MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersMethod_create
( self, request: FallbackCreateRequest, router: Router, prisma_client: MagicMock, proxy_config: ProxyC
tests/unit/proxy/test_fallback_management_endpoints.py:195
↓ 5 callersMethod_create_background_noma_check
Create a background task for Noma API calls without blocking the main flow
litellm/proxy/guardrails/guardrail_hooks/noma/noma.py:156
↓ 5 callersFunction_create_batch
(gateway: Gateway, key: str, model: str, input_file_id: JsonValue)
tests/integration/management/test_managed_file_create_ownership.py:123
↓ 5 callersFunction_create_body
(name: str, values: Mapping[str, JsonValue])
tests/integration/management/test_credential_federation_values.py:158
↓ 5 callersFunction_create_budget
(client: ManagementClient, resources: ResourceManager, body: BudgetNewBody)
tests/e2e/management/test_budget_customer_user_org_e2e.py:98
↓ 5 callersMethod_create_cbf_record
Create a single CBF record from LiteLLM daily spend row.
litellm/integrations/cloudzero/transform.py:100
↓ 5 callersFunction_create_credential
(body: dict)
tests/unit/proxy/credential_endpoints/test_endpoints.py:1658
↓ 5 callersFunction_create_index
Create a plain index by hand, the way an operator's workaround would, and return its oid.
tests/integration/database/migrations/test_request_log_indexes.py:850
↓ 5 callersFunction_create_management_rail
(rig: MatrixRig, name: str, params: Mapping[str, JsonValue])
tests/integration/observability/test_guardrail_stream_scope_matrix.py:1151
↓ 5 callersMethod_create_mock_logging_obj
Create a mock logging object for testing
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_gemini_passthrough_logging_handler.py:84
↓ 5 callersFunction_create_on_a_replica_that_then_dies
(logging_obj: LitellmLogging, store)
tests/unit/interactions/test_background_cost_polling.py:863
↓ 5 callersMethod_create_priority_based_descriptors
Create rate limit descriptors with normalized priority weights. Uses normalized weights to handle over-allocation scenarios.
litellm/proxy/hooks/dynamic_rate_limiter_v3.py:288
↓ 5 callersFunction_create_router
Create a Router with two deployments for testing.
tests/unit/test_router_retry_non_retryable_errors.py:43
↓ 5 callersFunction_create_team
(client: ManagementClient, resources: ResourceManager, alias: str, models: list[str])
tests/e2e/management/test_team_management_e2e.py:156
↓ 5 callersFunction_create_tool
(gateway: Gateway, scenario: Scenario, name: str, api_base: str)
tests/integration/authorization/test_search_tool_allowlist.py:24
↓ 5 callersFunction_create_toolset
( client: ManagementClient, resources: ResourceManager, server_id: str )
tests/e2e/management/test_mcp_lifecycle_e2e.py:203
↓ 5 callersFunction_create_user
(client: ManagementClient, resources: ResourceManager, email: str)
tests/e2e/management/test_team_management_e2e.py:162
↓ 5 callersFunction_created_then
(raw_id: str, read: Reply)
tests/integration/providers/test_responses_lifecycle_wire.py:512
↓ 5 callersFunction_credential_name
()
tests/integration/management/test_credential_federation_values.py:154
↓ 5 callersFunction_custom_key_policy_hook
( hooks: _CustomKeyHooksModule, )
litellm/proxy/management_endpoints/key_management_endpoints.py:389
↓ 5 callersFunction_custom_sso_returning_user_id
(custom_user_id: object)
tests/unit/proxy/management_endpoints/test_ui_sso.py:1755
↓ 5 callersFunction_customer
(scenario: Scenario, models: list[str] | None = None)
tests/integration/authorization/test_customer_model_allowlist.py:31
↓ 5 callersFunction_cyclic_fallback_router
(num_retries=0)
tests/unit/test_router/test_router.py:9747
↓ 5 callersFunction_daily_entity_txn
(entity_id_field: str)
tests/unit/proxy/db/test_db_spend_update_writer.py:5243
↓ 5 callersFunction_data
(current: ObservedPeriodData, previous: ObservedPeriodData | None = None)
tests/unit/proxy/roi_calculator/test_observed_analytics.py:33
↓ 5 callersMethod_data
(self, messages)
tests/unit/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py:2324
↓ 5 callersFunction_database_url
( admin_url: str, role: str, password: str, database: str, *, encode_password: bool =
tests/integration/database/test_v1_migration_error_logging.py:64
↓ 5 callersFunction_databricks
(scenario: Scenario, wire: Wire, **parameters: JsonValue)
tests/integration/providers/test_responses_bridge_verbosity_wire.py:89
↓ 5 callersFunction_day
(offset: int)
tests/integration/spend/test_daily_activity_key_metadata_query_timeout.py:139
↓ 5 callersFunction_day_window_from
(start: datetime, end: datetime)
tests/unit/integrations/ternary/test_ternary_logger.py:145
↓ 5 callersFunction_db_find_mcp_server_row
( prisma_client: PrismaClient, server_id: str )
litellm/proxy/mcp_server/db.py:733
↓ 5 callersFunction_db_find_mcp_server_rows
( prisma_client: PrismaClient, where: "prisma_db_types.LiteLLM_MCPServerTableWhereInput | None" = None
litellm/proxy/mcp_server/db.py:726
↓ 5 callersFunction_db_litellm_params
Shape produced by GuardrailRegistry.get_all_guardrails_from_db: litellm_params is a raw dict (not a LitellmParams), holding only the keys ori
tests/unit/proxy/guardrails/test_guardrail_registry.py:617
↓ 5 callersFunction_db_row
A Prisma-style row: attribute access, litellm_params/guardrail_info as plain dicts.
tests/unit/proxy/guardrails/test_usage_endpoints.py:60
↓ 5 callersMethod_declare
(self, op: _Op[_T])
litellm/caching/redis_batch.py:351
↓ 5 callersFunction_decode
(chunks: tuple[bytes, ...])
tests/unit/proxy/guardrails/test_anthropic_sse.py:25
↓ 5 callersFunction_decode
( parts: tuple[str | bytes, ...], is_messages_api: bool, mode: str )
tests/unit/llms/sagemaker/test_sagemaker_common_utils.py:321
↓ 5 callersFunction_decode_sse_chunk
(chunk)
tests/unit/proxy/test_response_model_sanitization.py:67
↓ 5 callersFunction_decode_user_env_vars
Decrypt a ``values_b64`` blob and parse it as a flat ``{name: value}`` dict.
litellm/proxy/mcp_server/db.py:2433
↓ 5 callersFunction_decoded_claims
(token: str, prefix: str)
tests/unit/proxy/mcp_server/outbound_credentials/test_session_token.py:244
↓ 5 callersFunction_deepseek_v4_tool_tokens
(function: Mapping[str, JsonValue], tokens: Callable[[str], int])
tests/integration/providers/test_chat_template_tool_count_wire.py:71
↓ 5 callersFunction_default_session
(runtime: str, region: str = _US_EAST)
tests/integration/providers/test_strands_decider_agentcore_wire.py:186
↓ 5 callersFunction_defineProperty
(s,o,i)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersMethod_delete_container
(self, container: ContainerHandle, params: SandboxToolParams | None)
litellm/integrations/code_interpreter_interception/handler.py:850
↓ 5 callersFunction_delete_team
(gateway: Gateway, team_id: str)
tests/integration/management/test_team_delete_member_cache_eviction.py:85
↓ 5 callersFunction_delivered
(wire: Wire)
tests/integration/providers/test_vertex_anthropic_inline_tools_beta_wire.py:112
↓ 5 callersFunction_delta_text
(chunk: ModelResponseStream)
litellm/router_utils/pre_call_checks/continuation_prefill_check.py:120
↓ 5 callersMethod_deltas_by_block
(result: bytes, field: str)
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:969
↓ 5 callersFunction_denial
( monkeypatch: pytest.MonkeyPatch, *, policy: str | None, data: UpdateKeyRequest, existing
tests/unit/proxy/management_endpoints/test_key_budget_change.py:256
↓ 5 callersFunction_deploy
(scenario: Scenario, api_base: str, label: str, deployment: _Deployment)
tests/integration/routing/test_non_chat_model_endpoint_gate.py:169
↓ 5 callersFunction_deployment
( name: str, params: Mapping[str, JsonValue], info: Mapping[str, JsonValue] = MappingProxyType({}) )
tests/integration/security/test_api_key_secret_reference.py:238
↓ 5 callersFunction_deployment
(scenario: Scenario, wire: Wire, **pricing: JsonValue)
tests/integration/providers/test_cursor_responses_wire.py:154
↓ 5 callersFunction_deployment
(scenario: Scenario, route: Route, wire_url: str)
tests/integration/providers/test_chat_completions_tool_search_history_wire.py:174
↓ 5 callersFunction_deployment
(scenario: Scenario, wire: Wire)
tests/integration/messages_endpoint/providers/bedrock/test_bedrock_messages_gpt_chat_completions_wire.py:23
↓ 5 callersFunction_deployment
(route: Route, wire: Wire)
tests/integration/sdk/test_stream_open_error_provider_headers_sdk.py:109
↓ 5 callersFunction_deployment
(gateway: Gateway, marker: str, provider: str)
tests/integration/routing/test_azure_passthrough_spend_row.py:98
↓ 5 callersFunction_deployment
(model_name: str, model: str = "openai/gpt-4o", **model_info)
tests/unit/proxy/test_model_list_discoverable.py:19
↓ 5 callersFunction_deployment
(deployment_id: str)
tests/unit/router_strategy/test_lowest_tpm_rpm.py:18
↓ 5 callersFunction_deployment_id
(name: str)
tests/integration/authorization/test_alias_chain_budget_waiver.py:149
↓ 5 callersMethod_deployment_of
(self, deployment_id: object)
litellm/router_rust/surface/health.py:163
↓ 5 callersFunction_deprecation_messages
(caplog: pytest.LogCaptureFixture)
tests/unit/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py:7673
↓ 5 callersMethod_detect_input_type
Detect whether to use 'converse' or 'invokeModel' input format. Args: request_data: The original request data R
litellm/llms/bedrock/count_tokens/transformation.py:80
↓ 5 callersMethod_detect_transcription_session_from_backend
Flag transcription-only sessions from backend session events.
litellm/litellm_core_utils/realtime_streaming.py:735
↓ 5 callersMethod_discovery_key
( self, server: MCPServer, user_api_key_auth: UserAPIKeyAuth | None, mcp_auth_
litellm/proxy/mcp_server/mcp_server_manager.py:4766
↓ 5 callersFunction_divider
Return a styled divider line (evaluated at call-time, not import-time).
litellm/setup_wizard.py:172
↓ 5 callersFunction_docker
(*args: str, check: bool = True)
tests/integration/database/image/test_component_image_serves_offline.py:50
↓ 5 callersMethod_download_object_from_s3
Download and parse JSON object from S3. Args: s3_object_key: The S3 object key to download Returns:
litellm/integrations/s3_v2.py:985
↓ 5 callersFunction_drain
(seen: SimpleQueue[str])
tests/integration/sdk/test_openai_sdk_client_sessions_wire.py:94
↓ 5 callersFunction_drain
()
tests/unit/proxy/test_budget_reservation.py:2762
↓ 5 callersFunction_drain
(analyzed: asyncio.Queue[PresidioAnalyzeRequest])
tests/unit/proxy/guardrails/guardrail_hooks/test_presidio.py:5349
↓ 5 callersFunction_drain_bridge_stream
(litellm_params: Mapping[str, object])
tests/unit/a2a_protocol/test_main.py:918
↓ 5 callersFunction_drain_logging
()
tests/unit/router_strategy/test_least_busy.py:912
↓ 5 callersFunction_drain_logging_worker
()
tests/unit/integrations/test_custom_callback_input.py:266
↓ 5 callersFunction_drain_publishes
()
tests/unit/proxy/management_helpers/test_team_roster_sync.py:596
↓ 5 callersFunction_drained_other_than_model_list_probes
(wire: Wire)
tests/integration/providers/test_files_batches_wire.py:166
↓ 5 callersFunction_drive_cyclic_fallback
(router, capture, recorder=None, **request_kwargs)
tests/unit/test_router/test_router.py:9772
↓ 5 callersFunction_drive_model_info
Drive one model-info merge to its end, answering each lookup with ``answer``. A lookup that raises raises out of the query, as it raised in the Py
litellm/router_rust/surface/model_info.py:125
↓ 5 callersFunction_drive_passthrough_request_and_capture_logging
( user_api_key_dict: UserAPIKeyAuth, on_pre_call: Callable[[LiteLLMLoggingObj | None], None] | None =
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:10162
↓ 5 callersFunction_dump_03
Dump a compat (0.3) pydantic model to its camelCase wire dict.
litellm/proxy/a2a/version_convert.py:43
↓ 5 callersFunction_dunder_args
(annotation: object)
litellm/proxy/guardrails/guardrail_endpoints.py:1747
↓ 5 callersFunction_echoed
(value: JsonValue)
tests/integration/mcp/test_mcp_llm_endpoints.py:1820
↓ 5 callersFunction_eden_embedding
Live `/v3/embeddings` body: OpenAI shape plus Eden's top-level `cost`, `provider` and `status`.
tests/unit/llms/edenai/embedding/test_edenai_embedding_transformation.py:23
↓ 5 callersFunction_eden_image
Live `/v3/images/generations` body: OpenAI shape plus Eden's top-level `cost` and `provider`.
tests/unit/llms/edenai/image_generation/test_edenai_image_generation_transformation.py:23
↓ 5 callersFunction_eden_message
Live body: Anthropic shape with the id sent to Eden echoed in `model` and Eden's top-level `cost`.
tests/unit/llms/edenai/messages/test_edenai_anthropic_messages_transformation.py:32
↓ 5 callersFunction_eden_response
Live `/v3/responses` body: OpenAI shape plus Eden's top-level `cost` and `provider`.
tests/unit/llms/edenai/responses/test_edenai_responses_transformation.py:42
↓ 5 callersFunction_effective_complexity_router_params
The model and complexity config a write leaves, for placement and capability decisions.
litellm/proxy/management_endpoints/model_management_endpoints.py:591
↓ 5 callersFunction_effective_key_for_generate
(data: GenerateKeyRequest, now: datetime)
litellm/proxy/management_endpoints/key_management_endpoints.py:492
↓ 5 callersFunction_effective_max_input_tokens
(router: Router)
tests/unit/test_router_model_cost_isolation.py:3928
↓ 5 callersFunction_embedding_media_uri
(kind: str, compressed: bool)
tests/unit/proxy/hooks/test_tpm_concurrent.py:3681
↓ 5 callersFunction_embedding_payload
(vectors: list[object], **overrides)
tests/unit/integrations/otel/test_otel_v2_sources_of_truth.py:730
↓ 5 callersFunction_embedding_router
(max_input_tokens: int)
tests/unit/test_router/test_router.py:4592
↓ 5 callersFunction_embedding_rows
(vectors: list[object])
tests/unit/llms/vertex_ai/vertex_embeddings/test_embedding_handler.py:70
↓ 5 callersMethod_emit
( provider: TracerProvider, destinations: tuple[OtelDestination, ...] = (), tracer_nam
tests/unit/integrations/otel/test_otel_v2_destinations.py:5774
↓ 5 callersMethod_emitted_payload_text
Every attribute this logger exported to langfuse, as one searchable string.
tests/unit/integrations/test_langfuse.py:611
↓ 5 callersFunction_encrypted_classifier_task
( request_kwargs: Mapping[str, object] | None, marker_pairs: tuple[tuple[str, str], ...], )
litellm/router_strategy/complexity_router/complexity_router.py:622
↓ 5 callersFunction_end_user_rows
(end_users: tuple[str, ...])
tests/integration/spend/test_disable_end_user_cost_tracking.py:378
↓ 5 callersFunction_endpoint
An async endpoint method, which the core serves by name.
tests/unit/test_router/core/test_host_settings_changes_characterization.py:57
↓ 5 callersFunction_enforce_alias_access
(token: UserAPIKeyAuth, data: dict, route: str, request, router: litellm.Router)
tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py:12659
↓ 5 callersFunction_enforce_caller_supplied_provider_key
SECURITY: refuse to use the proxy's shared GOOGLE_API_KEY / GEMINI_API_KEY env fallback for non-admin callers on Gemini managed-agent CRUD en
litellm/proxy/google_endpoints/agents_endpoints.py:43
↓ 5 callersMethod_engine_with
( expires_in: int | None, )
tests/unit/llms/base_llm/auth/test_token_exchange.py:1487
← previousnext →14,201–14,300 of 202,479, ranked by callers