feat] `token_counter` endpoint
 2024-05-16 13:39:23 -07:00
Ishaan Jaff
22ba5fa186 feat - try using hf tokenizer 2024-05-16 10:59:29 -07:00
Krrish Dholakia
e273e66618 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
6a60bfbd97
Update model config in utils.py 2024-05-16 16:39:37 +08:00
Ishaan Jaff
881812d5de
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
7aac76b485
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
25e4b34574
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
594ca947c8 fix(parallel_request_limiter.py): fix max parallel request limiter on retries 2024-05-15 20:16:11 -07:00
Ishaan Jaff
765d43d241 fix utils.py 2024-05-15 19:54:52 -07:00
Ishaan Jaff
b88ad61490 feat - predibase exceptions 2024-05-15 16:52:33 -07:00
Ishaan Jaff
59e18f23e0 fix - show litellm_debug_info 2024-05-15 13:07:04 -07:00
Krrish Dholakia
54587db402 fix(alerting.py): fix datetime comparison logic 2024-05-14 22:10:09 -07:00
Krrish Dholakia
a1dd341ca1 fix(utils.py): default claude-3 to tiktoken (0.8s faster than hf tokenizer) 2024-05-14 18:37:14 -07:00
Krish Dholakia
b04a8d878a
Revert "Logfire Integration" 2024-05-14 17:38:47 -07:00
Krrish Dholakia
dd0b4b8644 fix(utils.py): fix pydantic v1 error 2024-05-14 17:17:20 -07:00
Krrish Dholakia
2b41f09268 fix(utils.py): add lru-cache logic to _select_tokenizer 
speed up tokenizer load times
 2024-05-14 16:39:50 -07:00
alisalim17
765c382b2a Merge remote-tracking branch 'upstream/main' 2024-05-14 22:32:57 +04:00
Krrish Dholakia
f41b2a09a4 fix(utils.py): fix python 3.8 linting error 2024-05-14 11:25:36 -07:00
alisalim17
ed7c9e4e87 refactor: logging class to use continue instead of break for streaming logging 2024-05-14 21:21:21 +04:00
alisalim17
68637997c7 chore: fix typo 2024-05-14 21:18:00 +04:00
alisalim17
18bf68298f Merge remote-tracking branch 'upstream/main' 2024-05-14 18:42:20 +04:00
Krish Dholakia
2c867ea9a5
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
5b390b6512
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
155f1f164f refactor(utils.py): trigger local_testing 2024-05-13 18:18:22 -07:00
Krrish Dholakia
29449aa5c1 fix(utils.py): fix watsonx exception mapping 2024-05-13 18:13:13 -07:00
Krrish Dholakia
d7c28509d7 fix(utils.py): watsonx ai exception mapping fix 2024-05-13 17:11:33 -07:00
Krrish Dholakia
240c9550f0 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
b4a8665d11 fix(utils.py): fix custom pricing when litellm model != response obj model name 2024-05-13 15:25:35 -07:00
Krrish Dholakia
20456968e9 fix(openai.py): creat MistralConfig with response_format mapping for mistral api 2024-05-13 13:29:58 -07:00
Krrish Dholakia
39e4927752 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
73541b1f17 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
bfaf8d033d 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