MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersFunction_serialize
(value: object)
litellm/integrations/langfuse/langfuse_sdk.py:161
↓ 5 callersFunction_serialize
(cost_map: dict[str, object])
tests/unit/test_cost_map_guard.py:51
↓ 5 callersFunction_serve_model_groups
(router, model_groups)
tests/unit/proxy/management_endpoints/test_access_group_management.py:906
↓ 5 callersFunction_serve_response
(router: litellm.Router, request_input: object)
tests/unit/router_utils/pre_call_checks/test_prompt_caching_deployment_check.py:1635
↓ 5 callersFunction_served
(listing: tuple[str, Mapping[str, JsonValue]])
tests/integration/mcp/test_mcp_llm_endpoints.py:1672
↓ 5 callersFunction_server
(server_fields: Mapping[str, object], skip_setting: bool | None)
tests/unit/proxy/mcp_server/test_upstream.py:53
↓ 5 callersFunction_serves_tool_call
(call_id: str, city: str)
tests/integration/sdk/test_router_tool_call_stream_fallback_budget_wire.py:68
↓ 5 callersFunction_service
(action: str)
tests/unit/llms/bedrock/test_web_identity_session_policy.py:683
↓ 5 callersFunction_serving_deployment
(candidate: Gateway, model: str)
tests/integration/authorization/test_hidden_alias_budget_bypass.py:545
↓ 5 callersFunction_session_grouped_paginating_prisma
Mock prisma serving the grouped page read out of ``sessions``, honoring the LIMIT and OFFSET it asks for.
tests/unit/proxy/spend_tracking/test_spend_management_endpoints.py:7297
↓ 5 callersMethod_session_id
Reads back the vault id minted while redacting this request. Falls back to an unused id rather than to anything the caller supplied: a
litellm/proxy/guardrails/guardrail_hooks/llm_shield_proxy/llm_shield_proxy.py:310
↓ 5 callersFunction_session_row
(token: str = HASHED_TOKEN, user_id: str = USER_ID)
tests/unit/proxy/management_endpoints/test_session_endpoints.py:22
↓ 5 callersMethod_set_org_budget_metrics_after_api_request
Set org budget metrics after an LLM API request - Uses the auth-carried org budget when the request has one, else fetches via get_or
litellm/integrations/prometheus.py:4513
↓ 5 callersMethod_set_team_attributes_from_kwargs
Pull team_id / team_alias from the standard logging metadata in kwargs and stamp them onto span.
litellm/integrations/opentelemetry.py:1582
↓ 5 callersMethod_set_team_budget_metrics
Set team budget metrics for a single team - Remaining Budget - Max Budget - Budget Reset At
litellm/integrations/prometheus.py:4456
↓ 5 callersFunction_set_text
(text: str)
tests/unit/proxy/guardrails/test_anthropic_sse.py:39
↓ 5 callersFunction_set_virtual_key_metrics
(logger: PrometheusLogger, kwargs: dict)
tests/unit/integrations/test_prometheus_rate_limit_labels.py:356
↓ 5 callersFunction_set_weave_specific_attributes
Sets Weave-specific metadata attributes onto the OTEL span. Based on Weave's OTEL attribute mappings from: https://github.com/wandb/weav
litellm/integrations/weave/weave_otel.py:80
↓ 5 callersMethod_setup
(self, monkeypatch, team_obj, editable_fields)
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:23504
↓ 5 callersFunction_setup_model_block_mocks
(monkeypatch, *, updated_blocked: bool)
tests/unit/test_model_block_unblock.py:17
↓ 5 callersMethod_setup_response_with_docs
(self, mock_request_data, docs)
tests/unit/proxy/guardrails/guardrail_hooks/test_xecguard.py:589
↓ 5 callersFunction_shape_reply
(identity: str, stream: bool)
tests/integration/providers/test_databricks_chat_wire.py:248
↓ 5 callersFunction_shapes
(keys: Keys)
tests/integration/authorization/test_websocket_rejection_logging.py:112
↓ 5 callersFunction_shared_ptu_model_list
()
tests/unit/test_router/test_router.py:13611
↓ 5 callersFunction_shim_command_line
(*args)
tests/unit/proxy/client/cli/test_agents.py:2144
↓ 5 callersMethod_should_only_sensitive_data_failed
Check if only sensitive data detectors (PII, PCI, secrets) have result=true in the classification. Args: classification_
litellm/proxy/guardrails/guardrail_hooks/noma/noma.py:370
↓ 5 callersFunction_should_read_secret_from_secret_manager
Returns True if the secret manager should be used to read the secret, False otherwise - If the secret manager client is not set, return Fals
litellm/secret_managers/main.py:530
↓ 5 callersFunction_should_use_smtp_ssl
Port 465 expects an immediate TLS handshake (implicit SSL), so a plain smtplib.SMTP connection hangs waiting for an SMTP banner. Use SMTP_SSL
litellm/proxy/utils.py:8363
↓ 5 callersFunction_sign_in
( proxy: Gateway, idp: Idp, browser: httpx.Client, session: CliSession, *, subject: str | None = None )
tests/integration/authorization/test_cli_sso_login_ui_disabled.py:246
↓ 5 callersMethod_sign_s3_request_without_body
SigV4-sign a bodiless S3 request (GetObject, DeleteObject, ListObjectsV2), mirroring `_sign_s3_request` (PUT).
litellm/llms/bedrock/files/transformation.py:1731
↓ 5 callersFunction_signed_license
( expiration_date: str, allowed_features: tuple[str, ...] = ("auto_router",) )
tests/unit/proxy/auth/test_litellm_license.py:72
↓ 5 callersFunction_simple_chat_body
( model: str, marker: str, *, stream: bool = False, marked: bool = True, system_as_str
tests/integration/providers/_responses_bridge_prompt_cache_breakpoint.py:144
↓ 5 callersFunction_simulate_price_data_reload_with_provider_sets
Like `_simulate_price_data_reload`, plus the provider model-set refresh the proxy's `_swap_in_model_cost_map` does before replaying, so bare names
tests/unit/test_router_model_cost_isolation.py:3606
↓ 5 callersFunction_single
(declaration: Mapping[str, JsonValue], litellm_model: str = f"openai/{_CHAT_MODEL}")
tests/integration/routing/test_non_chat_model_endpoint_gate.py:129
↓ 5 callersFunction_single_span
(spans: tuple[dict[str, str], ...])
tests/integration/observability/_openinference_support.py:564
↓ 5 callersFunction_single_upstream_request
(wire: Wire)
tests/integration/translation/chat_completions/basic/test_chat_completions_openai_search_replay.py:29
↓ 5 callersMethod_skip_blocked_stdio_listing
(self, server: MCPServer, listing: str)
litellm/proxy/mcp_server/mcp_server_manager.py:4813
↓ 5 callersFunction_sku
( provider: Provider, mode: Mode, *, weight: int | None = None, endpoints: JsonValue = Non
tests/integration/routing/test_batch_mode_deployments_wire.py:70
↓ 5 callersFunction_slack_alerting_with_due_daily_report
()
tests/unit/integrations/SlackAlerting/test_slack_alerting.py:273
↓ 5 callersMethod_socket_timeouts
(timeout: float | httpx.Timeout | None)
litellm/llms/valkey/vector_stores/transformation.py:150
↓ 5 callersFunction_socket_turn_kwargs
( call_id: str, metadata: dict[str, object], call_type: str = CallTypes.aresponses_websocket.value )
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:4153
↓ 5 callersFunction_socket_with_tpm_limited_tag
()
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:4182
↓ 5 callersFunction_sort_bedrock_assistant_content_blocks
Sort assistant content blocks so that ``text`` blocks appear before ``toolUse`` blocks. Bedrock requires all ``text`` blocks to precede
litellm/litellm_core_utils/prompt_templates/factory.py:4727
↓ 5 callersFunction_source
(entries)
tests/unit/proxy/pass_through_endpoints/test_carry_guardrail_logging_info.py:17
↓ 5 callersMethod_span_attributes
(self, standard_logging_object, response_obj)
tests/unit/integrations/test_opentelemetry.py:6640
↓ 5 callersFunction_span_trace_id
(span)
tests/unit/integrations/test_langfuse.py:1680
↓ 5 callersMethod_spawned_since
(self, tasks_before)
tests/unit/proxy/pass_through_endpoints/test_streaming_handler_interrupt.py:1342
↓ 5 callersFunction_speaks_system_one
(route: Route)
tests/integration/providers/test_cloudflare_clef_images_wire.py:103
↓ 5 callersFunction_spend
(call_id: str)
tests/integration/spend/test_vertex_image_regional_uplift.py:144
↓ 5 callersFunction_spend
(limiter: PROXY_VirtualKeyModelMaxBudgetLimiter, spend_key: str)
tests/unit/proxy/hooks/test_model_max_budget_limiter.py:122
↓ 5 callersFunction_spend_log
(request_id: str, session_id: str, prompt: str, answer: str)
tests/unit/responses/litellm_completion_transformation/test_session_handler.py:464
↓ 5 callersFunction_spend_logs_copy
A private schema holding a copy of the migrated `LiteLLM_SpendLogs` with its indexes, seeded by `insert`.
tests/integration/spend/test_session_grouped_logs_pages.py:268
↓ 5 callersFunction_spend_payload
(flush_mock: MagicMock)
tests/unit/passthrough/test_streaming_interrupt_spend_tracking.py:59
↓ 5 callersFunction_spend_row
(call_id: str)
tests/integration/providers/test_decisions_openai_format_wire.py:347
↓ 5 callersFunction_spend_row
(call_id: str)
tests/integration/providers/test_strands_decider_agentcore_wire.py:390
↓ 5 callersFunction_spend_row
(request_id: str)
tests/integration/providers/test_anthropic_thinking_signature_stream_wire.py:171
↓ 5 callersFunction_spend_row_for_call
(call_id: str, content: bytes)
tests/integration/observability/test_guardrail_stream_scope_matrix.py:639
↓ 5 callersFunction_spend_rows
(request_ids: frozenset[str], *, expected: int, seconds: float = 90)
tests/integration/providers/test_bedrock_kimi_k3_cache_point_wire.py:533
↓ 5 callersFunction_spend_rows
(key: str, count: int)
tests/integration/providers/test_openai_realtime_transcription_url.py:214
↓ 5 callersFunction_spend_rows
(identity: str, expected: int)
tests/integration/messages_endpoint/providers/bedrock/test_bedrock_messages_gpt_chat_completions_wire.py:52
↓ 5 callersFunction_spend_rows
(model: str, expected: int)
tests/integration/streaming/test_interception_converted_stream_options.py:306
↓ 5 callersFunction_spend_rows_for_calls
( models: tuple[str, ...], expected: tuple[tuple[str, str, str], ...], *, tolerate_missing: bo
tests/integration/observability/_logging_only_scope_support.py:1056
↓ 5 callersFunction_spend_status_by_call
(served: tuple[_Served, ...])
tests/integration/providers/test_sagemaker_embedding_chaos.py:129
↓ 5 callersMethod_sse
(event, data)
tests/unit/proxy/pass_through_endpoints/llm_provider_handlers/test_anthropic_passthrough_logging_handler.py:1203
↓ 5 callersMethod_sse
(event_type, data)
tests/unit/llms/anthropic/chat/guardrail_translation/test_anthropic_guardrail_handler.py:3238
↓ 5 callersFunction_sse_event
Frame a JSON-RPC object as a single A2A SSE event (``data: <json>\\n\\n``).
litellm/proxy/agent_endpoints/a2a_endpoints.py:127
↓ 5 callersFunction_sse_event
(event_type: str, data: dict)
tests/unit/proxy/guardrails/guardrail_hooks/unified_guardrails/test_anthropic_streaming_block.py:48
↓ 5 callersFunction_sse_events
(body: str)
tests/unit/proxy/proxy_server/test_routes_audio.py:542
↓ 5 callersFunction_sse_events
Parses emitted SSE output, whatever its chunking, back into event payloads.
tests/unit/proxy/guardrails/guardrail_hooks/test_llm_shield_proxy.py:127
↓ 5 callersFunction_sse_response
(body: str)
tests/unit/google_genai/test_google_genai_streaming_iterator.py:104
↓ 5 callersFunction_sso_environment
(idp_url: str)
tests/integration/authorization/test_cli_sso_login_ui_disabled.py:123
↓ 5 callersFunction_sso_http_handler
litellm's SSO httpx client answered in-process, by ``route`` or by the active respx mock.
tests/unit/proxy/management_endpoints/test_ui_sso.py:112
↓ 5 callersFunction_sso_user_info_from_db
( custom_user_id: object, prisma_client: MagicMock, cached_user: LiteLLM_UserTable | None = None,
tests/unit/proxy/management_endpoints/test_ui_sso.py:2149
↓ 5 callersFunction_stamp_injection_points_for_the_hook
Carry onto the points the provider this layer resolved and the marks its pass cannot see. The hook reads ``custom_llm_provider`` from the request
litellm/responses/main.py:859
↓ 5 callersFunction_stamped
(chunk: Mapping[str, JsonValue])
tests/integration/routing/test_vllm_passthrough_stream_relay.py:86
↓ 5 callersMethod_start_session
(self, config)
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_transformation.py:356
↓ 5 callersFunction_statement
(queryid: int, query: str, calls: int)
tests/e2e_harness/perf/setup/test_observe.py:85
↓ 5 callersFunction_status_peer
(reply: Reply)
tests/integration/compatibility/test_openai_sdk_client_paths.py:168
↓ 5 callersFunction_statuses
(rows: Sequence[Mapping[str, JsonValue]])
tests/integration/mcp/test_mcp_llm_endpoints.py:1407
↓ 5 callersFunction_step_lists
()
tests/unit/test_circleci_rust_toolchain.py:86
↓ 5 callersFunction_step_text
Flatten one step into the shell text it runs, or '' for a command reference.
tests/unit/test_circleci_rust_toolchain.py:47
↓ 5 callersMethod_stop_engine_watcher
Stop watching the engine process and clean up all resources.
litellm/proxy/utils.py:7475
↓ 5 callersFunction_stop_frames
(frames: list[dict])
tests/integration/providers/test_google_genai_adapter_wire.py:824
↓ 5 callersFunction_stop_launch
(launch: _Launch)
tests/integration/_support/process.py:506
↓ 5 callersFunction_store
(db: Prisma, **faults: bool)
tests/integration/spend/test_baseline_accounting.py:48
↓ 5 callersFunction_store_per_user_token_server_side
Persist the OAuth token server-side and warm the Redis cache. Called from the token endpoint after a successful code exchange or refresh. Err
litellm/proxy/mcp_server/discoverable_endpoints.py:674
↓ 5 callersFunction_stored_chain
(*items: dict[str, object])
tests/unit/completion_extras/litellm_responses_transformation/test_completion_extras_litellm_responses_transformation_transformation.py:5842
↓ 5 callersFunction_stored_override
(database_url: str, config_type: str)
tests/integration/security/test_config_overrides.py:78
↓ 5 callersFunction_stored_params
(create_or_update_mock: AsyncMock)
tests/unit/proxy/guardrails/test_guardrail_registry.py:1766
↓ 5 callersFunction_stored_refresh_token_loader
(refresh_token: str | None)
tests/unit/proxy/mcp_server/test_oauth_identity_binding.py:71
↓ 5 callersFunction_stored_request_with_payload
(body: Mapping[str, object], standard_payload: Mapping[str, object])
tests/unit/proxy/spend_tracking/test_spend_tracking_utils.py:7699
↓ 5 callersFunction_stored_routes
(gateway: Gateway, key: str)
tests/integration/management/test_key_default_allowed_routes.py:91
↓ 5 callersFunction_stored_rows
(response_ids: tuple[str, ...], *, responses_api: bool = False)
tests/integration/spend/test_spend_log_tool_payload_content.py:134
↓ 5 callersFunction_stream
Stream `route`, releasing held scans once `release_after` text pieces have arrived.
tests/integration/streaming/test_bedrock_guardrail_background_stream_scan.py:248
↓ 5 callersFunction_stream
()
tests/unit/proxy/guardrails/guardrail_hooks/test_model_armor.py:3936
↓ 5 callersFunction_stream_chunks
( is_async: bool, handler: Callable[[httpx.Request], httpx.Response], api_base: str | None = None,
tests/unit/llms/vertex_ai/gemini/test_long_decode.py:722
↓ 5 callersFunction_stream_collector
(endpoint: str)
tests/unit/llms/bedrock/passthrough/test_bedrock_passthrough_transformation.py:621
↓ 5 callersFunction_stream_events
(response: dict)
tests/unit/integrations/websearch_interception/test_websearch_agentic_loop_cap.py:990
↓ 5 callersFunction_stream_frames
(frames: Sequence[bytes])
tests/unit/proxy/anthropic_endpoints/test_streaming_model_restamp.py:29
↓ 5 callersFunction_stream_frames
( frames: tuple[bytes, ...], is_messages_api: bool, mode: str )
tests/unit/llms/sagemaker/test_sagemaker_common_utils.py:304
← previousnext →15,101–15,200 of 202,479, ranked by callers