MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 19 callersMethodchildren
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 19 callersFunctioncleanup_batch
( client: BatchCleanupClient, batch_id: str, *, key: str, provider: str | None = None,
tests/e2e/batches/batch_cleanup.py:80
↓ 19 callersMethodclose
(self)
tests/unit/llms/custom_httpx/test_aiohttp_transport.py:78
↓ 19 callersMethodcopy
(e=null)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 19 callersFunctioncreate_scratch_key
( gateway_client: GatewayClient, seeder_cleartext: str, scratch_prefix: str, *, user_id: s
tests/integration/_support/actors.py:262
↓ 19 callersMethoddelete_guardrail
(self, guardrail_id: str)
tests/e2e/guardrails/guardrails_client.py:265
↓ 19 callersMethoddelete_in_memory_guardrail
Delete a guardrail in memory and remove from litellm callbacks. The callback is purged from every callback list, not just li
litellm/proxy/guardrails/guardrail_registry.py:961
↓ 19 callersMethoddeployment_callback_on_failure
Count the failure and cool the deployment down when the rules say so.
litellm/router_rust/surface/health.py:408
↓ 19 callersMethoddrain
(self)
tests/integration/observability/test_guardrail_stream_scope_matrix.py:609
↓ 19 callersMethodenqueue
Add a coroutine to the logging queue. Hot path: never blocks, aggressively clears queue if full.
litellm/litellm_core_utils/logging_worker.py:280
↓ 19 callersFunctionensure_batch_response_managed_file_ids
Normalize batch file IDs and register output and error file metadata.
litellm/proxy/openai_files_endpoints/common_utils.py:1463
↓ 19 callersMethodenter
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 19 callersMethodexchange
(self, subject_token, server, config, *, tenant_id="")
tests/unit/proxy/mcp_server/outbound_credentials/test_resolver.py:321
↓ 19 callersFunctionfailing
(message: str = "order one is down")
tests/integration/routing/test_fallback_hop_foreign_encrypted_reasoning.py:112
↓ 19 callersFunctionfallback_ok
(opened: list[ByteStream] | None = None)
tests/unit/test_router/core/test_streaming_characterization_anthropic.py:53
↓ 19 callersFunctionfetch_all_mcp_servers
Get all of the configured mcp servers for the user in the db with their associated teams ``` curl --location 'http://localhos
litellm/proxy/management_endpoints/mcp_management_endpoints.py:1394
↓ 19 callersFunctionfetch_keycloak_assertion
POSTs one fresh client_credentials grant and returns the resulting ``access_token`` as the workload assertion; the caller must not cache the resul
litellm/llms/base_llm/auth/client_credentials.py:190
↓ 19 callersFunctionfilter_and_transform_beta_headers
Filter and transform beta headers based on provider's mapping configuration. This function: 1. Only allows headers that are present in t
litellm/anthropic_beta_headers_manager.py:280
↓ 19 callersFunctionflatten_top_level_schema_combinators
Merge top-level ``allOf``/``anyOf``/``oneOf`` branches into an object tool schema. OpenAI's function-calling validator rejects tool ``parameters`
litellm/litellm_core_utils/prompt_templates/json_schema_utils.py:144
↓ 19 callersMethodgetAPIList
(e,t,s)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:29
↓ 19 callersMethodgetState
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 19 callersMethodget_allowed_mcp_servers
Get the allowed MCP Servers for the user. Priority: 1. If object_permission.mcp_servers is explicitly set, use it (even for
litellm/proxy/mcp_server/mcp_server_manager.py:3696
↓ 19 callersFunctionget_daily_activity
( prisma_client: PrismaClient | None, table_name: str, entity_id_field: str, entity_id: str |
litellm/proxy/management_endpoints/common_daily_activity.py:952
↓ 19 callersFunctionget_key_object
- Check if team id in proxy Team Table - if valid, return LiteLLM_TeamTable object with defined limits - if not, then raise an error
litellm/proxy/auth/auth_checks.py:4348
↓ 19 callersMethodget_mcp_server_by_name
(self, server_name: str, client_ip: str | None = None)
litellm/proxy/mcp_server/server_resolution.py:20
↓ 19 callersFunctionget_metadata_variable_name
Helper to return what the "metadata" field should be called in the request data For all /thread or /assistant endpoints we need to call this
litellm/proxy/litellm_pre_call_utils.py:883
↓ 19 callersFunctionget_object_permission
- Check if object permission id in proxy ObjectPermissionTable - if valid, return LiteLLM_ObjectPermissionTable object - if not, then rai
litellm/proxy/auth/auth_checks.py:4449
↓ 19 callersFunctionget_redis_connection_pool
( **env_overrides, )
litellm/_redis.py:936
↓ 19 callersMethodget_requested_anthropic_messages_optional_param
Filter parameters to only include those defined in AnthropicMessagesRequestOptionalParams. Args: params: Dictionary of p
litellm/llms/anthropic/messages/native/utils.py:296
↓ 19 callersFunctionget_response_cost_from_hidden_params
( hidden_params: Mapping[str, object] | BaseModel, )
litellm/cost_calculator.py:2479
↓ 19 callersMethodget_streaming_scan_key
(self, responses_so_far: Sequence[object])
litellm/llms/a2a/chat/guardrail_translation/handler.py:344
↓ 19 callersFunctionget_tags_from_request_body
Extract tags from request body metadata. Args: request_body: The request body dictionary Returns: List of tag names (st
litellm/proxy/common_utils/http_parsing_utils.py:768
↓ 19 callersFunctionget_valid_models
Returns a list of valid LLMs based on the set environment variables Args: check_provider_endpoint: If True, will check the provider'
litellm/utils.py:9189
↓ 19 callersFunctiongroup_members
(group: int)
tests/integration/_support/process.py:137
↓ 19 callersFunctionhandler
(approval: Approval)
tests/unit/harness/test_runtime.py:338
↓ 19 callersMethodhealth_check
Health check endpoint for the prisma client
litellm/proxy/utils.py:8165
↓ 19 callersFunctioniD
(e,t,r={path:[],schemaPath:[]})
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:53
↓ 19 callersFunctionids_of
The ids of a ``select(kind="healthy")`` result, in order (a single dict gives one id).
tests/unit/test_router/core/selection_helpers.py:80
↓ 19 callersMethodinitialize_azure_sdk_client
( self, litellm_params: dict, api_key: str | None, api_base: str | None,
litellm/llms/azure/common_utils.py:867
↓ 19 callersFunctionis_proxy_admin
(user_api_key_dict: UserAPIKeyAuth | None)
litellm/litellm_core_utils/resource_ownership.py:7
↓ 19 callersFunctioniter_message_text
Yield every text fragment from ``messages`` AND ``input``. Walks every role (user, assistant, system, …) — guardrails inspect the entire conv
litellm/proxy/guardrails/_content_utils.py:315
↓ 19 callersFunctionlives_one_hour
(pin: Pin)
tests/integration/routing/_prompt_cache_pin_support.py:42
↓ 19 callersFunctionload_guardrail_translation_mappings
()
litellm/llms/__init__.py:212
↓ 19 callersMethodlogging
(self, stream: bool = False)
tests/unit/proxy/hooks/test_autorouter_baseline_cache.py:239
↓ 19 callersFunctionmerge_guardrailed_tools
( original_tools: Sequence[Tool], flattened_groups: Sequence[Sequence[Tool]], guardrailed_tools: I
litellm/llms/openai/responses/guardrail_translation/tool_merge.py:165
↓ 19 callersFunctionmessage_stream
(message_id: str, model: str, text: str)
tests/integration/_support/anthropic_sse.py:89
↓ 19 callersMethodmget
(self, keys: Sequence[str])
litellm/caching/redis_batch.py:312
↓ 19 callersFunctionmint
(gateway: Gateway, key: str, model: str, text: str)
tests/integration/authorization/_responses_compact.py:255
↓ 19 callersMethodmodel
(self, mode: Mode)
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire.py:55
↓ 19 callersMethodmodel_dump
(self)
tests/unit/proxy/spend_tracking/test_spend_management_endpoints.py:380
↓ 19 callersMethodmodel_response_creator
( self, chunk: dict | None = None, hidden_params: Mapping[str, object] | None = None,
litellm/litellm_core_utils/streaming_handler.py:1000
↓ 19 callersFunctionn
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 19 callersFunctiono
(e,t,n,s,r,i)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 19 callersMethodonly_call
(self)
tests/unit/llms/nvidia_riva/audio_transcription/test_handler.py:65
↓ 19 callersMethodopen
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2421p_tyy9-sd.js:1
↓ 19 callersFunctionopenai_exception_handler
(request: Request, exc: ProxyException)
litellm/proxy/proxy_server.py:2346
↓ 19 callersFunctionoptional_str
(value: object)
litellm/rust_bridge/public_call.py:27
↓ 19 callersMethodpre_call_hook
( self, user_api_key_dict: UserAPIKeyAuth, data: None, call_type: CallTypesLit
litellm/proxy/utils.py:3201
↓ 19 callersMethodprocess_output_response
( self, response, guardrail_to_apply, litellm_logging_obj=None, user_api_key_dict=None, request_data=N
tests/unit/proxy/policy_engine/test_pipeline_executor.py:1611
↓ 19 callersFunctionprompt
(marker: str)
tests/integration/routing/_reasoning_effort_levels_support.py:47
↓ 19 callersMethodquery_raw
(self, query: str)
litellm/repositories/user_repository.py:63
↓ 19 callersFunctionr
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:8
↓ 19 callersMethodrate_limit_counter
( self, key: str, value: str, rate_limit_type: Literal["requests", "tokens"] )
litellm/proxy/hooks/parallel_request_limiter_v3.py:1193
↓ 19 callersFunctionraw_answer
(gateway: Gateway, body: Mapping[str, JsonValue])
tests/integration/providers/test_chat_completions_tool_search_wire.py:334
↓ 19 callersFunctionrelease_gil
Runs work detached from the interpreter and records the release. `f` must not access Python state while the interpreter is detached.
litellm-rust/crates/host-python/src/gil.rs:59
↓ 19 callersMethodrender
(self)
tests/code_coverage_tests/check_unbounded_in_lists.py:64
↓ 19 callersFunctionrequest_logging
The logging object a request shares across its attempts (``litellm_logging_obj``).
tests/unit/test_router/core/streaming_helpers.py:70
↓ 19 callersFunctionresolve_and_validate_end_user_id
Optionally drop end-user ids that don't resolve to a known DB row. Default: pass-through. LiteLLM's documented pattern is that the `user` fie
litellm/proxy/auth/auth_checks.py:2312
↓ 19 callersFunctions
(s,r)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:53
↓ 19 callersFunctions
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 19 callersMethodsafe_get_vertex_ai_credentials
Safely get Vertex AI credentials without mutating the litellm_params dict. Unlike get_vertex_ai_credentials(), this does NOT pop val
litellm/llms/vertex_ai/vertex_llm_base.py:1242
↓ 19 callersFunctionsent_body
(route: respx.Route)
tests/unit/llms/sail/helpers.py:28
↓ 19 callersMethodserialize
(self, frame: _Frame)
litellm/integrations/ternary/export_engine.py:75
↓ 19 callersFunctionsetOpen
(open: boolean)
ui/litellm-dashboard/src/app/(dashboard)/mcp-servers/_components/UserEnvVarsModal.integration.test.tsx:32
↓ 19 callersMethodset_local
A memory write alone, with ``default_in_memory_ttl`` when ``ttl`` is None.
litellm/proxy/common_utils/user_api_key_cache.py:166
↓ 19 callersMethodset_model_list
Replace every deployment (``set_model_list``). All or nothing: when an entry raises, the deployments served before the call are put back and t
litellm/router_rust/surface/registry.py:841
↓ 19 callersMethodsingle_span
(self, response_id: str)
tests/integration/observability/test_otel_conversation_id.py:170
↓ 19 callersMethodsnapshot
(self)
litellm/llms/xai/realtime/usage_meter.py:115
↓ 19 callersFunctionstarted
(sandbox=None, **kwargs)
tests/unit/llms/opencode/harness/test_transformation.py:200
↓ 19 callersFunctionstarted
(ctx: SessionContext)
tests/unit/llms/pi/harness/test_transformation.py:250
↓ 19 callersFunctionstream_reply
(chunks: tuple[bytes, ...], *, abort_after: int | None = None, pause: float = 0)
tests/integration/_support/anthropic_sse.py:119
↓ 19 callersFunctionsuccessful_response
(mount: str, url: str, status: int, headers: Mapping[str, str], body: bytes)
tests/e2e/provider_cache.py:185
↓ 19 callersFunctiontoken_response
(token: str = "sk-ant-oat01-minted", expires_in: int | None = 3600)
tests/unit/llms/anthropic/test_anthropic_wif.py:105
↓ 19 callersMethodtrace
(self, name, **kwargs)
litellm/litellm_core_utils/dd_tracing.py:49
↓ 19 callersMethodtrack_gateway_session
(self, gateway_session_id: str)
litellm/proxy/mcp_server/mcp_server_manager.py:6486
↓ 19 callersMethodtransform_request
( self, model: str, messages: list["AllMessageValues"], optional_params: dict,
litellm/completion_extras/litellm_responses_transformation/transformation.py:1257
↓ 19 callersMethodtransform_retrieve_file_response
( self, raw_response: httpx.Response, logging_obj: LiteLLMLoggingObj, litellm_
litellm/llms/xai/files/transformation.py:178
↓ 19 callersMethodtransform_streaming_response
(self, **kwargs)
tests/unit/responses/test_streaming_iterator.py:1695
↓ 19 callersMethodtransform_text_to_speech_response
(self, model, raw_response, logging_obj)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:5986
↓ 19 callersMethodtranslate_messages_to_responses_input
Convert Anthropic messages list to Responses API `input` items. Mapping: system text -> message(role=system, input_
litellm/llms/anthropic/messages/responses_adapters/transformation.py:299
↓ 19 callersFunctionturn_on_json
Turn on JSON logging - Adds a JSON formatter to all loggers
litellm/_logging.py:1185
↓ 19 callersFunctionu
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 19 callersMethodupdate
(self, *, data: Mapping[str, object], **kwargs: object)
tests/unit/proxy/agent_endpoints/test_endpoints.py:179
↓ 19 callersFunctionupstream
(request)
tests/unit/proxy/mcp_server/test_mcp_debug.py:366
↓ 19 callersMethodupstream_reply
(self)
tests/integration/providers/test_decisions_openai_format_wire.py:135
↓ 19 callersFunctionvalidate_budget_duration
Reject budget durations that can't be parsed, are non-positive, or overflow date math, so a bad value can't be persisted and later crash the b
litellm/proxy/management_endpoints/common_utils.py:28
↓ 19 callersMethodwrite
(self, name: str, value: str)
tests/e2e/secret_manager/secret_store.py:11
↓ 19 callersFunctionzip_bytes
(files: dict[str | zipfile.ZipInfo, bytes])
tests/unit/proxy/discovery_endpoints/test_agent_skills_archive.py:25
↓ 18 callersMethod__init__
(self)
tests/unit/proxy/policy_engine/test_pipeline_executor.py:1185
↓ 18 callersFunction_assert_billed
(row: Mapping[str, JsonValue], rates: tuple[float, float])
tests/integration/spend/test_background_interaction_settlement.py:372
← previousnext →3,001–3,100 of 202,479, ranked by callers