MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 22 callersFunctionget_complete_model_list
Logic for returning complete model list for a given key + team pair
litellm/proxy/auth/model_checks.py:222
↓ 22 callersMethodget_credentials
(self)
tests/unit/rust_bridge/host/test_redis_credentials.py:14
↓ 22 callersFunctionget_optional_params_embeddings
( # 2 optional params model: str, user: str | None = None, encoding_format: str | None = None,
litellm/utils.py:4784
↓ 22 callersMethodhandle_authentication_error
Handles Connection Errors when reading a Virtual Key from LiteLLM DB Use this if you don't want failed DB queries to block LLM API re
litellm/proxy/auth/auth_exception_handler.py:141
↓ 22 callersFunctioni
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/11et800l-khs-.js:1
↓ 22 callersMethodinfo
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 22 callersMethodinvocable_ids
(self)
tests/integration/_support/aws_control_plane.py:101
↓ 22 callersMethodis_callback_disabled_dynamically
Check if a callback is disabled via the x-litellm-disable-callbacks header or via `litellm_disabled_callbacks` in standard_callback_dynam
enterprise/litellm_enterprise/enterprise_callbacks/callback_controls.py:15
↓ 22 callersMethodkill_worker
(self, pid: int)
tests/integration/_support/process.py:337
↓ 22 callersMethodlist_user_batches
( self, user_api_key_dict: UserAPIKeyAuth, limit: int | None = None, after: st
litellm/proxy/batches_endpoints/endpoints.py:87
↓ 22 callersMethodmake_bedrock_api_request
(self, source, messages=None, response=None, request_data=None, **kwargs)
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:6626
↓ 22 callersMethodmap_cohere_rerank_params
( self, non_default_params: dict, model: str, drop_params: bool, query
litellm/llms/voyage/rerank/transformation.py:49
↓ 22 callersMethodmark_owned
Record that litellm created this client, so it may be closed on eviction.
litellm/caching/evicted_client_closer.py:210
↓ 22 callersFunctionmarker
(label: str)
tests/integration/authorization/_responses_compact.py:76
↓ 22 callersFunctionmerge_agent_card
Build the LiteLLM-fronted agent card. Args: upstream_card: Card returned by the upstream agent's well-known endpoint. Ma
litellm/proxy/a2a/agent_card.py:164
↓ 22 callersFunctionmeta
Attach a `Subject` to a test: `@meta(Subject(route=Route.RESPONSES, ...))`
tests/e2e/e2e_metadata.py:199
↓ 22 callersMethodmodel_dump
(self)
litellm/proxy/auth/auth_checks.py:230
↓ 22 callersMethodmodel_dump
(self)
enterprise/litellm_enterprise/proxy/hooks/managed_files.py:324
↓ 22 callersFunctionnative_backend
( message: Mapping[str, JsonValue], *, stream: bool, chunks: Sequence[bytes] | None = None )
tests/integration/_support/safeguards_rig.py:694
↓ 22 callersFunctionof
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 22 callersMethodparse
(value: &str)
litellm-rust/crates/storage-clickhouse/src/lib.rs:18
↓ 22 callersFunctionpeer
(marker_prefix: str, dialect: Dialect, **fields: object)
tests/integration/compatibility/_a2a_peers.py:209
↓ 22 callersMethodprepare
( self, result: _Terminal | InputRequiredResult )
litellm/proxy/mcp_server/interactions.py:214
↓ 22 callersFunctionptu_terms
The reservation this deployment accrues flat cost for, else None. A start is required rather than inferred because flat cost accrues from it, and
litellm/litellm_core_utils/ptu_pricing.py:302
↓ 22 callersFunctionpublished
(sources: Mapping[str, str])
tests/code_coverage_tests/check_workflow_job_name_collisions.py:426
↓ 22 callersFunctionrecover_key_metadata_from_spend_logs
( prisma_client: PrismaClient, missing_keys: AbstractSet[str], window: tuple[datetime, datetime],
litellm/proxy/spend_tracking/key_metadata_recovery.py:487
↓ 22 callersMethodregex
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 22 callersMethodremove
`remove_deployment`: every deployment with this id goes, and so does a pattern left empty.
litellm-rust/crates/router-core/src/host_index.rs:326
↓ 22 callersMethodreset_budget_windows
For keys and teams with budget_limits, reset any individual windows where reset_at <= now. Only the expired windows are reset; other
litellm/proxy/common_utils/reset_budget_job.py:1564
↓ 22 callersFunctionresolve_bridge_envelope
Classify an ``Authorization`` value presented to a bridge ``oauth_delegate`` server. Strips an optional ``Bearer`` scheme, then returns ``NotBrid
litellm/proxy/mcp_server/outbound_credentials/bridge_credentials.py:216
↓ 22 callersMethodresolve_credentials
(self, subject, server)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:12710
↓ 22 callersFunctionresponses_answer
( gateway: Gateway, client: str, target: Target, request_input: JsonValue, *, stream:
tests/integration/routing/test_fallback_hop_foreign_encrypted_reasoning.py:481
↓ 22 callersMethodresult
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 22 callersMethodroute
`route`: the deployments of the first pattern `request` matches, each a copy whose `litellm_params.model` takes the parts the wildcards matched; `filt
litellm-rust/crates/router-core/src/host_index.rs:343
↓ 22 callersFunctionscripted_peer
(first_turn: Sequence[Event] = SEARCH_TURN)
tests/integration/providers/_tool_search_support.py:157
↓ 22 callersMethodseed
Seed a row the way the rollup writes one: keyed on the deployment id.
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:805
↓ 22 callersMethodsetOptions
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 22 callersMethodset_cache
(self, key, value, **kwargs)
litellm/caching/s3_cache.py:63
↓ 22 callersMethodset_status
(self, status: int)
tests/integration/providers/test_vertex_gemini_count_tokens_wire.py:52
↓ 22 callersMethodsettled
(self, logged: int = 0, failed: int = 0)
tests/unit/responses/mcp/test_chat_completions_handler.py:1606
↓ 22 callersMethodshould_run_guardrail
(self, data, event_type)
tests/unit/proxy/guardrails/test_guardrail_load_balancing.py:26
↓ 22 callersMethodstop
Stop the logging worker and clean up resources.
litellm/litellm_core_utils/logging_worker.py:481
↓ 22 callersMethodstore
(self)
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:7826
↓ 22 callersMethodstore_unified_object_id
( self, unified_object_id: str, file_object: LiteLLMBatch, litellm_parent_otel
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:152
↓ 22 callersMethodsubmit
(self, coro: Coroutine[object, None, T])
litellm/harness/sync.py:65
↓ 22 callersFunctionsupports_httpx_timeout
Helper function to know if a provider implementation supports httpx timeout
litellm/utils.py:3197
↓ 22 callersMethodtaken
The story so far, led by a line counting the steps a full log dropped, so a story that starts mid-test says so rather than reading as complete
tests/e2e/e2e_metadata.py:280
↓ 22 callersFunctionteam_admin_edit_verdict
( data: UpdateTeamRequest, existing: LiteLLM_TeamTable, permitted: frozenset[str], member_defa
litellm/proxy/management_endpoints/team_admin_field_permissions.py:454
↓ 22 callersMethodtransform_create_file_request
( self, model: str, create_file_data: CreateFileRequest, optional_params: Mapp
litellm/llms/xai/files/transformation.py:143
↓ 22 callersMethodtransform_file_content_request
( self, file_content_request: FileContentRequest, optional_params: Mapping[str, object
litellm/llms/xai/files/transformation.py:233
↓ 22 callersMethodtransform_parsed_response
( self, completion_response: dict, raw_response: httpx.Response, model_respons
litellm/llms/anthropic/chat/transformation.py:3208
↓ 22 callersMethodtranslate_anthropic_tools_to_openai
Translate Anthropic tools to OpenAI format. Returns: Tuple of (translated_tools, tool_name_mapping) - tool_n
litellm/llms/anthropic/messages/adapters/transformation.py:927
↓ 22 callersFunctionunavailable
()
litellm-rust/crates/gateway-management/tests/keys/support.rs:65
↓ 22 callersMethodupdate
(self, where: Mapping[str, object], data: Mapping[str, object])
litellm/proxy/mcp_server/toolset_db.py:63
↓ 22 callersFunctionupdate_metadata_fields
Helper function to update all metadata fields (both premium and standard). Args: updated_kv: The key-value dict being used for the u
litellm/proxy/management_endpoints/common_utils.py:817
↓ 22 callersMethodupload
(self, body: bytes)
tests/unit/integrations/pointfive/test_logger.py:34
↓ 22 callersFunctionuploads_seen
(requests: tuple[Request, ...], mark: str)
tests/integration/management/_batch_file_caps.py:150
↓ 22 callersMethodurl
(self)
tests/integration/security/_sinks.py:94
↓ 22 callersFunctionuseUISettings
(options?: { staleTime?: number; refetchInterval?: number })
ui/litellm-dashboard/src/app/(dashboard)/hooks/uiSettings/useUISettings.ts:16
↓ 21 callersFunction_account_catalog
(respx_mock: respx.MockRouter)
tests/unit/proxy/pass_through_endpoints/test_codex_passthrough_endpoints.py:426
↓ 21 callersMethod_add_router_settings_from_db_config
( self, llm_router: Router | None, prisma_client: PrismaClient | None, )
litellm/proxy/proxy_server.py:8354
↓ 21 callersFunction_answering_model_listing
(respond: Callable[[Request], Reply])
tests/integration/spend/test_spend_log_tool_payload_content.py:66
↓ 21 callersFunction_as_list
(value: object)
litellm/router_rust/core.py:582
↓ 21 callersFunction_assert_answered
(answer: _Answer | None, marker: str)
tests/integration/routing/test_deployment_mode_routing_wire.py:349
↓ 21 callersFunction_bearers
(requests: Sequence[Request])
tests/integration/security/test_api_key_secret_reference.py:484
↓ 21 callersFunction_budget
( budget_id: str, *, max_budget: float | None = None, tpm_limit: int | None = None, rpm_li
tests/unit/proxy/management_endpoints/management_v1/test_teams.py:245
↓ 21 callersMethod_build_claims
Build JWT claims for the outbound MCP access token. Args: user_api_key_dict: LiteLLM auth context for the current reques
litellm/proxy/guardrails/guardrail_hooks/mcp_jwt_signer/mcp_jwt_signer.py:702
↓ 21 callersFunction_cfg
()
tests/unit/llms/bedrock/responses/test_bedrock_openai_responses.py:29
↓ 21 callersFunction_chat
( bridge: _Bridge, model: str, messages: Sequence[JsonValue], *, stream: bool = False, key: str | None = N
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire.py:94
↓ 21 callersFunction_chat_body
(model: str, marker: str, **extra: JsonValue)
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:337
↓ 21 callersFunction_chat_body
( deployment: _Deployment, *, stream: bool = True, tool: Mapping[str, JsonValue] = _SEARCH_FUN
tests/integration/streaming/test_interception_converted_stream_options.py:231
↓ 21 callersFunction_completion
(response: httpx.Response, marker: str)
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire.py:105
↓ 21 callersFunction_context
( logging_obj: LitellmLogging, timeout_seconds: float = 1.0, store: Optional[InMemoryBackgroundSet
tests/unit/interactions/test_background_cost_polling.py:77
↓ 21 callersFunction_create_body
( params: dict[str, object], model: str = SEEDANCE_2_5, drop_params: bool | None = None )
tests/unit/llms/volcengine/test_volcengine_video_transformation.py:46
↓ 21 callersMethod_dest
(index)
tests/unit/integrations/otel/test_otel_v2_destinations.py:4090
↓ 21 callersFunction_drain_async
(wrapper: AnthropicStreamWrapper)
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_first_delta.py:102
↓ 21 callersFunction_echo_tool_served
(tool_result: str)
tests/unit/responses/mcp/test_aresponses_api_with_mcp.py:1663
↓ 21 callersMethod_encode
(unified_id: str)
tests/unit/proxy/common_utils/test_check_batch_cost.py:2767
↓ 21 callersFunction_executor
(*rows: Row, **kwargs)
tests/unit/proxy/list_api/test_in_memory.py:31
↓ 21 callersFunction_fake_boto3_response
(status: str = "Completed", end_time=END_TIME)
tests/unit/llms/bedrock/batches/test_handler.py:42
↓ 21 callersFunction_generic
(vendor: _Vendor)
tests/integration/observability/test_bedrock_converse_guardrail_rewrites.py:253
↓ 21 callersMethod_get_aws_region_name
Get the AWS region name from the environment variables. Parameters: optional_params (dict): Optional parameters for the
litellm/llms/bedrock/base_aws_llm.py:689
↓ 21 callersMethod_get_public_key_from_jwks_url
(self, jwks_url: str, kid: str | None)
litellm/proxy/auth/handle_jwt.py:971
↓ 21 callersMethod_get_span_processor
( self, dynamic_headers: Mapping[str, str] | None = None, config_override: OpenTelemet
litellm/integrations/opentelemetry.py:3119
↓ 21 callersMethod_handle_error
(self, e: Exception, provider_config: _ErrorClassSource)
litellm/interactions/http_handler.py:51
↓ 21 callersFunction_listening
(deployment: _Deployment, count: Callable[[Request], Reply] = _counted)
tests/integration/providers/test_anthropic_count_tokens_system_lift_wire.py:140
↓ 21 callersFunction_make_env_var_server
Lightweight server stand-in for the per-user env-var endpoints. The handlers only read ``server_id``/``server_name``/``alias``/``env_vars``/
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:6765
↓ 21 callersFunction_make_regenerate_existing_key
()
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:13381
↓ 21 callersFunction_mock_agent_models
()
tests/unit/proxy/client/cli/test_configure_commands.py:79
↓ 21 callersMethod_mock_manager_with_toolsets
(self, toolset_perms)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:371
↓ 21 callersFunction_parse_ptu_model
The single holding a team_id deployment parses to, else None; shared deployments parse to one holding per team and have their own tests below.
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:46
↓ 21 callersFunction_patched_prisma_client
(prisma_client)
tests/unit/proxy/rag_endpoints/test_rag_endpoints.py:331
↓ 21 callersFunction_payload
( request_id: str, *, team_id: str | None = "team-a", api_key: str = "hashed-key-1", usage
tests/unit/proxy/guardrails/test_usage_tracking.py:27
↓ 21 callersFunction_peer_add_calls
(peer: McpPeer)
tests/integration/mcp/test_mcp_llm_endpoints.py:630
↓ 21 callersFunction_poll
(client: ManagementClient, attempt: Callable[[], T | None], failure: str)
tests/e2e/management/test_management_e2e.py:58
↓ 21 callersFunction_prisma_with_general_settings
A prisma client whose LiteLLM_Config `general_settings` row holds ``general_settings``.
tests/unit/proxy/management_endpoints/test_coordination_redis_endpoints.py:47
↓ 21 callersMethod_process_chunk
Process a single chunk of data from the stream
litellm/responses/streaming_iterator.py:463
↓ 21 callersMethod_provider
The provider's batch files by id, and a spend-log writer that journals each write. Reading any other file raises missing_file_error, or the No
tests/unit/proxy/common_utils/test_check_batch_cost.py:3914
↓ 21 callersFunction_provider_calls
(requests: tuple[Request, ...])
tests/integration/spend/test_spend_log_tool_payload_content.py:76
↓ 21 callersFunction_register
(scenario: Scenario, body: dict[str, JsonValue], *, status: int = 200)
tests/integration/providers/test_decisions_wire.py:231
← previousnext →2,501–2,600 of 202,479, ranked by callers