MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 21 callersFunction_register
( case: _Case, respx_mock: MockRouter, text: str, *, stream: bool = False, json_via_to
tests/unit/llms/base_llm/chat/test_provider_chat_translation.py:552
↓ 21 callersFunction_responses
(model: str, items: Sequence[JsonValue], **fields: JsonValue)
tests/integration/providers/test_responses_bridge_message_cache_control_wire.py:84
↓ 21 callersMethod_router
( tier_litellm_params: dict | None = None, max_tokens_from_tier_model: bool | Literal["clamp"]
tests/unit/router_strategy/test_complexity_router.py:17036
↓ 21 callersMethod_run
( self, request_data, original_exception: Exception | None = None, request_route=None, dispatched_call
tests/unit/proxy/test_proxy_utils_model_creation_and_error_logging.py:1005
↓ 21 callersFunction_scripted
(call: _Call, reply: Callable[[Mapping[str, JsonValue]], Reply])
tests/integration/routing/test_vllm_passthrough_stream_relay.py:123
↓ 21 callersMethod_sign_request
Sign a request for Bedrock or Sagemaker Returns: Tuple[dict, Optional[str]]: A tuple containing the headers and the json
litellm/llms/bedrock/base_aws_llm.py:1641
↓ 21 callersFunction_step
(*frames: dict[str, JsonValue], until: str)
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:540
↓ 21 callersFunction_stream_peer
(frames: bytes)
tests/integration/providers/test_bedrock_converse_stream_event_frames_wire.py:182
↓ 21 callersFunction_streamed_json_mode_contents
( fragments: tuple[str, ...], schema: dict[str, object] = _STREAMED_RISK_SCHEMA )
tests/unit/llms/anthropic/chat/test_anthropic_chat_handler.py:3207
↓ 21 callersFunction_token_file
(home)
tests/unit/litellm_core_utils/test_cli_token_utils.py:55
↓ 21 callersMethod_transform_response
( self, model: str, response: httpx.Response, model_response: ModelResponse,
litellm/llms/bedrock/chat/converse_transformation.py:2963
↓ 21 callersMethod_update_daily_spend
( n_retry_times: int, prisma_client: PrismaClient, proxy_logging_obj: ProxyLogging,
litellm/proxy/db/db_spend_update_writer.py:2723
↓ 21 callersFunction_upstream
(rig: _Rig, deployment: _Deployment)
tests/integration/streaming/test_interception_converted_stream_options.py:270
↓ 21 callersFunction_usage_core
gpt: a (tpm 100, rpm 10) and b (top-level tpm 1000, model_info tpm 50 / rpm 5); io: i (itpm 300, otpm 40).
tests/unit/test_router/core/test_registry_characterization_model_info.py:18
↓ 21 callersFunction_verdict
(payload: dict[str, object], status_code: int = 200)
tests/unit/proxy/guardrails/guardrail_hooks/test_alice.py:27
↓ 21 callersMethodaccess_groups
Access group name to model names (was ``get_model_access_groups``).
litellm/router_api.py:1047
↓ 21 callersMethodaclose
(self)
tests/unit/test_router/test_router.py:12633
↓ 21 callersMethodadd
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 21 callersFunctionanthropic_params
(wire: Wire)
tests/integration/routing/test_payment_required_mapping.py:69
↓ 21 callersMethodasync_batch_get_cache
With ``throttle_redis`` False every key memory cannot serve is read from Redis, exactly as a per-key ``async_get_cache`` would read it, instea
litellm/caching/dual_cache.py:377
↓ 21 callersMethodasync_delete_cache
(self, key: str)
litellm/proxy/common_utils/user_api_key_cache.py:365
↓ 21 callersMethodasync_filter_deployments
If the request ``input`` contains litellm-encoded item IDs, or its Anthropic ``messages`` replay a bridge-tagged thinking block, deco
litellm/router_utils/pre_call_checks/encrypted_content_affinity_check.py:510
↓ 21 callersMethodbefore
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 21 callersMethodbilling_auth_for_tool_call
The auth object a tool call's SPEND should be recorded against. ``auth`` unchanged for callers without inherited team grants. For an admitted
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:2500
↓ 21 callersFunctionchat_body
(model: str, messages: Sequence[JsonValue], stream: bool, **fields: JsonValue)
tests/integration/providers/_tool_search_support.py:224
↓ 21 callersFunctionclear_prometheus_registry
Helper function to clear the Prometheus registry
tests/unit/enterprise/integrations/test_prometheus.py:49
↓ 21 callersMethodclose
(self)
tests/e2e/e2e_http.py:315
↓ 21 callersMethodcommit
(self)
tests/unit/repositories/test_unit_of_work.py:46
↓ 21 callersMethodcompletion
(self, *args: object, **kwargs: object)
tests/unit/litellm_core_utils/test_text_completion_conversion.py:1307
↓ 21 callersMethodcopyMetaAndAttributes
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 21 callersMethodcount
(self, where: tuple[Predicate, ...])
litellm/proxy/list_api/list_framework.py:187
↓ 21 callersFunctioncount_request
(model: str, case: LiftCase)
tests/integration/providers/_count_tokens_system_lift.py:180
↓ 21 callersMethodcreate
(self, messages, model=None, **kwargs)
litellm/main.py:616
↓ 21 callersFunctioncreate_group
(candidate: Gateway, users: Sequence[str], *, display_name: str | None = None)
tests/integration/_support/scim.py:73
↓ 21 callersFunctioncreated_team
(scenario: Scenario, created: httpx.Response)
tests/integration/_support/scim.py:118
↓ 21 callersFunctiondeclared_authenticating_provider
The authenticating provider this pair already names, or None. get_llm_provider runs the OAuth device flow for github_copilot and chatgpt, because
litellm/litellm_core_utils/get_llm_provider_logic.py:155
↓ 21 callersFunctionencode_video_id_in_response
Stamps the provider, model and the deployment that answered into a returned video id. A poll of an existing video (`polled_video`) answered w
litellm/proxy/video_endpoints/utils.py:156
↓ 21 callersFunctionew
(e,s)
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 21 callersMethodexecute_raw
(self, query: str, *args: object)
litellm/proxy/db/prisma_client.py:910
↓ 21 callersFunctionextract_original_video_id
Extract original video ID without encoding.
litellm/types/videos/utils.py:172
↓ 21 callersFunctionfirst_ok
First successful call on a fresh key. A fresh key may briefly 401 until the data plane's auth cache picks it up, so retry on 401 to a deadline; a
tests/e2e/logging/logging_client.py:691
↓ 21 callersMethodflush_all_updates_from_in_memory_queue
Get all updates from the queue.
litellm/proxy/db/db_transaction_queue/base_update_queue.py:42
↓ 21 callersFunctionget_available_models_for_user
Get the list of models available to a user based on their API key and team permissions. Args: user_api_key_dict: User API key authen
litellm/proxy/utils.py:10167
↓ 21 callersFunctionget_azure_ad_token
Get Azure AD token from various authentication methods. This function tries different methods to obtain an Azure AD token: 1. From an ex
litellm/llms/azure/common_utils.py:550
↓ 21 callersMethodget_cache
Retrieves the cached result for the given arguments. Args: *args: args to litellm.completion() or embedding()
litellm/caching/caching.py:699
↓ 21 callersFunctionget_dynamic_litellm_params
Generate a unique model_id for the deployment. Returns - litellm_params: dict for generating a unique model_id.
litellm/litellm_core_utils/clientside_credential_handler.py:94
↓ 21 callersMethodget_sanitized_user_information_from_key
( user_api_key_dict: UserAPIKeyAuth, )
litellm/proxy/litellm_pre_call_utils.py:2077
↓ 21 callersFunctionhistory
(marker: str, *reasoning: dict[str, JsonValue])
tests/integration/routing/test_fallback_hop_foreign_encrypted_reasoning.py:404
↓ 21 callersFunctionisReferenceLikeElement
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 21 callersMethodis_multipart
Check if the request is a multipart/form-data request
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:569
↓ 21 callersMethodlisten
( self, session: ClientSession, requested: SubscriptionFilter )
litellm/proxy/mcp_server/subscriptions.py:149
↓ 21 callersMethodload_agents_from_config
Register the agents declared in config.yaml and remember them for later rebuilds. A config entry is skipped when its ``agent_name``
litellm/proxy/agent_endpoints/agent_registry.py:466
↓ 21 callersFunctionmake_config
( auth_method: str = "client_secret_basic", scope: str | None = None, token_url: str = TOKEN_URL,
tests/unit/llms/base_llm/auth/test_client_credentials.py:59
↓ 21 callersFunctionmake_ctx
(sandbox, **kwargs)
tests/unit/llms/codex/harness/test_transformation.py:159
↓ 21 callersFunctionmarker
()
tests/integration/providers/_gemini_tts_voice_support.py:85
↓ 21 callersFunctionmatch_capability_generalizations
Return the union of the ``model_info`` of every capability rule matching ``model``. Later rules override earlier ones on key conflicts. Returns `
litellm/litellm_core_utils/fallback_generalizations.py:225
↓ 21 callersMethodmaybe_seed_default_injection_points
For /chat/completions: resolve the injection points the request should carry. Configured injection points win over the automatic defaults and
litellm/integrations/anthropic_cache_control_hook.py:1669
↓ 21 callersMethodmodel_dump
(self, mode: str = "python")
tests/unit/proxy/guardrails/guardrail_hooks/test_alice.py:586
↓ 21 callersMethodpass_through_async_success_handler
( self, httpx_response: httpx.Response, response_body: dict | list[dict[str, object]]
litellm/proxy/pass_through_endpoints/success_handler.py:493
↓ 21 callersFunctionpatch_group
( candidate: Gateway, team: str, operations: Sequence[JsonValue], *, key: str | None = None )
tests/integration/management/test_scim_group_pathless_patch.py:27
↓ 21 callersMethodpopitem
(self)
litellm/router_rust/surface/indexes.py:173
↓ 21 callersFunctionposts
(wire: Wire)
tests/integration/compatibility/_a2a_peers.py:268
↓ 21 callersFunctionquery_raw_rows
( db: PrismaWrapper | RoutingPrismaWrapper, query: str, *args: object )
litellm/proxy/utils.py:412
↓ 21 callersMethodredact_standard_logging_payload_from_model_call_details
Redacts or excludes fields from StandardLoggingPayload before callbacks receive it. This method handles two features: 1. tur
litellm/integrations/custom_logger.py:906
↓ 21 callersMethodrespond
(self, request: httpx.Request)
tests/unit/llms/custom_httpx/test_llm_http_handler.py:398
↓ 21 callersFunctionsafeguards_rig
( directory: Path, *, environment: Callable[[str], Mapping[str, str]] = no_environment, remove
tests/integration/_support/safeguards_rig.py:286
↓ 21 callersMethodsetTimeout
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 21 callersFunctionsetup_store
( agent: AgentResponse | None = stored_agent(), human: LiteLLM_VerifiedSubject | None = None, cach
tests/unit/proxy/agent_endpoints/test_identity_store.py:57
↓ 21 callersMethodsomeProp
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 21 callersMethodsubtract
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 21 callersFunctionsystemone_request_to_ir
(request: DecisionsRequestBody)
litellm/llms/base_llm/decisions/transformation.py:114
↓ 21 callersFunctiont
()
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 21 callersMethodtargets
(self, marker: str)
tests/integration/routing/test_non_chat_model_endpoint_gate.py:119
↓ 21 callersFunctionttl
(key: &str)
litellm-rust/crates/redis-client/src/commands.rs:287
↓ 21 callersFunctionupload
( candidate: Gateway, key: str, content: bytes, *, path: str = "/v1/files", purpose: s
tests/integration/management/_batch_file_caps.py:206
↓ 21 callersFunctionupstreamed
(wire: Wire)
tests/integration/authorization/_responses_compact.py:194
↓ 21 callersFunctionut
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 21 callersFunctionverify_password
Verify a password against a stored hash. Supports scrypt and SHA256, or only PBKDF2 in FIPS mode.
litellm/proxy/utils.py:8507
↓ 21 callersFunctionwebsocket_passthrough_request
WebSocket passthrough request handler. Args: websocket: The incoming WebSocket connection target: The target WebSocket URL
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:3025
↓ 21 callersFunctionwindowed
A deployment declaring ``max_input_tokens`` under a model name no other test uses: a deployment's model_info is written into the process-wide cost
tests/unit/test_router/core/construction_precall_helpers.py:58
↓ 20 callersMethod__init__
( self, content=None, role=None, function_call=None, tool_calls=None,
litellm/types/utils.py:1677
↓ 20 callersFunction_admin_auth
()
tests/unit/proxy/management_endpoints/test_coordination_redis_endpoints.py:39
↓ 20 callersFunction_assert_logged
(identity: str, model: str, status: str)
tests/integration/providers/test_bedrock_mantle_output_limit_wire.py:307
↓ 20 callersFunction_assert_success_payload
( capture: _CallbackCapture, model: str, messages: list[dict[str, str]] | None, request_marker
tests/unit/integrations/test_custom_callback_input.py:272
↓ 20 callersFunction_await_spend_row
(interaction_id: str, seconds: float = 30)
tests/integration/spend/test_background_interaction_settlement.py:331
↓ 20 callersFunction_batch
(output_file_id)
tests/unit/batches/test_batch_utils.py:902
↓ 20 callersFunction_bedrock_guardrail_for_chunk_tests
()
tests/unit/proxy/guardrails/guardrail_hooks/test_bedrock_guardrails.py:3686
↓ 20 callersFunction_before
(rig: _Rig)
tests/integration/routing/test_prompt_cache_pin_ttl.py:222
↓ 20 callersFunction_body_id
(response: httpx.Response)
tests/integration/observability/test_signoz_delivery.py:152
↓ 20 callersFunction_build_router
(routing_strategy="simple-shuffle", routing_groups=None)
tests/unit/router_strategy/test_router_routing_groups.py:60
↓ 20 callersMethod_build_router
Build semantic router with tools (MCPTool objects or OpenAI function dicts).
litellm/proxy/mcp_server/semantic_tool_filter.py:141
↓ 20 callersFunction_bulk_update
( prisma: _FakePrisma | _ReplicatedPrisma, members: Sequence[Mapping[str, object]], team_id: str =
tests/unit/proxy/management_endpoints/management_v1/test_teams.py:264
↓ 20 callersFunction_chat_body
( model: str, prompt: str, guardrails: tuple[str, ...], *, stream: bool = False, no_ca
tests/integration/observability/test_azure_content_safety_dispatch.py:92
↓ 20 callersFunction_chat_messages
(marker: str)
tests/integration/providers/test_bedrock_mantle_claude_chat_wire.py:69
↓ 20 callersFunction_chat_request
(config: AnthropicConfig, model: str, messages: list[dict])
tests/unit/llms/anthropic/chat/test_anthropic_chat_transformation.py:7377
↓ 20 callersFunction_chatgpt_responses
(respx_mock: respx.MockRouter)
tests/unit/proxy/pass_through_endpoints/test_codex_passthrough_endpoints.py:419
↓ 20 callersFunction_completed
()
tests/integration/spend/test_background_interaction_settlement.py:249
↓ 20 callersFunction_configuration
( tmp_path: Path, identity: str, policy_url: str, scope: str | None, *, include_scope:
tests/integration/observability/_logging_only_scope_support.py:631
↓ 20 callersFunction_configure_anthropic_sdk_judge
(monkeypatch: pytest.MonkeyPatch)
tests/unit/proxy/management_endpoints/test_auto_router_endpoints.py:1720
↓ 20 callersFunction_converse_deployment
(scenario: Scenario, wire: Wire, **extra: JsonValue)
tests/integration/providers/test_bedrock_converse_stream_event_frames_wire.py:191
← previousnext →2,601–2,700 of 202,479, ranked by callers