MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 31 callersMethoderr
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 31 callersFunctionevent_types
(events: tuple[SseEvent, ...])
tests/integration/_support/anthropic_sse.py:156
↓ 31 callersMethodexecute_steps
Execute pipeline steps sequentially with conditional actions. Args: steps: Ordered list of pipeline steps mo
litellm/proxy/policy_engine/pipeline_executor.py:393
↓ 31 callersFunctionfailing
()
litellm-rust/crates/host-python/tests/lifecycle.py:75
↓ 31 callersFunctionget_anthropic_wif_token
( litellm_params: Mapping[str, object] | None, api_base: str | None, model: str, engine: JwtBe
litellm/llms/anthropic/wif.py:356
↓ 31 callersMethodget_available_deployments
( self, model_group: str, healthy_deployments: Sequence[Mapping[str, object]],
litellm/router_strategy/least_busy.py:465
↓ 31 callersMethodget_credentials
Return a boto3.Credentials object
litellm/llms/bedrock/base_aws_llm.py:296
↓ 31 callersFunctionget_custom_url
(request_base_url: str, route: str | None = None)
litellm/proxy/utils.py:9918
↓ 31 callersFunctionget_hidden_params_dict
( response: object, *, create: bool = False, )
litellm/litellm_core_utils/add_retry_fallback_headers.py:220
↓ 31 callersMethodget_model_group_info
(self, model_group: str, team_id: str | None = None)
tests/unit/proxy/public_endpoints/public_v1/test_model_hub.py:354
↓ 31 callersFunctionget_parent_otel_span_from_kwargs
( kwargs: Mapping[str, object] | None = None, )
litellm/litellm_core_utils/core_helpers.py:663
↓ 31 callersMethodget_provider_anthropic_messages_config
( model: str, provider: LlmProviders, )
litellm/utils.py:10425
↓ 31 callersMethodinfo
(self, section=None)
tests/unit/test_vcr_redis_persister.py:429
↓ 31 callersMethodjson
(self)
litellm/llms/black_forest_labs/image_edit/handler.py:66
↓ 31 callersMethodmember
(self)
tests/integration/authorization/test_team_admin_gate.py:76
↓ 31 callersMethodmemory
(&self)
litellm-rust/crates/redis-store/src/dual_cache/mod.rs:73
↓ 31 callersFunctionn
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 31 callersFunctionnormalize_drop_params
(value: object)
litellm/litellm_core_utils/core_helpers.py:227
↓ 31 callersFunctionopen_session_token
Validate a session ACCESS ``candidate`` and recover the principal. Never raises for bad input: every invalid, expired, tampered, or wrong-kind ca
litellm/proxy/mcp_server/outbound_credentials/session_token.py:380
↓ 31 callersFunctionparts_of
(value: object)
litellm/litellm_core_utils/prompt_templates/mid_conversation_system.py:74
↓ 31 callersFunctionr
(...n)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 31 callersFunctionrU
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 31 callersFunctionreceived
( wire: Wire, provider: Provider, stream: bool, continued: tuple[bool, ...] )
tests/integration/providers/_gemini_long_decode_support.py:210
↓ 31 callersMethodresult
(self)
litellm/harness/sync.py:136
↓ 31 callersMethodrun
(self, context)
tests/unit/proxy/proxy_server/test_proxy_config.py:825
↓ 31 callersFunctionrun_ptu_flat_cost_backfill
Price the elapsed days of every PTU window that carry no sentinel row yet. Writes only the charges that are missing and never rewrites or deletes
litellm/proxy/spend_tracking/ptu_flat_cost_rollup.py:619
↓ 31 callersFunctionsafe_get_request_headers
[Non-Blocking] Safely get the request headers. Caches the result on request.state to avoid re-creating dict(request.headers) per call. W
litellm/proxy/common_utils/http_parsing_utils.py:503
↓ 31 callersFunctionsame_response
(left: str, right: str)
tests/integration/_support/responses_vendor.py:113
↓ 31 callersFunctionserve
(stream: tuple[bytes, ...], target: str)
tests/integration/_support/responses_stream.py:113
↓ 31 callersMethodset_cache
(self, key: str, value: object, **kwargs: object)
tests/unit/proxy/auth/test_auth_checks.py:2376
↓ 31 callersMethodstart
Spawn PgBouncer, wait until it listens on port and unix socket, then supervise it from a daemon thread.
litellm/proxy/db/pgbouncer.py:575
↓ 31 callersMethodto_json
(self, **kwargs)
litellm/types/router.py:937
↓ 31 callersFunctionto_value
(value: &Bound<'_, PyAny>, depth: usize)
litellm-rust/crates/python-bridge/src/redis/store/value.rs:33
↓ 31 callersMethodtransform_image_generation_request
(self, model, prompt, optional_params, litellm_params, headers)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:5915
↓ 31 callersMethodtransform_rerank_request
( self, model: str, optional_rerank_params: dict, headers: dict, litel
litellm/llms/voyage/rerank/transformation.py:90
↓ 31 callersMethodtransform_search_request
( self, query: (str | list[str]), # mutable-ok: BaseSearchConfig.transform_search_request con
litellm/llms/xai/search/transformation.py:82
↓ 31 callersMethodtransform_video_create_response
( self, model: str, raw_response: httpx.Response, logging_obj: LiteLLMLoggingO
tests/integration/_support/custom_video_provider.py:78
↓ 31 callersMethodtransform_video_status_retrieve_response
( self, raw_response: httpx.Response, logging_obj: LiteLLMLoggingObj, custom_l
tests/integration/_support/custom_video_provider.py:97
↓ 31 callersMethodupdate_request_status
(self, litellm_call_id: str, status: Literal["success", "fail"])
litellm/proxy/utils.py:2223
↓ 31 callersFunctionuser_with_an_email
(scenario: Scenario)
tests/integration/_support/daily_activity.py:72
↓ 31 callersMethodvalue
(&self)
litellm-rust/crates/python-bridge/src/coercion.rs:151
↓ 31 callersFunctionx
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 30 callersFunction$
()
litellm/proxy/_experimental/out/_next/static/chunks/2-vteq4_63z28.js:1
↓ 30 callersFunctionB
()
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 30 callersMethodGET
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 30 callersMethod__init__
( self, message, model, llm_provider, litellm_debug_info: str | None =
litellm/exceptions.py:429
↓ 30 callersFunction_access_group
(group_id, servers, tool_permissions=None, **owners)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:11544
↓ 30 callersFunction_agent
( gateway: Gateway, databricks: _Databricks, *, url_path: str = "", static_headers: dict[s
tests/integration/providers/test_databricks_agent_wire.py:148
↓ 30 callersFunction_apply_patch_ops
Apply patch operations and return update data and the final teams in order.
litellm/proxy/management_endpoints/scim/scim_v2.py:2538
↓ 30 callersFunction_base_patches
( agent: MagicMock, add_litellm_data: AddLiteLLMData | None = None )
tests/unit/proxy/agent_endpoints/test_a2a_endpoints.py:423
↓ 30 callersFunction_body
(request: Request)
tests/integration/providers/test_sagemaker_embedding_wire.py:173
↓ 30 callersFunction_call_kwargs
(deployment_id: str, call_id: str = "call-1")
tests/unit/router_strategy/test_least_busy.py:42
↓ 30 callersFunction_config
()
tests/unit/llms/nimble/search/test_nimble_search_transformation.py:10
↓ 30 callersFunction_direction
(payload: Mapping[str, JsonValue])
tests/integration/observability/_logging_only_scope_support.py:1006
↓ 30 callersFunction_guardrail_entries
(row: Mapping[str, JsonValue])
tests/integration/observability/_logging_only_scope_support.py:1106
↓ 30 callersFunction_logger
(*, capture: str = "span_only", mappers: Sequence[str] = ("genai", "langfuse"))
tests/unit/integrations/otel/test_langfuse_logger.py:62
↓ 30 callersFunction_make_guardrail
(**kwargs)
tests/unit/proxy/guardrails/guardrail_hooks/test_headroom.py:90
↓ 30 callersFunction_make_history
(n_pairs: int, result_filler: str = "x" * 200)
tests/unit/llms/anthropic/messages/context_management/test_clear_tool_uses.py:57
↓ 30 callersFunction_matching_marker_span
(destination: Wire, marker: str)
tests/integration/observability/_openinference_support.py:578
↓ 30 callersFunction_monitor_bodies
(vendor: Wire, expected: int = 1, seconds: float = 30)
tests/integration/observability/test_grayswan_wire.py:173
↓ 30 callersMethod_normalize_otel_endpoint
Normalize the endpoint URL for a specific OpenTelemetry signal type. The OTLP exporters expect endpoints to use signal-specific path
litellm/integrations/opentelemetry.py:3376
↓ 30 callersFunction_only_call
(wire: Wire, target: str = _RESPONSES_PATH)
tests/integration/providers/test_bedrock_mantle_context_overflow_wire.py:233
↓ 30 callersFunction_patch_prisma
(existing_team: MagicMock)
tests/unit/proxy/management_endpoints/test_team_callback_endpoints.py:67
↓ 30 callersFunction_publish
(monkeypatch, infos: Sequence[ModelGroupInfo], prisma_client: object | None = None)
tests/unit/proxy/public_endpoints/public_v1/test_model_hub.py:47
↓ 30 callersFunction_responses_ws_frame_guard
Socket admission skips guardrails (the first frame's ``input`` is not part of the admitted request), so every ``response.create`` frame gets the p
litellm/proxy/response_api_endpoints/endpoints.py:2221
↓ 30 callersFunction_shielded
(vault: dict[str, str])
tests/unit/proxy/guardrails/guardrail_hooks/test_llm_shield_proxy.py:116
↓ 30 callersFunction_tiered
( **marker_params: object, )
tests/unit/test_router/core/test_selection_characterization_prerouting.py:63
↓ 30 callersFunction_translate_messages
(messages: List[Any])
tests/unit/llms/anthropic/messages/responses_adapters/test_responses_adapters_transformation.py:257
↓ 30 callersFunction_trigger_cooldown_for_failed_deployment
Trigger cooldown for a failed fallback deployment. In the fallback path the normal failure-callback cooldown is skipped because the Logg
litellm/router_utils/fallback_event_handlers.py:57
↓ 30 callersFunction_turn
( db, key: str, model: str, at: datetime, covered: int = 1, hit: int = 0, ttl: "in
tests/integration/spend/test_autorouter_session_rollup.py:82
↓ 30 callersFunctiona
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 30 callersMethodafile_retrieve
(self, file_id, litellm_parent_otel_span, llm_router)
tests/unit/proxy/openai_files_endpoint/test_files_endpoint.py:421
↓ 30 callersFunctionanswers
(response_id: str, hop: Hop)
tests/integration/providers/_gemini_long_decode_support.py:123
↓ 30 callersMethodas_str
(&self)
litellm-rust/crates/gateway-auth/src/keys.rs:15
↓ 30 callersMethodasync_add_model_id
( self, model_id: str, messages: list[AllMessageValues] | None, tools: Sequenc
litellm/router_utils/prompt_caching_cache.py:424
↓ 30 callersFunctionbearer_of
(route: respx.Route)
tests/unit/llms/openai/test_openai_workload_identity.py:1121
↓ 30 callersMethodcall_cato_guardrail
( self, data: dict, hook: str, key_alias: str | None, user_email: str
litellm/proxy/guardrails/guardrail_hooks/cato_networks/cato_networks.py:300
↓ 30 callersMethodclose
(self)
litellm/llms/custom_httpx/http_handler.py:1624
↓ 30 callersFunctioncreate_model_info_response
Create a standardized OpenAI-compatible model object. When include_metadata is true, attaches the model's configured fallbacks (resolved
litellm/proxy/utils.py:10415
↓ 30 callersFunctioncredential
()
tests/integration/_support/bedrock_discovery.py:52
↓ 30 callersMethoddecisions
( self, model: str, custom_llm_provider: str, logging_obj: LiteLLMLoggingObj |
litellm/llms/custom_httpx/llm_http_handler.py:1778
↓ 30 callersFunctiondecrypt_if_encrypted_with
None unless value is a ciphertext under signing_key.
litellm/proxy/common_utils/encrypt_decrypt_utils.py:247
↓ 30 callersMethoddiscard
(self, value: object)
litellm/router_rust/surface/indexes.py:219
↓ 30 callersFunctionduration_in_seconds
Parameters: - duration: - "<number>s" - seconds - "<number>m" - minutes - "<number>h" - hours - "<number>d" -
litellm/litellm_core_utils/duration_parser.py:51
↓ 30 callersMethodensure_access_token_async
( self, credentials: VERTEX_CREDENTIALS_TYPES | None, project_id: str | None,
litellm/llms/vertex_ai/vertex_llm_base.py:1174
↓ 30 callersMethodget_api_key
(api_key: str | None = None)
litellm/llms/baseten/chat.py:103
↓ 30 callersMethodget_param
(self, param_name: str)
tests/unit/proxy/roi_calculator/test_sync.py:81
↓ 30 callersFunctionget_vertex_base_url
Get the base URL for Vertex AI API calls. - ``global`` uses the global control plane host. - Multi-region geographies (e.g. ``us``, ``eu
litellm/llms/vertex_ai/common_utils.py:499
↓ 30 callersFunctioni
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 30 callersMethoditems
(self)
litellm/types/llms/openai.py:1785
↓ 30 callersMethodkey_with_alias
( self, alias: str, *, models: list[str], team_id: str | None = None,
tests/e2e/logging/logging_client.py:312
↓ 30 callersMethodmap_function
( self, value: list[dict[str, object]], # mutable-ok: mirrors override contract optio
litellm/llms/vertex_ai/gemini/vertex_and_google_ai_studio_gemini.py:1411
↓ 30 callersMethodmodel_dump
(self, **kwargs: object)
litellm/llms/sap/chat/models.py:86
↓ 30 callersFunctionno_secrets
()
litellm-rust/crates/inference-testing/src/lib.rs:23
↓ 30 callersFunctionredact_logged_api_key
(value: str | None, *, already_redacted: bool = False, key_alias: object = None)
litellm/proxy/spend_tracking/spend_tracking_utils.py:174
↓ 30 callersFunctionrelayed
(value: JsonValue, location: Location = ())
tests/integration/_support/anthropic_refusal.py:370
↓ 30 callersFunctionrequest_attachments
(request_data: Mapping[str, object])
litellm/proxy/guardrails/guardrail_hooks/akto/akto_attachments.py:187
↓ 30 callersFunctionresolve_cost_discount
( cost_discount_config: Mapping[str, float], custom_llm_provider: str | None, model: str | None,
litellm/litellm_core_utils/cost_discount.py:37
↓ 30 callersFunctionresolve_trace_id
Map a caller's trace id onto the 32 lowercase hex characters v4 requires.
litellm/integrations/langfuse/langfuse_sdk.py:139
↓ 30 callersFunctionrewrite_response_ids
Mint managed IDs for raw provider values listed in ``BUILTIN_OUTPUT_ID_FIELD_MAP`` and swap them into *body*. Returns the same *body* ob
litellm/proxy/pass_through_endpoints/managed_id_rewriter.py:725
← previousnext →1,601–1,700 of 202,479, ranked by callers