MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersFunctions
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 5 callersFunctions
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 5 callersFunctions3_media_url
Transcribe accepts media as s3://bucket/key or as an https S3 URL; the bucket is required to live in the job's region, so the s3 form maps on
litellm/proxy/pass_through_endpoints/llm_provider_handlers/transcribe_passthrough_logging_handler.py:484
↓ 5 callersFunctionsK
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 5 callersFunctionsL
litellm/proxy/_experimental/out/_next/static/chunks/269vry4mb17-_.js:3
↓ 5 callersFunctionsZ
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 5 callersFunctionsafe_get_request_query_params
(request: Request | None)
litellm/proxy/common_utils/http_parsing_utils.py:443
↓ 5 callersFunctionsameTierIdentity
(left: string, right: string)
ui/litellm-dashboard/src/components/add_model/tier_rows.ts:50
↓ 5 callersFunctionsanitize_prometheus_label_name
Sanitize a label name to comply with Prometheus label name requirements. Prometheus label names must match: ^[a-zA-Z_][a-zA-Z0-9_]*$ - F
litellm/types/integrations/prometheus.py:9
↓ 5 callersFunctionsanitize_vertex_anthropic_output_params
Strip Vertex-unsupported keys from ``output_config`` / ``output_format`` in-place; forward whatever remains. Behavior: * ``output_
litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/output_params_utils.py:66
↓ 5 callersMethodsave_health_check_result
Save health check result to database
litellm/proxy/utils.py:8263
↓ 5 callersFunctionschedule
(monkeypatch, models)
tests/unit/integrations/email_alerting/test_model_deprecation_email.py:78
↓ 5 callersMethodscheme
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersFunctionscope
(changed: list[str])
tests/unit/test_select_ui_test_scope.py:52
↓ 5 callersFunctionscoped_structured_message_indices
( messages: Sequence[AllMessageValues], *, scan_only_tool_results: bool, skip_system: bool,
litellm/llms/base_llm/guardrail_translation/utils.py:298
↓ 5 callersFunctionscripted_in_process
(response: JsonResponse | SseResponse)
tests/integration/caching/response_cache_case.py:262
↓ 5 callersMethodsdk
(self, key: str)
tests/integration/security/test_fine_tuning_managed_ids.py:185
↓ 5 callersFunctionse
(e)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:2
↓ 5 callersFunctionsearch
Synchronous Search function. Args: query: Search query (string or list of strings) search_provider: Provider name (e.g., "pe
litellm/search/main.py:174
↓ 5 callersFunctionseconds
(field: &Field<'_>)
litellm-rust/crates/python-bridge/src/redis/store/policy.rs:46
↓ 5 callersMethodseed_request_identity
Attach request-identity Baggage to the current context + server span. Seeding identity into Baggage makes **every** span emitted afterwards f
litellm/integrations/otel/logger.py:733
↓ 5 callersFunctionseen
(endpoint: Endpoint, stream: bool, frames: tuple[dict[str, JsonValue], ...], raw: str)
tests/integration/providers/_gemini_long_decode_support.py:480
↓ 5 callersFunctionselectAutoRouterOption
(field: string, option: string)
ui/litellm-dashboard/tests/autoRouterSetup.ts:27
↓ 5 callersFunctionselectModel
(page: PlaywrightPage, model: string)
tests/e2e/ui/helpers/playground.ts:48
↓ 5 callersFunctionselect_connection
(stored: StoredROISettings, selected: StoredConnection)
litellm/proxy/roi_calculator/settings.py:87
↓ 5 callersFunctionselect_global_otel_v2_logger
The single ``OpenTelemetryV2`` whose provider should become the OTel global. The callback factory designates one logger as canonical the moment i
litellm/integrations/otel/logger.py:913
↓ 5 callersFunctionsend
(call: DecisionsCall)
litellm/decisions/call.py:843
↓ 5 callersFunctionsend
(gateway: Gateway, endpoint: Endpoint, body: Mapping[str, JsonValue], *, key: str | None = None)
tests/integration/providers/_mantle_gpt_prompt_cache_support.py:580
↓ 5 callersFunctionsend
(gateway: Gateway, path: str, group: str, stream: bool = False)
tests/integration/spend/test_router_cooldown_failure_row.py:157
↓ 5 callersFunctionsend
(history_source: str)
tests/integration/management/test_tool_policy_user.py:755
↓ 5 callersFunctionsend
(payload: str)
tests/unit/llms/meta/realtime/test_meta_realtime_transformation.py:230
↓ 5 callersMethodsend
(self, message: str | bytes)
litellm/llms/soniox/realtime/transformation.py:407
↓ 5 callersMethodsend
(self, route: str, marker: str)
tests/integration/observability/test_otel_cache_hit_cost.py:196
↓ 5 callersMethodsend_daily_reports
Send a daily report on: - Top 5 deployments with most failed requests - Top 5 slowest deployments (normalized by latency/outp
litellm/integrations/SlackAlerting/slack_alerting.py:352
↓ 5 callersMethodsend_email
( self, from_email: str, to_email: List[str], subject: str, html_body:
enterprise/litellm_enterprise/enterprise_callbacks/send_emails/resend_email.py:43
↓ 5 callersFunctionsend_offsets
Seconds after the run starts to send each request of the plan, in plan order: a step's requests spread evenly over its window, each moved by up to
tests/e2e/perf/setup/ramp.py:27
↓ 5 callersFunctionsend_response
(response: Response)
tests/unit/proxy/lens/test_buffering.py:40
↓ 5 callersMethodsend_soft_budget_alert_email
Send email to user when soft budget is crossed
enterprise/litellm_enterprise/enterprise_callbacks/send_emails/base_email.py:223
↓ 5 callersFunctionsend_text_external
Send an absolute URL outside the proxy a raw text body (or none) and keep the answer as text, for an API that takes and returns neither JSON nor f
tests/e2e/e2e_http.py:596
↓ 5 callersFunctionsent
(server: RecordingServer)
tests/test_litellm_rust/messages/test_requests.py:15
↓ 5 callersMethodsentinel
(&self)
litellm-rust/crates/redis-testing/src/sentinel.rs:103
↓ 5 callersFunctionsequence
(value: object)
litellm/router_strategy/switchyard_router/translation.py:28
↓ 5 callersFunctionserialize_multipart_form_fields
Encode a JSON-shaped body as OpenAI-SDK-style multipart file-tuples so a file-less request is still sent as multipart/form-data, working arou
litellm/litellm_core_utils/llm_request_utils.py:102
↓ 5 callersFunctionserve
()
tests/unit/proxy/test_proxy_server.py:213
↓ 5 callersFunctionserve_unary
( machine: HostedMachine<P>, services: S, interceptors: H, encoder: A, observers: Option<O
litellm-rust/crates/host-http/src/driver.rs:22
↓ 5 callersMethodserved_by
(self, marker: str)
tests/integration/routing/test_prompt_cache_pin_ttl.py:116
↓ 5 callersFunctionserved_by_rust
(sents: tuple[Sent, ...])
tests/integration/providers/_idle_upstream_support.py:615
↓ 5 callersFunctionserved_identity
(status: int, text: str, marker: str)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:330
↓ 5 callersFunctionserver_owned_wif_fields_named
Server-owned federation or OAuth token-exchange field names appearing in ``keys``, whatever value they carry. The write gates on credentials
litellm/types/router.py:520
↓ 5 callersMethodservice_spans
(self)
tests/unit/proxy/db/test_log_db_metrics_service_spans.py:58
↓ 5 callersFunctionsession_logout
Revoke the UI session key this request authenticated with. Only accepts UI session keys (minted by dashboard login); any other credentia
litellm/proxy/management_endpoints/session_endpoints.py:121
↓ 5 callersMethodsession_updated_event
Build the OpenAI session.updated ack reflecting the client's requested modalities.
litellm/llms/bedrock/realtime/transformation.py:906
↓ 5 callersMethodset
`DualCache.async_set_cache`, writing `json.dumps(value)`.
litellm-rust/crates/redis-store/src/auth_cache/mod.rs:108
↓ 5 callersMethodsetCurSelection
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 5 callersFunctionsetGlobalLitellmHeaderName
(headerName: string = "Authorization")
ui/litellm-dashboard/src/components/networking.tsx:525
↓ 5 callersFunctionsetInvitedUserPassword
( request: APIRequestContext, userId: string, password: string, )
tests/e2e/ui/helpers/userOnboarding.ts:7
↓ 5 callersMethodset_cache
(self, credentials: dict, service_name: str, logging_obj: object)
litellm/litellm_core_utils/specialty_caches/dynamic_logging_cache.py:72
↓ 5 callersMethodset_cache
(self, key: str, value: tuple[object, ...], *, ttl: float)
litellm/router_strategy/least_busy.py:218
↓ 5 callersMethodset_cache
(self, key: object, value: int, local_only: bool = False, *, ttl: int = ...)
litellm/router_rust/core.py:1313
↓ 5 callersMethodset_cached_openai_client
Stores the OpenAI client in the in-memory cache for _DEFAULT_TTL_FOR_HTTPX_CLIENTS SECONDS ``litellm_owned_client`` says litellm built this c
litellm/llms/openai/common_utils.py:372
↓ 5 callersFunctionset_callbacks
Globally sets the callback client
litellm/litellm_core_utils/litellm_logging.py:5630
↓ 5 callersFunctionset_cooldown_deployments
Add a model to the list of models being cooled down for that minute, if it exceeds the allowed fails / minute or the exception is not o
litellm/router_utils/cooldown_handlers.py:583
↓ 5 callersMethodset_custom_routing_strategy
(self, CustomRoutingStrategy: "CustomRoutingStrategyBase")
litellm/router_rust/core.py:2047
↓ 5 callersMethodset_default_vertex_config
Sets vertex configuration from provided config and/or environment variables Args: config (Optional[dict]): Configuration dictiona
litellm/proxy/pass_through_endpoints/passthrough_endpoint_router.py:320
↓ 5 callersMethodset_hidden_params
(self, params: Mapping[str, object])
litellm/types/extraction.py:148
↓ 5 callersMethodset_password
(self, service_name: str, username: str, password: str)
litellm/litellm_core_utils/cli_keyring.py:98
↓ 5 callersMethodset_return
(self, return_inputs: GenericGuardrailAPIInputs)
tests/unit/proxy/management_endpoints/test_policy_endpoints.py:28
↓ 5 callersFunctionsetting
(kwarg: &str)
litellm-rust/crates/redis-resolve/src/keys.rs:268
↓ 5 callersMethodsettings
(self)
litellm/router_core.py:32
↓ 5 callersFunctionsettings_file_owners
The commands whose backups guard settings_path: `lite up` and `lite autoroute start` only ever manage the default file.
litellm/proxy/client/cli/commands/claude_settings.py:119
↓ 5 callersMethodsettle
(self)
tests/unit/llms/edenai/conftest.py:37
↓ 5 callersFunctionsettled
(send: Callable[[], T], text: Callable[[T], str])
tests/integration/routing/test_payment_required_mapping.py:97
↓ 5 callersFunctionsettled
(page: Page, timeout: float)
tests/e2e/perf/setup/ui_journeys.py:279
↓ 5 callersMethodsetup_generate_content_call
Common setup logic for generate_content calls Args: model: The model name contents: The content to generate
litellm/google_genai/main.py:93
↓ 5 callersFunctionsetup_profile_path
(target: Target, settings_path: Path)
litellm/proxy/client/cli/commands/configure_profiles.py:74
↓ 5 callersMethodshadowed_db_keys
Keys the config file owns whose stored value differs, so the stored one never reaches a reader.
litellm/proxy/config_resolvers/settings_store.py:74
↓ 5 callersFunctionshaped
(document: Document, object: Map<String, Value>)
litellm-rust/crates/python-bridge/src/router/config.rs:126
↓ 5 callersFunctionshard_errors
(executions: tuple[ShardExecution, ...], count: int)
tests/integration/_support/sharding.py:33
↓ 5 callersMethodshared
The parsed model, for a count-only counter to share instead of parsing it again.
litellm-rust/crates/token-counter-huggingface/src/lib.rs:48
↓ 5 callersFunctionshould_allow_legacy_cloud_file_ids
( litellm_params: Mapping[str, object] | None = None, )
litellm/litellm_core_utils/cloud_storage_security.py:135
↓ 5 callersMethodshould_rate_limit
Check if any of the rate limit descriptors should be rate limited. Returns a RateLimitResponse with the overall code and status for e
litellm/proxy/hooks/parallel_request_limiter_v3.py:1365
↓ 5 callersMethodshould_rate_limit
( self, *, descriptors: Sequence[RateLimitDescriptor], parent_otel_span: object, read_only: bool )
tests/unit/llms/anthropic/messages/test_caller_model_checks.py:168
↓ 5 callersMethodshould_run_guardrail
(self, data: dict, event_type: GuardrailEventHooks)
litellm/proxy/guardrails/guardrail_hooks/cisco_ai_defense/cisco_ai_defense_mcp.py:70
↓ 5 callersMethodshould_run_prompt_management_hooks
Return True if prompt management hooks should be run
litellm/litellm_core_utils/litellm_logging.py:1341
↓ 5 callersMethodshould_use_litellm_mcp_gateway
(tools: Iterable[ToolParam] | None)
litellm/responses/mcp/litellm_proxy_mcp_handler.py:144
↓ 5 callersFunctionshow_commands
Display available commands, minus any the operator chose to hide.
litellm/proxy/client/cli/interface.py:84
↓ 5 callersFunctionsidebarLink
(page: PlaywrightPage, name: string | RegExp)
tests/e2e/ui/helpers/navigation.ts:5
↓ 5 callersMethodsign_aws_request
Sign AWS request using Signature Version 4. Args: service_name: AWS service name ("bedrock" or "s3") data: R
litellm/llms/bedrock/common_utils.py:2718
↓ 5 callersFunctionsignature_only
(signature: JsonValue = SIGNATURE, index: int = 0)
tests/integration/_support/anthropic_thinking.py:208
↓ 5 callersMethodsize_hint
(&self)
litellm-rust/crates/gateway-forward/src/forward.rs:166
↓ 5 callersFunctionslow_start_stream
()
tests/unit/proxy/common_utils/test_sse_keepalive.py:65
↓ 5 callersMethodsnapshot
(self)
litellm/litellm_core_utils/json_fragment_accumulator.py:85
↓ 5 callersMethodsnapshot
(&self)
litellm-rust/crates/host/src/lifecycle.rs:64
↓ 5 callersMethodsnapshot
(&self)
litellm-rust/crates/python-bridge/src/redis/store/router_usage.rs:173
↓ 5 callersFunctionso
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 5 callersFunctionsource
()
tests/unit/integrations/otel/test_langfuse_logger.py:88
↓ 5 callersFunctionsource_from_location
Repo-relative `path:line` for a test, or '' when nothing is linkable. `pytest.Item.location` gives a rootdir-relative path and a ZERO-based line.
tests/e2e/junit_properties.py:50
↓ 5 callersMethodspan_names
(self)
tests/e2e/otel_client.py:94
↓ 5 callersFunctionspan_response_id
(span: Mapping[str, object])
tests/integration/observability/_langfuse_otel_metadata_support.py:295
↓ 5 callersFunctionspeech_event
( event_type: Literal["input_audio_buffer.speech_started", "input_audio_buffer.speech_stopped"], item_id:
litellm/llms/base_llm/realtime/transcription_protocol.py:245
← previousnext →16,601–16,700 of 202,479, ranked by callers