MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 63 callersFunctiondecode_video_id_with_provider
Decode provider and model_id from encoded video_id.
litellm/types/videos/utils.py:125
↓ 63 callersMethoderrors
(self)
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:252
↓ 63 callersMethodlanded
( self, model: str, call_id: str, marker: str | None, *, status: str = "success", seconds: float = 70
tests/integration/_support/prompt_cache_breakpoint.py:178
↓ 63 callersMethodload_config
Load config values into proxy global state
litellm/proxy/proxy_server.py:6798
↓ 63 callersFunctionmake
( fail: Exception | None = None, namespace: str | None = None, failure_threshold: int = 5 )
tests/unit/caching/test_redis_batch.py:226
↓ 63 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/bedrock/chat/converse_transformation.py:1101
↓ 63 callersMethodmax
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 63 callersMethodnullish
()
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 63 callersFunctiono
({proxySettings:e})
litellm/proxy/_experimental/out/_next/static/chunks/30kytutlzx6eq.js:1
↓ 63 callersMethodsend
(self, event: RealtimeClientEvent)
tests/e2e/llm_translation/realtime/realtime_client.py:396
↓ 63 callersMethodset
(self, key: str, value: object, ttl_seconds: float | None = None)
tests/unit/redis/stores/auth_cache_double.py:72
↓ 62 callersFunction_make_guardrail
(api_key: str = "hs-cato-key", **extra)
tests/unit/proxy/guardrails/guardrail_hooks/test_cato_networks.py:351
↓ 62 callersFunction_make_guardrail
( handler: FakeHandler, *, unreachable_fallback: str = "fail_closed", )
tests/unit/proxy/guardrails/guardrail_hooks/test_agent_365.py:121
↓ 62 callersFunction_patch_credential
(name: str, body: dict, auth=_as_admin)
tests/unit/proxy/credential_endpoints/test_endpoints.py:67
↓ 62 callersFunction_prisma_for
(model_rows, daily_table)
tests/unit/proxy/spend_tracking/test_ptu_flat_cost_rollup.py:823
↓ 62 callersFunction_record
(custom_id, content="hello", url="/v1/chat/completions")
tests/unit/proxy/openai_files_endpoint/test_batch_guardrails.py:24
↓ 62 callersFunctionchain
(py: Python<'_>, scripts: &Py<PyDict>, asynchronous: bool)
litellm-rust/crates/host-python/tests/hook_chain.rs:222
↓ 62 callersFunctioncreate_scratch_team
( db: ManagementDatabase, team_id: str, *, organization_id: str | None = None, admin_user_
tests/integration/_support/actors.py:284
↓ 62 callersMethoddeployments
(self, model_name, *, source)
tests/unit/router_strategy/test_router_tag_routing.py:1216
↓ 62 callersMethodget_cache
(self, key, **kwargs)
tests/unit/caching/test_caching.py:552
↓ 62 callersMethodnames
(self)
litellm/integrations/anthropic_cache_control_hook.py:395
↓ 62 callersMethodset
(self, key: str, value: object, ttl: float | None = None)
litellm/caching/redis_batch.py:335
↓ 61 callersFunctionP
(e,s)
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 61 callersFunctionadd_guardrail_to_applied_guardrails_header
(request_data: dict, guardrail_name: str | None)
litellm/proxy/common_utils/callback_utils.py:596
↓ 61 callersFunctiondb_span
(call_type: str, table: str | None, operation: str | None = None)
litellm/proxy/db/db_span.py:72
↓ 61 callersMethoddetail
(&self)
litellm-rust/crates/gateway-mcp/src/error.rs:108
↓ 61 callersMethodglob
(self, pattern: str, path: str | None = None)
litellm/llms/deepagents/harness/sandbox_backend.py:337
↓ 61 callersFunctionh
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 61 callersFunctiononClose
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 61 callersFunctionprint_verbose
(print_statement: object, *args: object)
litellm/_logging.py:1226
↓ 61 callersFunctionrouter
(config: RouterConfig, dynamic: serde_json::Value, host: Arc<ScriptedHost>)
litellm-rust/crates/router-core/tests/call_loop.rs:157
↓ 61 callersFunctionrun_claude_models_parallel
Invoke `run_claude` for every `models[i]` concurrently and collect outcomes. Each `claude` CLI invocation is a long-lived subprocess that spends
tests/e2e/claude_code/cli_driver.py:351
↓ 61 callersMethodstartswith
(self, prefix: str, /)
litellm/integrations/websearch_interception/tools.py:21
↓ 61 callersMethodtransform_anthropic_messages_request
( self, model, messages, anthropic_messages_optional_request_params, litellm_params, headers
tests/unit/llms/anthropic/test_anthropic_common_utils.py:3421
↓ 61 callersMethodupdate_from_kwargs
Convenience wrapper around update_environment_variables that automatically extracts metadata/litellm_metadata from kwargs, so
litellm/litellm_core_utils/litellm_logging.py:1287
↓ 61 callersFunctiony
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 60 callersFunction_common_key_generation_helper
( data: GenerateKeyRequest, user_api_key_dict: UserAPIKeyAuth, litellm_changed_by: str | None,
litellm/proxy/management_endpoints/key_management_endpoints.py:1444
↓ 60 callersFunction_make_streaming
(**kwargs)
tests/unit/responses/test_responses_websocket_all_providers.py:3204
↓ 60 callersFunction_repository_holding
The credentials repository seam, answering ``find_by_name`` with ``stored`` and recording the writes the handler attempts. Patched at both import
tests/unit/proxy/credential_endpoints/test_endpoints.py:119
↓ 60 callersFunctionconfig_only_mcp_manager_factory
()
tests/unit/proxy/mcp_server/conftest.py:72
↓ 60 callersFunctionconnect
(deployment: &RedisDeployment)
litellm-rust/crates/redis-store/tests/support/mod.rs:34
↓ 60 callersMethoddict
(self)
litellm/proxy/auth/auth_checks.py:366
↓ 60 callersMethoddispatchEvent
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 60 callersMethodformat
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 60 callersMethodget_complete_url
(self, api_base, api_key, model, optional_params, litellm_params, stream=None)
tests/unit/llms/anthropic/test_anthropic_common_utils.py:3415
↓ 60 callersFunctionget_request_stash
()
litellm/proxy/hooks/parallel_request_limiter_v3.py:593
↓ 60 callersFunctionget_user_object
- Check if user id in proxy User Table - if valid, return LiteLLM_UserTable object with defined limits - if not, then raise an error
litellm/proxy/auth/auth_checks.py:3011
↓ 60 callersMethodjson
(self)
litellm/llms/openai/responses/transformation.py:330
↓ 60 callersMethodmodel_dump_json
(self, *, exclude_none: bool = False)
litellm/proxy/management_endpoints/model_management_endpoints.py:252
↓ 60 callersMethodset
(self, key: str, value: bytes, ex: int)
tests/_ws_vcr.py:74
↓ 60 callersFunctionu
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 60 callersFunctionu
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 60 callersFunctionv
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 59 callersFunction_deployment
(api_base: str = _SERVICE_URL, kubernetes_pod_discovery: bool | None = True)
tests/unit/router_utils/test_kubernetes_pod_discovery.py:56
↓ 59 callersFunction_jsonl
(*records)
tests/unit/proxy/openai_files_endpoint/test_batch_guardrails.py:36
↓ 59 callersFunction_local
(handler: _PROXY_MaxParallelRequestsHandler, entry: RateLimitEntry)
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:110
↓ 59 callersFunction_marker
(shape: str)
tests/integration/providers/test_vertex_anthropic_structured_output_wire.py:633
↓ 59 callersFunction_send
( rig: _Rig, family: _Family, marker: str, stream: bool, *, model: str | None = None,
tests/integration/providers/test_malformed_tools_wire.py:474
↓ 59 callersMethod_update_general_settings
(self, db_general_settings: Mapping[str, SettingsJsonValue] | str | None)
litellm/proxy/proxy_server.py:8505
↓ 59 callersMethodapply_guardrail
( self, inputs: dict, request_data: dict, input_type: str, **kwargs )
tests/unit/llms/cohere/rerank/test_rerank_guardrail_handler.py:417
↓ 59 callersMethodaspeech
(self, *args: object, **kwargs: object)
litellm/router_rust/core.py:2599
↓ 59 callersFunctionc
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 59 callersMethodregistry
(&self)
litellm-rust/crates/router-core/src/lib.rs:410
↓ 59 callersMethodrun
( &self, agent: &impl Drive, prompt: &Prompt, limit: Duration, )
litellm-rust/crates/testkit/src/session.rs:45
↓ 59 callersMethodsend
An answer the yield no longer awaits is discarded.
litellm-rust/crates/coroutine/src/reply.rs:21
↓ 59 callersFunctionset
redis-py's `set(ex=...)` takes whole seconds, as `int(ttl)` or a `timedelta`'s `int(total_seconds())`
litellm-rust/crates/redis-client/src/commands.rs:221
↓ 59 callersMethodshutdown
(self)
tests/e2e/provider_edge.py:1175
↓ 59 callersFunctiont9
(e,t,s,r)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:2
↓ 59 callersMethodtransform_image_generation_response
( self, model, raw_response, model_response, logging_obj, requ
tests/unit/llms/custom_httpx/test_llm_http_handler.py:5918
↓ 58 callersFunction_make_signer
(**kwargs: Any)
tests/unit/proxy/guardrails/test_mcp_jwt_signer.py:55
↓ 58 callersFunction_prisma
(jobs=(), attempt_counts=(), attempt_costs=())
tests/unit/integrations/test_shadow_eval_logger.py:62
↓ 58 callersMethodadecisions
( self, **kwargs: object, # kwargs-ok: forwarded to the router endpoint as given )
litellm/router_api.py:1624
↓ 58 callersMethodbuild_mcp_server_from_table
( self, mcp_server: LiteLLM_MCPServerTable, *, credentials_are_encrypted: bool
litellm/proxy/mcp_server/mcp_server_manager.py:3214
↓ 58 callersMethodconsume
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0g3hfgh2z8the.js:1
↓ 58 callersFunctiondrops_unsupported_params
(drop_params: object)
litellm/litellm_core_utils/core_helpers.py:231
↓ 58 callersMethodfind
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 58 callersMethodgetAPIList
(e,t,r)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 58 callersMethodinsert
(self, rows: Sequence[Row])
tests/unit/integrations/zerobus/test_zerobus_logger.py:171
↓ 58 callersMethodregistry
(self)
litellm/router_core.py:30
↓ 58 callersFunctions
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 58 callersMethodtransform_search_response
( self, raw_response: httpx.Response, logging_obj: LiteLLMLoggingObj, **kwargs
litellm/llms/xai/search/transformation.py:98
↓ 58 callersFunctionu
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0r8bcbns1_gw5.js:1
↓ 58 callersMethoduse
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 58 callersMethodworker_pids
(self)
tests/integration/_support/process.py:263
↓ 58 callersMethodwrite
(self, path: str, data: bytes)
litellm/harness/sandbox/base.py:52
↓ 57 callersFunction_counter
(key: str, value: str, kind: CounterKind = "tokens")
tests/unit/proxy/hooks/test_parallel_request_limiter_v3.py:106
↓ 57 callersFunction_job
(**overrides)
tests/unit/integrations/test_shadow_eval_logger.py:49
↓ 57 callersFunction_ollama_server
(respond: Callable[[Request], Reply])
tests/integration/providers/test_ollama_prompt_tools_wire.py:124
↓ 57 callersFunction_ws_base
(http_url: str)
tests/integration/providers/test_realtime_transcription_guardrail_session_update.py:267
↓ 57 callersMethodall
The live model list, in configured order (was the ``model_list`` attribute).
litellm/router_api.py:600
↓ 57 callersFunctionanswering_model_discovery
(respond: Callable[[Request], Reply])
tests/integration/_support/openai_wire.py:15
↓ 57 callersMethodasync_log_success_event
(self, kwargs, response_obj, start_time, end_time)
tests/unit/integrations/otel/test_otel_v2_logger.py:2568
↓ 57 callersFunctionauto_mode_body
(model: str, request_nonce: str, **extra: JsonValue)
tests/integration/_support/safeguards_rig.py:341
↓ 57 callersMethodcalculate_usage
( self, usage_object: Mapping[str, Any], reasoning_content: str | None, comple
litellm/llms/anthropic/chat/transformation.py:2988
↓ 57 callersMethodclose
(self)
tests/unit/harness/core_fakes.py:102
↓ 57 callersFunctionget_model_from_request
Resolve the model(s) a request targets, for model-access and budget checks. Returns ``None`` when the request was dispatched to a user-defined pa
litellm/proxy/auth/auth_utils.py:2427
↓ 57 callersMethodmin
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 57 callersFunctionmock_token_exchange
(access_token: str = "exchanged-bearer-token")
tests/unit/llms/openai/test_openai_workload_identity.py:97
↓ 57 callersFunctionnavigateToPage
(page: PlaywrightPage, pageEnum: Page)
tests/e2e/ui/helpers/navigation.ts:32
↓ 57 callersMethodpost_call_success_hook
Allow user to modify outgoing data Covers: 1. /chat/completions 2. /embeddings 3. /image/generation
litellm/proxy/utils.py:4435
← previousnext →701–800 of 202,479, ranked by callers