phoenix/litellm
1
0
Fork 0
forked from phoenix/litellm-mirror
Code Pull requests Activity
5189 commits 1603 branches 645 tags 320 MiB
Commit graph

5189 commits

This branch
This branch
All branches
Author SHA1 Message Date
Max Deichmann
b93fe99b74 debug langfuse on env variable 2023-12-19 12:20:58 +01:00
Max Deichmann
a05a955653 add log 2023-12-19 10:06:03 +01:00
Max Deichmann
dc8ae16d84 add users 2023-12-19 09:54:51 +01:00
Max Deichmann
c397da7c59 changes 2023-12-19 09:41:49 +01:00
sumanth
96e23daf4d fix 2023-12-19 13:15:48 +05:30
ishaan-jaff
ce1b0b89ba (fix) proxy - health checks support cli model 2023-12-19 12:55:20 +05:30
ishaan-jaff
b82fcd51d7 (docs) ollama/llava 2023-12-19 11:32:28 +05:30
Krrish Dholakia
f73c4b494c docs(model_management.md): adding docs on how to add model metadata in the config.yaml 2023-12-18 17:57:29 -08:00
Krish Dholakia
67112ea81d
Merge pull request #1168 from clevcode/main 
Fix for issue that occured when proxying to ollama
 2023-12-18 17:54:59 -08:00
Krish Dholakia
408f232bd7
Merge branch 'main' into main 2023-12-18 17:54:34 -08:00
Krrish Dholakia
071283c102 fix(router.py): init deployment_latency_map even if model_list is empty 2023-12-18 17:50:26 -08:00
Krrish Dholakia
34509d8dda fix(main.py): return async completion calls 2023-12-18 17:41:54 -08:00
Krish Dholakia
6edc7cc2b3
Merge pull request #1178 from speedyankur/langfuse-doc-update 
doc: updated langfuse ver 1.14 in pip install cmd
 2023-12-18 17:33:29 -08:00
dependabot[bot]
8b439d374a
Bump aiohttp from 3.8.4 to 3.9.0 
Bumps [aiohttp](https://github.com/aio-libs/aiohttp) from 3.8.4 to 3.9.0.
- [Release notes](https://github.com/aio-libs/aiohttp/releases)
- [Changelog](https://github.com/aio-libs/aiohttp/blob/master/CHANGES.rst)
- [Commits](https://github.com/aio-libs/aiohttp/compare/v3.8.4...v3.9.0)

---
updated-dependencies:
- dependency-name: aiohttp
  dependency-type: direct:production
...

Signed-off-by: dependabot[bot] <support@github.com>
 2023-12-18 23:15:58 +00:00
Krrish Dholakia
014abddff6 fix(requirements.txt): pin all dependencies 2023-12-18 15:15:05 -08:00
Max Deichmann
99034709dc improve integration 2023-12-18 23:32:02 +01:00
Ankur Garha
d6ed13fa4f doc: updated langfuse ver 1.14 in pip install cmd 2023-12-18 22:56:08 +01:00
ishaan-jaff
bd15c61a65 (feat) OR default transforms=[] 2023-12-18 10:59:09 +05:30
Ishaan Jaff
6f97855925
Merge pull request #1174 from ericmjl/ericmjl-patch-1 
Update mistral.md
 2023-12-18 10:42:46 +05:30
Eric Ma
8ec7e25c06
Update mistral.md 
Eliminated typo with extra quotation mark.
 2023-12-17 23:51:02 -05:00
ishaan-jaff
3a97a2817f (fix) default args batch completion 2023-12-18 10:05:44 +05:30
ishaan-jaff
6a0c853ae4 (feat) add open router transforms, models, route 2023-12-18 09:55:35 +05:30
ishaan-jaff
1e57c0c152 (feat) completion set function, function_call default None 2023-12-18 09:54:43 +05:30
ishaan-jaff
6b272076d7 (feat) openrouter set transforms=[] default 2023-12-18 09:16:33 +05:30
ishaan-jaff
b15682bc1f (feat) set default openrouter configs 2023-12-18 08:55:51 +05:30
Joel Eriksson
e214e6ab47 Fix bug when iterating over lines in ollama response 
async for line in resp.content.iter_any() will return
incomplete lines when the lines are long, and that
results in an exception being thrown by json.loads()
when it tries to parse the incomplete JSON

The default behavior of the stream reader for aiohttp
response objects is to iterate over lines, so just
removing .iter_any() fixes the bug
 2023-12-17 20:23:26 +02:00
Joel Eriksson
a419d59542 Fix for issue that occured when proxying to ollama 
In the text_completion() function, it previously threw an exception at:
raw_response = response._hidden_params.get("original_response", None)

Due to response being an coroutine object to an ollama_acompletion call,
so I added an asyncio.iscoroutine() check for the response and handle it
by calling response = asyncio.run(response)

I also had to fix atext_completion(), where init_response was an instance
of TextCompletionResponse.

Since this case was not handled by the if-elif that checks if init_response
is a coroutine, a dict or a ModelResponse instance, response was unbound
which threw an exception on the "return response" line.

Note that a regular pyright based linter detects that response is possibly
unbound, and that the same code pattern is used in multiple other places
in main.py.

I would suggest that you either change these cases:

init_response = await loop.run_in_executor(...
if isinstance(init_response, ...
    response = init_response
elif asyncio.iscoroutine(init_response):
    response = await init_response

To either just:

response = await loop.run_in_executor(
if asyncio.iscoroutine(response):
    response = await response

Or at the very least, include an else statement and set response = init_response,
so that response is never unbound when the code proceeds.
 2023-12-17 17:27:47 +02:00
Krish Dholakia
c703fb2f2c
Merge pull request #1162 from nirga/patch-2 
clarify the need to set an exporter
 2023-12-16 21:31:56 -08:00
Krish Dholakia
f0093fae45
Merge pull request #1163 from ku-suke/patch-1 
(fix) curl example on proxy/quick_start
 2023-12-16 21:31:02 -08:00
Krrish Dholakia
a3c7a340a5 fix(ollama.py): fix sync ollama streaming 2023-12-16 21:23:21 -08:00
Krrish Dholakia
13d088b72e feat(main.py): add support for image generation endpoint 2023-12-16 21:07:29 -08:00
Krrish Dholakia
7847ae1e23 fix(traceloop.py): add additional openllmetry traces 2023-12-16 19:21:39 -08:00
Yusuke Kawabata
de8a3d5369
fix curl example 
Remove unnecessary `,` from curl example
 2023-12-17 12:00:06 +09:00
Krrish Dholakia
7c2fad2d57 fix(azure.py): fix azure streaming logging 2023-12-16 18:06:08 -08:00
Krrish Dholakia
3923c389fd build(Dockerfile): fixing build requirements 2023-12-16 17:52:30 -08:00
Krrish Dholakia
50b741f8fa fix(Dockerfile): support mac 2023-12-16 16:01:02 -08:00
Nir Gazit
4dc774ab8e
clarify the need to set an exporter 2023-12-16 22:19:07 +01:00
Krish Dholakia
9660f0e0b1
Merge pull request #1076 from Manouchehri/public-fix-1 
Use current Git folder for building Dockerfile
 2023-12-16 12:28:09 -08:00
Krish Dholakia
47ba8082df
Merge branch 'main' into public-fix-1 2023-12-16 12:27:58 -08:00
Krrish Dholakia
3291de9e11 fix(proxy_server.py): setup depedencies on server startup 2023-12-16 11:56:11 -08:00
Krrish Dholakia
4e828ff541 fix(health.md): add background health check details to docs 2023-12-16 10:31:59 -08:00
ishaan-jaff
abd7e48dee (ci/cd) run again 2023-12-16 22:34:10 +05:30
Krish Dholakia
50f61bcea4
Merge pull request #1157 from nanowell/patch-1 
Update mistral.md
 2023-12-16 08:56:39 -08:00
ishaan-jaff
c33cbbe068 (docs) - gemini-pro-visio n 2023-12-16 22:18:30 +05:30
ishaan-jaff
5ee6b87f2e (fix) vertexai - gemini 2023-12-16 22:15:41 +05:30
nanowell
9f762bbd5b
Update mistral.md 
Incorrect syntax
 2023-12-16 17:51:41 +03:00
ishaan-jaff
8522bb60f3 bump: version 1.15.0 → 1.15.1 2023-12-16 19:23:03 +05:30
ishaan-jaff
cb34c3c3f3 (docs) gemini pro vison 2023-12-16 19:20:57 +05:30
ishaan-jaff
a5fce3b2de (test) gemini vision 2023-12-16 19:16:32 +05:30
ishaan-jaff
6f643a6107 (docs) add gemini-pro-vision 2023-12-16 19:07:36 +05:30