MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions68,180 in github.com/BerriAI/litellm

⨍ Functions 68,180◇ Types & classes 10,037↳ Endpoints 1,734
↓ 43 callersFunctionmake_logger
Instantiate NewRelicLogger with NR agent calls mocked out.
tests/test_litellm/integrations/newrelic/test_newrelic.py:41
↓ 43 callersMethodreload
Clear the cache and re-load from GitLab.
litellm/integrations/gitlab/gitlab_prompt_manager.py:699
↓ 43 callersFunctionz
({userRole:e,accessToken:s,onCreateSuccess:n,isModalVisible:a,setModalVisible:d})
litellm/proxy/_experimental/out/_next/static/chunks/01_xjyxcb1uco.js:1
↓ 42 callersFunction_guardrail
(**overrides)
tests/test_litellm/proxy/guardrails/guardrail_hooks/test_repelloai.py:62
↓ 42 callersFunction_logger
(legacy_compat=True, team_metadata_keys=None)
tests/test_litellm/integrations/otel/test_otel_v2_logger.py:99
↓ 42 callersMethodfirst
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 42 callersMethoditems
(self)
litellm/router_strategy/budget_limiter.py:78
↓ 42 callersMethodprocess_mcp_request
Process and validate MCP request headers from the ASGI scope. This includes: 1. Extracting and validating authentication head
litellm/proxy/_experimental/mcp_server/auth/user_api_key_auth_mcp.py:123
↓ 42 callersMethodseek
(self, *args)
tests/test_litellm/llms/vertex_ai/files/test_vertex_ai_files_streaming.py:215
↓ 42 callersMethodsign_request
( self, headers: dict, optional_params: dict, request_data: dict, api_
litellm/llms/oci/chat/transformation.py:383
↓ 42 callersMethodtransform_anthropic_messages_request
( self, model: str, messages: List[Dict], anthropic_messages_optional_request_
litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py:653
↓ 41 callersFunctionR
({providerName:e,displayName:r})
litellm/proxy/_experimental/out/_next/static/chunks/01_xjyxcb1uco.js:1
↓ 41 callersFunction_simple_messages
()
tests/test_litellm/llms/anthropic/experimental_pass_through/context_management/test_compact.py:47
↓ 41 callersMethodabort
()
litellm/proxy/_experimental/out/_next/static/chunks/16.oisvgwzo8s.js:7
↓ 41 callersMethodenter
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 41 callersMethodget_config
Load config file Supports reading from: - .yaml file paths - LiteLLM connected DB - GCS - S3
litellm/proxy/proxy_server.py:3724
↓ 41 callersFunctiononClose
()
litellm/proxy/_experimental/out/_next/static/chunks/0mzw3maijoev6.js:1
↓ 40 callersMethodasync_post_call_streaming_iterator_hook
( self, user_api_key_dict, response, request_data )
tests/test_litellm/proxy/guardrails/test_deferred_guardrail_logging.py:847
↓ 40 callersMethodlabels
(self, *args, **kwargs)
tests/enterprise/litellm_enterprise/integrations/test_prometheus.py:493
↓ 40 callersMethodresponses
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 40 callersMethodstop
Stop the logging worker and clean up resources.
litellm/litellm_core_utils/logging_worker.py:338
↓ 40 callersMethodupsert
(self, where: Dict[str, Any], data: Dict[str, Any])
tests/test_litellm/repositories/test_repositories.py:115
↓ 39 callersMethod_ensure_access_token_async
Async version of _ensure_access_token
litellm/llms/vertex_ai/vertex_llm_base.py:1092
↓ 39 callersMethodasync_get_cache
( self, key: Any, parent_otel_span: Any = None, local_only: bool = False,
litellm/proxy/common_utils/user_api_key_cache.py:86
↓ 39 callersFunctiongenerate_mock_mcp_server_db_record
Generate a mock MCP server record from database
tests/test_litellm/proxy/management_endpoints/test_mcp_management_endpoints.py:35
↓ 38 callersFunctionA
litellm/proxy/_experimental/out/_next/static/chunks/0~-ovi6c4wjt1.js:1
↓ 38 callersMethod_reset_all_callbacks
Reset all callbacks to an empty list Note: this is an internal function and should be used sparingly.
litellm/litellm_core_utils/logging_callback_manager.py:322
↓ 38 callersMethodadd_update
Enqueue an update.
litellm/proxy/db/db_transaction_queue/base_update_queue.py:35
↓ 38 callersMethodbody
(self)
tests/local_testing/test_http_parsing_utils.py:22
↓ 38 callersMethodconsume
()
tests/llm_translation/test_llm_response_utils/test_convert_dict_to_chat_completion.py:1729
↓ 38 callersFunctioncreateQueryKeys
(resource: T)
ui/litellm-dashboard/src/app/(dashboard)/hooks/common/queryKeysFactory.ts:25
↓ 38 callersMethodget_azure_openai_client
( self, api_key: Optional[str], api_base: Optional[str], api_version: Optional
litellm/llms/azure/common_utils.py:398
↓ 38 callersMethodjson
Return JSON response data.
litellm/integrations/mock_client_factory.py:70
↓ 38 callersMethodnon_proxy_admin_allowed_routes_check
Checks if Non Proxy Admin User is allowed to access the route
litellm/proxy/auth/route_checks.py:229
↓ 38 callersMethodtag
(self, suffix: str = "")
tests/proxy_behavior/management/conftest.py:98
↓ 37 callersFunctionP
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0rdv7_7_95b-1.js:1
↓ 37 callersFunction_managed_files_hook
(store_side_effect: Any = None)
tests/pass_through_unit_tests/test_passthrough_managed_ids.py:83
↓ 37 callersFunctionapply_compact_20260112
Apply ``compact_20260112``; return a ``PolyfillResult``. See module docstring for the algorithm. Errors are best-effort: when the summary cal
litellm/llms/anthropic/experimental_pass_through/context_management/editors/compact.py:936
↓ 37 callersMethodemit
Emit one complete span: dedup, start, map attributes, status, end. Return the span, or ``None`` if it was deduplicated away. ``tracer``
litellm/integrations/otel/emitter.py:135
↓ 37 callersMethodget_cache
Retrieves the cached result for the given arguments. Args: *args: args to litellm.completion() or embedding()
litellm/caching/caching.py:571
↓ 37 callersMethodget_credentials
Return a boto3.Credentials object
litellm/llms/bedrock/base_aws_llm.py:185
↓ 37 callersFunctionget_model_info
Get a dict for the maximum tokens (context window), input_cost_per_token, output_cost_per_token for a given model. Parameters: - model
litellm/utils.py:5484
↓ 37 callersFunctionis_request_body_safe
Check if the request body is safe. A malicious user can set the api_base to their own domain and invoke POST /chat/completions to intercept
litellm/proxy/auth/auth_utils.py:335
↓ 37 callersFunctionlist
Sync: List all agents on the provider side.
litellm/interactions/agents/main.py:241
↓ 37 callersMethodread
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 37 callersFunctionvalidate_url
Validate a user-supplied URL and rewrite it to connect to a validated IP. Resolves the hostname, checks all resolved IPs against blocked net
litellm/litellm_core_utils/url_utils.py:231
↓ 36 callersFunctionH
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0rdv7_7_95b-1.js:1
↓ 36 callersFunctionQ
()
litellm/proxy/_experimental/out/_next/static/chunks/01_xjyxcb1uco.js:1
↓ 36 callersFunction_make_streaming
(**kwargs)
tests/test_litellm/responses/test_responses_websocket_all_providers.py:1293
↓ 36 callersMethodasync_set_cache
Asynchronously set cache using run_in_executor to avoid blocking the event loop. Compatible with Python 3.8+.
litellm/caching/s3_cache.py:102
↓ 36 callersMethodload_servers_from_config
Load the MCP Servers from the config Args: mcp_servers_config: Dictionary of MCP server configurations mcp_a
litellm/proxy/_experimental/mcp_server/mcp_server_manager.py:645
↓ 36 callersMethodpost_call
(self, original_response, input=None, api_key=None, additional_args={})
litellm/types/utils.py:3437
↓ 36 callersFunctionset
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0.4.bbjx7y007.js:141
↓ 36 callersFunctionuser_api_key_auth
Parent function to authenticate user api key / jwt token.
litellm/proxy/auth/user_api_key_auth.py:2385
↓ 35 callersMethodapply_guardrail
( self, inputs: dict, request_data: dict, input_type: str, **kwargs )
tests/test_litellm/llms/cohere/rerank/test_rerank_guardrail_handler.py:420
↓ 35 callersFunctionmap_finish_reason
(finish_reason: str)
litellm/litellm_core_utils/core_helpers.py:107
↓ 35 callersMethodmutate
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/058o-fyv9lb_l.js:10
↓ 35 callersMethodrerank
( self, model: str, query: str, documents: List[Union[str, Dict[str, Any]]],
litellm/llms/bedrock/rerank/handler.py:53
↓ 35 callersMethodsearch
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/0nnx~7-7e5t~1.js:1
↓ 35 callersMethodset_attributes
(self, span: Span, kwargs, response_obj: Optional[Any])
litellm/integrations/opentelemetry.py:2091
↓ 35 callersMethodtransform_request
Translate messages to anthropic format.
litellm/llms/anthropic/chat/transformation.py:1729
↓ 35 callersMethodtype
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 34 callersFunctionJ
(t)
litellm/proxy/_experimental/out/_next/static/chunks/03~yq9q893hmn.js:1
↓ 34 callersFunction_is_base64_encoded_unified_file_id
(b64_uid: str)
litellm/proxy/openai_files_endpoints/common_utils.py:20
↓ 34 callersFunction_make_spend_counter_cache
( *, redis_get_value=None, redis_get_side_effect=None, redis_increment_value=None, redis_i
tests/test_litellm/proxy/proxy_server/test_spend_counters.py:33
↓ 34 callersMethodasync_pre_call_hook
Mock pre-call hook that raises BlockedPiiEntityError
tests/mcp_tests/test_mcp_guardrails.py:50
↓ 34 callersFunctioneI
()
litellm/proxy/_experimental/out/_next/static/chunks/0~0su3wi_7f6-.js:1
↓ 34 callersMethodgetQueryCache
()
litellm/proxy/_experimental/out/_next/static/chunks/0n.a~e5dwfnkn.js:1
↓ 34 callersMethodindex
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 34 callersMethodmodel_dump
(self, mode="json", exclude_none=True)
tests/agent_tests/test_a2a_agent.py:27
↓ 34 callersMethodpost_call_success_hook
Allow user to modify outgoing data Covers: 1. /chat/completions 2. /embeddings 3. /image/generation
litellm/proxy/utils.py:2233
↓ 34 callersMethodtoArray
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 34 callersMethodtransform_request
( self, model: str, messages: List[AllMessageValues], optional_params: dict,
litellm/llms/oci/chat/transformation.py:529
↓ 33 callersFunction_
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 33 callersMethod_create_mcp_client
Create an MCPClient instance for the given server. Auth resolution (single place for all auth logic): 1. ``mcp_auth_header``
litellm/proxy/_experimental/mcp_server/mcp_server_manager.py:1786
↓ 33 callersFunction_make_client
(auth: UserAPIKeyAuth)
tests/test_litellm/proxy/memory/test_memory_endpoints.py:200
↓ 33 callersFunction_make_response
(payload: dict)
tests/test_litellm/proxy/guardrails/guardrail_hooks/test_cato_networks.py:342
↓ 33 callersFunction_patch_prisma
Patch the endpoint module's _require_prisma to return our fake.
tests/test_litellm/proxy/memory/test_memory_endpoints.py:221
↓ 33 callersMethod_update_kwargs_with_deployment
3 jobs: - Adds selected deployment, model_info and api_base to kwargs["metadata"] (used for logging) - Adds default litellm p
litellm/router.py:2897
↓ 33 callersFunctionacompletion
Asynchronously executes a litellm.completion() call for any of litellm supported llms (example gpt-4, gpt-3.5-turbo, claude-2, command-nightly)
litellm/main.py:401
↓ 33 callersFunctionanthropic_messages_pt
format messages for anthropic 1. Anthropic supports roles like "user" and "assistant" (system prompt sent separately) 2. The first messag
litellm/litellm_core_utils/prompt_templates/factory.py:2322
↓ 33 callersMethodapply_guardrail
( self, inputs, request_data, input_type, logging_obj=None )
tests/test_litellm/litellm_core_utils/test_realtime_streaming.py:1809
↓ 33 callersMethodauth_jwt
(self, token: str)
litellm/proxy/auth/handle_jwt.py:995
↓ 33 callersMethodclassify
Classify a prompt by complexity. Args: prompt: The user's prompt/message. system_prompt: Optional system pro
litellm/router_strategy/complexity_router/complexity_router.py:191
↓ 33 callersFunctionencrypt_value_helper
(value: str, new_encryption_key: Optional[str] = None)
litellm/proxy/common_utils/encrypt_decrypt_utils.py:19
↓ 33 callersFunctionget_policy_registry
Get the global PolicyRegistry singleton. Returns: The global PolicyRegistry instance
litellm/proxy/policy_engine/policy_registry.py:909
↓ 33 callersFunctionmake_kwargs
Build a minimal kwargs dict representative of a litellm callback invocation.
tests/test_litellm/integrations/newrelic/test_newrelic.py:47
↓ 33 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/bedrock/chat/converse_transformation.py:843
↓ 33 callersMethodshift
()
litellm/proxy/_experimental/out/_next/static/chunks/101az3fsw7lje.js:1
↓ 33 callersFunctiont
(t,e,r,o,i,a)
litellm/proxy/_experimental/out/_next/static/chunks/0ys10755n8os_.js:1
↓ 32 callersMethodasync_get_cache
Async get cache implementation. Used for embedding calls in async wrapper
litellm/caching/caching.py:606
↓ 32 callersMethodbuild
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0n.a~e5dwfnkn.js:1
↓ 32 callersFunctioncloneDeep
(s,o={})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 32 callersMethoddone
()
litellm/proxy/_experimental/out/_next/static/chunks/16.oisvgwzo8s.js:7
↓ 32 callersFunctionev
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0c4pfjjue0uc-.js:1
↓ 32 callersMethodevaluate
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 32 callersMethodfinally
(e)
litellm/proxy/_experimental/out/_next/static/chunks/16.oisvgwzo8s.js:4
↓ 32 callersMethodfrom_standard_logging_payload
(cls, payload: "StandardLoggingPayload")
litellm/integrations/otel/model/metadata.py:147
↓ 32 callersMethodgetValue
()
litellm/proxy/_experimental/out/_next/static/chunks/0.4.bbjx7y007.js:1
↓ 32 callersMethodget_mcp_client_ip
Extract client IP from a FastAPI request for MCP access control. Security: Only trusts X-Forwarded-For if: 1. use_x_forwarde
litellm/proxy/auth/ip_address_utils.py:248
← previousnext →301–400 of 68,180, ranked by callers