MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersFunctionO
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:53
↓ 5 callersFunctionO
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 5 callersFunctionO
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 5 callersFunctionP
(e,t,n,r,a)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 5 callersFunctionPg
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctionR
()
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:96
↓ 5 callersFunctionSl
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:401
↓ 5 callersFunctionTg
(s,o,i,a)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctionTn
(t,e,r)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 5 callersFunctionU
litellm/proxy/_experimental/out/_next/static/chunks/2jxpy6eth1zvy.js:1
↓ 5 callersFunctionV
()
litellm/proxy/_experimental/out/_next/static/chunks/39v0w3tgm6n4z.js:1
↓ 5 callersFunctionV
(e,t,n,r,a)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 5 callersFunctionX
()
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 5 callersFunctionY
(e,t,r,i,a,s)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 5 callersFunctionZ
({onInsert:e})
litellm/proxy/_experimental/out/_next/static/chunks/39v0w3tgm6n4z.js:1
↓ 5 callersFunction_
()
litellm/proxy/_experimental/out/_next/static/chunks/1k52o6u_65gki.js:1
↓ 5 callersFunction_
litellm/proxy/_experimental/out/_next/static/chunks/0-i21ejarohtj.js:1
↓ 5 callersFunction_
litellm/proxy/_experimental/out/_next/static/chunks/2j96ftcthirif.js:19
↓ 5 callersFunction_
()
litellm/proxy/_experimental/out/_next/static/chunks/2bsaba02innfw.js:1
↓ 5 callersMethod__anext__
( self, )
litellm/responses/litellm_completion_transformation/streaming_iterator.py:1291
↓ 5 callersMethod__anext__
(self)
tests/unit/llms/anthropic/messages/native/test_agentic_streaming_iterator.py:231
↓ 5 callersMethod__del__
Best-effort correlation-context cleanup for an abandoned async stream. Only meaningfully applies to streams created by wrapper_async(): it
litellm/litellm_core_utils/streaming_handler.py:599
↓ 5 callersMethod__init__
( self, message: str, type: str, param: str | None, code: int | str |
litellm/proxy/_types.py:3910
↓ 5 callersMethod__init__
(self)
litellm/caching/redis_batch.py:73
↓ 5 callersMethod__init__
(self, *events)
tests/unit/a2a_protocol/test_main.py:73
↓ 5 callersMethod__init__
(self, message: str, status_code: int)
tests/unit/litellm_core_utils/test_exception_mapping_utils.py:1032
↓ 5 callersMethod__init__
(self, stdout: str)
tests/unit/litellm_core_utils/test_chat_completion_agentic_loop.py:86
↓ 5 callersMethod__init__
(self)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:16060
↓ 5 callersMethod__init__
(self)
tests/unit/proxy/mcp_server/guardrail_translation/test_mcp_guardrail_handler.py:26
↓ 5 callersMethod__init__
(self, execute_raw: Callable[[], int] | None = None)
tests/unit/proxy/db/test_db_spend_update_writer.py:386
↓ 5 callersMethod__init__
(self)
tests/unit/responses/mcp/test_chat_completions_handler.py:1584
↓ 5 callersFunction_a2a
( gateway: Gateway, name: str, method: str, marker: str, metadata: dict[str, JsonValue] | None = None )
tests/integration/providers/test_databricks_agent_wire.py:172
↓ 5 callersFunction_absent
()
tests/unit/proxy/utils/prisma_and_spend/test_prisma_client_lifecycle.py:176
↓ 5 callersFunction_access_group_none_server
A non-oauth2, access-group gated MCP server: no client_id, no OAuth.
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:8884
↓ 5 callersMethod_access_group_updates
(mock_prisma)
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:8739
↓ 5 callersFunction_access_token
()
tests/unit/proxy/mcp_server/outbound_credentials/test_session_credentials.py:46
↓ 5 callersFunction_account_responder
(payload=None, status=200, model_payload=None)
tests/unit/llms/github_copilot/test_per_user_auth.py:402
↓ 5 callersMethod_accumulate_streamed_delta
(self, delta: object)
litellm/litellm_core_utils/streaming_handler.py:2843
↓ 5 callersFunction_accumulating_gemini_iterator
()
tests/unit/llms/vertex_ai/gemini/test_vertex_and_google_ai_studio_gemini.py:7414
↓ 5 callersMethod_active_tier_severity
Position of a tier in the active severity order: TIER_SEVERITY_ORDER for the built-in set, tier_definitions list order or inferred mapping ord
litellm/router_strategy/complexity_router/complexity_router.py:3454
↓ 5 callersFunction_activity
(proxy: Gateway, path: str, params: Mapping[str, str], requests: int)
tests/integration/spend/test_ptu_share_attribution.py:222
↓ 5 callersMethod_add
(self, name: CallbackList, callback: object)
tests/unit/test_router/core/scripted_host.py:194
↓ 5 callersMethod_addCheck
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 5 callersMethod_addMessage
(e,t=!0)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:11
↓ 5 callersMethod_add_mcp_per_team_rate_limit_descriptor
Add a per-MCP-server rpm descriptor for the team, if a limit is configured for the server being called.
litellm/proxy/hooks/parallel_request_limiter_v3.py:2627
↓ 5 callersMethod_add_metrics_from_log
Extracts latencies and appends Datadog metric series to the queue
litellm/integrations/datadog/datadog_metrics.py:105
↓ 5 callersFunction_add_provider_mapping_route
(router: respx.MockRouter)
tests/unit/llms/huggingface/chat/test_huggingface_chat_transformation.py:72
↓ 5 callersFunction_add_tag_to_deployment
Helper function to add tag to deployment
litellm/proxy/management_endpoints/tag_management_endpoints.py:364
↓ 5 callersFunction_admin
()
tests/unit/proxy/test_model_list_callback_filter.py:117
↓ 5 callersFunction_admin_auth
()
tests/unit/proxy/memory/test_memory_endpoints.py:233
↓ 5 callersMethod_admin_headers
A fresh admin token per call: the master realm's tokens are short lived, and a cached one would expire in the middle of a slow test.
tests/e2e/idp.py:159
↓ 5 callersMethod_admin_url
(self, path: str)
tests/e2e/idp.py:156
↓ 5 callersFunction_admission_refusing_the_next_turn
()
tests/unit/responses/test_responses_websocket_all_providers.py:1602
↓ 5 callersFunction_admission_request
Request whose ``body()`` serves the peeked JSON-RPC method (``b"{}"`` when nothing is stashed).
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:116
↓ 5 callersFunction_agen
()
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_tool_args.py:401
↓ 5 callersMethod_ageneric
`_ageneric_api_call_with_fallbacks`.
litellm/router_rust/invoke/endpoints.py:1625
↓ 5 callersFunction_agent
(access_group_ids: list[str] | None)
tests/unit/proxy/agent_endpoints/auth/test_agent_access_groups.py:16
↓ 5 callersMethod_agent_object_permission
(self, *, toolset_ids, servers=(), tool_permissions=None)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:5184
↓ 5 callersMethod_agent_toolset_patches
(self, agent_object_permission, mock_manager)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:5199
↓ 5 callersFunction_aggregate_batch_cost_usage_models
Aggregate cost, usage, models, and pass/fail counts from batch output entries in a single pass, holding one small stats record per line instead
litellm/batches/batch_utils.py:377
↓ 5 callersFunction_aiter
(items)
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:279
↓ 5 callersFunction_analyze
(database_url: str, vacuum: bool)
tests/integration/spend/test_key_metadata_recovery_probe_bounds.py:146
↓ 5 callersFunction_answer_script
(text: str, output_json: str | None = None)
tests/unit/harness/test_runtime.py:403
↓ 5 callersFunction_answered
(response: httpx.Response, marker: str)
tests/integration/providers/test_openai_responses_prompt_cache_breakpoint_wire.py:85
↓ 5 callersFunction_answered_as_openai_api
(respond: Callable[[Request], Reply])
tests/integration/providers/test_openai_responses_tool_search_wire.py:137
↓ 5 callersFunction_answered_tool_names
(response: httpx.Response, stream: bool)
tests/integration/messages_endpoint/test_guardrail_long_tool_names_wire.py:259
↓ 5 callersFunction_anthropic_body
(messages: list, litellm_params: dict | None = None, tools: list | None = None)
tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py:4708
↓ 5 callersFunction_anthropic_errored_row
()
tests/unit/batches/test_batch_utils.py:1483
↓ 5 callersFunction_anthropic_message
( client: anthropic.Anthropic, model: str, messages: Sequence[anthropic.types.MessageParam], *
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire.py:388
↓ 5 callersFunction_anthropic_message_body
(content: list[dict[str, object]], stop_reason: str)
tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py:10071
↓ 5 callersFunction_anthropic_overloaded_error_frame
()
tests/unit/proxy/pass_through_endpoints/test_streaming_handler_interrupt.py:953
↓ 5 callersFunction_anthropic_stream_head
()
tests/unit/proxy/guardrails/guardrail_hooks/test_presidio.py:3039
↓ 5 callersFunction_anthropic_stream_tail
()
tests/unit/proxy/guardrails/guardrail_hooks/test_presidio.py:3031
↓ 5 callersFunction_app
(role: LitellmUserRoles | None)
tests/unit/proxy/management_endpoints/test_prompt_caching_requests.py:21
↓ 5 callersFunction_apply
( guardrail: TypeSafeGuardrail, messages: list[dict[str, object]], input_type: str = "request" )
tests/unit/proxy/guardrails/guardrail_hooks/test_typesafe.py:103
↓ 5 callersMethod_apply_common_transform_content_item
( self, content_item: OpenAIMessageContentListBlock, )
litellm/llms/openai/chat/gpt_transformation.py:386
↓ 5 callersMethod_apply_masking_function
Apply a masking function to data, handling different data types. Args: data: The data to mask (can be str, dict, list, o
litellm/integrations/langfuse/langfuse.py:1085
↓ 5 callersFunction_apply_persisted_dcr_credentials
(mcp_server: MCPServer, credentials: _PersistedDcrCredentials)
litellm/proxy/mcp_server/discoverable_endpoints.py:1664
↓ 5 callersFunction_apply_search_filter_to_models
Apply search filter to models, querying database for additional matching models. Args: all_models: List of models to filter
litellm/proxy/proxy_server.py:17061
↓ 5 callersFunction_approx
(value: float)
tests/integration/providers/test_fal_ai_image_wire.py:63
↓ 5 callersMethod_argument_masking_guardrail
()
tests/unit/llms/openai/responses/test_openai_responses_guardrail_handler.py:2560
↓ 5 callersFunction_arrived
The copy of ``sent`` at ``url`` once every span name in ``expected`` and a usage-bearing model span landed.
tests/integration/observability/test_otel_team_capture_message_content.py:323
↓ 5 callersFunction_as_async
(chunks: Iterator[object])
tests/unit/litellm_core_utils/test_streaming_handler.py:2238
↓ 5 callersFunction_as_gettable
(value: object)
litellm/integrations/langfuse/langfuse_otel.py:70
↓ 5 callersFunction_as_json_object
(value: object)
litellm/proxy/guardrails/guardrail_registry.py:92
↓ 5 callersFunction_as_mapping
(value: object)
litellm/router_attempt.py:219
↓ 5 callersFunction_as_object
(value: object)
litellm/proxy/management_endpoints/team_admin_field_permissions.py:296
↓ 5 callersFunction_as_object_dict
(values: Mapping[str, object])
litellm/proxy/management_endpoints/key_management_endpoints.py:561
↓ 5 callersFunction_as_role
(role: LitellmUserRoles, user_id, log_team_lookup)
tests/unit/proxy/management_endpoints/management_v1/test_spend_logs.py:75
↓ 5 callersFunction_as_sequence
(value: object)
litellm/anthropic_beta_gated_fields.py:83
↓ 5 callersFunction_ask
(rig: Rig, model: str, surface: Surface, guardrail: str, prompt: str)
tests/integration/observability/test_presidio_masking_endpoints.py:461
↓ 5 callersMethod_assemble_user_object
Assemble a LiteLLM_UserTable object ``budget_reset_at`` and ``user_alias`` come from the auth-carried snapshot when the requ
litellm/integrations/prometheus.py:4851
↓ 5 callersFunction_assembled_stream_result
()
tests/unit/litellm_core_utils/test_litellm_logging.py:8844
↓ 5 callersFunction_assert_alias_resolved
(embedding_route: respx.Route, search_route: respx.Route, response)
tests/unit/llms/milvus/vector_stores/test_milvus_vector_stores_transformation.py:298
↓ 5 callersFunction_assert_answered
(item: _Served)
tests/integration/providers/test_anthropic_refusal_stop_details_chaos.py:148
↓ 5 callersFunction_assert_answered_in_its_own_shape
(served: _Served)
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire_chaos.py:174
↓ 5 callersFunction_assert_answered_with_its_own_marker
(served: _Served)
tests/integration/providers/test_gemini_tool_result_part_reference_chaos.py:299
↓ 5 callersFunction_assert_answered_with_its_own_marker
(served: _Served)
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:383
↓ 5 callersFunction_assert_answered_with_its_own_marker
(served: _Served)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_safeguards_beta_chaos.py:97
↓ 5 callersFunction_assert_anthropic_message
(response: object, model: str)
tests/unit/llms/anthropic/messages/native/test_anthropic_messages_router.py:206
← previousnext →13,801–13,900 of 202,479, ranked by callers