litellm/litellm/proxy
2024-06-11 16:16:10 -07:00
..
_experimental docs(ui.md): add okta sso support to docs 2024-06-11 13:17:41 -07:00
auth Merge branch 'main' into litellm_svc_logger 2024-06-07 14:01:54 -07:00
db
example_config_yaml feat(bedrock_httpx.py): moves to using httpx client for bedrock cohere calls 2024-05-11 13:43:08 -07:00
hooks fix(litellm_pre_call_utils.py): add support for key level caching params 2024-06-07 22:09:14 -07:00
management_helpers fix(proxy_server.py): allow passing in a list of team members 2024-06-08 19:03:45 -07:00
proxy_load_test
queue docs(scheduler.md): add request prioritization to docs 2024-05-31 19:35:47 -07:00
secret_managers fix(aws_secret_manager.py): fix boto import 2024-06-07 08:02:58 -07:00
tests doc - OTEL trace propogation 2024-06-11 14:25:33 -07:00
utils fix refactor management endpoint utils 2024-06-11 16:16:10 -07:00
__init__.py
_logging.py feat(proxy/_logging.py): support controlling log level when json logs=True 2024-06-10 17:33:43 -07:00
_new_secret_config.yaml fix(langfuse.py): fix langfuse environ check 2024-04-24 13:21:00 -07:00
_super_secret_config.yaml fix(proxy_server.py): return updated member list in /team/member_delete 2024-06-08 16:33:07 -07:00
_types.py feat - log management endpoint logs to otel 2024-06-11 16:09:11 -07:00
.gitignore
admin_ui.py
cached_logo.jpg
custom_callbacks1.py feat - async_post_call_streaming_hook 2024-05-23 09:30:53 -07:00
custom_callbacks.py
enterprise
health_check.py
lambda.py
litellm_pre_call_utils.py fix(litellm_pre_call_utils.py): add support for key level caching params 2024-06-07 22:09:14 -07:00
llamaguard_prompt.txt
logo.jpg
openapi.json
otel_config.yaml
post_call_rules.py
proxy_cli.py fix(proxy/_logging.py): fix default logging level 2024-06-05 17:42:49 -07:00
proxy_config.yaml fix - cache - true 2024-06-07 16:21:23 -07:00
proxy_server.py fix refactor management endpoint utils 2024-06-11 16:16:10 -07:00
README.md
schema.prisma Merge pull request #4084 from BerriAI/litellm_batch_add_team_members 2024-06-10 20:26:35 -07:00
start.sh
utils.py fix refactor management endpoint utils 2024-06-11 16:16:10 -07:00

litellm-proxy

A local, fast, and lightweight OpenAI-compatible server to call 100+ LLM APIs.

usage

$ pip install litellm
$ litellm --model ollama/codellama 

#INFO: Ollama running on http://0.0.0.0:8000

replace openai base

import openai # openai v1.0.0+
client = openai.OpenAI(api_key="anything",base_url="http://0.0.0.0:8000") # set proxy to base_url
# request sent to model set on litellm proxy, `litellm --model`
response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [
    {
        "role": "user",
        "content": "this is a test request, write a short poem"
    }
])

print(response)

See how to call Huggingface,Bedrock,TogetherAI,Anthropic, etc.