MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 18 callersMethodregistration
(self)
tests/integration/_support/mcp.py:55
↓ 18 callersMethodremoveListener
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 18 callersFunctionreplay_messages
( marker: str, assistant: Event, answers: Sequence[JsonValue] = (tool_answer(WEATHER_ID),) )
tests/integration/providers/_tool_search_support.py:248
↓ 18 callersMethodresolve
( self, host: str, port: int = 0, family: socket.AddressFamily = socket.AF_INET )
tests/unit/llms/custom_httpx/test_aiohttp_transport.py:1205
↓ 18 callersMethodresolve_policy_guardrails
Resolve the final guardrails for a single policy, including inheritance. This method: 1. Resolves the inheritance chain
litellm/proxy/policy_engine/policy_resolver.py:70
↓ 18 callersMethodretrieve
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 18 callersFunctionrewrite_body_ids
( body: dict[str, object] | None, provider: str, user_api_key_dict: UserAPIKeyAuth, prisma_cli
litellm/proxy/pass_through_endpoints/managed_id_rewriter.py:1295
↓ 18 callersFunctionrootPath
()
tests/e2e/ui/helpers/traffic.ts:22
↓ 18 callersMethodrun
(self, context: RoutingContext)
tests/unit/test_router/core/test_deprecated_members.py:254
↓ 18 callersFunctionsI
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 18 callersMethodschedule
(&self)
litellm-rust/crates/cost/src/price.rs:260
↓ 18 callersMethodsecret
(self, index: int = 0)
tests/integration/observability/test_guardrail_effects.py:2426
↓ 18 callersFunctionsecs
(seconds: u64)
litellm-rust/crates/cache-memory/tests/cache.rs:40
↓ 18 callersMethodseek
(self, offset: int, /)
litellm/llms/black_forest_labs/image_edit/transformation.py:68
↓ 18 callersFunctionselect_model_name_for_cost_calc
1. If custom pricing is true, return received model name 2. If base_model is set (e.g. for azure models), return that 3. If completion re
litellm/cost_calculator.py:1058
↓ 18 callersFunctionsend_email
smtp_host, smtp_port, smtp_username, smtp_password, sender_name, sender_email,
litellm/proxy/utils.py:8410
↓ 18 callersMethodset_attributes
(self, span: Span, kwargs, response_obj: object)
litellm/integrations/arize/arize.py:169
↓ 18 callersMethodset_cache
(self, *args, **kwargs)
tests/unit/proxy/management_endpoints/test_key_generate_prisma.py:2272
↓ 18 callersFunctionset_fallback_generalizations
Install the active rule list, compiling and classifying each rule. Malformed, mixed-kind, and invalid-regex rules are warned about and skipped.
litellm/litellm_core_utils/fallback_generalizations.py:203
↓ 18 callersMethodset_local
(self, counter: str, spend: float, ttl: float | None = None)
litellm/redis/stores/spend_counters/__init__.py:142
↓ 18 callersFunctionshould_use_polling_for_request
Determine if polling via cache should be used for a request. Args: background_mode: Whether background=true was set in the request
litellm/proxy/response_polling/polling_handler.py:273
↓ 18 callersFunctionspans_for_trace
(spans: tuple[Span, ...], trace_id: str)
tests/integration/_support/otlp_sink.py:149
↓ 18 callersFunctionspend_log_write_batches
Yield consecutive slices of ``rows`` within both ``max_bytes`` and ``max_rows``. What is measured for the byte budget is the encoded slice, not t
litellm/proxy/db/spend_log_batching.py:104
↓ 18 callersFunctionspend_row_lands
(response_id: str)
tests/integration/routing/_prompt_cache_pin_support.py:115
↓ 18 callersFunctionsse_frames
(*events: Mapping[str, JsonValue], done: bool = False)
tests/integration/cost_calculation/stream_parity/case.py:14
↓ 18 callersMethodstart_phase_span
A live INTERNAL span the service calls inside the block nest under. Parents like a service span: ambient first, and from the post-response ph
litellm/integrations/otel/logger.py:782
↓ 18 callersFunctionstrip_known_server_prefix
Strip ``server``'s registered prefix from a prefixed tool/resource name. Unlike :func:`split_server_prefix_from_name`, which guesses the boundary
litellm/proxy/mcp_server/utils.py:481
↓ 18 callersMethodsync_guardrail_from_db
Sync a guardrail from DB - initializes if new, re-initializes if changed. DB values that do not decrypt with the current key keep the
litellm/proxy/guardrails/guardrail_registry.py:1197
↓ 18 callersFunctiontask_of
(video_id: str)
tests/integration/providers/_dashscope_video_support.py:109
↓ 18 callersMethodteardown
(self)
tests/e2e/lifecycle.py:86
↓ 18 callersFunctionthinking_block
(thinking: str, signature: JsonValue)
tests/integration/_support/anthropic_thinking.py:204
↓ 18 callersMethodtransform
Transform LiteLLM data to CBF format, dropping records with zero successful_requests or invalid CZRNs.
litellm/integrations/cloudzero/transform.py:52
↓ 18 callersFunctiontransform_openai_input_gemini_content
Transform OpenAI embedding input to Gemini batchEmbedContents format. Each input element becomes a separate EmbedContentRequest, supporting
litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:392
↓ 18 callersFunctiontransform_openai_input_gemini_embed_content
Transform OpenAI embedding input to Gemini embedContent format (multimodal). Args: input: GeminiEmbeddingInput with text, data URIs,
litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:440
↓ 18 callersMethodtransform_request
( self, model: str, messages: list[AllMessageValues], optional_params: dict,
litellm/llms/vertex_ai/vertex_ai_partner_models/anthropic/transformation.py:142
↓ 18 callersFunctionupstream_error_response
(error: Exception)
litellm/llms/openai/common_utils.py:195
↓ 18 callersMethodurl
(&self, path_and_query: &str)
litellm-rust/crates/gateway-forward/tests/support/mod.rs:66
↓ 18 callersFunctionuseTeams
()
ui/litellm-dashboard/src/app/(dashboard)/hooks/useTeams.tsx:10
↓ 18 callersMethodvalidate_environment
( self, headers: dict, model: str, messages: list[AllMessageValues], o
litellm/llms/gdc/chat/transformation.py:222
↓ 18 callersFunctionvalues
(samples: Sequence[Sample], metric: str, **labels: str)
tests/integration/observability/test_prometheus_provider_auth_failure.py:428
↓ 18 callersFunctionx
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 17 callersMethod_add_proxy_hooks
Add proxy hooks to litellm.callbacks
litellm/proxy/utils.py:2142
↓ 17 callersFunction_agent_turns_with_tool_results
(rounds: int)
tests/unit/proxy/test_proxy_token_counter.py:3685
↓ 17 callersFunction_alias_request
A request as auth sees it: the body already read once and cached alongside its parsed form.
tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py:12523
↓ 17 callersFunction_answer_body
(provider: _Provider)
tests/integration/providers/test_decisions_wire.py:222
↓ 17 callersFunction_anthropic_sse
(event_type: str, payload: dict)
tests/unit/proxy/guardrails/guardrail_hooks/test_presidio.py:2396
↓ 17 callersFunction_apply_credential_overrides_from_model_config
Walk the model_config precedence chain in team/project metadata. If a matching credential is found, set api_base/api_key/api_version on data
litellm/proxy/litellm_pre_call_utils.py:3696
↓ 17 callersFunction_apply_stream_usage_tracking
( data: dict, general_settings: dict, route_type: str, supports_stream_options: Callable[[], b
tests/unit/proxy/test_common_request_processing.py:9608
↓ 17 callersFunction_ask
(marker: str, *, compact: bool = False)
tests/integration/providers/test_responses_compaction_items_wire.py:63
↓ 17 callersFunction_assert_deltas_match_their_block_type
Enforce the invariant the Anthropic SDK enforces client-side: every ``content_block_delta`` must be of a type valid for the block opened by th
tests/unit/llms/anthropic/messages/adapters/test_streaming_iterator_first_delta.py:326
↓ 17 callersFunction_assert_invocation
(request: Request, bearer: str, *, stream: bool = False)
tests/integration/providers/test_databricks_agent_wire.py:205
↓ 17 callersFunction_assert_restreamed
(stream: _Stream, text: str, *, usage: Mapping[str, int] | None)
tests/integration/streaming/test_interception_converted_stream_options.py:290
↓ 17 callersFunction_assistant_turn
( output: Sequence[Mapping[str, object]], *, stream: bool, model: str = f"openai/responses/{MO
tests/unit/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_history.py:186
↓ 17 callersMethod_build_success_event_pipeline_operations
Build Redis pipeline increment ops for TPM / parallel-request counters.
litellm/proxy/hooks/parallel_request_limiter_v3.py:4658
↓ 17 callersFunction_call_client
( client_kind: ClientKind, endpoint: Endpoint, gateway: Gateway, model: str, prompt: str,
tests/integration/observability/_logging_only_scope_support.py:480
↓ 17 callersFunction_chat
(bridge: _Bridge, model: str, messages: Sequence[JsonValue], *, stream: bool = False)
tests/integration/providers/test_responses_bridge_input_audio_wire.py:95
↓ 17 callersFunction_chat_body_sent
( respx_mock: respx.MockRouter, model: str, reasoning_effort: str | None, model_info: Mapping[
tests/unit/test_main.py:10208
↓ 17 callersFunction_collect_async
(payload)
tests/unit/litellm_core_utils/llm_response_utils/test_convert_to_streaming_response.py:50
↓ 17 callersFunction_completion
(response: httpx.Response, marker: str)
tests/integration/providers/test_responses_bridge_input_audio_wire.py:103
↓ 17 callersFunction_configure
(backend: SpeechStreamingBackend)
tests/unit/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_backend.py:126
↓ 17 callersFunction_convert_to_bedrock_tool_call_invoke
OpenAI tool invokes: { "role": "assistant", "content": null, "tool_calls": [ { "id": "call_abc123",
litellm/litellm_core_utils/prompt_templates/factory.py:4285
↓ 17 callersFunction_disconnect_rig
( gateway: Gateway, tmp_path: Path, *, params: Mapping[str, JsonValue] = _END_OF_STREAM_ONLY,
tests/integration/observability/test_guardrail_effects.py:2434
↓ 17 callersMethod_estimate_input_and_output_tokens
Estimate input tokens and output (max_tokens) budget separately, so callers needing independent ITPM/OTPM reservations (rather than o
litellm/proxy/hooks/parallel_request_limiter_v3.py:1032
↓ 17 callersFunction_exchange_for_bridge_server
(server, upstream_body, key_hash, code="auth-code", fake_client_out=None)
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:6361
↓ 17 callersFunction_expire_time
(seconds_from_now: float)
tests/unit/llms/vertex_ai/context_caching/test_known_cached_contents.py:42
↓ 17 callersFunction_family_limiter
( groups_by_model: Mapping[str, frozenset[str]] = OPUS_GROUP_MEMBERS, dual_cache: DualCache | None = N
tests/unit/proxy/hooks/test_model_max_budget_limiter.py:473
↓ 17 callersMethod_fetch_tools_with_timeout
Fetch tools from MCP client with timeout and error handling. Uses anyio.fail_after() instead of asyncio.wait_for() to avoid conflict
litellm/proxy/mcp_server/mcp_server_manager.py:5639
↓ 17 callersFunction_first_turn
(session: str, marker: str, mark: JsonValue)
tests/integration/routing/test_prompt_cache_pin_ttl.py:228
↓ 17 callersFunction_flow_cookie_from
(response)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:336
↓ 17 callersFunction_full_text
(marker: str)
tests/integration/streaming/test_noma_v2_streaming_settings.py:157
↓ 17 callersFunction_ga_client_ws
()
tests/unit/litellm_core_utils/test_realtime_streaming.py:3891
↓ 17 callersMethod_get_model_endpoint
Get the API endpoint for a given model.
litellm/llms/stability/image_edit/transformations.py:118
↓ 17 callersMethod_get_optional_params
(self, vendor: OCIVendors, optional_params: dict, model: str = "")
litellm/llms/oci/chat/transformation.py:567
↓ 17 callersFunction_get_prisma_client_or_raise_exception
Check if database is connected and raise HTTPException if not.
litellm/proxy/management_endpoints/scim/scim_v2.py:303
↓ 17 callersFunction_groups
(tools)
tests/unit/llms/openai/responses/test_openai_responses_guardrail_tool_merge.py:15
↓ 17 callersFunction_headers
(**values: str)
tests/unit/proxy/pass_through_endpoints/test_upstream_usage_headers.py:21
↓ 17 callersFunction_http
(gateway: Gateway, call: _Call, extra: Mapping[str, JsonValue] = _NO_RETRIES)
tests/integration/routing/test_deployment_mode_routing_wire.py:260
↓ 17 callersMethod_instance
(self, key_row=None, team_row=None, user_row=None, prisma=None)
tests/unit/proxy/common_utils/test_check_batch_cost.py:2440
↓ 17 callersMethod_job
(self, **overrides)
tests/unit/proxy/common_utils/test_check_batch_cost.py:2450
↓ 17 callersFunction_landed
(model: str, response_id: str, *, expected: int = 1)
tests/integration/providers/test_chatgpt_responses_caller_stream_wire.py:120
↓ 17 callersMethod_lookup
(self)
litellm/router_rust/surface/registry.py:1672
↓ 17 callersFunction_make_cache
(sync_client=None, async_client=None, similarity_threshold=0.8)
tests/unit/caching/test_valkey_semantic_cache.py:18
↓ 17 callersFunction_make_file_object
(file_id: str = "file-output-abc")
tests/unit/enterprise/proxy/test_managed_files_hook.py:31
↓ 17 callersFunction_make_logging_obj
Return a mock LiteLLMLoggingObj pre-configured for prompt management.
tests/unit/responses/test_responses_prompt_management.py:39
↓ 17 callersFunction_make_model_list
Build a router model_list from a compact spec. spec entry shape: { "model_name": str, "quality_tier": Optional[int],
tests/unit/router_strategy/test_quality_router.py:25
↓ 17 callersFunction_make_prisma
(invite: MagicMock, user: MagicMock | None = None)
tests/unit/proxy/auth/test_onboarding.py:63
↓ 17 callersFunction_make_router
()
tests/unit/router_strategy/adaptive_router/test_adaptive_router.py:19
↓ 17 callersFunction_make_server
( *, server_id: str = "abcdef-1234", server_name: str = "github_onprem", alias: str = "github_
tests/unit/proxy/mcp_server/test_short_mcp_tool_prefix.py:31
↓ 17 callersFunction_make_wrappers
()
tests/unit/proxy/db/test_routing_prisma_wrapper.py:21
↓ 17 callersFunction_marked_message
(part_type: str, marker: object)
tests/unit/llms/openai/responses/test_openai_responses_transformation.py:4420
↓ 17 callersFunction_marked_system
(model: str, marker: str, mark: JsonValue = EPHEMERAL, **fields: JsonValue)
tests/integration/providers/test_responses_bridge_message_cache_control_wire.py:88
↓ 17 callersFunction_marker
()
tests/integration/streaming/test_chat_stream_guardrail_error_events.py:238
↓ 17 callersFunction_marker
()
tests/integration/spend/test_spend_log_caller_session.py:55
↓ 17 callersFunction_member
(user_id: str, role: Literal["admin", "user"] = "user")
tests/unit/proxy/management_helpers/test_team_roster_sync.py:256
↓ 17 callersFunction_metadata
(**overrides: object)
tests/unit/proxy/db/test_autorouter_session_rollup.py:48
↓ 17 callersFunction_one_post
(wire: Wire, target: str)
tests/integration/messages_endpoint/providers/anthropic/test_anthropic_messages_overloaded_wire.py:153
↓ 17 callersFunction_one_row
(model: str, identity: str | None = None)
tests/integration/routing/test_vllm_passthrough_stream_relay.py:175
↓ 17 callersFunction_openai_tool
(name: str, schema: Mapping[str, JsonValue], **extra: JsonValue)
tests/integration/providers/test_bedrock_converse_lookaround_regex_wire.py:146
↓ 17 callersMethod_otel_key
( rpm_limit: int | None = None, api_key: str = "hashed-key", model_rpm_limit: dict[str
tests/unit/proxy/test_common_request_processing.py:8454
↓ 17 callersFunction_patch_logging_flags
(monkeypatch, needs_wrap=False, needs_per_chunk=False)
tests/unit/proxy/proxy_server/test_streaming_helpers.py:1099
← previousnext →3,301–3,400 of 202,479, ranked by callers