MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 25 callersFunction_user
(*blocks: JsonValue)
tests/integration/observability/test_bedrock_converse_guardrail_rewrites.py:372
↓ 25 callersFunction_worker
(shared: SharedRedisCounters | None)
tests/unit/router_strategy/test_least_busy.py:94
↓ 25 callersFunctionacompletion
Asynchronously executes a litellm.completion() call for any of litellm supported llms (example gpt-4, gpt-3.5-turbo, claude-2, command-nightly)
litellm/main.py:645
↓ 25 callersMethodacreate_file
( self, model: str, file: tuple[str, bytes, str], purpose: str, litell
tests/unit/enterprise/proxy/test_managed_files_hook.py:2261
↓ 25 callersMethodaimage_generation
( self, model: str, prompt: str, api_key: Optional[str], api_base: Opt
tests/unit/llms/test_custom_llm.py:229
↓ 25 callersFunctionanswered_ids
(request: Request)
tests/integration/providers/_tool_search_support.py:338
↓ 25 callersMethodasync_get_cache
Internal method to get from the cache. Handles different call types (embeddings, chat/completions, text_completion, transcription)
litellm/caching/caching_handler.py:368
↓ 25 callersFunctionattach_lazy_features
(app: "FastAPI", features: tuple[LazyFeature, ...] = LAZY_FEATURES)
litellm/proxy/_lazy_features.py:566
↓ 25 callersMethodauth_connections
(self)
tests/integration/_support/device_login.py:256
↓ 25 callersMethodbudget_alerts
(self, type, user_info)
tests/unit/proxy/auth/test_auth_checks.py:1084
↓ 25 callersFunctionbuild_tracer_provider
Build the shared :class:`TracerProvider`. Attach the Baggage processor first (so identity attributes land on each span before any export deci
litellm/integrations/otel/plumbing/providers.py:1548
↓ 25 callersFunctionbuild_window_spend_transaction
( entity_type: str, entity_id: str, window_duration: str, window_start: datetime, spend: f
litellm/proxy/db/db_transaction_queue/window_spend_update_queue.py:91
↓ 25 callersFunctioncall
(route: str)
tests/unit/proxy/auth/test_handle_jwt.py:7014
↓ 25 callersFunctioncall_edge
( edge: ProviderEdge, method: str, path: str, *, body: bytes | None = None, headers: d
tests/e2e_harness/test_provider_edge.py:332
↓ 25 callersMethodcall_tool
( self, key: str, *, server_id: str, name: str, arguments: Mcp
tests/e2e/mcp/mcp_client.py:468
↓ 25 callersFunctioncheck_feature_access_for_user
Raise HTTP 403 if the user's role is blocked from accessing the given feature by the UI settings stored in general_settings. Args:
litellm/proxy/common_utils/rbac_utils.py:17
↓ 25 callersFunctionclassification_system_prompt
The classifier's system role, closing on the line that matches the payload it will be sent. One static closing cannot serve both. With no window
litellm/router_strategy/complexity_router/complexity_router.py:395
↓ 25 callersMethodclear
(self)
tests/integration/observability/test_ovalix_guardrail.py:54
↓ 25 callersFunctionconversation
( marker: str, calls: Sequence[JsonValue], *, ask_marked: bool = True, assistant: dict[str
tests/integration/providers/_cache_control_marks_support.py:103
↓ 25 callersMethoddefaultQueryOptions
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 25 callersFunctiondeployed
(gateway: Gateway, scenario: Scenario, **parameters: JsonValue)
tests/integration/providers/_dashscope_video_support.py:173
↓ 25 callersFunctiondrain_logging_tasks
(timeout: float = 5.0)
litellm/responses/streaming_iterator.py:235
↓ 25 callersFunctionerror_frame
(error_type: str = "overloaded_error", message: str = "Overloaded")
tests/unit/test_router/core/streaming_helpers.py:262
↓ 25 callersFunctionfree_reads
(status: str, count: int)
tests/integration/spend/_background_responses.py:213
↓ 25 callersFunctiongetProviderLogoAndName
(providerValue: string)
ui/litellm-dashboard/src/components/provider_info_helpers.tsx:464
↓ 25 callersMethodget_credentials
( self, custom_llm_provider: str, region_name: str | None, )
litellm/proxy/pass_through_endpoints/passthrough_endpoint_router.py:95
↓ 25 callersFunctionget_custom_llm_provider_from_request_headers
Get the `custom_llm_provider` from the request header `custom-llm-provider`
litellm/proxy/common_utils/openai_endpoint_utils.py:78
↓ 25 callersFunctionhealth_services_endpoint
Use this admin-only endpoint to check if the service is healthy. Example: ``` curl -L -X GET 'http://0.0.0.0:4000/health/services?se
litellm/proxy/health_endpoints/_health_endpoints.py:418
↓ 25 callersFunctioni
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 25 callersMethodimage_edit
( self, model: str, image: Any, prompt: str, model_response: ImageResp
tests/unit/llms/test_custom_llm.py:299
↓ 25 callersMethodinit
No global setup needed today; present for lifecycle symmetry.
tests/e2e/lifecycle.py:60
↓ 25 callersMethodis_adaptive_thinking_model
( cls, model: str, custom_llm_provider: str, )
litellm/llms/anthropic/common_utils.py:1151
↓ 25 callersFunctionis_allowed_to_call_vector_store_endpoint
Check if the user is allowed to call the vector store endpoint. Cover: 1. Creating a vector store index 2. Reading a vector store in
litellm/proxy/vector_store_endpoints/utils.py:416
↓ 25 callersFunctionis_audit_logging_enabled
(store_audit_logs: bool | None = None)
litellm/proxy/management_helpers/audit_logs.py:28
↓ 25 callersFunctionis_ptu_cost_attribution_enabled
Whether PTU flat-cost attribution is turned on for this process. A configured secret manager that ``get_secret`` would ask decides, as it does fo
litellm/litellm_core_utils/ptu_pricing.py:30
↓ 25 callersFunctionmake_mcp_request_obj
()
tests/unit/proxy/utils/proxy_logging/conftest.py:119
↓ 25 callersFunctionmantle_peer
(*, pause: float = 0)
tests/integration/providers/_mantle_gpt_prompt_cache_support.py:284
↓ 25 callersFunctionmodel_budget_spend_cache_key
Sole owner of the per-model spend counter key, shared by its writer and all of its readers.
litellm/proxy/hooks/model_max_budget_limiter.py:114
↓ 25 callersFunctionnew_group
()
tests/integration/routing/test_payment_required_mapping.py:60
↓ 25 callersFunctionnew_managed_id
Mint a fresh managed ID for a given raw provider ID.
litellm/proxy/pass_through_endpoints/managed_id_codec.py:95
↓ 25 callersFunctionopenai_error
(status: int)
tests/integration/_support/openai_wire.py:28
↓ 25 callersFunctionprint_verbose
Prints the given `print_statement` to the console if `litellm.set_verbose` is True. Also logs the `print_statement` at the debug level using
litellm/proxy/utils.py:454
↓ 25 callersFunctionready
(replicas: tuple[Replica, ...], database: Database)
tests/e2e/migrations/containers.py:99
↓ 25 callersFunctionreceived_markers
(wire: Wire)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:163
↓ 25 callersMethodrecord
(self, server_id: str, resolution: AuthResolution)
litellm/proxy/mcp_server/mcp_debug.py:154
↓ 25 callersFunctionredis_async
Runs one Redis operation as a Python awaitable, reported to `ServiceLogging` as `call_type`.
litellm-rust/crates/python-bridge/src/redis/store/mod.rs:46
↓ 25 callersMethodregister
(s,o=!0)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 25 callersMethodrelease
(cronjob_id)
tests/unit/proxy/common_utils/test_key_rotation_e2e.py:54
↓ 25 callersFunctionrelease_budget_reservation
(budget_reservation: dict | None)
litellm/proxy/spend_tracking/budget_reservation.py:392
↓ 25 callersMethodremove
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 25 callersMethodremove
(self, value: object)
litellm/router_rust/surface/indexes.py:222
↓ 25 callersMethodresolve_server_api_key
Resolve a single-secret search API key, falling back to a server-managed secret only when the request targets a trusted host.
litellm/llms/base_llm/search/transformation.py:165
↓ 25 callersMethodrun
()
tests/unit/redis/stores/fake_rate_limits.py:256
↓ 25 callersFunctionrun_aws_signing
( sign: Callable[_SignParams, _SignedRequest], /, *args: _SignParams.args, **kwargs: _SignPara
litellm/llms/bedrock/base_aws_llm.py:1738
↓ 25 callersFunctions
()
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 25 callersMethodsafe_get_vertex_ai_project
Safely get Vertex AI project without mutating the litellm_params dict. Unlike get_vertex_ai_project(), this does NOT pop values from
litellm/llms/vertex_ai/vertex_llm_base.py:1221
↓ 25 callersFunctionsafe_json_loads
Safely parse a JSON string. If parsing fails, return the default value (None by default).
litellm/litellm_core_utils/safe_json_loads.py:13
↓ 25 callersMethodsend
(slf: &Bound<'_, Self>, py: Python<'_>, value: Py<PyAny>)
litellm-rust/crates/host-python/src/handle.rs:126
↓ 25 callersMethodset
Store NaCl-encrypted access_token in Redis with the given TTL.
litellm/proxy/mcp_server/oauth2_token_cache.py:277
↓ 25 callersFunctionset_request_destinations
Anchor the destinations this request exports to and return a reset token.
litellm/integrations/otel/plumbing/context.py:467
↓ 25 callersMethodstart
( self, database: Database, migrations: tuple[Migration, ...] = (), *,
tests/e2e/migrations/containers.py:157
↓ 25 callersFunctiontask_api
( status: TaskStatus = succeeded, oss: Reply = MP4_REPLY, prefix: str = "task" )
tests/integration/providers/_dashscope_video_support.py:68
↓ 25 callersMethodtell
(self)
litellm/images/utils.py:21
↓ 25 callersMethodtext
(self)
tests/integration/providers/_gemini_long_decode_support.py:59
↓ 25 callersMethodtoRefractedElement
(s,o,i={})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 25 callersMethodtransform_create_batch_request
( self, model, create_batch_data, optional_params, litellm_params )
tests/unit/llms/base_llm/batches/test_transformation.py:64
↓ 25 callersMethodtransform_request
( self, model: str, messages: list[AllMessageValues], optional_params: dict,
litellm/llms/bedrock/chat/invoke_transformations/anthropic_claude_transformation.py:245
↓ 25 callersMethodupdate
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 25 callersFunctionupdate_headers_with_filtered_beta
Update headers dict by filtering and transforming anthropic-beta header values. Modifies the headers dict in place and returns it. Args:
litellm/anthropic_beta_headers_manager.py:425
↓ 25 callersFunctionupdate_model
Old endpoint for model update. Makes a PUT request. Use `/model/{model_id}/update` to PATCH the stored model in db.
litellm/proxy/management_endpoints/model_management_endpoints.py:3348
↓ 25 callersMethodupload_file
( self, *, content: bytes, form: FileUploadForm, key: str, mod
tests/e2e/batches/batch_client.py:160
↓ 24 callersFunctionJ
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 24 callersFunctionZ
litellm/proxy/_experimental/out/_next/static/chunks/2s7apn3nfa3q3.js:1
↓ 24 callersFunction_accumulator
()
tests/unit/proxy/db/test_gateway_request_tracking.py:37
↓ 24 callersFunction_as_user
(user_id="user-a")
tests/unit/proxy/credential_endpoints/test_endpoints.py:2093
↓ 24 callersFunction_assert_rag_query_outcome
(request: Awaitable[bool], denied_by: ProxyErrorTypes | None)
tests/unit/proxy/auth/test_auth_checks_object_access_and_lookup.py:1999
↓ 24 callersFunction_bedrock_tools_pt
OpenAI tools looks like: tools = [ { "type": "function", "function": { "name": "get_current_w
litellm/litellm_core_utils/prompt_templates/factory.py:5843
↓ 24 callersFunction_billed
(model: str)
tests/integration/providers/test_ollama_prompt_tools_wire.py:186
↓ 24 callersFunction_body
(endpoint: Endpoint, model: str, *, stream: bool = True, **extra: JsonValue)
tests/integration/providers/test_bedrock_stream_timeout_wire.py:223
↓ 24 callersFunction_cache
(callback_name, exporters=None)
tests/unit/integrations/otel/test_otel_v2_dynamic.py:20
↓ 24 callersFunction_caller_loader
(email: str | None)
tests/unit/proxy/mcp_server/test_oauth_identity_binding.py:64
↓ 24 callersFunction_chat
(gateway: Gateway, name: str, **extra: JsonValue)
tests/integration/providers/test_databricks_agent_wire.py:164
↓ 24 callersFunction_chat_caller_response
(reply: Reply, model: str)
tests/integration/observability/_openinference_support.py:184
↓ 24 callersFunction_chat_rounds_logging_obj
(recorder: _ChatRoundRecorder, call_id: str, stream: bool)
tests/unit/responses/mcp/test_chat_completions_handler.py:1637
↓ 24 callersFunction_client
( http_client: FakeHTTPClient, max_retries: int = 3, api_url: str = API_URL, validate_upload_u
tests/unit/integrations/pointfive/test_upload_client.py:93
↓ 24 callersMethod_commit_spend_updates_to_db
Commits all the spend `UPDATE` transactions to the Database
litellm/proxy/db/db_spend_update_writer.py:2338
↓ 24 callersFunction_common_call_kwargs
(client)
tests/unit/llms/soniox/audio_transcription/test_soniox_audio_transcription_handler.py:90
↓ 24 callersFunction_deployment
( scenario: Scenario, wire: Wire, route: str, backend: str, model_info: Mapping[str, JsonValue] | None = N
tests/integration/providers/test_bedrock_native_structured_output_wire.py:449
↓ 24 callersFunction_echo_tool_served
()
tests/unit/responses/mcp/test_chat_completions_handler.py:1652
↓ 24 callersFunction_emit
``log_event_on_langfuse`` is the entry point that folds ``langfuse_*`` headers into metadata. Both the trace-level and the observation fields are
tests/unit/integrations/test_langfuse.py:1684
↓ 24 callersFunction_emitted
(auth: httpx2.Auth)
tests/unit/proxy/mcp_server/outbound_credentials/test_resolver.py:136
↓ 24 callersFunction_enable_aes
(monkeypatch)
tests/unit/proxy/management_endpoints/test_credential_migration.py:40
↓ 24 callersMethod_env
(self, monkeypatch)
tests/unit/proxy/test_litellm_pre_call_utils.py:10261
↓ 24 callersFunction_failure_fields_to_lift
Failure-path callbacks run after ``litellm_logging_obj`` is popped from request_data (it is not serialisable), so the caller merges these fields
litellm/proxy/utils.py:1821
↓ 24 callersFunction_get
(query: str = WINDOW)
tests/unit/proxy/management_endpoints/management_v1/test_spend_logs.py:82
↓ 24 callersFunction_guardrail_info
(data: dict)
tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py:300
↓ 24 callersFunction_headers
(key: str | None)
tests/unit/proxy/discovery_endpoints/test_skill_hub_endpoints.py:69
↓ 24 callersFunction_inputs
(**overrides: object)
tests/unit/proxy/guardrails/guardrail_hooks/test_airia.py:67
↓ 24 callersFunction_jwt_handler_double
()
tests/unit/proxy/management_endpoints/test_ui_sso.py:354
↓ 24 callersMethod_loader
( groups: Sequence[LiteLLM_AccessGroupTable], unreadable: AbstractSet[str] = frozenset(),
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:11697
← previousnext →2,101–2,200 of 202,479, ranked by callers