mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-25 18:54:30 +00:00
ef6ac42658
* fix(proxy/_types.py): allow internal user to call api playground * fix(new_usage.tsx): cleanup tag based usage - only show for proxy admin not clear what tags internal user should be allowed to see * fix(team_endpoints.py): allow internal user view spend for teams they belong to * fix(team_endpoints.py): return team alias on `/team/daily/activity` API allows displaying team alias on ui * fix: fix linting error * fix(entity_usage.tsx): allow viewing top keys by team * fix(entity_usage.tsx): show alias, if available in breakdown allows entity alias to be easily displayed * Show usage by key (on all up, team, and tag usage dashboards) (#10152) * fix(entity_usage.tsx): allow user to select team in team usage tab * fix(new_usage.tsx): load all tags for filtering * fix(tag_management_endpoints.py): return dynamic tags from db on `/tag/list` * fix(litellm_pre_call_utils.py): support x-litellm-tags even if tag based routing not enabled * fix(new_usage.tsx): show breakdown of usage by api key on dashboard helpful when looking at spend by team * fix(networking.tsx): exclude litellm-dashboard team id's from calls adds noisy ui tokens to key activity * fix(new_usage.tsx): allow user to see activity by key on main tab * feat(internal_user_endpoints.py): refactor to use common_daily_activity function reuses same logic across teams/keys/tags Allows returning team_alias in api_keys consistently * fix(leftnav.tsx): swap old usage with new usage tab * fix(entity_usage.tsx): show breakdown of teams in daily spend chart * style(new_usage.tsx): show global usage tab if user is admin / has admin view * fix(new_usage.tsx): add disclaimer for new usage dashboard * fix(new_usage.tsx): fix linting error * Allow filtering usage dashboard by team + tag (#10150) * fix(entity_usage.tsx): allow user to select team in team usage tab * fix(new_usage.tsx): load all tags for filtering * fix(tag_management_endpoints.py): return dynamic tags from db on `/tag/list` * fix(litellm_pre_call_utils.py): support x-litellm-tags even if tag based routing not enabled * fix: fix linting error |
||
|---|---|---|
| .. | ||
| _experimental | ||
| analytics_endpoints | ||
| anthropic_endpoints | ||
| auth | ||
| batches_endpoints | ||
| common_utils | ||
| config_management_endpoints | ||
| credential_endpoints | ||
| db | ||
| example_config_yaml | ||
| fine_tuning_endpoints | ||
| guardrails | ||
| health_endpoints | ||
| hooks | ||
| management_endpoints | ||
| management_helpers | ||
| middleware | ||
| openai_files_endpoints | ||
| pass_through_endpoints | ||
| rerank_endpoints | ||
| response_api_endpoints | ||
| spend_tracking | ||
| swagger | ||
| types_utils | ||
| ui_crud_endpoints | ||
| vertex_ai_endpoints | ||
| .gitignore | ||
| __init__.py | ||
| _logging.py | ||
| _new_new_secret_config.yaml | ||
| _new_secret_config.yaml | ||
| _super_secret_config.yaml | ||
| _types.py | ||
| cached_logo.jpg | ||
| caching_routes.py | ||
| common_request_processing.py | ||
| custom_prompt_management.py | ||
| custom_sso.py | ||
| custom_validate.py | ||
| enterprise | ||
| health_check.py | ||
| lambda.py | ||
| litellm_pre_call_utils.py | ||
| llamaguard_prompt.txt | ||
| logo.jpg | ||
| mcp_tools.py | ||
| model_config.yaml | ||
| openapi.json | ||
| post_call_rules.py | ||
| prisma_migration.py | ||
| proxy_cli.py | ||
| proxy_config.yaml | ||
| proxy_server.py | ||
| README.md | ||
| route_llm_request.py | ||
| schema.prisma | ||
| start.sh | ||
| utils.py | ||
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.
Folder Structure
Routes
proxy_server.py- all openai-compatible routes -/v1/chat/completion,/v1/embedding+ model info routes -/v1/models,/v1/model/info,/v1/model_group_inforoutes.health_endpoints/-/health,/health/liveliness,/health/readinessmanagement_endpoints/key_management_endpoints.py- all/key/*routesmanagement_endpoints/team_endpoints.py- all/team/*routesmanagement_endpoints/internal_user_endpoints.py- all/user/*routesmanagement_endpoints/ui_sso.py- all/sso/*routes