MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 14 callersFunctionskill
( skill_id: str, *, display_title: str | None = "PDF Summarizer", description: str | None = No
tests/unit/proxy/discovery_endpoints/test_agent_skills_endpoints.py:55
↓ 14 callersFunctionsse_chunks
(events: Sequence[Event])
tests/integration/_support/anthropic_thinking.py:112
↓ 14 callersMethodstats
(self)
litellm/proxy/spend_tracking/spend_event_producer.py:191
↓ 14 callersMethodstop
(self)
litellm/proxy/db/pgbouncer.py:634
↓ 14 callersMethodstop
(&self)
litellm-rust/crates/cache-qdrant-semantic/tests/support/mod.rs:75
↓ 14 callersFunctionstore
(client: Option<RedisClient>)
litellm-rust/crates/redis-store/tests/auth_cache.rs:127
↓ 14 callersFunctionstore
(client: Option<RedisClient>)
litellm-rust/crates/redis-store/tests/spend_counters.rs:48
↓ 14 callersMethodstore_message
Store message in list
litellm/litellm_core_utils/realtime_streaming.py:664
↓ 14 callersFunctionstored_connections
(stored: StoredROISettings)
litellm/proxy/roi_calculator/settings.py:80
↓ 14 callersFunctionstored_rows
(name: str)
tests/integration/management/test_claude_code_plugin_installation_preference.py:114
↓ 14 callersFunctionstrategy_router_dependencies
The model names a strategy-router deployment must reach, in no particular order. A field is a dependency only under the condition the runtime its
litellm/router_strategy/auto_router/auto_router_model_naming.py:120
↓ 14 callersFunctionstream
( rig: Rig, key: str, model: str, prompt: str, releases: Sequence[Release] = (), extra
tests/integration/streaming/test_mid_stream_fallback_continuation.py:404
↓ 14 callersFunctionstringify
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 14 callersFunctionstrip_beta_gated_system_messages
Drop the gated fields of every mid-conversation ``role: system`` message. Returns the same sequence when nothing is gated, or when dropping an emp
litellm/anthropic_beta_gated_fields.py:205
↓ 14 callersFunctionsuccess_machine
Answers to projection, to the route op and to `before_provider_request` all reach the response, so a driver that misroutes a reply changes what the ca
litellm-rust/crates/host-python/tests/support/mod.rs:460
↓ 14 callersMethodsum
(amounts: I)
litellm-rust/crates/cost/src/money.rs:80
↓ 14 callersFunctiont
litellm/proxy/_experimental/out/_next/static/chunks/2jxpy6eth1zvy.js:1
↓ 14 callersMethodteam_key
( self, capture: Capture | None, name: str, *, callback: str = "langfu
tests/integration/observability/test_otel_team_capture_message_content.py:213
↓ 14 callersFunctionteam_membership_auth_cache_key
Cache key one team member's ``LiteLLM_TeamMembership`` row is stored under for the admission check.
litellm/proxy/common_utils/user_api_key_cache.py:565
↓ 14 callersMethodtext
(text: impl Into<String>)
litellm-rust/crates/llms-types/src/formats/messages/request.rs:100
↓ 14 callersMethodthrow
(self, error: BaseException)
tests/unit/rust_bridge/test_bindings.py:113
↓ 14 callersMethodto_wire
(self, value: object)
litellm/router_rust/surface/model_info.py:98
↓ 14 callersFunctiontp
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0ayyip3c-drm1.js:1
↓ 14 callersMethodtransform_litellm_user_to_scim_user
( user: LiteLLM_UserTable | NewUserResponse, )
litellm/proxy/management_endpoints/scim/scim_transformations.py:26
↓ 14 callersMethodtransform_realtime_request
Translate OpenAI realtime client messages to Vertex AI format. On the first ``session.update`` (when no setup has been sent yet) the
litellm/llms/vertex_ai/realtime/transformation.py:204
↓ 14 callersMethodtransform_request_to_count_tokens
Transform request to Anthropic CountTokens format. Includes optional system and tools fields for accurate token counting; a leading
litellm/llms/anthropic/count_tokens/transformation.py:379
↓ 14 callersMethodtransform_to_anthropic_error
Transform an error message to Anthropic format. - If already in Anthropic format: passthrough unchanged - Otherwise: extract
litellm/anthropic_interface/exceptions/exception_mapping_utils.py:129
↓ 14 callersFunctiontrim_messages
Trim a list of messages to fit within a model's token limit. Args: messages: Input messages to be trimmed. Each message is a diction
litellm/utils.py:8908
↓ 14 callersFunctionttl
(value: Option<f64>)
litellm-rust/crates/python-bridge/src/redis/store/mod.rs:87
↓ 14 callersFunctiontuning_fingerprint
Digest of explicitly supplied heuristic-v1 tuning fields, normalized, or None when invalid.
litellm/router_strategy/auto_router/auto_router_tuning_baseline.py:42
↓ 14 callersFunctionunique_id
A deployment id no other test uses, for tests that write into the process-wide ``litellm.model_cost``.
tests/unit/test_router/core/registry_helpers.py:45
↓ 14 callersFunctionunix_socket_path
(runtime_dir: Path, port: int)
litellm/proxy/db/pgbouncer.py:467
↓ 14 callersMethodunregister_tools_with_prefix
Remove tools whose registered name starts with ``prefix``. Used when an OpenAPI-backed MCP server leaves the runtime registry so stal
litellm/proxy/mcp_server/tool_registry.py:90
↓ 14 callersMethodunshift
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 14 callersFunctionuntil
(gateway: Gateway, metric: str, **labels: str)
tests/integration/observability/test_prometheus_provider_auth_failure.py:432
↓ 14 callersFunctionupdate_access_group
Update an access group's model names. This will: 1. Add the access group to all deployments for the new model_names list 2. Remo
litellm/proxy/management_endpoints/model_access_group_management_endpoints.py:1055
↓ 14 callersMethodupdate_from_kwargs
(self, **kwargs)
tests/unit/llms/xai/test_xai_key_fallback.py:18
↓ 14 callersFunctionupload
( gateway: Gateway, route: Route | None, model: str, content: bytes, *, client: httpx.Client | None = None
tests/integration/providers/_vertex_batch_rows.py:108
↓ 14 callersMethodupstream_body
(self)
tests/integration/providers/test_decisions_openai_format_wire.py:123
↓ 14 callersFunctionupstream_body_for
(wire: Wire, marker: str)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:564
↓ 14 callersFunctionuseOrganizations
(filters?: OrganizationListFilters)
ui/litellm-dashboard/src/app/(dashboard)/hooks/organizations/useOrganizations.ts:13
↓ 14 callersFunctionuser_info_v2
Lightweight endpoint to get user info. Returns only the user object — no keys, no teams objects. This is the v2 replacement for /user/info,
litellm/proxy/management_endpoints/internal_user_endpoints.py:1163
↓ 14 callersFunctionuser_is_org_admin
Helper function to check if user is an org admin for all of the passed organizations. Checks both: - `organization_id` (singular string)
litellm/proxy/auth/auth_checks_organization.py:136
↓ 14 callersFunctionuser_prompt
(body: Mapping[str, JsonValue])
tests/integration/_support/anthropic_sse.py:179
↓ 14 callersFunctionvertex_gemini_count_context
( system: object | None, tools: object | None, model: str, )
litellm/llms/vertex_ai/count_tokens/context.py:118
↓ 14 callersMethodvertex_passthrough_handler
( httpx_response: httpx.Response, logging_obj: LiteLLMLoggingObj, url_route: str,
litellm/proxy/pass_through_endpoints/llm_provider_handlers/vertex_passthrough_logging_handler.py:155
↓ 14 callersMethodwait
(self)
tests/unit/llms/codex/harness/test_transformation.py:78
↓ 14 callersMethodwith
Appends one command in its pipelined form; `RedisClient::run` answers it in order, undecoded.
litellm-rust/crates/redis-client/src/pipeline.rs:33
↓ 13 callersFunctionV
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 13 callersMethod__anext__
(self)
tests/unit/llms/anthropic/messages/native/test_streaming_iterator.py:1342
↓ 13 callersMethod__init__
(self, mock_team_data, mock_key_data)
tests/unit/proxy/test_proxy_utils.py:1734
↓ 13 callersFunction_agent_command
(name)
tests/unit/proxy/client/cli/test_agents.py:49
↓ 13 callersFunction_anthropic_messages_logging_obj
()
tests/unit/litellm_core_utils/test_litellm_logging.py:7038
↓ 13 callersFunction_assert_index_covers_every_partition
(database_url: str, parent_index: str, suffix: str)
tests/integration/database/migrations/test_request_log_indexes.py:282
↓ 13 callersFunction_assert_no_password_fragments
(output: str)
tests/integration/database/test_v1_migration_error_logging.py:214
↓ 13 callersFunction_assert_one_row
(call_id: str, status: str)
tests/integration/messages_endpoint/chat_bridge/test_chat_bridge_multi_tool_call_blocks_wire.py:488
↓ 13 callersFunction_assert_reported_usage
(row: Mapping[str, JsonValue])
tests/integration/routing/test_vllm_passthrough_stream_relay.py:160
↓ 13 callersMethod_auth
(self, user_id: str = "human-1", **kwargs)
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:10633
↓ 13 callersFunction_auth_cache
A worker's auth cache with ``enable_redis_auth_cache`` on, whose connection the credential cache shares.
tests/unit/proxy/credential_endpoints/test_user_provider_credentials.py:29
↓ 13 callersFunction_b64
(raw: bytes)
tests/integration/observability/test_bedrock_guardrail_attachments.py:36
↓ 13 callersFunction_background_response
(response_id: str, status: str, input_tokens: int)
tests/unit/proxy/response_api_endpoints/test_endpoints.py:1097
↓ 13 callersFunction_bare
(model: str)
tests/integration/providers/test_bedrock_mantle_count_tokens_wire.py:291
↓ 13 callersFunction_batch_dict
A minimal-but-valid dict for ``LiteLLMBatch(**response.model_dump())``.
tests/unit/llms/azure/batches/test_handler.py:54
↓ 13 callersMethod_bedrock_events
(stream: FakeBedrockStream)
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_handler.py:1826
↓ 13 callersFunction_body
(endpoint: Endpoint, model: str, nonce: str, *, stream: bool, outage: bool = False)
tests/integration/routing/test_include_fallback_errors_wire.py:183
↓ 13 callersFunction_browser
()
tests/integration/authorization/test_sso_blank_identity.py:411
↓ 13 callersFunction_bucket
(kwargs: Mapping[str, object], name: str = "metadata")
tests/unit/test_router/core/test_endpoints_characterization_inference.py:34
↓ 13 callersFunction_budget
The injected per-statement bound: a callable re-read before each statement.
tests/unit/proxy/db/db_transaction_queue/test_spend_logs_partition_manager.py:27
↓ 13 callersFunction_buffer
(redis: FakeRedis, *, leader: bool)
tests/unit/proxy/db/test_gateway_request_tracking.py:534
↓ 13 callersFunction_build_langfuse_logger
(monkeypatch, **overrides)
tests/unit/integrations/test_langfuse.py:1473
↓ 13 callersFunction_build_ranking_request
Run map_cohere_rerank_params + transform_rerank_request for /v1/ranking.
tests/unit/llms/nvidia_nim/rerank/test_nvidia_nim_rerank_transformation.py:30
↓ 13 callersMethod_calculate_usage_per_chunk
( self, chunks: Sequence["_UsageBearingChunk | ModelResponse"], )
litellm/litellm_core_utils/streaming_chunk_builder_utils.py:956
↓ 13 callersFunction_call
( key: str, trace_id: str | None, endpoint: Endpoint = "chat", stream: bool = False, content: str = "hello
tests/integration/observability/test_otel_team_sampling_across_pods.py:147
↓ 13 callersMethod_call_agentic_completion_hooks
Call agentic completion hooks for all custom loggers (Anthropic Messages API). 1. Call async_should_run_agentic_loop to check if age
litellm/llms/custom_httpx/llm_http_handler.py:6379
↓ 13 callersFunction_call_embedding
(router: Router, *, sync: bool, **kwargs: object)
tests/unit/router_utils/test_embedding_batch_size_check.py:110
↓ 13 callersFunction_caller
(user_id: str | None = "user-123")
tests/unit/proxy/management_endpoints/test_password_endpoints.py:42
↓ 13 callersFunction_chat
(model: str, prompt: str, stream: bool = False)
tests/integration/providers/test_bedrock_mantle_context_overflow_wire.py:183
↓ 13 callersFunction_chat
(rig: _Rig, body: Mapping[str, JsonValue])
tests/integration/streaming/test_interception_converted_stream_options.py:262
↓ 13 callersMethod_check_content
Evaluate content against Purview DLP policies. Args: user_id: Entra object ID. text: Content to evaluate.
litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/purview_dlp.py:109
↓ 13 callersFunction_check_team_key_limits
Check if the team key is allocating guaranteed throughput limits. If so, raise an error if we're overallocating. Only runs check if tpm_limi
litellm/proxy/management_endpoints/key_management_endpoints.py:1994
↓ 13 callersFunction_clear_proxy_environment
Clear the proxy environment the router's own pod discovery reads, so it substitutes pod IPs.
tests/unit/router_utils/test_kubernetes_pod_discovery.py:280
↓ 13 callersFunction_coerce_redis_kwargs_types
Coerces string values to the numeric/boolean type ``client``'s constructor declares for that parameter. ``client`` may be a tuple of client classe
litellm/_redis.py:208
↓ 13 callersFunction_complete_page
(response, scoped_server=None, vendor=None, reachable=None, cache=None, **overrides)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:1072
↓ 13 callersFunction_completed_chunk
(output, response_id: str = "resp-1")
tests/unit/responses/mcp/test_mcp_streaming_iterator.py:55
↓ 13 callersFunction_configure
(runner, *args)
tests/unit/proxy/client/cli/test_configure_commands.py:103
↓ 13 callersFunction_configure_key_endpoints
( monkeypatch: pytest.MonkeyPatch, user_api_key_cache: UserApiKeyCache, )
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:22059
↓ 13 callersFunction_content_json
(message: Mapping[str, JsonValue])
tests/integration/providers/test_bedrock_native_structured_output_wire.py:491
↓ 13 callersFunction_count_requests
(wire: Wire)
tests/integration/providers/test_vertex_gemini_count_tokens_wire.py:97
↓ 13 callersFunction_ctx_double
A RoutingContext double answering the registry, settings and health reads the cooldown helpers make.
tests/unit/router_utils/test_cooldown_handlers.py:63
↓ 13 callersFunction_cursors
(pods: Pods)
tests/integration/observability/test_otel_team_sampling_across_pods.py:280
↓ 13 callersFunction_daily_activity_database
( *, include_tag_activity: bool = False, include_tag_float_tie_activity: bool = False, include
tests/integration/spend/test_daily_activity_repository.py:91
↓ 13 callersFunction_daily_txn
(user_id: str = "user1")
tests/unit/proxy/db/test_db_spend_update_writer.py:476
↓ 13 callersMethod_database
(team: LiteLLM_TeamTable, row: LiteLLM_ProxyModelTable)
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:9033
↓ 13 callersFunction_db_prompt_spec
(content: str, environment: str = "development", version: int = 1)
tests/unit/proxy/prompts/test_prompt_registry.py:9
↓ 13 callersFunction_db_systems
(spans: tuple[Span, ...])
tests/integration/observability/test_otel_excluded_services_matrix.py:340
↓ 13 callersFunction_dcr_redirect_test_server
(client_id)
tests/unit/proxy/mcp_server/test_discoverable_endpoints.py:1992
↓ 13 callersFunction_decide
(gateway: Gateway, model: str, *, route: str = "/v1/decisions", **extra: JsonValue)
tests/integration/providers/test_decisions_openai_format_wire.py:322
↓ 13 callersFunction_decide
(gateway: Gateway, model: str, *, key: str | None = None, **extra: JsonValue)
tests/integration/providers/test_decisions_wire.py:243
↓ 13 callersFunction_decode_json_object
Decode a realtime frame into its top-level field mapping.
litellm/litellm_core_utils/realtime_streaming.py:223
↓ 13 callersMethod_delegate_admission
( admission: AsyncMock, allowed_server_ids: Sequence[str] = ("test-server-id",) )
tests/unit/proxy/mcp_server/auth/test_user_api_key_auth_mcp.py:2674
← previousnext →4,601–4,700 of 202,479, ranked by callers