MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 7 callersFunction_polled
(payload: object, logging_obj: object = None)
tests/unit/llms/volcengine/test_volcengine_video_transformation.py:71
↓ 7 callersFunction_post
(gateway: Gateway, path: str, body: Mapping[str, JsonValue])
tests/integration/providers/test_pdf_input_support_wire.py:114
↓ 7 callersFunction_post
(body: object, path: str = BULK_UPDATE_PATH)
tests/unit/proxy/management_endpoints/management_v1/test_teams.py:775
↓ 7 callersFunction_post_chat
(gateway: Gateway, model: str, messages: Sequence[dict[str, JsonValue]])
tests/integration/providers/test_hosted_vllm_reasoning_content_wire.py:128
↓ 7 callersFunction_prefs
(*, hints=None, cost=None, speed=None, intelligence=None)
tests/unit/proxy/mcp_server/test_mcp_sampling_model_resolution.py:21
↓ 7 callersFunction_prepare
(model: str, extra_kwargs: dict[str, object], thinking: dict[str, object] | None = None)
tests/unit/llms/anthropic/messages/adapters/test_handler_prompt_cache_key.py:18
↓ 7 callersMethod_prepare
(self, headers: Dict[str, Any], data: str, extra_headers: Optional[Dict[str, str]] = None)
tests/unit/llms/bedrock/test_base_aws_llm.py:3385
↓ 7 callersMethod_prepare_request
( self, credentials, data: dict, optional_params: dict, aws_region_nam
litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py:854
↓ 7 callersFunction_present
()
tests/unit/proxy/utils/prisma_and_spend/test_prisma_client_lifecycle.py:180
↓ 7 callersFunction_preset_config
(**overrides: object)
tests/unit/router_strategy/test_llm_v2.py:199
↓ 7 callersFunction_presidio
(gateway: Gateway, mode: str, entities: Mapping[str, str] | None)
tests/integration/observability/test_presidio_entity_masking.py:83
↓ 7 callersFunction_priority_provider
(respx_mock: respx.MockRouter, monkeypatch: pytest.MonkeyPatch)
tests/unit/test_router/test_router.py:16528
↓ 7 callersFunction_prisma_with_policy_rows
(production_rows, non_production_rows=None)
tests/unit/proxy/policy_engine/test_policy_versioning.py:457
↓ 7 callersFunction_probes_sent_to
(gateway: Gateway, handle: ScenarioHandle)
tests/integration/management/test_model_health_check.py:273
↓ 7 callersMethod_process_grayswan_response
Legacy method for processing GraySwan API responses. This method is maintained for backward compatibility with existing tests.
litellm/proxy/guardrails/guardrail_hooks/grayswan/grayswan.py:390
↓ 7 callersFunction_project_rows
(project_id: str)
tests/integration/management/test_project_lifecycle.py:57
↓ 7 callersFunction_promoted_trace_control_fields
Return the caller's trace-control fields that ``litellm_metadata`` does not already set.
litellm/proxy/litellm_pre_call_utils.py:932
↓ 7 callersFunction_prompt_table
(prisma_client: "PrismaClient")
litellm/proxy/prompts/prompt_endpoints.py:108
↓ 7 callersFunction_provider_calls
(requests: tuple[Request, ...])
tests/integration/providers/test_azure_entra_token_reuse_wire.py:217
↓ 7 callersFunction_provider_file_id
(provider: str)
tests/unit/enterprise/proxy/hooks/test_managed_files.py:2446
↓ 7 callersFunction_provisioning_caller
(role: LitellmUserRoles)
tests/unit/proxy/management_endpoints/test_team_endpoints.py:14625
↓ 7 callersFunction_proxy_environment
( gateway: Gateway, overrides: Mapping[str, str], remove_environment: tuple[str, ...], source:
tests/integration/_support/process.py:764
↓ 7 callersFunction_proxy_issued_id
(provider_response_id: str)
tests/unit/proxy/response_api_endpoints/test_endpoints.py:1375
↓ 7 callersFunction_proxy_url
(gateway: Gateway)
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:768
↓ 7 callersFunction_proxy_url
(proxy: Gateway)
tests/integration/authorization/test_sso_blank_identity.py:407
↓ 7 callersFunction_ptu_warnings
(caplog)
tests/unit/test_router_model_cost_isolation.py:3485
↓ 7 callersFunction_push_schema_with_environment_variables_revision_trigger
()
tests/integration/configuration/test_effective_settings.py:1138
↓ 7 callersFunction_query
(upgrade: dict[str, JsonValue])
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:770
↓ 7 callersFunction_query_params
(url: str)
tests/unit/llms/azure/image_edit/test_azure_image_edit_transformation.py:165
↓ 7 callersFunction_query_raw_by_table
( active_rows: Sequence[dict[str, str | None]], deleted_rows: Sequence[dict[str, str | None]], )
tests/unit/proxy/spend_tracking/test_key_metadata_recovery.py:74
↓ 7 callersFunction_queue_router
( monkeypatch: pytest.MonkeyPatch, default_priority: int | None, mock_response: str = "queued" )
tests/unit/proxy/proxy_server/test_routes_queue.py:124
↓ 7 callersFunction_rail_scans
(rows: Sequence[Request], rail_name: str, marker: str)
tests/integration/observability/test_guardrail_stream_scope.py:413
↓ 7 callersMethod_raise
(self, litellm_params: dict, status_code: int, monkeypatch: pytest.MonkeyPatch)
tests/unit/llms/anthropic/test_anthropic_wif.py:820
↓ 7 callersFunction_raise_if_ptu_cost_attribution_disabled
Reject PTU model_info fields unless the operator opted into PTU cost attribution. Takes the incoming request's model_info rather than the merged
litellm/proxy/management_endpoints/model_management_endpoints.py:1070
↓ 7 callersFunction_raise_on_missing_project_model_quota_on_update
Require the positive `rpm`/`tpm` quotas the policy asks of each model over the RESULTING state on project UPDATE. `/project/update` replaces `mod
enterprise/litellm_enterprise/proxy/management_endpoints/project_endpoints.py:359
↓ 7 callersFunction_ranked_session_ips
(session_id: str)
tests/unit/router_utils/test_kubernetes_pod_discovery.py:309
↓ 7 callersFunction_read
(pinned: Pinned, digest: str)
tests/integration/spend/test_daily_activity_key_metadata_query_timeout.py:336
↓ 7 callersMethod_read
(self, request: Mapping[str, object])
litellm/tracing/remote.py:98
↓ 7 callersFunction_read_comm_and_ppid
(pid: int, proc_root: str)
litellm/proxy/db/query_engine_reaper.py:56
↓ 7 callersMethod_read_image_bytes
Read raw bytes from various image input types.
litellm/llms/openrouter/image_edit/transformation.py:402
↓ 7 callersFunction_read_stored_manifest
(name: str)
tests/unit/proxy/anthropic_endpoints/test_claude_code_marketplace.py:154
↓ 7 callersFunction_reader
(owned: OwnedProxy)
tests/integration/spend/test_key_metadata_recovery_dropped_connection.py:139
↓ 7 callersMethod_receive
(stream: AsyncGenerator[object, None], count: int)
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_unified_guardrail.py:3075
↓ 7 callersFunction_received
(wire: Wire, text: str)
tests/integration/providers/test_gemini_tts_voice_mapping_wire.py:211
↓ 7 callersFunction_received
(wire: Wire)
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:294
↓ 7 callersMethod_record
( self, state: _State, model: object, kwargs: Mapping[str, object], response: object, problems: Sequen
tests/unit/test_router/test_router_callback_hook_sequence.py:153
↓ 7 callersMethod_record
(self, error_information)
tests/unit/integrations/test_opentelemetry.py:5566
↓ 7 callersMethod_record_error_metric
Record error metric to New Relic.
litellm/integrations/newrelic/newrelic.py:714
↓ 7 callersMethod_record_guardrail_metrics
Record guardrail metrics for prometheus. Args: guardrail_name: Name of the guardrail latency_seconds: Execut
litellm/integrations/prometheus.py:3650
↓ 7 callersFunction_record_to_spend_metrics
Build a SpendMetrics directly from one already-aggregated rollup row. SUM() over zero rows is SQL NULL, so rollup rows (notably the grand-total
litellm/proxy/management_endpoints/common_daily_activity.py:747
↓ 7 callersFunction_recorded
(args_dir: Path, name: str)
tests/unit/test_pre_commit_lint.py:475
↓ 7 callersMethod_recorded_entries
(self, data: dict)
tests/unit/llms/openai/chat/guardrail_translation/test_openai_guardrail_handler.py:2359
↓ 7 callersFunction_recorded_guardrail_entries
(request_data: dict)
tests/unit/proxy/guardrails/guardrail_hooks/test_headroom.py:159
↓ 7 callersFunction_records
(*ips: str, port: int = 8000)
tests/unit/router_utils/test_kubernetes_pod_discovery.py:87
↓ 7 callersFunction_recovery_transaction
( mock_prisma: MagicMock, spend_log_rows: Sequence[dict[str, str | None]] = (), daily_spend_owner_
tests/unit/proxy/management_endpoints/test_common_daily_activity.py:1078
↓ 7 callersFunction_redact_credentials
Mask configured database passwords before passing the text to LiteLLM redaction.
litellm-proxy-extras/litellm_proxy_extras/_redaction.py:42
↓ 7 callersFunction_redact_responses_api_output
Helper to redact ResponsesAPIResponse output items.
litellm/litellm_core_utils/redact_messages.py:378
↓ 7 callersFunction_redis_cache
()
tests/integration/sdk/test_dual_cache_redis.py:15
↓ 7 callersFunction_redis_mock_for_sync_batch
(redis_result: dict)
tests/unit/caching/test_dual_cache.py:64
↓ 7 callersFunction_refunds
(fakes: FakeRateLimits)
tests/unit/caching/test_request_redis_batch_pre_call.py:97
↓ 7 callersFunction_refused
(response: httpx.Response, wire: Wire, detail: str)
tests/integration/security/test_fine_tuning_managed_ids.py:285
↓ 7 callersFunction_refused
(response: httpx.Response, status: int, error_type: str)
tests/integration/management/test_team_member_lifecycle.py:165
↓ 7 callersMethod_register_models
()
tests/unit/litellm_core_utils/test_litellm_logging.py:10936
↓ 7 callersMethod_register_tiered_model
(self, model_key: str, tiered_pricing: list[dict])
tests/unit/llms/dashscope/test_dashscope_cost_calculator.py:641
↓ 7 callersFunction_registered_chat_models
(provider_by_model: Mapping[str, str])
tests/unit/proxy/auth/test_model_checks.py:1948
↓ 7 callersMethod_registry
(self)
tests/unit/proxy/vector_store_endpoints/test_vector_store_endpoints.py:3112
↓ 7 callersFunction_registry_mock
Return a mock registry with is_initialized=True and get_effective_policies returning policy_map.
tests/unit/proxy/guardrails/guardrail_hooks/test_tool_policy_guardrail.py:73
↓ 7 callersFunction_rejected
(message: str)
tests/unit/llms/vertex_ai/gemini/test_rejected_thought_signature_retry.py:76
↓ 7 callersMethod_relay
(self, llm_router, endpoint: str, body: dict, user_api_key_dict=None)
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:7465
↓ 7 callersFunction_relay_elicitation_to_downstream
( params: ElicitRequestParams, downstream_session: _DownstreamElicitSession, downstream_capabiliti
litellm/proxy/mcp_server/elicitation_handler.py:81
↓ 7 callersFunction_relay_through_pass_through
( client_body: Mapping[str, object], target: str, guardrails_config: dict[str, object] | None,
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:6651
↓ 7 callersFunction_relayed_proxy
( gateway: Gateway, directory: Path, relayed_url: str, environment: Mapping[str, str] = NO_ENV
tests/integration/spend/test_key_metadata_recovery_dropped_connection.py:115
↓ 7 callersMethod_remember_upstream_initialize_instructions
(self, server: MCPServer, client: MCPClient)
litellm/proxy/mcp_server/mcp_server_manager.py:2460
↓ 7 callersFunction_rendered_page_cost
(width: int = 612, height: int = 792)
tests/unit/litellm_core_utils/test_token_counter.py:2829
↓ 7 callersFunction_repinning_router
(enabled: bool | None = True)
tests/unit/router_utils/pre_call_checks/test_session_id_affinity.py:30
↓ 7 callersFunction_replay
(marker: str)
tests/integration/providers/test_responses_bridge_tool_search_replay.py:101
↓ 7 callersFunction_replayed
(gateway: Gateway, messages: Sequence[JsonValue])
tests/integration/providers/test_anthropic_tool_search_result_matrix_wire.py:264
↓ 7 callersFunction_replayed_upstream
( gateway: Gateway, scenario: Scenario, wire: Wire, marker: str, body: Mapping[str, JsonVa
tests/integration/providers/test_responses_bridge_tool_search_replay.py:205
↓ 7 callersFunction_request
()
tests/unit/proxy/telemetry/test_attempt_logger.py:45
↓ 7 callersMethod_request_body
( self, tool_choice: str | Mapping[str, object], drop_params: bool = False, to
tests/unit/llms/mistral/test_mistral_chat_transformation.py:2105
↓ 7 callersFunction_request_ids_for_key
(gateway: Gateway, key: str, count: int)
tests/integration/spend/test_responses_stream_spend_row_id.py:163
↓ 7 callersFunction_request_kwargs
(shape: _Shape, wire: Wire)
tests/integration/sdk/test_sync_stream_connection_release_wire.py:112
↓ 7 callersFunction_require_proxy_admin
Catalog mutations are restricted to proxy admins: marketplace.json is served unauthenticated and any registered/updated entry is immediately insta
litellm/proxy/anthropic_endpoints/claude_code_endpoints/claude_code_marketplace.py:545
↓ 7 callersMethod_reschedule_spend_log_cleanup_job
Reschedule the spend log cleanup job based on current general_settings. This is called when maximum_spend_logs_retention_period is up
litellm/proxy/proxy_server.py:8412
↓ 7 callersFunction_reserve
()
tests/unit/proxy/middleware/test_budget_reservation_release_middleware.py:67
↓ 7 callersFunction_reserve_for_stream
(counter_cache, key_cache, proxy_logging_obj, token: str)
tests/unit/proxy/test_budget_reservation.py:2695
↓ 7 callersFunction_reserved_tokens_for
Drive the pre-call hook and read back what landed on the :tokens counter.
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:6864
↓ 7 callersFunction_resolve_cache_url_precedence
Return cache settings with the url-vs-discrete-fields ambiguity resolved. When a full ``url`` is supplied it wins: the discrete host/port/db/
litellm/proxy/management_endpoints/cache_settings_endpoints.py:92
↓ 7 callersMethod_resolve_db_team_fallback
Resolve a team for a user whose JWT carries no team claims by selecting the first DB team membership that loads successfully and, whe
litellm/proxy/auth/handle_jwt.py:2342
↓ 7 callersMethod_resolve_json_mode_non_streaming
Strip internal response_format tool calls; merge payload into content when mixed with user tools.
litellm/llms/anthropic/chat/transformation.py:2754
↓ 7 callersMethod_resolve_model_for_quality_tier
Resolve a quality tier to a concrete model name. Strategy: 1. Exact tier match → first model registered at that tier.
litellm/router_strategy/quality_router/quality_router.py:275
↓ 7 callersMethod_resolve_trusted_user_id
Resolve user ID from API-key/JWT-bound identity for blocking DLP. Uses only ``UserAPIKeyAuth.user_id`` (bound on the LiteLLM key or JWT).
litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py:335
↓ 7 callersMethod_resolve_user_id_for_blocking
Resolve user ID for blocking (pre_call / post_call) DLP hooks. Uses only trusted proxy-authenticated sources (``_resolve_trusted_user_id``).
litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/purview_dlp.py:351
↓ 7 callersMethod_resolve_user_id_from_logging_kwargs
Trusted-identity-only resolver for logging-only hooks. Uses only the proxy-injected ``user_api_key_user_id`` (populated from the API-
litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py:356
↓ 7 callersFunction_resolved_callback
(registry: InMemoryPromptRegistry, environment: str | None = None)
tests/unit/proxy/prompts/test_prompt_registry.py:23
↓ 7 callersFunction_resolved_scope
( resolver: EntityScopeResolver, query: EntityQuery, user_api_key_dict: UserAPIKeyAuth, prisma
litellm/proxy/management_endpoints/daily_activity_routes.py:96
↓ 7 callersFunction_response
( route: str, *, streaming: bool = False, )
tests/integration/compatibility/test_missing_body_param_status.py:664
↓ 7 callersFunction_response
(tool_name: str | None = None)
tests/unit/proxy/spend_tracking/test_spend_event.py:31
↓ 7 callersFunction_response
( *results: tuple[str, bool], speech_event: str = "none", billed_seconds: float = 0.0 )
tests/unit/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_transformation.py:93
↓ 7 callersFunction_response
(status: int = 200, body: Any = None)
tests/unit/integrations/focus/test_ternary_destination.py:46
← previousnext →10,301–10,400 of 202,479, ranked by callers