mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-26 03:04:13 +00:00
98c34a7e27
* fix(caching.py): set ttl for async_increment cache fixes issue where ttl for redis client was not being set on increment_cache Fixes https://github.com/BerriAI/litellm/issues/5609 * fix(caching.py): fix increment cache w/ ttl for sync increment cache on redis Fixes https://github.com/BerriAI/litellm/issues/5609 * fix(router.py): support adding retry policy + allowed fails policy via config.yaml * fix(router.py): don't cooldown single deployments No point, as there's no other deployment to loadbalance with. * fix(user_api_key_auth.py): support setting allowed email domains on jwt tokens Closes https://github.com/BerriAI/litellm/issues/5605 * docs(token_auth.md): add user upsert + allowed email domain to jwt auth docs * fix(litellm_pre_call_utils.py): fix dynamic key logging when team id is set Fixes issue where key logging would not be set if team metadata was not none * fix(secret_managers/main.py): load environment variables correctly Fixes issue where os.environ/ was not being loaded correctly * test(test_router.py): fix test * feat(spend_tracking_utils.py): support logging additional usage params - e.g. prompt caching values for deepseek * test: fix tests * test: fix test * test: fix test * test: fix test * test: fix test |
||
|---|---|---|
| .. | ||
| _experimental | ||
| analytics_endpoints | ||
| auth | ||
| common_utils | ||
| config_management_endpoints | ||
| db | ||
| example_config_yaml | ||
| fine_tuning_endpoints | ||
| guardrails | ||
| health_endpoints | ||
| hooks | ||
| management_endpoints | ||
| management_helpers | ||
| openai_files_endpoints | ||
| out | ||
| pass_through_endpoints | ||
| proxy_load_test | ||
| queue | ||
| rerank_endpoints | ||
| spend_tracking | ||
| tests | ||
| ui_crud_endpoints | ||
| vertex_ai_endpoints | ||
| .gitignore | ||
| __init__.py | ||
| _logging.py | ||
| _new_secret_config.yaml | ||
| _super_secret_config.yaml | ||
| _types.py | ||
| admin_ui.py | ||
| cached_logo.jpg | ||
| caching_routes.py | ||
| custom_callbacks.py | ||
| custom_callbacks1.py | ||
| custom_guardrail.py | ||
| custom_handler.py | ||
| enterprise | ||
| health_check.py | ||
| lambda.py | ||
| litellm_pre_call_utils.py | ||
| llamaguard_prompt.txt | ||
| logo.jpg | ||
| openapi.json | ||
| otel_config.yaml | ||
| 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.