mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-28 04:04:31 +00:00
355f4a7c90
* fix(vertex_ai): Fixes issue where multimodal message without text was failing vertex calls Fixes https://github.com/BerriAI/litellm/issues/5515 * fix(azure.py): move to using httphandler for oidc token calls Fixes issue where ssl certificates weren't being picked up as expected Closes https://github.com/BerriAI/litellm/issues/5522 * feat: Allows admin to set a default_max_internal_user_budget in config, and allow setting more specific values as env vars * fix(proxy_server.py): fix read for max_internal_user_budget * build(model_prices_and_context_window.json): add regional gpt-4o-2024-08-06 pricing Closes https://github.com/BerriAI/litellm/issues/5540 * test: skip re-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.