MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 18 callersFunction_assert_rejected
(response: httpx.Response, message: str, param: str = "tools")
tests/integration/providers/test_malformed_tools_wire.py:543
↓ 18 callersFunction_assert_response_id
(endpoint: Endpoint, request_id: str, response_id: str, scenario_id: str)
tests/integration/observability/_logging_only_scope_support.py:1128
↓ 18 callersFunction_async_payload
(content="Hello world! How are you?")
tests/unit/litellm_core_utils/llm_response_utils/test_convert_to_streaming_response.py:28
↓ 18 callersFunction_attribute
(entries: Sequence[KeyValue], key: str)
tests/integration/observability/test_langfuse_delivery.py:137
↓ 18 callersFunction_auto_register_jwt_mapping
Auto-register: create a new virtual key + mapping for an unrecognised JWT claim value, or point the mapping at a key the resolved user alread
litellm/proxy/auth/user_api_key_auth.py:1671
↓ 18 callersFunction_auto_router
(routelayer: Any, router: Any = None, **kwargs: Any)
tests/unit/router_strategy/test_auto_router.py:389
↓ 18 callersFunction_bodies
(wire: Wire, provider: _Provider)
tests/integration/providers/test_anthropic_count_tokens_system_lift_wire.py:256
↓ 18 callersFunction_body
(endpoint: Endpoint, model: str, *, user: str | None = None)
tests/integration/providers/test_bedrock_converse_stream_event_frames_wire.py:213
↓ 18 callersFunction_boot_db_backed_proxy
( tmp_path, monkeypatch, config_pass_through_endpoints: list[dict[str, object]], db_pass_throu
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:11562
↓ 18 callersFunction_build_batch_response
( *, batch_id: str = "batch_managed_ids_test", status: str = "completed", output_file_id: Opti
tests/unit/enterprise/proxy/test_batch_update_db_managed_output_file_id.py:18
↓ 18 callersFunction_captured_policy
()
tests/unit/llms/bedrock/test_web_identity_session_policy.py:136
↓ 18 callersFunction_carrying
(requests: Sequence[Request], marker: str)
tests/integration/security/test_api_key_secret_reference.py:480
↓ 18 callersFunction_chat_body
(model: str, marker: str, **extra: JsonValue)
tests/integration/providers/test_bedrock_native_structured_output_wire.py:455
↓ 18 callersFunction_chat_body
(model: str, call: _Call, **extra: JsonValue)
tests/integration/routing/test_vllm_passthrough_stream_relay.py:119
↓ 18 callersFunction_cimd_oauth_server
()
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:14550
↓ 18 callersFunction_client_ws_that_never_sends
()
tests/unit/litellm_core_utils/test_realtime_streaming.py:4864
↓ 18 callersFunction_close_dangling_otel_server_span
(request: Request, status_code: int, exc: Exception | None = None)
litellm/proxy/proxy_server.py:2412
↓ 18 callersMethod_common_logic
(self, kwargs: Mapping[str, object], response_obj)
litellm/integrations/openmeter.py:58
↓ 18 callersFunction_config
(**overrides: object)
tests/unit/proxy/mcp_server/outbound_credentials/test_client_credentials.py:52
↓ 18 callersFunction_config
()
tests/unit/llms/fastcrw/search/test_transformation.py:13
↓ 18 callersFunction_drain
(queue)
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:13863
↓ 18 callersFunction_drive
( ws_base: str, query: str, key: str, steps: tuple[Step, ...], *, path: str = "/v1/rea
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:599
↓ 18 callersFunction_encode_rsa_jwt
( private_key, issuer: str, audience: str, kid: str, extra_claims: dict | None = None, )
tests/unit/proxy/auth/test_handle_jwt.py:4139
↓ 18 callersFunction_engine
(legacy_compat=True)
tests/unit/integrations/otel/test_otel_v2_emitter.py:64
↓ 18 callersMethod_execute_command
( self, target_node: _FakeClusterNode, *args: object, **kwargs: object )
tests/unit/caching/test_redis_cluster_node_isolation.py:63
↓ 18 callersFunction_gemini_default_mode_streaming
( monkeypatch: pytest.MonkeyPatch, client_messages: Sequence[str], model: str = "gemini-live-2.5-f
tests/unit/litellm_core_utils/test_realtime_streaming.py:2985
↓ 18 callersFunction_get_proxy_server_request_for_spend_logs_payload
Only store if should_store_prompts_and_responses_in_spend_logs() is True If turn_off_message_logging is enabled, redact messages in the requ
litellm/proxy/spend_tracking/spend_tracking_utils.py:2063
↓ 18 callersFunction_get_token_base_cost
Return prompt cost, completion cost, and cache costs for a given model and usage. If input_tokens > threshold and `input_cost_per_token_abov
litellm/litellm_core_utils/llm_cost_calc/utils.py:723
↓ 18 callersFunction_granted_actions
(policy: WebIdentitySessionPolicy)
tests/unit/llms/bedrock/test_web_identity_session_policy.py:140
↓ 18 callersMethod_handle_anthropic_messages_response_logging
Handles logging for Anthropic messages responses. Args: result: The response object from the model call Returns
litellm/litellm_core_utils/litellm_logging.py:5360
↓ 18 callersMethod_inc_labeled_counter
( self, counter: Any, metric_name: DEFINED_PROMETHEUS_METRICS, enum_values: Us
litellm/integrations/prometheus.py:1623
↓ 18 callersFunction_ingest
( gateway: Gateway, key: str, vector_store: Mapping[str, JsonValue] = OPENAI, *, name: str
tests/integration/authorization/test_rag_team_provider_credentials.py:772
↓ 18 callersFunction_ingest_form
(vector_store, **request_fields)
tests/unit/proxy/rag_endpoints/test_rag_endpoints.py:300
↓ 18 callersFunction_issue_managed_id
Mint an id exactly the way the proxy hands one to a client on create.
tests/unit/test_responses_id_security.py:789
↓ 18 callersMethod_keys
(self, username: str)
litellm/proxy/auth/login_throttle.py:315
↓ 18 callersFunction_make_checker
()
tests/unit/test_check_licenses.py:40
↓ 18 callersFunction_make_guardrail
(apply_result: dict)
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:72
↓ 18 callersFunction_make_model
(model_id: str, model_name: str = "gpt-4")
tests/unit/router_utils/test_health_check_allowed_fails_integration.py:34
↓ 18 callersFunction_make_row
( policy_id="pid-1", policy_name="test-policy", version_number=1, version_status="production",
tests/unit/proxy/policy_engine/test_policy_versioning.py:24
↓ 18 callersFunction_make_streaming_response
(chunks)
tests/unit/proxy/pass_through_endpoints/test_streaming_handler_interrupt.py:32
↓ 18 callersFunction_messages
()
tests/unit/llms/microsoft_365_copilot/chat/test_handler.py:44
↓ 18 callersFunction_model
(scenario_model: Callable[..., str], url: str)
tests/integration/messages_endpoint/chat_bridge/test_chat_bridge_multi_tool_call_blocks_wire.py:493
↓ 18 callersFunction_names
(executor: InMemoryListExecutor[Row], plan: QueryPlan)
tests/unit/proxy/list_api/test_in_memory.py:39
↓ 18 callersFunction_new_marker
()
tests/integration/providers/test_responses_compaction_items_wire.py:59
↓ 18 callersFunction_non_admin
(**kwargs)
tests/unit/proxy/test_model_list_callback_filter.py:113
↓ 18 callersFunction_oauth_identity_jwt
( signing_key: "RSAPrivateKey", *, expires_in: int = 300, audience: str = "litellm-proxy",
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:12949
↓ 18 callersFunction_ollama_model
(scenario: Scenario, wire: Wire, template: Mapping[str, JsonValue])
tests/integration/providers/test_custom_prompt_template_wire.py:117
↓ 18 callersFunction_ollama_server
(respond: Callable[[Request], Reply] = _echo_answer)
tests/integration/providers/test_custom_prompt_template_wire.py:93
↓ 18 callersFunction_only_forwarded
(rig: _Rig, marker: str, *, stream: bool = True)
tests/integration/providers/test_chatgpt_responses_caller_stream_wire.py:104
↓ 18 callersFunction_parameters
(value: JsonValue)
tests/integration/providers/test_gemini_anyof_null_branches_wire.py:148
↓ 18 callersFunction_patched_ingest_boundary
(registry_store, aingest_response)
tests/unit/proxy/rag_endpoints/test_rag_endpoints.py:317
↓ 18 callersFunction_payload
(response: httpx.Response)
tests/integration/providers/test_bedrock_runtime_chat_completions_wire.py:120
↓ 18 callersFunction_raw
(body: dict, status_code: int = 200)
tests/unit/llms/bedrock/batches/test_transformation.py:53
↓ 18 callersFunction_redact_pii_matches
Redact match-like fields from a Bedrock ApplyGuardrail JSON payload. Delegates to :func:`redact_nested_match_and_regex_keys` (same rules as
litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py:213
↓ 18 callersFunction_redact_response
( *, sanitized_text=None, sanitized_messages=None, sanitized_mcp_arguments=None, sanitized
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:175
↓ 18 callersFunction_relay_session
( client_ws: MagicMock, backend_ws: MagicMock, provider_config: BaseRealtimeConfig | None = None )
tests/unit/litellm_core_utils/test_realtime_streaming.py:4879
↓ 18 callersFunction_replying
(result: Mapping[str, object])
tests/unit/llms/bedrock/passthrough/guardrail_translation/test_handler.py:1411
↓ 18 callersFunction_resolve_group_member_ids
Resolve SCIM group members to LiteLLM user ids, dropping members that are not users. Member ids are matched by ``user_id`` first, then by SS
litellm/proxy/management_endpoints/scim/scim_v2.py:1047
↓ 18 callersFunction_response
(body: dict)
tests/unit/llms/vertex_ai/context_caching/test_known_cached_contents.py:55
↓ 18 callersFunction_response_body_without_ids
(value: JsonValue)
tests/integration/observability/_logging_only_scope_support.py:312
↓ 18 callersFunction_response_format
(schema: Mapping[str, JsonValue])
tests/integration/providers/test_bedrock_native_structured_output_wire.py:165
↓ 18 callersFunction_router_entry
A deployment as the router stores one: a plain dict whose id lives in model_info.
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:434
↓ 18 callersFunction_row
(request_id: str)
tests/integration/database/test_spendlogs_delivery.py:65
↓ 18 callersFunction_row
(db, key: str, session_id: str = "s1", router: str = "auto-1")
tests/integration/spend/test_autorouter_session_rollup.py:149
↓ 18 callersFunction_run_server_and_capture_urls
( config_path: str, database_url: str = "postgresql://t:t@localhost:5432/t", direct_url: str | Non
tests/unit/proxy/test_proxy_cli.py:3654
↓ 18 callersMethod_scan_tool_calls_for_guardrail
Scan tool calls with allow/block/mask treatment (in-place modification). Tool name and arguments go out as plain prompt/response text, newlin
litellm/proxy/guardrails/guardrail_hooks/panw_prisma_airs/panw_prisma_airs.py:1548
↓ 18 callersFunction_scrub_db_overlay_remote_module_loads
Strip ``s3://`` / ``gcs://`` entries from the DB-overlay value for fields whose contents reach ``get_instance_fn``. The same scheme is allowed
litellm/proxy/proxy_server.py:5198
↓ 18 callersFunction_serve
(call: _Call)
tests/integration/providers/test_device_code_login_guard_wire.py:329
↓ 18 callersFunction_settings
(estimator_prompt: str = "Estimate effort.")
tests/unit/proxy/roi_calculator/test_sync.py:169
↓ 18 callersFunction_spend_report_mock_prisma
(query_raw_returns=None, team_rows=None, user_row=None)
tests/unit/proxy/spend_tracking/test_spend_management_endpoints.py:6700
↓ 18 callersFunction_spend_rows
(model: str, minimum: int)
tests/integration/observability/_logging_only_scope_support.py:1042
↓ 18 callersFunction_stateful_upstream
()
tests/unit/mcp_client/test_mcp_client.py:4217
↓ 18 callersFunction_team
( *members: Member, default_team_member_models: list[str] | None = None, metadata: dict[str, objec
tests/unit/proxy/management_helpers/test_team_roster_sync.py:260
↓ 18 callersFunction_tier_name
The plain tier name, whether the pipeline carries a built-in tier or a defined name.
litellm/router_strategy/complexity_router/complexity_router.py:167
↓ 18 callersFunction_tool_result_request
(call_item: dict[str, str], output_type: str, output: object)
tests/unit/llms/openai/responses/test_openai_responses_guardrail_handler.py:651
↓ 18 callersFunction_transcribe
( riva: _Riva, optional_params: dict[str, object] | None = None, *, api_key: str | None = None
tests/unit/llms/nvidia_riva/audio_transcription/test_handler.py:220
↓ 18 callersMethod_transform
(messages, optional_params=None)
tests/unit/llms/snowflake/chat/test_snowflake_chat_transformation.py:318
↓ 18 callersFunction_uploaded_rows
( config: VertexAIFilesConfig, litellm_params: Mapping[str, object], entries: Sequence[Mapping[str, object
tests/unit/llms/vertex_ai/files/test_vertex_ai_files_transformation.py:1996
↓ 18 callersFunction_upstream_calls
(gateway: Gateway, handle: ScenarioHandle)
tests/integration/providers/test_decisions_openai_format_wire.py:343
↓ 18 callersFunction_user
(user_id: str, *teams: str)
tests/unit/proxy/management_helpers/test_team_roster_sync.py:273
↓ 18 callersFunction_virtual_key
( object_permission_id: str | None = None, api_key: str = "sk-standalone", user_role: LitellmUserR
tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py:1902
↓ 18 callersFunction_w3c_headers
(header_trace: str, baggage_session: str | None)
tests/integration/observability/test_langfuse_delivery.py:466
↓ 18 callersFunction_wait_until_finished
(manager: SyncManager)
tests/unit/proxy/roi_calculator/test_sync.py:241
↓ 18 callersFunction_wire_team_create_tx
`/team/new` inserts the team and mirrors it onto the access groups in one transaction, so a mocked client has to hand its team table back out of `
tests/unit/proxy/management_endpoints/test_team_endpoints.py:159
↓ 18 callersFunction_zip
(files: Mapping[str, bytes], prefix: str = "")
tests/unit/proxy/discovery_endpoints/test_skill_hub_endpoints.py:58
↓ 18 callersFunctiona
()
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 18 callersMethodaclose
(self)
tests/unit/llms/anthropic/messages/native/test_streaming_iterator.py:1112
↓ 18 callersFunctionactor
(tools: tuple[str, ...] | None, *, delegated: bool = False)
tests/unit/proxy/mcp_server/auth/test_managed_agent_access.py:16
↓ 18 callersMethodadd
(self, event: TranscriptionStreamEvent)
litellm/litellm_core_utils/audio_utils/transcription_streaming.py:161
↓ 18 callersMethodadd_deployment_to_cooldown
( self, model_id: str, original_exception: Exception, exception_status: int, cooldown_time: float | No
litellm/router_utils/cooldown_cache.py:28
↓ 18 callersMethodadvance
(self, seconds: float)
tests/unit/llms/base_llm/auth/test_token_exchange.py:64
↓ 18 callersMethodalist_batches
( self, openai_client: AsyncOpenAI, after: str | None = None, limit: int | Non
litellm/llms/openai/openai.py:2345
↓ 18 callersMethodapply_guardrail
Apply Bedrock guardrail to a batch of texts for testing purposes. This method allows users to test Bedrock guardrails without making
litellm/proxy/guardrails/guardrail_hooks/bedrock_guardrails.py:3343
↓ 18 callersFunctionassemble_anthropic_sse_stream
Assemble raw Anthropic SSE frames into a ModelResponse. ``restore_identity`` stamps the upstream message id and model onto the result, which the
litellm/llms/anthropic/messages/stream_assembly.py:710
↓ 18 callersFunctionassert_served
(response: httpx.Response, group: str, identity: str)
tests/integration/routing/test_per_model_rate_limit_fallbacks.py:298
↓ 18 callersFunctionassert_within_factor_of_control
(observed: float, *, control: float, factor: float)
tests/integration/_support/timing.py:39
↓ 18 callersMethodassign
A deprecated attribute assignment of one index (``router.model_names = {...}``).
litellm/router_rust/surface/indexes.py:439
↓ 18 callersMethodasync_pre_call_check
Async pre-call check for model rate limits. Raises RateLimitError if deployment exceeds TPM/RPM or ITPM/OTPM limits.
litellm/router_utils/pre_call_checks/model_rate_limit_check.py:386
↓ 18 callersMethodasync_pre_call_deployment_hook
( self, kwargs: Mapping[str, object], call_type: CallTypes | None )
tests/unit/proxy/hooks/test_autorouter_baseline_cache.py:897
↓ 18 callersMethodasync_pre_call_hook
Pre-call hook to sanitize user prompts.
litellm/proxy/guardrails/guardrail_hooks/model_armor/model_armor.py:706
← previousnext →3,101–3,200 of 202,479, ranked by callers