MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 6 callersFunctionduration_in_seconds_from
How long a period of `duration` lasts when it begins at `start`. `duration_in_seconds` measures `Nmo` from now, so a monthly window that opened i
litellm/litellm_core_utils/duration_parser.py:85
↓ 6 callersFunctione
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersFunctione
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:1
↓ 6 callersFunctione
litellm/proxy/_experimental/out/_next/static/chunks/1kqcfeiw5h1ti.js:1
↓ 6 callersFunctione
litellm/proxy/_experimental/out/_next/static/chunks/0lwp6btjdlmlz.js:1
↓ 6 callersFunctione$
(e,t,r,n=!0)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 6 callersFunctione1
()
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 6 callersFunctione5
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 6 callersFunctione8
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 6 callersFunctioneN
()
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:74
↓ 6 callersFunctioneV
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 6 callersFunctioneV
(e,t,r,n=eW(e))
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 6 callersFunctioneX
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 6 callersFunctioneb
(e,t,r,i)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 6 callersFunctionec
litellm/proxy/_experimental/out/_next/static/chunks/2r8xiri7nad3g.js:1
↓ 6 callersFunctionedge_request
The identity replay matches on: the edge path (mount included), the query as params, and the body as parsed JSON, as parsed multipart fields and f
tests/e2e/provider_edge.py:379
↓ 6 callersMethodeffective
(self, stored: TelemetryConsent | None)
litellm/proxy/telemetry/settings.py:78
↓ 6 callersFunctioneffective_py_args
What `original_function(*args, **kwargs)` sees: the signature base with the keyword dict laid over it, so a rewritten keyword wins and a deleted keywo
litellm-rust/crates/host-python/src/argument.rs:25
↓ 6 callersFunctioneg
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 6 callersFunctioneh
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 6 callersFunctionej
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 6 callersFunctioneligible_models
( config: ComplexityRouterConfig, decision: StandardLoggingRoutingDecision )
litellm/proxy/common_utils/cache_aware_routing.py:78
↓ 6 callersFunctionem
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 6 callersFunctionembed_body
(model: str, elements: JsonValue)
tests/integration/caching/test_embedding_file_block_cache.py:89
↓ 6 callersMethodembedding
( self, model: str, input: list, timeout: float, logging_obj,
litellm/llms/openai_like/embedding/handler.py:139
↓ 6 callersFunctionemitLocalStorageChange
(key: string)
ui/litellm-dashboard/src/utils/localStorageUtils.ts:3
↓ 6 callersFunctionemptyMap
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersFunctionemptyToUndefined
(value: string)
ui/litellm-dashboard/src/components/logs/request/RequestLogsFilters.tsx:65
↓ 6 callersFunctionencode_gcs_object_name_for_url
(object_name: str)
litellm/litellm_core_utils/cloud_storage_security.py:127
↓ 6 callersFunctionencode_state_with_base_url
Encode the base_url, original state, and PKCE parameters using encryption. Args: base_url: The base URL to encode original_s
litellm/proxy/mcp_server/discoverable_endpoints.py:219
↓ 6 callersFunctionencode_thinking_blocks
(thinking_blocks: Sequence[Mapping[str, object]])
litellm/responses/litellm_completion_transformation/reasoning_items.py:27
↓ 6 callersMethodencrypt_env_variables
Encrypts a dictionary of environment variables and returns them.
litellm/proxy/proxy_server.py:8194
↓ 6 callersFunctionend_user_counter
(end_user_id: str)
litellm/redis/stores/spend_counters/types.py:40
↓ 6 callersFunctionendpoint
(deployment: &RedisDeployment)
litellm-rust/crates/redis-client/tests/support/mod.rs:17
↓ 6 callersFunctionendpoint_func
( timeout: int = 600, custom_llm_provider: Literal["openai", "azure", "azure_text"] = "openai"
litellm/containers/endpoint_factory.py:60
↓ 6 callersFunctionenforce_all_proxy_mcp_servers_grant_is_admin_only
Only a proxy admin may newly grant the all-proxy MCP sentinel. Scoping a team to every MCP server on the proxy is a proxy-wide authorization
litellm/proxy/management_helpers/object_permission_utils.py:520
↓ 6 callersFunctionenforce_fips_mode
(general_settings: Mapping[str, object])
litellm/proxy/common_utils/fips.py:88
↓ 6 callersFunctionenqueue
(body: object, status: int = 200)
tests/base_sdk_tests/check_sdk_http.py:67
↓ 6 callersMethodensureMarks
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 6 callersMethodensure_initialized_and_enqueue
(self, async_coroutine: Coroutine[object, object, None])
tests/unit/litellm_core_utils/test_realtime_streaming.py:4822
↓ 6 callersFunctionensure_schema
(client: &Client, config: &Config)
litellm-rust/crates/spend-clickhouse/src/schema.rs:15
↓ 6 callersMethodentries
(self)
tests/integration/caching/test_response_cache_chaos.py:120
↓ 6 callersFunctionentry
(callback_type: str, capture: str)
tests/unit/proxy/common_utils/test_callback_config_validation.py:444
↓ 6 callersFunctionenvironment
(pairs: &[(&str, &str)])
litellm-rust/crates/secrets/tests/oidc.rs:10
↓ 6 callersFunctioner
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 6 callersFunctionerror_body_call_id
(general_settings: Mapping[str, object], call_id: str | None)
litellm/proxy/common_utils/error_body_call_id.py:11
↓ 6 callersFunctionerror_response_without_credentials
(status_code: int, upstream: object, fallback_url: str)
litellm/exceptions.py:151
↓ 6 callersFunctionestimate_audio_tokens
Estimate audio tokens from container duration within a bounded decoding budget.
litellm/litellm_core_utils/audio_utils/utils.py:365
↓ 6 callersFunctioneval
(py: Python<'py>, source: &std::ffi::CStr)
litellm-rust/crates/python-bridge/src/marshal.rs:215
↓ 6 callersFunctioneval
(py: Python<'py>, source: &std::ffi::CStr)
litellm-rust/crates/python-bridge/src/routes/ocr/project.rs:364
↓ 6 callersFunctionevents_of_type
( events: tuple[ReceivedEvent, ...], event_type: str )
tests/e2e/llm_translation/realtime/realtime_client.py:326
↓ 6 callersMethodevict_cache
`evict_cache`: drops expired entries, then the earliest-expiring ones until a new key fits.
litellm-rust/crates/cache-memory/src/cache.rs:134
↓ 6 callersFunctionex
(e,a)
litellm/proxy/_experimental/out/_next/static/chunks/2r8xiri7nad3g.js:1
↓ 6 callersMethodexit
(self, server_id: str)
tests/unit/proxy/mcp_server/test_mcp_max_concurrent_requests.py:94
↓ 6 callersMethodexpected
(self, caller: Caller)
tests/integration/authorization/test_team_admin_gate.py:132
↓ 6 callersMethodexpire
(self, name: str, time: timedelta)
tests/unit/caching/test_redis_batch.py:67
↓ 6 callersMethodexplicit_vertex_ai_location
The location explicitly configured in the given params, without any module-level or environment fallback. None when not configured.
litellm/llms/vertex_ai/vertex_llm_base.py:1262
↓ 6 callersMethodexport_window
( self, *, window: FocusTimeWindow, limit: int | None, )
litellm/integrations/focus/export_engine.py:128
↓ 6 callersFunctionextractPromptCacheTokens
( usage: ProviderCacheUsage | null | undefined, includeZero = false, )
ui/litellm-dashboard/src/utils/promptCacheUsage.ts:27
↓ 6 callersMethodextract_cacheable_prefix
Extract the cacheable prefix from messages. The cacheable prefix is everything UP TO AND INCLUDING the LAST content block (a
litellm/router_utils/prompt_caching_cache.py:233
↓ 6 callersMethodextract_target_server_names_from_path
Extract the target MCP server name(s) from the standard MCP transport URL patterns: ``/mcp/{server_name_or_csv}[/...]`` and `
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:1014
↓ 6 callersMethodextract_text_from_message
Extract text content from A2A message parts. Args: message: A2A message dict or object with 'parts' containing text part
litellm/a2a_protocol/utils.py:29
↓ 6 callersMethodextract_tool_calls_from_chat_response
Extract the tool calls of the first choice that made any, since the follow-up turn continues it alone.
litellm/responses/mcp/litellm_proxy_mcp_handler.py:633
↓ 6 callersFunctionfactory
(addr_info: _AddrInfo)
litellm/llms/custom_httpx/http_handler.py:160
↓ 6 callersFunctionfactory
( headers: dict[str, str] | None = None, timeout: httpx2.Timeout | None = None, auth:
tests/unit/mcp_client/test_mcp_client.py:2199
↓ 6 callersFunctionfactory
()
tests/unit/proxy/middleware/test_billable_request_metrics_middleware.py:370
↓ 6 callersFunctionfacts
(entries: &[(&str, DeploymentFacts)])
litellm-rust/crates/router-core/src/precall.rs:184
↓ 6 callersMethodfail
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 6 callersMethodfailure_handler
(self, *_args, **_kwargs)
tests/unit/proxy/mcp_server/test_mcp_block_recording.py:50
↓ 6 callersFunctionfailure_kwargs
( model_info: object, exception: Exception, **extra: object )
tests/unit/test_router/core/test_retries_health_characterization_cooldowns.py:50
↓ 6 callersFunctionfake_codex_version
( monkeypatch: pytest.MonkeyPatch, tmp_path: Path )
tests/unit/proxy/client/cli/conftest.py:24
↓ 6 callersMethodfal_ai_passthrough_handler
( self, response_body: Mapping[str, object], request_body: Mapping[str, object],
litellm/proxy/pass_through_endpoints/llm_provider_handlers/fal_ai_passthrough_logging_handler.py:30
↓ 6 callersFunctionfallback_attempt_key
Identity of one fallback attempt, so the same attempt is never made twice per request. A bare model group name and a `{"model": name}` entry
litellm/router_utils/fallback_event_handlers.py:192
↓ 6 callersMethodfeed
(self, chunk: bytes)
tests/integration/_support/database_relay.py:156
↓ 6 callersFunctionfetch
(client: httpx.AsyncClient, budget: BufferBudget, body: bytes = b"data")
tests/unit/proxy/lens/test_buffering.py:53
↓ 6 callersMethodfetchNextPage
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 6 callersMethodfetchQuery
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 6 callersFunctionfetchVectorStores
()
ui/litellm-dashboard/src/app/(dashboard)/vector-stores/_components/index.tsx:47
↓ 6 callersFunctionfetch_mcp_toolsets
Return toolsets the calling key is allowed to access.
litellm/proxy/management_endpoints/mcp_management_endpoints.py:3592
↓ 6 callersMethodfield
(&mut self, field: &Field, value: Value)
litellm-rust/crates/tracing/src/lib.rs:118
↓ 6 callersMethodfile
(self)
litellm/proxy/roi_calculator/gitlab.py:84
↓ 6 callersFunctionfilter_ptu_shared_deployments
Keep only the deployments ``request_team_id`` holds a share on when it holds one, else only the ones split into no shares, so a team's ceiling and
litellm/litellm_core_utils/ptu_shares.py:57
↓ 6 callersFunctionfilter_tools_by_key_team_permissions
Filter tools based on key/team mcp_tool_permissions. Note: Tool names in the DB are stored without server prefixes, but tool names from
litellm/proxy/mcp_server/operations.py:1668
↓ 6 callersFunctionfinal_report
(run: HarnessRun, exit_code: int, strategies: Sequence[Strategy])
tests/rust-python-harness/shared/reporting/ui.py:132
↓ 6 callersMethodfinalize
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 6 callersMethodfind_all
Find all models.
litellm/repositories/model_repository.py:96
↓ 6 callersMethodfind_guardrail_callback
Look up an initialized guardrail callback by name from litellm.callbacks.
litellm/proxy/policy_engine/pipeline_executor.py:718
↓ 6 callersMethodfind_many
(self, *, where: Mapping[str, object] | None = None)
litellm/proxy/management_endpoints/model_access_group_management_endpoints.py:119
↓ 6 callersMethodfind_many
( self, where: Mapping[str, object] | None = None, skip: int | None = None, ta
litellm/proxy/management_endpoints/scim/scim_v2.py:128
↓ 6 callersMethodfind_unique
(self, where: Mapping[str, str])
litellm/proxy/management_endpoints/config_override_endpoints.py:57
↓ 6 callersMethodfind_unique
(self, where: Mapping[str, object])
litellm/proxy/management_endpoints/access_group_endpoints.py:119
↓ 6 callersFunctionfirst_validation_error
(e: ValidationError, prefix: tuple[str | int, ...] = ())
litellm/litellm_core_utils/tool_fields.py:104
↓ 6 callersFunctionfit_indexed_messages
``attrs`` with indexed message attributes shed, least valuable first, until at most ``budget`` keys remain. ``None`` means the span has no attrib
litellm/integrations/otel/mappers/openinference.py:156
↓ 6 callersFunctionfixture_clock
A clock fixed just after the fixture timestamps, so every fixture cooldown is still active.
litellm-rust/crates/redis-store/tests/router_cooldowns.rs:29
↓ 6 callersFunctionfixture_mode_collection_error
Session-abort reason for a fixture-mode setup that can never work, or None. Called at collection time (conftest pytest_sessionstart) so a stale or
tests/e2e/fixture_mode.py:109
↓ 6 callersFunctionfixture_path
(directory: Path, case_input: FixtureInput)
tests/rust-python-harness/shared/parity/fixtures/store.py:48
↓ 6 callersFunctionflatten_form_field_values
Flatten JSON-shaped bodies into ``(name, value)`` form fields for a ``dict``-backed multipart body, applying ``sources`` in order so a later
litellm/litellm_core_utils/llm_request_utils.py:83
↓ 6 callersMethodflush
(self)
litellm/telemetry/sink.py:17
↓ 6 callersMethodflush
Return and clear all pending rows.
litellm/proxy/db/db_transaction_queue/tool_discovery_queue.py:54
↓ 6 callersMethodflush
(&self)
litellm-rust/crates/redis-store/src/memory.rs:49
← previousnext →12,901–13,000 of 202,479, ranked by callers