litellm-mirror/litellm/proxy
2024-09-06 18:10:46 -07:00
..
_experimental ui new build 2024-09-06 18:10:46 -07:00
analytics_endpoints show correct key aliases on ui 2024-06-21 14:36:38 -07:00
auth fix(pass_through_endpoints): support bedrock agents via pass through (#5527) 2024-09-04 22:22:22 -07:00
common_utils add gcs bucket base 2024-08-30 10:41:39 -07:00
config_management_endpoints feat(ui): for adding pass-through endpoints 2024-08-15 21:58:11 -07:00
db refactor get_secret 2024-09-03 10:42:12 -07:00
example_config_yaml call spend logs endpoint 2024-08-30 16:35:07 -07:00
fine_tuning_endpoints use native endpoints 2024-08-03 16:52:43 -07:00
guardrails allow init guardrails with output parsing logic 2024-09-04 14:40:35 -07:00
health_endpoints fix email health checks 2024-08-06 15:59:26 -07:00
hooks v0 add rerank on litellm proxy 2024-08-27 17:28:39 -07:00
management_endpoints Merge pull request #5566 from BerriAI/litellm_ui_regen_keys 2024-09-06 18:05:51 -07:00
management_helpers feat(team_endpoints.py): return team member budgets in /team/info call 2024-08-28 19:14:01 -07:00
openai_files_endpoints feat(router.py): Support Loadbalancing batch azure api endpoints (#5469) 2024-09-02 21:32:55 -07:00
out bump: version 1.43.15 → 1.43.16 2024-08-15 23:04:30 -07:00
pass_through_endpoints LiteLLM Minor Fixes and Improvements (08/06/2024) (#5567) 2024-09-06 17:16:24 -07:00
proxy_load_test (fix) locust load test use uuid 2024-03-25 15:36:30 -07:00
queue docs(scheduler.md): add request prioritization to docs 2024-05-31 19:35:47 -07:00
rerank_endpoints v0 add rerank on litellm proxy 2024-08-27 17:28:39 -07:00
spend_tracking fix allow internal user to view their own usage 2024-09-05 12:53:44 -07:00
tests use chunk_processort 2024-09-02 15:51:52 -07:00
ui_crud_endpoints ui - add Create, get, delete endpoints for IP Addresses 2024-07-09 15:12:08 -07:00
vertex_ai_endpoints fix(pass_through_endpoints): support bedrock agents via pass through (#5527) 2024-09-04 22:22:22 -07:00
.gitignore
__init__.py
_logging.py fix(_logging.py): fix timestamp format for json logs 2024-06-20 15:20:21 -07:00
_new_secret_config.yaml LiteLLM Minor Fixes and Improvements (08/06/2024) (#5567) 2024-09-06 17:16:24 -07:00
_super_secret_config.yaml docs(enterprise.md): cleanup docs 2024-07-15 14:52:08 -07:00
_types.py Merge pull request #5566 from BerriAI/litellm_ui_regen_keys 2024-09-06 18:05:51 -07:00
admin_ui.py
cached_logo.jpg (feat) use hosted images for custom branding 2024-02-22 14:51:40 -08:00
caching_routes.py feat - refactor team endpoints 2024-06-15 11:40:36 -07:00
custom_callbacks.py LiteLLM Minor fixes + improvements (08/04/2024) (#5505) 2024-09-04 22:16:55 -07:00
custom_callbacks1.py v0 add rerank on litellm proxy 2024-08-27 17:28:39 -07:00
custom_guardrail.py v0 add rerank on litellm proxy 2024-08-27 17:28:39 -07:00
custom_handler.py feat(proxy_server.py): support custom llm handler on proxy 2024-07-25 19:35:52 -07:00
enterprise
health_check.py fix(health_check.py): return 'missing mode' error message, if error with health check, and mode is missing 2024-08-16 17:24:29 -07:00
lambda.py
litellm_pre_call_utils.py fix allow setting language per call to presidio 2024-09-04 12:46:59 -07:00
llamaguard_prompt.txt
logo.jpg (feat) admin ui custom branding 2024-02-21 17:34:42 -08:00
openapi.json
otel_config.yaml
post_call_rules.py
prisma_migration.py refactor secret managers 2024-09-03 10:58:02 -07:00
proxy_cli.py refactor secret managers 2024-09-03 10:58:02 -07:00
proxy_config.yaml fix init presidio guardrail 2024-09-04 15:22:37 -07:00
proxy_server.py LiteLLM Minor Fixes and Improvements (08/06/2024) (#5567) 2024-09-06 17:16:24 -07:00
README.md
route_llm_request.py v0 add rerank on litellm proxy 2024-08-27 17:28:39 -07:00
schema.prisma fix created_at and updated_at not existing error 2024-08-26 21:04:39 -07:00
start.sh
utils.py fix use view for getting tag usage 2024-09-06 16:28:24 -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.