MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersFunctionopenAutoRouterAdvanced
(section: string)
ui/litellm-dashboard/tests/autoRouterSetup.ts:14
↓ 8 callersFunctionopen_refresh_envelope
Validate a refresh ``candidate`` and recover the identity and inner refresh grant. Total over hostile input exactly like :func:`open_envelope`: e
litellm/proxy/mcp_server/outbound_credentials/envelope.py:391
↓ 8 callersFunctionopenai_client
(candidate: Gateway, key: str)
tests/integration/authorization/_hidden_alias_budget.py:299
↓ 8 callersFunctionopenai_route
(scenario: str)
tests/integration/_support/sagemaker_embedding.py:39
↓ 8 callersFunctionopenai_static_api_key
(api_key: str | None)
litellm/llms/openai/workload_identity.py:109
↓ 8 callersFunctionopened_at
(redis: Redis, window: Window)
tests/integration/management/test_budget_reset_windows.py:183
↓ 8 callersMethodorg_member
(self, organization_id: str, role: str)
tests/integration/_support/client.py:231
↓ 8 callersFunctionoss_connection
( provider: OssDecisionProvider, api_base: str | None = None, api_key: str | None = None )
litellm/llms/oss_decision.py:64
↓ 8 callersFunctionowned_config
( directory: Path, wire: Wire, groups: Sequence[str], settings: Mapping[str, JsonValue], *
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:197
↓ 8 callersFunctionowned_sinks
(directory: Path)
tests/integration/_support/otlp_sink.py:433
↓ 8 callersFunctionp
(e)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 8 callersFunctionp
litellm/proxy/_experimental/out/_next/static/chunks/3yrgf44a9g52e.js:1
↓ 8 callersFunctionparse
(obj: Mapping[str, object], state: PiStreamState)
tests/unit/llms/pi/harness/test_transformation.py:71
↓ 8 callersMethodparse
(source: &'a str)
litellm-rust/crates/llms/src/base_llm/ocr/document.rs:15
↓ 8 callersFunctionparseQuery
(language: QueryLanguage<F>, text: string)
ui/litellm-dashboard/src/components/shared/search/language.ts:98
↓ 8 callersFunctionparse_config_value
Parse a config_value from DB (may be JSON string or dict).
litellm/proxy/management_endpoints/config_override_endpoints.py:238
↓ 8 callersFunctionparse_fixture
(name: str)
tests/unit/llms/claude_code/harness/test_transformation.py:75
↓ 8 callersMethodparse_rss_to_posts
Parse RSS XML into blog posts. Extracts title, description, date (YYYY-MM-DD), url and the <category> tags from each <item>.
litellm/litellm_core_utils/get_blog_posts.py:101
↓ 8 callersFunctionpassthrough
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:55
↓ 8 callersFunctionpatch_proxy_general_settings
(settings: dict)
tests/unit/proxy/management_endpoints/test_mcp_management_endpoints.py:155
↓ 8 callersMethodpayloads
(self)
tests/integration/observability/_azure_storage_support.py:173
↓ 8 callersFunctionpe
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 8 callersFunctionpem_of
(key: ec.EllipticCurvePrivateKey)
tests/unit/llms/base_llm/auth/test_jwt_signing.py:33
↓ 8 callersMethodpending
(self, interaction_id)
tests/unit/interactions/test_background_cost_polling.py:1168
↓ 8 callersFunctionperform_health_check
Perform a health check on the system. When model_id is provided, only the deployment with that id is checked (so models that share the s
litellm/proxy/health_check.py:952
↓ 8 callersMethodperform_shared_health_check
Perform health check with shared state coordination. This method: 1. First checks if there are recent cached results
litellm/proxy/health_check_utils/shared_health_check_manager.py:206
↓ 8 callersFunctionpicked_id
The ``model_info.id`` of a picked deployment dict.
tests/unit/test_router/core/test_deprecated_members.py:35
↓ 8 callersFunctionpin_at
(redis: Redis, key: str)
tests/integration/routing/_prompt_cache_pin_support.py:107
↓ 8 callersMethodping
(self)
tests/unit/test_redis.py:786
↓ 8 callersFunctionpoll_until_blocked
Retry a call that a guardrail should reject until it is, returning the last result. Registering a guardrail is a control-plane write; the data-pl
tests/e2e/guardrails/guardrails_client.py:616
↓ 8 callersMethodpop_reservation
( self, batch_id: str, litellm_parent_otel_span: "Span | None" = None, )
litellm/proxy/hooks/batch_enqueued_tokens.py:406
↓ 8 callersFunctionprepare_object_permission_upsert
Read-and-merge half of an object permission upsert; performs no writes. Merges the sent grants over the existing row (looked up by ``exi
litellm/proxy/management_helpers/object_permission_utils.py:83
↓ 8 callersFunctionpreservedAdminCredentials
( credentials: Record<string, unknown> | null | undefined, )
ui/litellm-dashboard/src/components/mcp_tools/types.tsx:194
↓ 8 callersFunctionprocess_anthropic_headers
(headers: httpx.Headers | dict)
litellm/llms/anthropic/common_utils.py:2777
↓ 8 callersFunctionprocess_azure_headers
(headers: httpx.Headers | dict)
litellm/llms/azure/common_utils.py:246
↓ 8 callersMethodprocess_input_messages
Process input prompt by applying guardrails to text content. Args: data: Request data dictionary containing 'prompt' par
litellm/llms/openai/completion/guardrail_translation/handler.py:50
↓ 8 callersMethodprocess_openai_embedding_input
Process the input for multimodal embedding requests. Args: _input (Union[list, str]): The input data to process.
litellm/llms/vertex_ai/multimodal_embeddings/transformation.py:130
↓ 8 callersMethodprocess_output_response
Process OCR output by applying guardrails to extracted page text. Extracts markdown text from each OCR page, applies guardrails,
litellm/llms/mistral/ocr/guardrail_translation/handler.py:88
↓ 8 callersMethodprocess_output_response
Process output transcription by applying guardrails to transcribed text. Args: response: Transcription response object c
litellm/llms/openai/transcriptions/guardrail_translation/handler.py:57
↓ 8 callersFunctionprocess_response
( input: GeminiEmbeddingInput, model_response: EmbeddingResponse, model: str, _predictions: Ve
litellm/llms/vertex_ai/gemini_embeddings/batch_embed_content_transformation.py:613
↓ 8 callersFunctionprompt
(text: &str)
litellm-rust/crates/testkit/tests/session.rs:56
↓ 8 callersFunctionprompt_cache_breakpoint_for_wire
(marker: object, drop_params: bool)
litellm/litellm_core_utils/prompt_templates/prompt_cache_breakpoint_utils.py:71
↓ 8 callersFunctionprovider
(exchange: httpx.Request)
tests/unit/proxy/mcp_server/test_operations.py:146
↓ 8 callersFunctionprovider_reported_usage_cost
The request cost a provider states on its usage block, as a number or a breakdown with ``total_cost``. OpenCode Go reports the model's list price
litellm/litellm_core_utils/core_helpers.py:1154
↓ 8 callersMethodprovision
Register this provider's realtime deployment through /model/new and return (model_name, model_id). The name is marker-unique so it never colli
tests/e2e/llm_translation/realtime/realtime_client.py:472
↓ 8 callersMethodpublish
(self, event: ServerEvent)
litellm/proxy/mcp_server/subscriptions.py:128
↓ 8 callersMethodpublish
(self, key: str, lease: CaptureLease, payload: bytes)
tests/e2e/provider_cache.py:123
↓ 8 callersMethodput
(self, model_id: str, value: CooldownCacheValue, ttl: float)
litellm/redis/stores/router_cooldowns/__init__.py:57
↓ 8 callersFunctionpython_redact_string
(value: str)
litellm/litellm_core_utils/secret_redaction.py:91
↓ 8 callersFunctionq
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 8 callersFunctionquestion
(marker: str)
tests/integration/providers/_tool_search_support.py:76
↓ 8 callersFunctionqueue_entries
(cache: OwnedRedis, group: str)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:357
↓ 8 callersMethodqueue_size
(self)
litellm/router_strategy/adaptive_router/update_queue.py:205
↓ 8 callersMethodqueue_spend_zero
(self, where: Mapping[str, object])
litellm/repositories/unit_of_work.py:67
↓ 8 callersFunctionr
(e)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 8 callersFunctionraised
(exception: &'static str, detail: impl Into<String>)
litellm-rust/crates/router-core/src/model_info.rs:53
↓ 8 callersFunctionraw_multipart
A body assembled from literal part headers, so a test can send the shapes a well-formed helper cannot: a file part with no filename, a declared pe
tests/e2e_harness/test_provider_edge.py:724
↓ 8 callersFunctionraw_stream_post
POST over a raw socket and read the reply at the transfer layer: the response head, one entry per HTTP chunk (or the whole body for a content-leng
tests/e2e_harness/test_provider_edge.py:275
↓ 8 callersFunctionrd
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:74
↓ 8 callersFunctionread
(kwargs: Mapping[str, object])
litellm/proxy/db/log_db_metrics.py:34
↓ 8 callersMethodread
(self)
litellm/litellm_core_utils/cli_keyring.py:88
↓ 8 callersMethodread
(self)
litellm/proxy/client/cli/commands/statusline_script.py:93
↓ 8 callersMethodread
(value, authoritative) for a bound counter, None when the caller must read Redis itself.
litellm/proxy/spend_tracking/spend_counter_batch.py:79
↓ 8 callersMethodread
(self)
litellm/llms/vertex_ai/image_edit/vertex_imagen_transformation.py:44
↓ 8 callersMethodread
(self)
tests/unit/litellm_core_utils/test_token_counter.py:1025
↓ 8 callersMethodread
(self)
tests/unit/llms/bedrock/files/test_bedrock_files_handler.py:221
↓ 8 callersMethodread
(self, path)
tests/unit/llms/opencode/harness/test_transformation.py:138
↓ 8 callersMethodread
(&self, py: Python<'_>)
litellm-rust/crates/host-python/src/file_reader.rs:47
↓ 8 callersMethodreads
(self)
litellm-rust/crates/cache-response/src/caching.rs:112
↓ 8 callersFunctionready
(gateway: Gateway, model: str, seconds: float = 60)
tests/integration/providers/_coralbricks.py:345
↓ 8 callersMethodreceived
Every span name each set of headers received; an exporter that got nothing is absent.
tests/unit/integrations/otel/test_otel_v2_destinations.py:3295
↓ 8 callersFunctionrecord_fixtures
( targets: tuple[RecordingTarget[InputT], ...], root: Path, examples: int, concurrency: int,
tests/rust-python-harness/shared/parity/fixtures/pipeline.py:170
↓ 8 callersMethodrecord_request
(self, record: RequestRecord)
tests/unit/telemetry/test_consent.py:41
↓ 8 callersFunctionredact_mcp_resource_url
Reduce an MCP server URL to its origin (scheme + host + port) for logging. Everything else is dropped: userinfo (``user:pass@``), the query strin
litellm/proxy/mcp_server/oauth_utils.py:97
↓ 8 callersMethodredact_standard_logging_payload_from_model_call_details
( self, model_call_details: dict[str, object] )
tests/test_litellm_rust/messages/test_callbacks.py:151
↓ 8 callersMethodrefresh
Apply the current groups and destination; only called between windows so every report has a single set
litellm/proxy/telemetry/runtime.py:203
↓ 8 callersMethodregister
(self, pending)
tests/unit/interactions/test_background_cost_polling.py:1165
↓ 8 callersFunctionregister_aggregate_client
RFC 7591 dynamic registration against the gateway itself, statelessly. Only ``redirect_uris`` is authoritative; every client is registered as a p
litellm/proxy/mcp_server/gateway_dcr_flow.py:515
↓ 8 callersFunctionregister_plugins_from_config
Replace the plugin registry from general_settings. Replaces (not merges) so plugins removed from config are immediately unreachable without r
litellm/proxy/plugin_routes.py:194
↓ 8 callersMethodregistry
(self)
tests/unit/router_strategy/test_router_tag_routing.py:1220
↓ 8 callersMethodrelease
Drop one open-span count; shut a retired provider down once drained. ``None`` (the default route) is a no-op so callers can release a
litellm/integrations/otel/plumbing/routing.py:195
↓ 8 callersFunctionremove
(index: number)
ui/litellm-dashboard/src/components/add_model/ReminderMarkers.tsx:24
↓ 8 callersMethodremoveFromSet
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 8 callersMethodremove_callback_from_list_by_object
``LoggingCallbackManager.remove_callback_from_list_by_object``, on the host's lists.
tests/unit/test_router/core/construction_precall_helpers.py:20
↓ 8 callersMethodremove_endpoint_routes
Remove all routes for a specific endpoint ID from the registry and clean up corresponding entries from LiteLLMRoutes.openai_routes.
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:4022
↓ 8 callersMethodrender
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctionrender_transcript
(messages: Sequence[Mapping[str, object]])
litellm/llms/anthropic/messages/safeguards.py:341
↓ 8 callersFunctionreplay_server
()
tests/rust-python-harness/shared/parity/replay.py:123
↓ 8 callersFunctionreport
What the operator reads: the per-migration time the real upgrade will hold its locks, or the migration Postgres rejected with Postgres's own words
litellm-proxy-extras/litellm_proxy_extras/migration_dry_run.py:161
↓ 8 callersFunctionreport_to_json
Only the fields of the report's enabled groups, so a stored or sent report shows exactly what was collected
litellm/telemetry/report.py:225
↓ 8 callersMethodrepositories
( self, query: str = "", page: int = 1, )
litellm/proxy/roi_calculator/github.py:384
↓ 8 callersFunctionrequire_github_copilot_user_session
The attached session, or None for shared mode. Per-user params with no attached session only reach here via paths that skipped the attach step, so
litellm/llms/github_copilot/per_user_auth.py:697
↓ 8 callersFunctionreset_team_member_spend_fn
Reset a team member's tracked spend against their per-member budget. A member's spend is tracked separately from both their own personal
litellm/proxy/management_endpoints/team_endpoints.py:4404
↓ 8 callersMethodresolveDepth
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 8 callersFunctionresolve_a2a_hop_auth_header
( litellm_params: Mapping[str, object], custom_llm_provider: object, resolve_entra_header: AgentAu
litellm/llms/a2a/common_utils.py:159
↓ 8 callersMethodresolve_api_base
(api_base: str | None)
litellm/llms/databricks/common_utils.py:192
↓ 8 callersMethodresolve_credentials
( &self, config: AwsAuthConfig, env_lookup: &(dyn Fn(&str) -> Option<String> + Sync),
litellm-rust/crates/auth-aws/src/aws.rs:264
↓ 8 callersFunctionresolve_fields
Resolve every descriptor to (values, provenance). Precedence per field: a set stored value wins, else a non-blank process env var, else the d
litellm/proxy/config_resolvers/_descriptors.py:55
↓ 8 callersMethodresolve_guardrail_context
(kwargs: Mapping[str, object])
litellm/responses/mcp/request_context.py:93
↓ 8 callersMethodresolve_identity
( api_key: str, jwt_handler: JWTHandler, prisma_client: PrismaClient | None, u
litellm/proxy/auth/handle_jwt.py:2541
← previousnext →9,501–9,600 of 202,479, ranked by callers