litellm-mirror/litellm/proxy
2024-08-09 08:54:55 -07:00
..
_experimental bump: version 1.43.4 → 1.43.5 2024-08-08 23:47:01 -07:00
analytics_endpoints show correct key aliases on ui 2024-06-21 14:36:38 -07:00
auth fix(user_api_key_auth.py): Fixes https://github.com/BerriAI/litellm/issues/5111 2024-08-08 17:18:59 -07:00
common_utils Merge branch 'main' into litellm_support_lakera_config_thresholds 2024-08-06 22:47:13 -07:00
db (feat) stop eagerly evaluating fstring 2024-03-25 09:01:42 -07:00
example_config_yaml test- otel span recording 2024-07-11 08:47:16 -07:00
fine_tuning_endpoints use native endpoints 2024-08-03 16:52:43 -07:00
guardrails Merge branch 'main' into litellm_parallel_requests 2024-07-24 19:25:56 -07:00
health_endpoints fix email health checks 2024-08-06 15:59:26 -07:00
hooks fix(utils.py): handle scenario where model="azure/*" and custom_llm_provider="azure" 2024-08-02 17:48:53 -07:00
management_endpoints fix(management_helpers/utils.py): use user_default max_budget, budget duration on new user upsert during team member add 2024-08-08 19:14:43 -07:00
management_helpers fix(management_helpers/utils.py): use user_default max_budget, budget duration on new user upsert during team member add 2024-08-08 19:14:43 -07:00
openai_files_endpoints fix POST files 2024-07-31 16:27:59 -07:00
pass_through_endpoints fix pass through endpoint tests 2024-08-06 21:16:07 -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
secret_managers fix(aws_secret_manager.py): fix litellm license check 2024-07-03 22:07:48 -07:00
spend_tracking SpendLogsPayload- track user ip 2024-07-08 10:16:58 -07:00
tests docs cachedContent endpoint 2024-08-08 23:27:02 -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 add native cachedContents endpoint 2024-08-08 17:19:12 -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 feat(vertex_httpx.py): return vertex grounding, citation, and safety results 2024-08-09 08:54:55 -07:00
_super_secret_config.yaml docs(enterprise.md): cleanup docs 2024-07-15 14:52:08 -07:00
_types.py fix(proxy_server.py): respect internal_user_budget_duration for sso user 2024-08-08 17:28:28 -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 (feat) fix custom handler bug 2024-02-28 14:48:55 -08:00
custom_callbacks1.py fix: fix linting errors 2024-07-13 14:39:42 -07:00
custom_handler.py feat(proxy_server.py): support custom llm handler on proxy 2024-07-25 19:35:52 -07:00
enterprise feat(llama_guard.py): add llama guard support for content moderation + new async_moderation_hook endpoint 2024-02-17 19:13:04 -08:00
health_check.py fix linting errors on main 2024-07-18 13:32:48 -07:00
lambda.py
litellm_pre_call_utils.py use itellm.forward_traceparent_to_llm_provider 2024-08-01 18:07:38 -07:00
llamaguard_prompt.txt feat(llama_guard.py): allow user to define custom unsafe content categories 2024-02-17 17:42:47 -08:00
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 fix(prisma_migration.py): support decrypting variables in a python script 2024-06-28 16:31:37 -07:00
proxy_cli.py Merge pull request #5057 from BerriAI/litellm_rds_iam_auth 2024-08-06 10:44:33 -07:00
proxy_config.yaml add default_vertex_config 2024-08-08 17:19:12 -07:00
proxy_server.py fix(proxy_server.py): ensure internal_user params only apply to internal_user role 2024-08-08 17:50:29 -07:00
README.md
schema.prisma fix DB accept null values for api_base, user, etc 2024-07-23 16:33:04 -07:00
start.sh
utils.py Merge pull request #5058 from BerriAI/litellm_add_debug_statements_connecting_prisma 2024-08-05 20:53:55 -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.