MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 20 callersFunction_counted_bodies
(wire: Wire)
tests/integration/providers/test_vertex_partner_count_tokens_wire.py:202
↓ 20 callersFunction_create
(params: dict, model: str = "wan3.0-video", prompt: str = "a cat on a roof")
tests/unit/llms/dashscope/test_dashscope_video_transformation.py:77
↓ 20 callersFunction_decision_router
(probability: float = 0.9, answer_name: str = "prompt_injection")
tests/unit/proxy/guardrails/guardrail_hooks/test_decision_model.py:389
↓ 20 callersFunction_delete
( prisma: _FakePrisma, user_ids: Sequence[str], caller: UserAPIKeyAuth = ADMIN, cache: UserApi
tests/unit/proxy/management_helpers/test_bulk_user_deletion.py:266
↓ 20 callersFunction_deployment
(gateway: Gateway, respond: Callable[[Request], Reply])
tests/integration/routing/test_vllm_passthrough_stream_relay.py:143
↓ 20 callersFunction_discovered_tool
(gateway: Gateway, tool_name: str)
tests/integration/management/test_tool_policy_user.py:53
↓ 20 callersFunction_evaluator
(classifier: _RecordingClassifier, **overrides: object)
tests/unit/llms/anthropic/messages/test_safeguards.py:84
↓ 20 callersFunction_file_block
(**file: object)
tests/unit/llms/vertex_ai/gemini_embeddings/test_batch_embed_content_transformation.py:40
↓ 20 callersMethod_get_allowed_mcp_servers_for_team
Get allowed MCP servers a caller inherits from the team it is pinned to. Exactly one team, or none. A subject that reaches servers through SE
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:3657
↓ 20 callersMethod_handle_success
Create the litellm_request span then close the proxy span.
litellm/integrations/opentelemetry.py:1413
↓ 20 callersFunction_http_response
(status_code: int = 200, json_body: dict | None = None)
tests/unit/llms/vertex_ai/batches/test_handler.py:75
↓ 20 callersMethod_instance
(self, prisma, llm_router)
tests/unit/proxy/common_utils/test_check_batch_cost.py:2738
↓ 20 callersFunction_key_rows
(key: str)
tests/integration/management/test_project_lifecycle.py:67
↓ 20 callersFunction_make_id_token
(exp_offset: int = 3600, iss: str = ISSUER)
tests/unit/proxy/mcp_server/outbound_credentials/test_sso_assertion_store.py:56
↓ 20 callersFunction_make_limiters
(clock: _Clock | None = None)
tests/unit/proxy/hooks/test_batch_rate_limiter.py:43
↓ 20 callersFunction_make_rate_limiter
()
tests/unit/proxy/hooks/test_batch_file_validation.py:891
↓ 20 callersFunction_make_response
Build a stub httpx-like response.
tests/unit/interactions/test_agents_http_handler.py:39
↓ 20 callersFunction_marker
()
tests/integration/security/test_api_key_secret_reference.py:459
↓ 20 callersFunction_marker
(label: str)
tests/integration/providers/test_vertex_anthropic_inline_tools_beta_wire.py:141
↓ 20 callersMethod_maybe_raise_for_error_event
(self, result: object)
litellm/responses/streaming_iterator.py:803
↓ 20 callersFunction_membership
(user_id: str, budget_id: str | None = None, team_id: str = TEAM_ID)
tests/unit/proxy/management_endpoints/management_v1/test_teams.py:241
↓ 20 callersFunction_mock_http_response
(status_code: int = 200, payload: dict | None = None)
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_invoke_guardrail_checks.py:31
↓ 20 callersFunction_mock_mcp_resolution_cache
()
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:9239
↓ 20 callersFunction_models
(scenario: Scenario, provider_url: str, **key_fields: JsonValue)
tests/integration/observability/test_s3_v2_partition_granularity.py:142
↓ 20 callersFunction_native_schema
(body: Mapping[str, JsonValue], invoke: bool)
tests/integration/providers/test_bedrock_native_structured_output_wire.py:192
↓ 20 callersFunction_notes_server
(pinned_tools: dict[str, PinnedMCPTool] | None = None)
tests/unit/proxy/mcp_server/test_mcp_server_manager.py:20009
↓ 20 callersFunction_one_call
(wire: Wire, marker_hex: str)
tests/integration/providers/test_bedrock_native_structured_output_wire.py:463
↓ 20 callersFunction_one_group
( make_core: MakeCore, **litellm_params: object )
tests/unit/test_router/core/test_endpoints.py:70
↓ 20 callersFunction_one_group
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_parity_regress5_settings.py:30
↓ 20 callersFunction_outbound
(gateway: Gateway, backend: str, messages: list[JsonValue], **fields: JsonValue)
tests/integration/providers/test_bedrock_mantle_claude_chat_wire.py:81
↓ 20 callersFunction_outside_layout
(objects: Mapping[str, bytes], granularity: str, prefix: str = "")
tests/integration/observability/test_s3_v2_partition_granularity.py:99
↓ 20 callersFunction_payload
(marker_hex: str)
tests/integration/providers/test_bedrock_native_structured_output_wire.py:156
↓ 20 callersFunction_picked_ids
( core: RouterCore, model: str, times: int = PICKS, **select_arguments: object )
tests/unit/test_router/core/test_selection.py:34
↓ 20 callersFunction_plan
(where=(), order=(SortKey(field="name", descending=False),), skip=0, take=50)
tests/unit/proxy/list_api/test_in_memory.py:35
↓ 20 callersFunction_problem
(query_params: Mapping[str, str], spec: ListSpec[BudgetRow, BudgetOut] | None = None)
tests/unit/proxy/list_api/test_list_framework.py:127
↓ 20 callersFunction_prompt
()
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_messages_pre_content_retry_wire.py:93
↓ 20 callersFunction_ptu_router
A router built the way loading config.yaml builds one.
tests/unit/test_router_model_cost_isolation.py:3026
↓ 20 callersFunction_redact_prompt_leaks_in_error_string
Strip echoed request input from provider error strings. Provider validation errors (e.g. OpenAI ``RateLimitError`` carrying 178 pydantic
litellm/proxy/spend_tracking/spend_tracking_utils.py:1609
↓ 20 callersFunction_redeem_native
(code, client_id, minter, cache=None, resource=PROXY_API_RESOURCE, **overrides)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:1846
↓ 20 callersFunction_reject_url_valued_destinations
Reject URL-valued ``model``/``file_id`` unless admin-allowlisted. Some providers (HuggingFace, Oobabooga, Gemini files) accept a URL in the i
litellm/proxy/litellm_pre_call_utils.py:543
↓ 20 callersFunction_relay_turns
( client: MagicMock, upstream_ws: ScriptedUpstreamWebSocket, gate: WebsocketFrameModelGate, en
tests/unit/proxy/pass_through_endpoints/test_pass_through_endpoints.py:8394
↓ 20 callersFunction_router
()
tests/unit/proxy/auth/test_fallback_budget.py:44
↓ 20 callersMethod_router
()
tests/unit/proxy/common_utils/test_check_batch_cost.py:3233
↓ 20 callersMethod_run
( self, monkeypatch, headers: list[tuple[bytes, bytes]], authenticated: UserAP
tests/unit/proxy/pass_through_endpoints/test_llm_pass_through_endpoints.py:4711
↓ 20 callersFunction_sent_passthrough_request
( action: str, body: dict[str, object], identity: dict[str, object], deployment_params: Mappin
tests/unit/llms/bedrock/passthrough/test_bedrock_passthrough_transformation.py:925
↓ 20 callersFunction_setup_batch_upload_endpoint
(monkeypatch, llm_router: Router)
tests/unit/proxy/openai_files_endpoint/test_files_endpoint.py:4310
↓ 20 callersFunction_shared
( model: str = "azure/gpt-4.1", shares: object = _SHARES, deployment_id: str = "shared", ptu_count: int |
tests/unit/router_utils/test_ptu_shares.py:27
↓ 20 callersFunction_snapshot
(cost_map: dict[str, object], backup: str | None = None, pins: str = NO_PINS)
tests/unit/test_cost_map_guard.py:58
↓ 20 callersFunction_spend_rows
(request_id: str)
tests/integration/spend/test_background_interaction_settlement.py:300
↓ 20 callersFunction_state
(marker: str)
tests/integration/providers/test_cloudflare_clef_images_wire.py:77
↓ 20 callersMethod_stored
Wait for the line items the poll handed to the background.
tests/unit/proxy/common_utils/test_check_batch_cost.py:3908
↓ 20 callersFunction_sync
(prisma: _FakePrisma, plan: RosterPlan, cache: UserApiKeyCache | None = None)
tests/unit/proxy/management_helpers/test_team_roster_sync.py:308
↓ 20 callersFunction_table
(repository: UserRepository)
litellm/proxy/management_endpoints/scim/scim_v2.py:170
↓ 20 callersFunction_team_db
(prisma_client: PrismaClient | None)
litellm/proxy/management_endpoints/team_endpoints.py:526
↓ 20 callersFunction_token
(label: str)
tests/integration/spend/test_spend_log_caller_session.py:59
↓ 20 callersFunction_update_request_stub
()
tests/unit/proxy/management_endpoints/test_team_endpoints.py:18132
↓ 20 callersFunction_upload
( hub: HubClient, content: bytes, key: str | None = MASTER_KEY, version: str | None = "2.0.0", )
tests/unit/proxy/discovery_endpoints/test_skill_hub_endpoints.py:165
↓ 20 callersFunction_usage
(p, c, t=None)
tests/unit/batches/test_batch_utils.py:46
↓ 20 callersFunction_user_responder
(payload=None, status=200)
tests/unit/llms/github_copilot/test_per_user_auth.py:94
↓ 20 callersFunction_user_turn
(marker: str)
tests/integration/providers/test_bedrock_mantle_claude_chat_wire.py:65
↓ 20 callersMethod_v3_limiter_rig
Real v3 limiter (the default ``parallel_request_limiter``) wired in through the ``proxy_logging_obj`` seam, so ``common_processing_pre_call_lo
tests/unit/proxy/test_common_request_processing.py:8382
↓ 20 callersFunction_vault
(monkeypatch: pytest.MonkeyPatch, address: str)
tests/unit/rust_bridge/host/test_secret_manager.py:40
↓ 20 callersMethodacompletion
(self, **kwargs)
tests/unit/proxy/management_endpoints/policy_endpoints/test_endpoints.py:271
↓ 20 callersMethodaocr
(self, *, model: str, document: Document, **kwargs: object)
tests/integration/sdk/test_ocr_matrix_sdk.py:54
↓ 20 callersMethodapply_baggage_tag_mappings_pre_auth
Resolve configured baggage tags before the existing tag-budget gate.
litellm/proxy/litellm_pre_call_utils.py:2403
↓ 20 callersFunctionas_object
`value` as a JSON object, or None. `isinstance(value, dict)` alone leaves the keys and values unknown to the type checker. A JSON object's ke
litellm/proxy/guardrails/guardrail_hooks/llm_shield_proxy/payload.py:26
↓ 20 callersFunctionassert_billed
(model: str, endpoint: Endpoint, usage: tuple[int, int], identities: frozenset[str])
tests/integration/providers/_gemini_long_decode_support.py:586
↓ 20 callersMethodassert_done
(self)
tests/e2e_harness/batches/test_batch_cleanup.py:36
↓ 20 callersFunctionassert_server_span_attrs
The four required attributes on the SERVER span must all be set.
tests/unit/integrations/open_telemetry/_helpers.py:33
↓ 20 callersMethodasync_delete_cache
Delete a key from the cache
litellm/caching/dual_cache.py:687
↓ 20 callersMethodasync_filter_deployments
( self, model: str, healthy_deployments: list, messages: list[AllMessageValues
litellm/router_utils/pre_call_checks/prompt_caching_deployment_check.py:261
↓ 20 callersMethodasync_get_available_deployment_for_pass_through
The full healthy chain, then only ``use_in_pass_through`` deployments, picked with the async strategies.
litellm/router_rust/core.py:2501
↓ 20 callersMethodasync_post_call_streaming_iterator_hook
Allow user to modify outgoing streaming data -> Given a whole response iterator. This hook is best used when you need to modify multi
litellm/proxy/utils.py:4854
↓ 20 callersMethodasync_sse_wrapper
Generic async SSE wrapper that converts streaming chunks to SSE format and handles logging. The upstream read runs in a deta
litellm/llms/anthropic/messages/native/streaming_iterator.py:582
↓ 20 callersMethodasync_write_secret
Write a secret to the in-memory store.
tests/unit/secret_managers/test_custom_secret_manager.py:53
↓ 20 callersMethodatomic_check_and_increment_by_n
Atomic check-and-increment-by-N across one or more descriptors. All-or-nothing: if any descriptor would exceed its limit, no counter
litellm/proxy/hooks/parallel_request_limiter_v3.py:1751
↓ 20 callersFunctionattempt_sync
(core: RouterCore, model: str = "g", **kwargs: object)
tests/unit/test_router/core/retries_health_helpers.py:94
↓ 20 callersFunctionbuild
Build `entries` (model_list entries) through `host`, in order. `resolve_secrets` resolves top-level `os.environ/` references first, as `set_model_list
litellm-rust/crates/router-core/src/build.rs:57
↓ 20 callersFunctionbuild_web_search_call
( tool_id: str, tool_input: object, result: object, status: Literal["in_progress", "searching"
litellm/types/responses/main.py:101
↓ 20 callersFunctioncall
(**kwargs: object)
tests/unit/rust_bridge/test_detectors.py:44
↓ 20 callersMethodcalls
(self)
tests/integration/authorization/test_rag_team_provider_credentials.py:155
↓ 20 callersFunctioncan_key_call_model
Checks if token can call a given model 1. First checks native key-level model permissions (current implementation) 2. If not allowed nat
litellm/proxy/auth/auth_checks.py:5518
↓ 20 callersFunctioncan_team_access_model
Returns True if the team can access a specific model. 1. First checks native team-level model permissions (current implementation) 2. If
litellm/proxy/auth/auth_checks.py:5746
↓ 20 callersMethodcancel
Stop the turn. Iteration still ends with Done(stop_reason='cancelled').
litellm/harness/sync.py:139
↓ 20 callersMethodcancel
Drops the body and fails every yield still waiting, or yet to be made, with [`Abandoned`](crate::Abandoned).
litellm-rust/crates/coroutine/src/coroutine.rs:89
↓ 20 callersFunctionchat_row
(custom_id: str, model: str, text: str)
tests/integration/providers/_vertex_batch_rows.py:87
↓ 20 callersMethodchunks
(self)
litellm/llms/bedrock/passthrough/transformation.py:264
↓ 20 callersFunctionclaude_frames
A Claude invoke stream with one text content block, one ``text_delta`` event per string.
tests/integration/observability/test_bedrock_invoke_stream_post_call_guardrail.py:81
↓ 20 callersMethodclear
()
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 20 callersMethodclient
( &self, config: &HttpClientConfig, variant: ClientVariant, )
litellm-rust/crates/http/src/pool.rs:53
↓ 20 callersMethodclose
(self)
litellm/harness/sync.py:178
↓ 20 callersMethodclose
(self)
tests/unit/rust_bridge/test_bindings.py:116
↓ 20 callersMethodconnect
( self, *, key: str, model: str, route: str = REALTIME_ROUTE,
tests/e2e/llm_translation/realtime/realtime_client.py:486
↓ 20 callersFunctionconvert_to_gemini_tool_call_invoke
OpenAI tool invokes: { "role": "assistant", "content": null, "tool_calls": [ { "id": "call_abc123",
litellm/litellm_core_utils/prompt_templates/factory.py:1349
↓ 20 callersMethodcreate_and_finish
(self, endpoint: str = CHAT_ENDPOINT)
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:368
↓ 20 callersFunctiond
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 20 callersFunctiondecode_model_from_file_id
Extract model name from an encoded file/batch ID. Handles IDs that start with "file-" or "batch_" prefix.
litellm/proxy/openai_files_endpoints/common_utils.py:293
↓ 20 callersFunctionderiveErrorMessage
(errorData: any)
ui/litellm-dashboard/src/app/(dashboard)/hooks/router/useRouterFields.ts:24
↓ 20 callersMethoddestroy
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 20 callersMethoddrain
(self)
tests/unit/proxy/telemetry/test_middleware.py:47
← previousnext →2,701–2,800 of 202,479, ranked by callers