mirror of
https://github.com/BerriAI/litellm.git
synced 2025-04-27 11:43:54 +00:00
b516cf21cb
* refactor(organization.tsx): initial commit with orgs tab refactor make it similar to 'Teams' tab - simplifies org management actions * fix(page.tsx): pass user orgs to component * fix(organization_view.tsx): fix to pull info from org info endpoint * feat(organization_endpoints.py): return org members when calling /org/info * fix(organization_view.tsx): show org members on info page * feat(organization_view.tsx): allow adding user to org via user email Resolves https://github.com/BerriAI/litellm/issues/8330 * fix(organization_endpoints.py): raise better error when duplicate user_email found in db * fix(organization_view.tsx): cleanup user_email for now not in initial org info - will need to prefetch * fix(page.tsx): fix getting user models on page load allows passing down the user models to org * fix(organizations.tsx): fix creating org on ui * fix(proxy/_types.py): include org created at and updated at cleans up ui * fix(navbar.tsx): cleanup * fix(organizations.tsx): fix tpm/rpm limits on org * fix(organizations.tsx): fix linting error * fix(organizations.tsx): fix linting \ * (Feat) - Add `/bedrock/meta.llama3-3-70b-instruct-v1:0` tool calling support + cost tracking + base llm unit test for tool calling (#8545) * Add support for bedrock meta.llama3-3-70b-instruct-v1:0 tool calling (#8512) * fix(converse_transformation.py): fixing bedrock meta.llama3-3-70b tool calling * test(test_bedrock_completion.py): adding llama3.3 tool compatibility check * add TestBedrockTestSuite * add bedrock llama 3.3 to base llm class * us.meta.llama3-3-70b-instruct-v1:0 * test_basic_tool_calling * TestAzureOpenAIO1 * test_basic_tool_calling * test_basic_tool_calling --------- Co-authored-by: miraclebakelaser <65143272+miraclebakelaser@users.noreply.github.com> * fix(general_settings.tsx): filter out empty dictionaries post fallback delete (#8550) Fixes https://github.com/BerriAI/litellm/issues/8331 * bump: version 1.61.3 → 1.61.4 * (perf) Fix memory leak on `/completions` route (#8551) * initial mem util test * fix _cached_get_model_info_helper * test memory usage * fix tests * fix mem usage --------- Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com> Co-authored-by: miraclebakelaser <65143272+miraclebakelaser@users.noreply.github.com> |
||
|---|---|---|
| .. | ||
| _experimental | ||
| analytics_endpoints | ||
| auth | ||
| batches_endpoints | ||
| common_utils | ||
| config_management_endpoints | ||
| db | ||
| example_config_yaml | ||
| fine_tuning_endpoints | ||
| guardrails | ||
| health_endpoints | ||
| hooks | ||
| management_endpoints | ||
| management_helpers | ||
| openai_files_endpoints | ||
| pass_through_endpoints | ||
| rerank_endpoints | ||
| spend_tracking | ||
| 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 | ||
| custom_sso.py | ||
| enterprise | ||
| health_check.py | ||
| lambda.py | ||
| litellm_pre_call_utils.py | ||
| llamaguard_prompt.txt | ||
| logo.jpg | ||
| 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