MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 32 callersFunction_delivered
(rig: _Rig, marker: str)
tests/integration/providers/test_malformed_tools_wire.py:496
↓ 32 callersFunction_entity_params
(query_name: str, entity_id: str)
tests/unit/proxy/management_endpoints/test_daily_activity_routes.py:630
↓ 32 callersMethod_get_auth_headers
Generate authentication headers based on auth type.
litellm/mcp_client/client.py:938
↓ 32 callersFunction_id_jag_config
()
tests/unit/proxy/mcp_server/outbound_credentials/test_resolver.py:72
↓ 32 callersFunction_make_mock_response
( content: str, prompt_tokens: int = 50, completion_tokens: int = 100, )
tests/unit/llms/anthropic/messages/context_management/test_compact.py:83
↓ 32 callersFunction_make_single_compress_response
( compressed_context: str = "compressed summary", original_tokens: int = 1000, compressed_tokens:
tests/unit/proxy/guardrails/guardrail_hooks/test_compresr.py:77
↓ 32 callersFunction_make_user_api_key_dict
( user_id: str = "user-123", team_id: str = "team-abc", user_email: str = "user@example.com",
tests/unit/proxy/guardrails/test_mcp_jwt_signer.py:27
↓ 32 callersFunction_mock_response
(action: str, turn_id: str = "turn-1", schema_version: str = "1", **extra)
tests/unit/proxy/guardrails/guardrail_hooks/test_straiker.py:37
↓ 32 callersFunction_new_identity
()
tests/integration/spend/test_autorouter_session_rollup.py:54
↓ 32 callersFunction_one_delivery
(rig: _Rig, marker: str, target: str)
tests/integration/providers/test_malformed_tools_wire.py:500
↓ 32 callersFunction_payload
(**overrides)
tests/unit/integrations/otel/test_otel_v2_logger.py:90
↓ 32 callersFunction_record
( team_id="team-a", team_alias=None, model="gpt-4o", model_group=None, status="success",
tests/unit/integrations/newrelic/test_newrelic_metrics.py:34
↓ 32 callersMethod_request
(self, model: str)
tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py:9830
↓ 32 callersFunction_scan
Collapses "the scan found nothing to do" to None so the reject-mode cases read plainly.
tests/unit/proxy/openai_files_endpoint/test_batch_guardrails.py:83
↓ 32 callersFunction_stream_chunk
(content, finish_reason=None, index=0)
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_unified_guardrail.py:980
↓ 32 callersMethodaccept
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 32 callersMethodadd
(self, chunk: ModelResponseStream)
litellm/llms/bedrock/passthrough/transformation.py:249
↓ 32 callersFunctionahealth_check
Support health checks for different providers. Return remaining rate limit, etc. Returns: { "x-ratelimit-remaining-reque
litellm/main.py:9424
↓ 32 callersFunctionanswer
(marker: str)
tests/integration/_support/bedrock_runtime_peer.py:56
↓ 32 callersFunctionanswered
(endpoint: Endpoint, stream: bool, response: httpx.Response)
tests/integration/providers/_gemini_long_decode_support.py:496
↓ 32 callersMethodapply_guardrail
(self, inputs, request_data, input_type, logging_obj=None)
tests/unit/integrations/test_custom_guardrail.py:2402
↓ 32 callersFunctionarize_destination
(**rates: str)
tests/unit/integrations/otel/test_otel_v2_destinations.py:1177
↓ 32 callersFunctionassert_client_error
(result: StreamingResponse, context: str)
tests/e2e/e2e_http.py:262
↓ 32 callersMethodatext_completion
(self, *args: object, **kwargs: object)
litellm/router_rust/core.py:2577
↓ 32 callersMethodaudio_transcriptions
( self, model: str, audio_file: FileTypes, optional_params: dict, lite
litellm/llms/custom_httpx/llm_http_handler.py:2095
↓ 32 callersFunctionauthenticate_user
Authenticate a user and generate an API key for UI access. This function handles two login scenarios: 1. Admin login using UI_USERNAME a
litellm/proxy/auth/login_utils.py:228
↓ 32 callersFunctionbuild
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_streaming_characterization_responses.py:76
↓ 32 callersFunctioncall
(server: RecordingServer, *, asynchronous: bool = True, **kwargs: object)
tests/test_litellm_rust/messages/data.py:51
↓ 32 callersMethodcheck_responses_cost
Check if background responses are complete and track their cost. - Get all status="queued" or "in_progress" and file_purpose="respons
enterprise/litellm_enterprise/proxy/common_utils/check_responses_cost.py:516
↓ 32 callersMethodchunk_parser
Parse a Responses API streaming chunk and convert to OpenAI format. Args: chunk: Dict containing the Responses API event
litellm/completion_extras/litellm_responses_transformation/transformation.py:2471
↓ 32 callersFunctioncloneDeep
(s,o={})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 32 callersFunctionconvert_content_list_to_str
- handles scenario where content is list and not string - content list is just text, and no images Motivation: mistral api + azure ai do
litellm/litellm_core_utils/prompt_templates/common_utils.py:342
↓ 32 callersFunctioncreate_tool_function
Create a tool function for an OpenAPI operation. This function creates an async tool function that can be called with keyword arguments. Para
litellm/proxy/mcp_server/openapi_to_mcp_generator.py:612
↓ 32 callersFunctioncut
The error the bridge iterator raises when its stream breaks (before output when nothing was generated).
tests/unit/test_router/core/test_streaming_characterization_responses.py:54
↓ 32 callersMethoddecompress
(self, data: bytes, /, max_length: int)
litellm/proxy/middleware/request_body_decompression_middleware.py:53
↓ 32 callersFunctiondismissFeedbackPopup
(page: PlaywrightPage)
tests/e2e/ui/helpers/navigation.ts:54
↓ 32 callersFunctionencode
Return a urlsafe-base64 managed ID string (trailing ``=`` stripped).
litellm/proxy/pass_through_endpoints/managed_id_codec.py:40
↓ 32 callersFunctionfn
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 32 callersFunctionfresh_marker
()
tests/integration/providers/_mantle_gpt_prompt_cache_support.py:166
↓ 32 callersMethodgenerate_key
( self, *, user_id: str, mcp_servers: list[str] | None, mcp_access_gro
tests/e2e/mcp/mcp_client.py:272
↓ 32 callersFunctionget_call_types_for_route
Get the CallTypes for a given API route. Supports both exact keys and dynamic patterns (e.g. /a2a/my-agent/message/send matches /a2a/{ag
litellm/litellm_core_utils/api_route_to_call_types.py:61
↓ 32 callersFunctionget_tracer
(provider: TracerProvider, name: str = LITELLM_TRACER_NAME)
litellm/integrations/otel/plumbing/providers.py:1764
↓ 32 callersFunctionhoist_developer_messages_into_leading_system_message
Place instructions for an OpenAI-compatible model whose chat template allows a single system message and only at the start: developer message
litellm/llms/base_llm/base_utils.py:744
↓ 32 callersMethodinfo
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 32 callersMethodis
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 32 callersFunctionis_base64_encoded_unified_file_id
(b64_uid: object)
litellm/proxy/openai_files_endpoints/common_utils.py:142
↓ 32 callersFunctionkey_spend
(key: str)
tests/integration/spend/_background_responses.py:230
↓ 32 callersMethodlabels
(self, *labelvalues: str)
tests/unit/integrations/test_prometheus_series_cardinality.py:233
↓ 32 callersMethodmodel_dump
(self)
litellm/proxy/management_endpoints/team_endpoints.py:317
↓ 32 callersFunctionn
()
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 32 callersFunctiononly_request
(server: &MockServer)
litellm-rust/crates/inference-messages/tests/support/mod.rs:56
↓ 32 callersFunctionopenai_error_type
OpenAI types ``error.type`` as a required string, so an exception carrying none falls back to the type its status code stands for.
litellm/proxy/common_utils/openai_error_payload.py:100
↓ 32 callersFunctionprepare_context
( user_api_key_auth: UserAPIKeyAuth | None = None, mcp_auth_header: str | None = None, mcp_servers
litellm/proxy/mcp_server/operations.py:3717
↓ 32 callersFunctionprocess_audio_file
Common utility function to process audio files for audio transcription APIs. Handles various input types: - File paths (str, os.PathLike
litellm/litellm_core_utils/audio_utils/utils.py:50
↓ 32 callersMethodprocess_output_streaming_response
Process output streaming response by applying guardrails to text content. Mirrors the Chat Completions handler pattern: extract text
litellm/llms/openai/responses/guardrail_translation/handler.py:1234
↓ 32 callersMethodquery
( self, statement: LiteralString | sql.Composed, params: tuple[Scalar, ...] = () )
tests/e2e/migrations/database.py:64
↓ 32 callersMethodrows
(self, count: int, where: str = "TRUE", seconds: int = 70)
tests/integration/spend/test_spend_logs_metadata_fields.py:294
↓ 32 callersFunctionscripted
(scenario: Scenario, response: JsonResponse | SseResponse)
tests/integration/caching/response_cache_case.py:255
↓ 32 callersFunctionset_request_root_span
Anchor the request's root (server) span for explicit child parenting. No-ops for a non-recordable span so a bad capture can never replace a good
litellm/integrations/otel/plumbing/context.py:67
↓ 32 callersFunctionshould_redact_message_logging
Determine if message logging should be redacted. Priority order: 1. Dynamic parameter (turn_off_message_logging in request) 2. Heade
litellm/litellm_core_utils/redact_messages.py:712
↓ 32 callersFunctionstem
()
tests/integration/_support/bedrock_discovery.py:56
↓ 32 callersFunctionsupports_factory
Check if the given model supports function calling and return a boolean value. Parameters: model (str): The model name to be checked.
litellm/utils.py:3429
↓ 32 callersFunctiont
()
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 32 callersMethodtoArray
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 32 callersMethodtrigger
(self)
litellm/proxy/common_utils/scheduled_job_stagger.py:85
↓ 32 callersFunctionvalidate_trusted_redirect_uri
Accept ``redirect_uri`` when it is (a) same-origin with the proxy's own request origin, (b) loopback, (c) listed in the ``MCP_TRUSTED_REDIRECT
litellm/proxy/mcp_server/oauth_utils.py:701
↓ 32 callersFunctionwire_server
(respond: Callable[[Request], Reply], port: int = 0, *, policy_edge: bool = True)
tests/integration/observability/_logging_only_scope_support.py:233
↓ 32 callersMethodwrite
(self, path: str, data: bytes)
tests/unit/harness/core_fakes.py:87
↓ 31 callersFunctionG
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 31 callersFunction_build_logger
(**overrides)
tests/unit/integrations/test_azure_sentinel.py:306
↓ 31 callersFunction_deployment
(scenario: Scenario, provider: Provider, rig: Rig)
tests/integration/providers/test_anthropic_refusal_stop_details_wire.py:218
↓ 31 callersFunction_emit_llm
Drive the real boundary flow: open at ``pre_call`` then close at the async callback. ``ambient``, if given, is the span that is the active OTel co
tests/unit/integrations/otel/test_otel_v2_logger.py:140
↓ 31 callersFunction_event
(event_type: str, **fields: object)
tests/unit/llms/meta/realtime/test_meta_realtime_transformation.py:38
↓ 31 callersMethod_fan_out
( dest_exporter: InMemorySpanExporter, trace_id: int | None = None, global_exporter: I
tests/unit/integrations/otel/test_otel_v2_destinations.py:1207
↓ 31 callersFunction_function_tool
(defer_loading: JsonValue | EllipsisType = True)
tests/integration/providers/test_responses_bridge_tool_search_wire.py:105
↓ 31 callersFunction_hook
( general_settings: Mapping[str, object] | None = None, signing_key: str | None = _UNIT_TEST_SALT_KEY )
tests/unit/test_responses_id_security.py:773
↓ 31 callersFunction_id_token
A distinct token per call. Two mints with the same claims in the same second would encode identically, which would let a test that means "the rene
tests/unit/proxy/mcp_server/outbound_credentials/test_sso_assertion_refresher.py:65
↓ 31 callersFunction_make_guardrail
(**kwargs)
tests/unit/proxy/guardrails/guardrail_hooks/test_compresr.py:66
↓ 31 callersFunction_make_mock_response
Build a minimal mock ResponsesAPIResponse.
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:1336
↓ 31 callersFunction_make_request
(parent_otel_span=None, path="/chat/completions", headers=())
tests/unit/proxy/proxy_server/test_exception_handlers.py:39
↓ 31 callersFunction_make_row
Build a Prisma-like row object.
tests/unit/proxy/memory/test_memory_endpoints.py:23
↓ 31 callersFunction_midnight
(day)
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:1141
↓ 31 callersFunction_replay
(hops: Sequence[httpx.Response], sent: list[dict[str, object]])
tests/unit/llms/vertex_ai/gemini/test_long_decode.py:94
↓ 31 callersFunction_run
(repo: Path, bin_dir: Path, extra_env: dict[str, str])
tests/unit/test_pre_commit_lint.py:143
↓ 31 callersFunction_safe_response
(url: str = CHAT_URL)
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:79
↓ 31 callersFunction_sent
(observed: tuple[dict[str, JsonValue], ...])
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:751
↓ 31 callersFunction_serve
(query_raw, rows: list[dict[str, Any]], total: int | None = None)
tests/unit/proxy/management_endpoints/management_v1/test_budgets.py:84
↓ 31 callersMethod_sse_chunks
(self, tool_name, tool_id="tu_1")
tests/unit/proxy/guardrails/guardrail_hooks/test_tool_permission.py:3572
↓ 31 callersFunction_windowed_row
(effective_from=None, effective_to=None, **overrides)
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:1128
↓ 31 callersMethodallows
Team admin is checked before org admin, so only callers off the roster pay for the org lookup.
litellm/proxy/management/teams/authz.py:25
↓ 31 callersMethodarun
(self, prompt: str)
litellm/harness/runtime.py:750
↓ 31 callersFunctionas_str
(value: object)
litellm/integrations/otel/model/utils.py:20
↓ 31 callersFunctionassertion_from_sso_login
The typed carrier built where the raw token response exists; ``None`` when the provider sent no id_token or sent one that is not a decodable JWT,
litellm/proxy/mcp_server/outbound_credentials/sso_assertion_store.py:162
↓ 31 callersMethodasync_pre_routing_hook
( self, model, request_kwargs, messages=None, input=None, specific_deployment=False, call_type=Non
tests/unit/test_router/test_router.py:9008
↓ 31 callersFunctionbackground_routes
(read_status: str, **fields: JsonValue)
tests/integration/spend/_background_responses.py:100
↓ 31 callersMethodbatch
(self, redis_cache: RedisCache)
litellm/caching/redis_batch.py:554
↓ 31 callersFunctioncase_timeout_seconds
()
tests/integration/_support/budget.py:63
↓ 31 callersMethodclassifier_calls
(self, requests: Sequence[Request])
tests/integration/_support/safeguards_rig.py:278
↓ 31 callersFunctioncount
(title: str)
tests/unit/proxy/test_proxy_token_counter.py:2125
↓ 31 callersFunctioncreated_id
(response: httpx.Response)
tests/integration/providers/_dashscope_video_support.py:201
← previousnext →1,501–1,600 of 202,479, ranked by callers