MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 27 callersMethodasync_success_handler
( self, result: TranscriptionResponse, start_time: datetime.datetime, end_time: datetime.datetime
tests/unit/litellm_core_utils/audio_utils/test_transcription_streaming.py:70
↓ 27 callersFunctionbatch_file
(mark: str, records: int, separator: bytes = b"\n", ending: bytes = b"\n")
tests/integration/management/_batch_file_caps.py:60
↓ 27 callersMethodbegin_shutdown
(self)
tests/integration/_support/process.py:372
↓ 27 callersMethodcalculate_usage
( cls, completion_response: GenerateContentResponseBody | BidiGenerateContentServerMessage,
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:2684
↓ 27 callersMethodcall
(self, py: Python<'py>, args: A)
litellm-rust/crates/callbacks-legacy-python/src/python.rs:102
↓ 27 callersFunctioncall_cancel
( harness: CancelHarness, batch_id: str, *, provider: Optional[str] = None, user: Optional
tests/unit/proxy/batches_endpoints/test_endpoints.py:2560
↓ 27 callersMethodchild
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 27 callersFunctionclassify_list_exception
Classify a per-server listing failure into exactly one outcome. Total: an exception this function cannot recognize is the gateway's own fault (``i
litellm/proxy/mcp_server/faults/list_outcomes.py:182
↓ 27 callersMethodclear
(self)
litellm/proxy/db/db_lookup_gate.py:47
↓ 27 callersFunctioncollect_event_types
(stream: object)
tests/unit/test_router/core/streaming_helpers.py:443
↓ 27 callersFunctioncost_per_web_search_request
Calculate the cost of web search requests for X.AI models. Counts invocations from usage.server_side_tool_usage_details.web_search_calls.
litellm/llms/xai/cost_calculator.py:139
↓ 27 callersMethodcreate
(self, data: Mapping[str, object])
litellm/proxy/search_endpoints/search_tool_registry.py:38
↓ 27 callersFunctioncreate_audit_log_for_update
Create an audit log for an object.
litellm/proxy/management_helpers/audit_logs.py:277
↓ 27 callersFunctiondestination_for
The destination ``params`` names for ``callback_name``, or ``None``. ``None`` means the caller configured nothing usable for this backend, so the
litellm/integrations/otel/presets/destinations.py:205
↓ 27 callersFunctionensure_optional_import
(module: str)
litellm/litellm_core_utils/optional_imports.py:4
↓ 27 callersFunctionexchange_token_with_server
( request: Request, mcp_server: MCPServer, grant_type: str, code: str | None, redirect_uri
litellm/proxy/mcp_server/discoverable_endpoints.py:1260
↓ 27 callersMethodexec
( self, cmd: Sequence[str], *, env: Mapping[str, str] | None = None, c
litellm/harness/sandbox/base.py:33
↓ 27 callersMethodfetch
(self, user_id: str)
tests/unit/proxy/mcp_server/outbound_credentials/test_sso_assertion_refresher.py:95
↓ 27 callersMethodfrom_client
(client: &Bound<'_, PyAny>)
litellm-rust/crates/python-bridge/src/secrets/runtime.rs:94
↓ 27 callersMethodfrom_str
(json: str)
litellm/litellm_core_utils/tokenizer.py:239
↓ 27 callersMethodget_cost_for_built_in_tools
Get the cost of using built-in tools. Supported tools: - Web Search - File Search - Vector Store (Azure)
litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py:82
↓ 27 callersFunctionget_end_user_id_from_request_body
( request_body: Mapping[str, object], request_headers: Mapping[str, object] | None = None )
litellm/proxy/auth/auth_utils.py:1996
↓ 27 callersMethodget_mcp_server_by_id
Get the MCP Server from the server id.
litellm/proxy/mcp_server/mcp_server_manager.py:7388
↓ 27 callersFunctionget_nested_value
Retrieves a value from a nested dictionary using dot notation. Args: data: The dictionary to search in key_path: The path to
litellm/litellm_core_utils/dot_notation_indexing.py:32
↓ 27 callersFunctionget_oci_base_url
Return the OCI inference base URL, respecting any explicit api_base override. If ``api_base`` already ends with a fully-formed OCI action path
litellm/llms/oci/common_utils.py:316
↓ 27 callersFunctionget_redis_async_client
( connection_pool: async_redis.BlockingConnectionPool | None = None, **env_overrides, )
litellm/_redis.py:863
↓ 27 callersFunctionget_secret_bool
Guarantees response from 'get_secret' is either boolean or none. Used for fixing linting errors. Args: secret_name: The name of the
litellm/secret_managers/main.py:336
↓ 27 callersFunctionget_team_membership
Returns team membership object if user is member of team. Do a isolated check for team membership vs. doing a combined key + team + user + t
litellm/proxy/auth/auth_checks.py:2764
↓ 27 callersMethodinstrument
(&self, future: F)
litellm-rust/crates/tracing/src/lib.rs:90
↓ 27 callersMethodis_agent_allowed
Check if a specific agent is allowed for the given user/key. Args: agent_id: The agent ID to check user_api_
litellm/proxy/agent_endpoints/auth/agent_permission_handler.py:210
↓ 27 callersMethodload
(self, loads: _TokenizerLoads, loop: asyncio.AbstractEventLoop)
litellm/proxy/proxy_server.py:15575
↓ 27 callersFunctionload_settings
()
litellm/proxy/telemetry/settings.py:56
↓ 27 callersMethodlog_pre_api_call
(self, model, messages, kwargs)
tests/unit/proxy/test_proxy_server.py:1223
↓ 27 callersMethodlog_pre_api_call
(self, model, messages, kwargs)
tests/unit/router_strategy/test_complexity_router.py:17523
↓ 27 callersFunctionlone
(**arguments: object)
tests/unit/test_router/core/test_parity_cooldown_service_model.py:143
↓ 27 callersFunctionmarker
()
tests/integration/routing/test_fallback_hop_foreign_encrypted_reasoning.py:436
↓ 27 callersMethodmaybe_inject_cache_control
Extract cache_control_injection_points from kwargs and apply if present. Configured points are applied even when the client marked its own
litellm/integrations/anthropic_cache_control_hook.py:1799
↓ 27 callersFunctionmine
(plane: ControlPlane, credential_id: str)
tests/integration/_support/bedrock_discovery.py:230
↓ 27 callersFunctionmint
(engine: JwtBearerTokenExchangeEngine, spec: TokenExchangeSpec)
tests/unit/llms/base_llm/auth/test_token_exchange.py:244
↓ 27 callersMethodmodel_dump
(self)
litellm/router_strategy/budget_limiter.py:133
↓ 27 callersMethodmodel_dump
(self)
tests/unit/llms/azure/test_azure_fine_tuning_api.py:27
↓ 27 callersFunctionnew_marker
()
tests/integration/routing/test_payment_required_mapping.py:56
↓ 27 callersFunctionopen_sse_before_first_byte
Write SSE keepalive comments while the upstream LLM call is still in flight. The whole time-to-first-token is spent inside `produce_response`: th
litellm/proxy/common_request_processing.py:1688
↓ 27 callersMethodplugins
( self, kind: Literal["auto"] )
litellm/router_api.py:1093
↓ 27 callersMethodpost_call_failure_hook
(self, **kwargs)
tests/unit/proxy/test_common_request_processing.py:11582
↓ 27 callersMethodpost_call_response_headers_hook
Calls async_post_call_response_headers_hook on all CustomLogger callbacks. Merges all returned header dicts (later callbacks override
litellm/proxy/utils.py:4666
↓ 27 callersMethodprocess_input_messages
(self, data, guardrail_to_apply, litellm_logging_obj=None)
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_unified_guardrail.py:101
↓ 27 callersMethodprocessor_data
The exact `data` dict the processor was constructed with.
tests/unit/proxy/video_endpoints/test_endpoints.py:130
↓ 27 callersFunctionr
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 27 callersMethodrecreate_prisma_client
Disconnect and reconnect the Prisma client with a new database URL. Kills the old engine subprocess directly (SIGTERM → SIGKILL) rather than
litellm/proxy/db/prisma_client.py:602
↓ 27 callersMethodreject
A flat rejection count cannot separate a connection that went away from a body the provider finished sending and the rules turned down, and th
tests/e2e/provider_cache.py:650
↓ 27 callersFunctionremote
`client` with `RedisCache`'s default TTL when `litellm.default_redis_ttl` is unset.
litellm-rust/crates/redis-store/tests/support/mod.rs:39
↓ 27 callersFunctionrequest_json
(request: Request)
tests/integration/_support/safeguards_rig.py:350
↓ 27 callersFunctionrun_message
(call: MessagesCall)
litellm-rust/crates/inference-messages/tests/messages/main.rs:120
↓ 27 callersFunctionset_hidden_params
(obj: object, hidden_params: dict[str, object] | HiddenParams)
litellm/litellm_core_utils/hidden_params.py:135
↓ 27 callersFunctionsigv4_deployment
( scenario: Scenario, key: str, secret: str, region: str, *, model_name: str = "bedroc
tests/integration/_support/bedrock_discovery.py:169
↓ 27 callersFunctiont8
(e,t,s,r,a)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:2
↓ 27 callersFunctiontext_delta
(text: str)
tests/unit/test_router/core/streaming_helpers.py:255
↓ 27 callersFunctiontimed
(operation: Callable[[], T])
tests/integration/_support/timing.py:13
↓ 27 callersMethodtoValue
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 27 callersMethodtx
(self)
litellm/proxy/management_helpers/access_group_team_sync.py:99
↓ 27 callersMethodui_friendly_name
()
tests/unit/proxy/guardrails/test_guardrail_endpoints.py:1039
↓ 27 callersFunctionupsert_budget_and_membership
Apply a merge-patch of per-member budget fields to a team membership. ``budget_patch`` holds only the budget columns the caller explicitly s
litellm/proxy/management_endpoints/common_utils.py:628
↓ 27 callersFunctionwire_assistant
(request: Request, position: int = 1)
tests/integration/providers/_tool_search_support.py:332
↓ 27 callersFunctionwith_fields
(call: MessagesCall, fields: Value)
litellm-rust/crates/inference-messages/tests/messages/main.rs:42
↓ 26 callersFunctionX
()
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 26 callersFunction_akto
(event_hook, **kwargs)
tests/unit/proxy/guardrails/guardrail_hooks/akto/test_akto.py:503
↓ 26 callersMethod_arm_deferred_stream_dispatch
Streaming with post-call guardrails active: attach a closure that ProxyLogging._fire_deferred_stream_logging fires after all guardrai
litellm/proxy/common_request_processing.py:4403
↓ 26 callersFunction_armor_post_mock
(payload)
tests/unit/proxy/guardrails/guardrail_hooks/test_model_armor.py:3882
↓ 26 callersFunction_assert_answered
(family: _Family, response: httpx.Response, marker: str)
tests/integration/providers/test_malformed_tools_wire.py:524
↓ 26 callersFunction_b64
(xml: str)
tests/unit/proxy/management_endpoints/test_saml_sso.py:176
↓ 26 callersFunction_build_responses_kwargs
Build the kwargs dict to pass directly to litellm.responses() / litellm.aresponses().
litellm/llms/anthropic/messages/responses_adapters/handler.py:279
↓ 26 callersFunction_build_signed_response
( key_pem: str, cert_pem: str, *, in_response_to: str | None = None, response_level_in_res
tests/unit/proxy/management_endpoints/test_saml_sso.py:104
↓ 26 callersFunction_catalog_row
(name="initial")
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:17925
↓ 26 callersFunction_chat
( rig: Rig, text: str, *, key: str | None = None, headers: dict[str, str] | None = None, **extra: object )
tests/integration/observability/test_straiker_v3_platform.py:461
↓ 26 callersFunction_chat_body
( model: str, prompt: str, markers: frozenset[Marker], *, stream: bool = False, with_tools: bool = False )
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:340
↓ 26 callersFunction_create
( replica: Gateway, model: str, key: str, *, path: str = "/v1beta/interactions", backg
tests/integration/spend/test_background_interaction_settlement.py:253
↓ 26 callersFunction_delta_text
(item)
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_unified_guardrail.py:1009
↓ 26 callersFunction_full_grant
()
tests/unit/proxy/mcp_server/outbound_credentials/test_envelope.py:68
↓ 26 callersFunction_get_call_stack_info
Get the function names of the nearest meaningful callers of the cache method. Frames that merely forward the call (this module's circuit-bre
litellm/caching/redis_cache.py:182
↓ 26 callersFunction_get_redis_client_logic
Common functionality across sync + async redis client implementations
litellm/_redis.py:579
↓ 26 callersFunction_llm_call
(**overrides)
tests/unit/integrations/otel/test_otel_v2_vendor_mappers.py:39
↓ 26 callersFunction_make_guardrail
(**overrides)
tests/unit/proxy/guardrails/test_llm_as_a_judge.py:32
↓ 26 callersFunction_make_perm
(**kwargs: Any)
tests/unit/proxy/mcp_server/test_mcp_tool_search.py:57
↓ 26 callersFunction_make_regenerate_user_api_key_dict
()
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:13373
↓ 26 callersFunction_make_trusted_request
Build a request-like object whose same-origin is ``base_url``. ``get_request_base_url`` defers to ``request.base_url`` unless the caller is a
tests/unit/proxy/mcp_server/test_byok_oauth_endpoints.py:1376
↓ 26 callersFunction_marker
()
tests/integration/observability/test_signoz_delivery.py:37
↓ 26 callersFunction_mock_response
(payload: dict, status_code: int = 200)
tests/unit/llms/dashscope/test_dashscope_video_transformation.py:49
↓ 26 callersFunction_ok_response
()
tests/unit/integrations/test_s3_v2.py:3090
↓ 26 callersFunction_patch_user_connection_env
Per-user env: credential in memory, prisma table answering find_many with rows, and a real in-memory cache for device-flow + credential caching.
tests/unit/proxy/credential_endpoints/test_endpoints.py:2166
↓ 26 callersFunction_per_user_credential
( name: str = "copilot-cred", host: str | None = None, )
tests/unit/proxy/credential_endpoints/test_endpoints.py:2097
↓ 26 callersFunction_prepare_mcp_server_headers
Build auth and extra headers for a server. ``scope_servers`` is the full server list a fan-out handler iterates. Passing it lets the client-f
litellm/proxy/mcp_server/operations.py:996
↓ 26 callersFunction_provider_response
(endpoint: Endpoint, _scenario_id: str, reply: str, stream: bool)
tests/integration/observability/_logging_only_scope_support.py:530
↓ 26 callersMethod_router
( self, fallbacks: list[dict[str, object]] | None, model_group_alias: dict[str, str] |
tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py:9798
↓ 26 callersMethod_run
(config, messages)
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_transformation.py:998
↓ 26 callersFunction_s3_config
(path: Path, sink_url: str, extra: Mapping[str, JsonValue])
tests/integration/observability/test_s3_v2_upload_fanout.py:67
↓ 26 callersFunction_teardown_batch_upload_endpoint
()
tests/unit/proxy/openai_files_endpoint/test_files_endpoint.py:4341
↓ 26 callersFunction_update_single_user_helper
Helper function to update a single user. Used by both user_update and bulk_user_update endpoints. Returns the updated user data or raise
litellm/proxy/management_endpoints/internal_user_endpoints.py:1551
↓ 26 callersFunction_warnings
(caplog: pytest.LogCaptureFixture)
tests/unit/proxy/utils/proxy_logging/test_guardrail_pipeline.py:2248
↓ 26 callersMethodacreate_batch
(self, model: str, **kwargs: object)
litellm/router.py:279
← previousnext →1,901–2,000 of 202,479, ranked by callers