MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 14 callersMethod_finalize_translation_usage
(self)
litellm/litellm_core_utils/realtime_streaming.py:955
↓ 14 callersFunction_function
(name, description="")
tests/unit/llms/openai/responses/test_openai_responses_guardrail_tool_merge.py:23
↓ 14 callersFunction_function_call_item
(call_id="c1", name=LITELLM_CODE_EXECUTION_TOOL_NAME)
tests/unit/integrations/code_interpreter_interception/test_handler.py:81
↓ 14 callersFunction_gemini_config
(path: Path, wire_url: str)
tests/integration/observability/test_passthrough_upstream_error_visibility.py:87
↓ 14 callersFunction_generate_requests
(wire: Wire)
tests/integration/providers/test_gemini_anyof_null_branches_wire.py:197
↓ 14 callersMethod_get_async_client_cache_key
Generate a cache key for the async Redis client based on connection parameters. This ensures different Redis configurations use diffe
litellm/caching/redis_cache.py:699
↓ 14 callersMethod_get_async_embedding
Asynchronously generate an embedding for the given prompt. Args: prompt: The text to generate an embedding for
litellm/caching/redis_semantic_cache.py:521
↓ 14 callersFunction_get_cors_config
Compute CORS allowed origins and credentials flag from environment variables. Extracted into a function so it can be unit-tested without rel
litellm/proxy/proxy_server.py:2614
↓ 14 callersMethod_get_token_and_url_context_caching
Internal function. Returns the token and url for the call. Handles logic if it's google ai studio vs. vertex ai. Returns
litellm/llms/vertex_ai/context_caching/vertex_ai_context_caching.py:161
↓ 14 callersFunction_guardrails_on
(*guardrails: CustomGuardrail)
tests/unit/proxy/response_api_endpoints/test_endpoints.py:2452
↓ 14 callersFunction_history_from_stored_turns
( spend_logs: tuple[dict[str, object], ...], previous_response_id: str )
tests/unit/responses/litellm_completion_transformation/test_session_handler.py:915
↓ 14 callersFunction_input_line
(custom_id: str, text: str)
tests/integration/observability/test_batch_line_items_cold_storage.py:301
↓ 14 callersFunction_insert
( connection: psycopg.Connection[tuple[object, ...]], rows: Sequence[Mapping[str, object]], *, ledger: boo
tests/integration/database/test_spendlogs_delivery.py:42
↓ 14 callersFunction_is_base_audit_leg
()
tests/integration/observability/_logging_only_scope_support.py:204
↓ 14 callersFunction_is_blocked_ip
Return True for any IP not safe to reach from a user-supplied URL. Policy: default-deny via ``ip.is_global`` (RFC 6890), plus an explicit exc
litellm/litellm_core_utils/url_utils.py:171
↓ 14 callersFunction_is_multimodal_input
Check if the input contains multimodal data (data URIs, file references, GCS URLs, file content blocks, or nested lists for combined embeddin
litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:326
↓ 14 callersFunction_issuer
()
tests/integration/authorization/test_jwt_auto_register_map_existing_key.py:65
↓ 14 callersFunction_json_array
(*values: JsonValue)
tests/integration/authorization/test_rag_query_vector_store_allowlist.py:39
↓ 14 callersFunction_label_values
(series: frozenset[str], label: str)
tests/unit/integrations/test_prometheus_series_cardinality.py:69
↓ 14 callersFunction_ladder
( counter: _ScriptedCounter, settings: TokenCountSettings, local_estimate_allowed: bool = True,
tests/unit/proxy/test_proxy_token_counter.py:1744
↓ 14 callersFunction_least_busy_router
(group: str = ROUTER_GROUP, *, use_in_pass_through: bool = False)
tests/unit/router_strategy/test_least_busy.py:345
↓ 14 callersFunction_legacy_ct
Produce a legacy (nacl) ciphertext with the AES gate off.
tests/unit/proxy/management_endpoints/test_credential_migration.py:34
↓ 14 callersFunction_load_jsonl
Load eval cases from a JSONL file. One JSON object per line.
litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/guardrail_benchmarks/test_eval.py:36
↓ 14 callersFunction_make_deployment_dict
Helper to build a minimal deployment dict as returned by router.registry().deployments().
tests/unit/proxy/auth/test_auth_utils.py:2956
↓ 14 callersFunction_make_httpx_status_error
Create a real httpx.HTTPStatusError for testing.
tests/unit/llms/custom_httpx/test_credential_leak_prevention.py:28
↓ 14 callersFunction_make_logging_obj
(test_name: str, failure_recorder: _FailureRecorder | None = None)
tests/unit/llms/anthropic/messages/native/test_streaming_iterator.py:55
↓ 14 callersMethod_make_logging_obj
( self, llm_api_duration_ms: float | None = None, llm_api_timing_windows: object = Non
tests/unit/litellm_core_utils/llm_response_utils/test_response_metadata.py:240
↓ 14 callersFunction_make_mock_request
Create a mock FastAPI Request object.
tests/unit/proxy/management_endpoints/scim/test_scim_v2_discovery.py:30
↓ 14 callersFunction_make_prisma
(user: MagicMock | None)
tests/unit/proxy/management_endpoints/test_password_endpoints.py:35
↓ 14 callersFunction_make_prisma_client
Return a minimal mock PrismaClient accepted by get_prisma_client_or_throw.
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:5686
↓ 14 callersFunction_make_request_mock
(path: str, headers: dict)
tests/unit/proxy/test_litellm_pre_call_utils.py:7379
↓ 14 callersFunction_make_router
(deployments)
tests/unit/proxy/common_utils/test_model_deprecation.py:27
↓ 14 callersFunction_make_router
()
tests/unit/router_strategy/adaptive_router/test_async_pre_routing.py:22
↓ 14 callersFunction_make_user
(role: str, user_id: str = "user-1")
tests/unit/proxy/common_utils/test_rbac_utils.py:20
↓ 14 callersFunction_map_reasoning_effort
(model: str, reasoning_effort: str)
tests/unit/llms/databricks/chat/test_databricks_chat_transformation.py:1142
↓ 14 callersFunction_marked_fallback_file_row
( *, size_bytes: int = 0, created_at: int = 123, )
tests/unit/enterprise/proxy/hooks/test_managed_files.py:198
↓ 14 callersFunction_marker
()
tests/integration/observability/test_content_filter_logging_only.py:264
↓ 14 callersFunction_marker
()
tests/integration/observability/test_otel_excluded_services_matrix.py:46
↓ 14 callersFunction_mcp_request
(name="lookup", args=None, jsonrpc=False, **extra)
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:110
↓ 14 callersFunction_mcp_upstream
Drive the SDK's streamable-HTTP transport off an httpx2 MockTransport; respx only sees httpx.
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:16428
↓ 14 callersFunction_messages_body
(model: str, marker: str, *, stream: bool = False, **extra: JsonValue)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:663
↓ 14 callersFunction_metrics_by_name
{metric_name: [data_point, ...]} from everything the reader has collected.
tests/unit/integrations/otel/test_otel_v2_metrics.py:147
↓ 14 callersFunction_mock_http_handler
Return a mock that mirrors litellm's ``AsyncHTTPHandler`` contract. Two properties of the real handler matter for these tests and were the so
tests/unit/proxy/agent_endpoints/test_databricks_oauth.py:35
↓ 14 callersFunction_native_code
(client_id, team_id="team-b", cache=None)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:1838
↓ 14 callersFunction_non_empty_string
(value: object)
litellm/proxy/guardrails/guardrail_hooks/tool_permission.py:125
↓ 14 callersFunction_only_generate_calls
(wire: Wire, count: int, *, target: str = _GENERATE)
tests/integration/spend/test_vertex_regional_uplift_spend.py:185
↓ 14 callersFunction_output_limits
(request: Mapping[str, object])
tests/unit/llms/vertex_ai/gemini/test_long_decode.py:1346
↓ 14 callersFunction_page
(*event_ids: str)
tests/e2e_harness/logging/test_datadog_reader.py:51
↓ 14 callersMethod_parse
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 14 callersMethod_parse_json_response
Parse direct JSON response (non-streaming). Supports multiple agent response schemas: 0. {"jsonrpc": "2.0", "result": {"mess
litellm/llms/bedrock/chat/agentcore/transformation.py:398
↓ 14 callersFunction_pod_lock
A lock manager that acquires (or not) and, by default, still owns the lease.
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:650
↓ 14 callersFunction_poller_over
(table: _InMemoryManagedObjectTable, billed_logger: _RecordingBilledLogger)
tests/unit/proxy/common_utils/test_check_responses_cost.py:144
↓ 14 callersFunction_post
(client: TestClient, body: bytes, content_encodings: tuple[str, ...], path: str = "/v1/systemone")
tests/unit/proxy/middleware/test_request_body_decompression_middleware.py:83
↓ 14 callersFunction_prefs
Build a minimal ModelPreferences-like object.
tests/unit/proxy/mcp_server/test_mcp_sampling_priority_selection.py:23
↓ 14 callersFunction_priority_deployments
( primary_response: str = "primary", primary_blocked: bool = False, backup_response: str = "backup" )
tests/unit/router_strategy/test_router_routing_groups.py:677
↓ 14 callersFunction_priority_group
( name: str = "priority-group", primary: int = 1, backup: int = 2 )
tests/unit/router_strategy/test_router_routing_groups.py:666
↓ 14 callersFunction_priority_router
(default_priority: int | None)
tests/unit/test_router/test_router.py:16516
↓ 14 callersMethod_processInputParams
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 14 callersFunction_prompt
(marker: str)
tests/integration/providers/test_responses_bridge_tool_search_wire.py:152
↓ 14 callersFunction_provider_file_id
(bearer: str, filename: str)
tests/integration/management/test_vector_store_file_list_managed_ids.py:50
↓ 14 callersFunction_ptu_request
(model: str = "test-model")
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:8843
↓ 14 callersFunction_query
(request: Request)
tests/integration/management/test_vector_store_file_list_managed_ids.py:74
↓ 14 callersFunction_query_raw
Run a raw read query and return its rows as the row type the caller declares.
litellm/proxy/spend_tracking/spend_management_endpoints.py:258
↓ 14 callersFunction_read_team
(client: ManagementClient, team_id: str, caller_key: str | None = None)
tests/e2e/management/test_team_management_e2e.py:174
↓ 14 callersFunction_reasoning_input_minted_by
(origin: str)
tests/unit/router_utils/pre_call_checks/test_encrypted_content_affinity_check.py:2599
↓ 14 callersFunction_recv
(backend: SpeechStreamingBackend)
tests/unit/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_backend.py:113
↓ 14 callersFunction_redact_containing
(needle)
tests/unit/proxy/openai_files_endpoint/test_batch_guardrails.py:56
↓ 14 callersFunction_register
(client: PassthroughClient, resources: ResourceManager, backend: str)
tests/e2e/llm_translation/test_together_ai_e2e.py:202
↓ 14 callersFunction_registry_with
(agent: AgentResponse)
tests/unit/proxy/test_route_a2a_models.py:220
↓ 14 callersFunction_remove
( prisma: _FakePrisma, team_id: str, members: Sequence[Mapping[str, str]], caller: UserAPIKeyA
tests/unit/proxy/management_helpers/test_bulk_user_deletion.py:283
↓ 14 callersFunction_request
(prompt: str, **config_overrides: object)
tests/unit/proxy/management_endpoints/test_auto_router_endpoints.py:107
↓ 14 callersFunction_request_token
(client: TestClient, device_code: str)
tests/unit/proxy/anthropic_endpoints/test_gateway_endpoints.py:222
↓ 14 callersFunction_resolve
Resolve attributes with the two DB env vars set, as the proxy sets them.
tests/unit/integrations/otel/test_db_endpoint.py:27
↓ 14 callersMethod_response
( usage: litellm.Usage | None = None, model: str = "gpt-5.4-nano", **hidden_params: object )
tests/unit/litellm_core_utils/test_litellm_logging.py:755
↓ 14 callersFunction_retrieve_route
(mock_router: respx.MockRouter, provider: StreamProvider)
tests/unit/responses/test_responses_api_lifecycle.py:170
↓ 14 callersFunction_root_attrs
(exporter)
tests/unit/integrations/otel/test_langfuse_logger.py:75
↓ 14 callersMethod_router
(self, mock_router_instance, config: dict)
tests/unit/router_strategy/test_complexity_router.py:7806
↓ 14 callersMethod_router
(self, mock_router_instance, config: dict)
tests/unit/router_strategy/test_complexity_router.py:13325
↓ 14 callersFunction_routes
(attempts: tuple[_Attempt, ...])
tests/integration/routing/test_deployment_mode_routing_wire.py:141
↓ 14 callersFunction_run
(payload: object, env: dict[str, str], fetch)
tests/unit/proxy/client/cli/test_statusline_script.py:96
↓ 14 callersFunction_run_db_sync_cycle
(proxy: _DbBackedProxy)
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:11605
↓ 14 callersFunction_run_hooks
( handler: BaseLLMHTTPHandler, callback: CustomLogger, kwargs: dict, response: object = None,
tests/unit/integrations/websearch_interception/test_websearch_agentic_loop_cap.py:223
↓ 14 callersFunction_scope
(limit: int, key: str = "api_key")
tests/unit/proxy/hooks/test_batch_enqueued_tokens.py:38
↓ 14 callersFunction_scraped_series
(sample_name: str, registry: CollectorRegistry = REGISTRY)
tests/unit/integrations/test_prometheus_series_cardinality.py:64
↓ 14 callersFunction_scripted
(scenario: Scenario, response: RealtimeResponse, *, control_url: str | None = None)
tests/integration/providers/test_realtime_unguarded_voice_turns.py:230
↓ 14 callersFunction_select_tokenizer_helper
(model: str)
litellm/utils.py:2852
↓ 14 callersFunction_sent
( requested: RequestedReasoningEffort, deployment_model_info: Mapping[str, object] | None = KIMI_DEPLO
tests/unit/router_utils/test_reasoning_effort_capability.py:491
↓ 14 callersFunction_serving_model_probe
(respond: Callable[[Request], Reply])
tests/integration/observability/test_grayswan_wire.py:119
↓ 14 callersFunction_set_admin
()
tests/unit/proxy/management_endpoints/test_config_override_endpoints.py:86
↓ 14 callersFunction_setup_team_keys_mocks
Set up mocks for bulk_update_team_keys; returns mock_prisma.
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:15562
↓ 14 callersFunction_shape
( source: str, rule_id: JsonValue, *, token_file: str = _DEFAULT_TOKEN_FILE, keycloak_toke
tests/integration/management/test_credential_federation_values.py:102
↓ 14 callersFunction_single_part
(transformed_input: object)
tests/unit/llms/openai/responses/test_openai_responses_transformation.py:4437
↓ 14 callersFunction_slg_entry
Build a StandardLoggingGuardrailInformation entry the way ``add_standard_logging_guardrail_information_to_request_data`` does.
tests/unit/integrations/test_otel_guardrail_violation_spans.py:89
↓ 14 callersFunction_spend_log_session_id
Resolve session_id the way LiteLLM_SpendLogs does, reading the omit decision stamped on the request.
tests/unit/proxy/test_litellm_pre_call_utils.py:9394
↓ 14 callersFunction_spend_record
(api_key, *, model="gpt-4o-mini-ptu", spend=0.0, ptu_flat_cost=0.0)
tests/unit/proxy/management_endpoints/test_common_daily_activity.py:1902
↓ 14 callersFunction_spend_row
(identity: str)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_wire.py:210
↓ 14 callersFunction_stream
(gateway: Gateway, path: str, body: Mapping[str, JsonValue], *, key: str | None = None)
tests/integration/routing/test_vllm_passthrough_stream_relay.py:182
↓ 14 callersFunction_stream_text
(chunks: list)
tests/unit/llms/vertex_ai/gemini/test_long_decode.py:756
↓ 14 callersFunction_streamed
(body: Mapping[str, object], **terminal: object)
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:2487
↓ 14 callersFunction_summarize
(rows: list[SpendLogRow])
tests/e2e/quota_management/spend_tracking/test_spend_tracking_e2e.py:53
← previousnext →4,301–4,400 of 202,479, ranked by callers