MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 57 callersMethodproject
(self, team_id: str, **fields: JsonValue)
tests/integration/_support/client.py:187
↓ 57 callersMethodtag
(self, suffix: str = "")
tests/integration/_support/actors.py:60
↓ 56 callersFunction_guardrail
()
tests/unit/enterprise/enterprise_callbacks/test_secret_detection.py:50
↓ 56 callersFunction_mantle
(count: Callable[[Request], Reply] = _mantle_counted)
tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py:211
↓ 56 callersFunction_mock_post
Queues one shield response per expected call.
tests/unit/proxy/guardrails/guardrail_hooks/test_llm_shield_proxy.py:59
↓ 56 callersFunctiona
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 56 callersMethodaanthropic_messages
( self, **kwargs: object, # kwargs-ok: forwarded to the router endpoint as given )
litellm/router_api.py:1630
↓ 56 callersMethodapply_db_row
(self, row: DbRow, db_row: Mapping[str, JsonValue])
litellm/proxy/config_resolvers/settings_store.py:81
↓ 56 callersFunctioncreateQueryKeys
(resource: T)
ui/litellm-dashboard/src/app/(dashboard)/hooks/common/queryKeysFactory.ts:25
↓ 56 callersMethodcreate_batch
( self, *, body: BatchCreateBody, key: str, provider: str | None = None )
tests/e2e/batches/batch_client.py:200
↓ 56 callersMethodfind_unique
(self, where: Mapping[str, object])
litellm/proxy/management_endpoints/scim/scim_v2.py:126
↓ 56 callersFunctiongenerate_mock_mcp_server_config_record
Generate a mock MCP server record from config.yaml
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:75
↓ 56 callersMethodprocess_input_messages
Process input messages by applying guardrails to text content. ``request_data`` is what the guardrail sees as the request when ``data
litellm/llms/anthropic/chat/guardrail_translation/handler.py:828
↓ 56 callersMethodread
(self, path: str)
tests/unit/harness/core_fakes.py:83
↓ 56 callersMethodsearch
Sync Search handler.
litellm/llms/custom_httpx/llm_http_handler.py:2253
↓ 56 callersMethodtext
(self)
tests/e2e/a2a/a2a_client.py:155
↓ 56 callersMethodupdate
(tools)
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_handler.py:884
↓ 56 callersFunctionuseZodForm
( schema: z.core.$ZodType, props?: Omit<UseFormProps<FieldValues, unknown, FieldValues>, "resolver">, )
ui/litellm-dashboard/src/lib/forms/useZodForm.ts:20
↓ 56 callersMethodvalidate_environment
( self, headers: dict, model: str, messages: list[AllMessageValues], o
litellm/llms/cohere/common_utils.py:51
↓ 55 callersFunctionS
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2s7apn3nfa3q3.js:1
↓ 55 callersFunction_make_admitted_subject
(user_id, *, org_id=None, own_servers=None, own_tool_perms=None)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:8849
↓ 55 callersFunction_make_guardrail
( handler: FakeHandler, *, unreachable_fallback="fail_closed", api_base="https://vigil.test",
tests/unit/proxy/guardrails/guardrail_hooks/test_vigil_guard.py:55
↓ 55 callersFunction_shadow_prisma
The job-table fake honours the filters it is handed, so a read that forgets stopped_at sees rows the partial index would have released, one that f
tests/unit/proxy/management_endpoints/test_auto_router_endpoints.py:1555
↓ 55 callersMethodcopy
()
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 55 callersMethoddescribe
(self)
tests/integration/caching/test_response_cache_chaos.py:146
↓ 55 callersMethodfreeze
(self)
tests/integration/_support/process.py:240
↓ 55 callersMethodis_llm_api_route
Helper to checks if provided route is an OpenAI route Returns: - True: if route is an OpenAI route - False:
litellm/proxy/auth/route_checks.py:461
↓ 55 callersFunctioniter_items
(value: object)
litellm/litellm_core_utils/core_helpers.py:183
↓ 55 callersFunctionmasterKey
()
tests/e2e/ui/helpers/traffic.ts:14
↓ 55 callersFunctionnew_marker
()
tests/integration/providers/_api_base_trailing_slash_support.py:39
↓ 55 callersFunctionnew_marker
()
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:81
↓ 55 callersMethodstore
(self)
tests/unit/redis/stores/spend_counters_double.py:78
↓ 54 callersFunctionT
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 54 callersFunction_apply
Run the production call path: load from env, write to env.
tests/unit/proxy/db/test_db_url_settings.py:46
↓ 54 callersFunction_build_request
( headers: Optional[Dict[str, str]] = None, *, path: str = "/mcp-rest/test/tools/list", method
tests/unit/proxy/mcp_server/test_rest_endpoints.py:43
↓ 54 callersFunction_make_response
(body: dict, status_code: int = 200)
tests/unit/proxy/guardrails/guardrail_hooks/test_xecguard.py:56
↓ 54 callersFunction_marker
()
tests/integration/routing/test_non_chat_model_endpoint_gate.py:217
↓ 54 callersFunctionbuild
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_fallbacks.py:36
↓ 54 callersMethodclose
(self)
tests/integration/_support/wire.py:153
↓ 54 callersFunctionderiveErrorMessage
(errorData: any)
ui/litellm-dashboard/src/lib/http/client.ts:71
↓ 54 callersMethodfirst
()
tests/unit/integrations/otel/test_otel_v2_destinations.py:3707
↓ 54 callersFunctionget_metadata_variable_name_from_kwargs
Helper to return what the "metadata" field should be called in the request data - New endpoints return `litellm_metadata` - Old endpoint
litellm/litellm_core_utils/core_helpers.py:482
↓ 54 callersMethodlocal
(source: Error)
litellm-rust/crates/secrets-cyberark/src/error.rs:69
↓ 54 callersMethodrefine
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 54 callersFunctionresolve_anthropic_wif_params
(litellm_params: Mapping[str, object] | None)
litellm/llms/anthropic/wif.py:136
↓ 54 callersMethodsetMetaProperty
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 54 callersFunctionupstream_requests
(upstream_url: str)
tests/integration/authorization/_hidden_alias_budget.py:207
↓ 53 callersFunctionE
()
litellm/proxy/_experimental/out/_next/static/chunks/2ye73h9seja-1.js:1
↓ 53 callersFunction_one_delivery
(wire: Wire, marker_hex: str)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:611
↓ 53 callersFunction_owned_url
(owned: OwnedProxy)
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:275
↓ 53 callersMethodapi_base
(self)
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire.py:62
↓ 53 callersMethodcancel
(self)
litellm/proxy/roi_calculator/sync.py:501
↓ 53 callersMethoddeployment
(self, id: str)
litellm/proxy/management_endpoints/router_weights.py:36
↓ 53 callersMethoddisconnect
(self)
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:1663
↓ 53 callersFunctiongetGlobalLitellmHeaderName
()
ui/litellm-dashboard/src/components/networking.tsx:530
↓ 53 callersMethodgetValue
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 53 callersFunctionlist
Sync: List all agents on the provider side.
litellm/interactions/agents/main.py:386
↓ 53 callersFunctionlog_redis_failure
( logger: logging.Logger, level: int, message: str, exc: BaseException, with_traceback: bool = False )
litellm/caching/redis_cache.py:402
↓ 53 callersMethodnumber
(key: str)
litellm/router_rust/core.py:4992
↓ 53 callersFunctionscrape
(gateway: Gateway)
tests/integration/_support/prometheus_series.py:240
↓ 53 callersFunctionset_body
(harness: Harness, body: Dict[str, Any])
tests/unit/proxy/batches_endpoints/test_endpoints.py:279
↓ 53 callersMethodsetdefault
(self, key: str, default: object, /)
litellm/llms/bedrock/vector_stores/transformation.py:40
↓ 53 callersFunctionsetup_proxy_logging_object
(monkeypatch, llm_router: Router)
tests/unit/proxy/openai_files_endpoint/test_files_endpoint.py:82
↓ 53 callersFunctionupstream_hits
(observed: tuple[str, ...], marker: str)
tests/integration/authorization/_hidden_alias_budget.py:218
↓ 52 callersFunction_logger
(router=None, prisma=None, jobs=(), counter_store=None, jobs_by_target=None)
tests/unit/integrations/test_shadow_eval_logger.py:240
↓ 52 callersFunction_observed
(upstream_url: str, scenario_id: str)
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:739
↓ 52 callersFunction_post_call_pipeline_data
( guardrail: str = "gr-post", step: PipelineStep | None = None, **extra: Any )
tests/unit/proxy/utils/proxy_logging/test_guardrail_pipeline.py:997
↓ 52 callersFunction_scripted
(scenario: Scenario, response: RealtimeResponse, *, control_url: str | None = None)
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:386
↓ 52 callersMethodasync_post_call_failure_hook
(self, *args, **kwargs)
tests/unit/proxy/hooks/test_post_call_failure_hook_integration.py:86
↓ 52 callersFunctioncall_create
( harness: Harness, *, provider: Optional[str] = None, user: Optional[UserAPIKeyAuth] = None,
tests/unit/proxy/batches_endpoints/test_endpoints.py:283
↓ 52 callersMethodcheck
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 52 callersMethodclient_ack_messages
(self)
litellm/litellm_core_utils/realtime_streaming.py:2230
↓ 52 callersFunctionclone
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 52 callersMethodcontext
( &'a self, snapshot: &'a RouterStateSnapshot, op: &'a Op, request: &'a Router
litellm-rust/crates/router-core/src/select.rs:233
↓ 52 callersFunctionget
(key: &str)
litellm-rust/crates/redis-client/src/commands.rs:175
↓ 52 callersMethodget_config
Load config file Supports reading from: - .yaml file paths - LiteLLM connected DB - GCS - S3
litellm/proxy/proxy_server.py:6570
↓ 52 callersMethodget_error_information
( original_exception: Exception | None, traceback_str: str | None = None, )
litellm/litellm_core_utils/litellm_logging.py:7407
↓ 52 callersFunctionperform_redaction
Performs the actual redaction on the logging object and result. redact_streaming_responses=False skips the in-place redaction of the shared
litellm/litellm_core_utils/redact_messages.py:616
↓ 52 callersFunctionreserve_budget_for_request
( request_body: dict, route: str, llm_router: Router | None, valid_token: UserAPIKeyAuth | Non
litellm/proxy/spend_tracking/budget_reservation.py:250
↓ 52 callersFunctionsecret_vault_factory
()
tests/unit/proxy/conftest.py:247
↓ 52 callersMethodshould_run_guardrail
Override to add debug logging.
litellm/proxy/guardrails/guardrail_hooks/grayswan/grayswan.py:218
↓ 52 callersFunctionto_server_spec
Map a v1 server onto a ServerSpec for a migrated mode, or None to defer to v1. BYOK is the per-user source of the ``api_key`` mode; its scheme ri
litellm/proxy/mcp_server/outbound_credentials/adapter.py:81
↓ 52 callersMethodusage
(self)
tests/integration/providers/_gemini_long_decode_support.py:63
↓ 51 callersFunction_entitlement_fault_globals
(prisma_client=None, user_api_key_cache=None)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:11016
↓ 51 callersMethodadd_deployment
(self, prisma_client=None, proxy_logging_obj=None)
tests/unit/proxy/test_proxy_server.py:3363
↓ 51 callersFunctionanthropic_stream
( *frames: bytes, error: BaseException | None = None, hidden_params: Mapping[str, object] | None =
tests/unit/test_router/core/streaming_helpers.py:311
↓ 51 callersMethodcompletion
(self, *args, **kwargs)
tests/unit/test_router/test_router.py:1774
↓ 51 callersMethodcreate
(e=null,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 51 callersMethodcreate_model
(self, model_name: str, litellm_params: LiteLLMParamsBody)
tests/e2e/batches/batch_client.py:152
↓ 51 callersMethodevaluate
( self, request: JevSystemOneRequest, timeout_s: float, request_kwargs: Mapping[str, object] | None =
tests/unit/router_strategy/test_complexity_router.py:167
↓ 51 callersFunctionfc
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 51 callersMethodfinally
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:1
↓ 51 callersMethodget_cache
(self, key: str, **kwargs: object)
tests/unit/proxy/anthropic_endpoints/test_gateway_endpoints.py:91
↓ 51 callersFunctionget_standard_logging_object_payload
( kwargs: dict | None, init_response_obj: object, start_time: dt_object, end_time: dt_object,
litellm/litellm_core_utils/litellm_logging.py:7861
↓ 51 callersFunctionmake_engine
( poster, reader: Mapping[str, str] | Callable[[str], str | None] | None = None, clock: FakeClock
tests/unit/llms/base_llm/auth/test_token_exchange.py:225
↓ 51 callersMethodmember
Create an internal user and add them to ``team_id``; deleting the user later removes the membership.
tests/integration/_support/client.py:252
↓ 51 callersMethodread
(self)
tests/unit/proxy/client/cli/test_claude_settings.py:414
↓ 51 callersMethodrefetch
({...e}={})
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 51 callersMethodsend
(self, gateway: Gateway, model: str)
tests/integration/providers/test_vertex_partner_count_tokens_wire.py:254
↓ 51 callersMethodtransform_response_api_usage_to_chat_usage
Transforms ResponseAPIUsage or ImageUsage to a Usage object. Both have the same spec with input_tokens, output_tokens, and i
litellm/responses/utils.py:1291
← previousnext →801–900 of 202,479, ranked by callers