MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 14 callersFunction_table
(repository: BudgetRepository)
litellm/proxy/management_endpoints/organization_endpoints.py:229
↓ 14 callersFunction_table
(size: int)
tests/unit/repositories/test_chunked_in.py:72
↓ 14 callersFunction_token
(private_key: rsa.RSAPrivateKey, subject: str, **claims: str)
tests/integration/authorization/test_jwt_auto_register_map_existing_key.py:78
↓ 14 callersFunction_transcription_guardrail
A minimal real CustomGuardrail registered for one realtime event hook.
tests/unit/litellm_core_utils/test_realtime_streaming.py:4554
↓ 14 callersMethod_transform
(self, record: dict)
tests/unit/llms/bedrock/files/test_bedrock_files_transformation.py:1557
↓ 14 callersMethod_transform
(self, config, rows, url="https://example.com")
tests/unit/llms/vertex_ai/files/test_vertex_ai_files_transformation.py:1687
↓ 14 callersFunction_trust_peer_without_global_http2
(monkeypatch: pytest.MonkeyPatch, peer: TlsPeer)
tests/integration/sdk/test_http2_wire.py:275
↓ 14 callersFunction_two
(tag: str)
tests/integration/messages_endpoint/chat_bridge/test_chat_bridge_multi_tool_call_blocks_wire.py:128
↓ 14 callersFunction_unverified_claims
(sealed_token: str)
tests/unit/proxy/mcp_server/outbound_credentials/test_envelope.py:88
↓ 14 callersFunction_update
( monkeypatch: pytest.MonkeyPatch, *, policy: str | None, data: UpdateKeyRequest, existing
tests/unit/proxy/management_endpoints/test_key_budget_change.py:228
↓ 14 callersFunction_update_config_setup
Install fakes for the /config/update endpoint and return (client, prisma).
tests/unit/proxy/test_proxy_server_endpoints_and_startup.py:9881
↓ 14 callersFunction_update_internal_user_params
(data_json: dict, data: UpdateUserRequest | UpdateUserRequestNoUserIDorEmail)
litellm/proxy/management_endpoints/internal_user_endpoints.py:1379
↓ 14 callersMethod_update_model
( stored_model_info: Mapping[str, object], model_info: ModelInfo, litellm_params: Mapp
tests/unit/proxy/management_endpoints/test_model_management_endpoints.py:1725
↓ 14 callersFunction_user
(marker: str, breakpoint: JsonValue)
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire.py:90
↓ 14 callersFunction_user_block_on_wire
(bridge: _Bridge, marker: str, *, stream: bool = False)
tests/integration/providers/test_responses_bridge_prompt_cache_breakpoint_wire.py:121
↓ 14 callersMethod_user_text
(text: str, role: str = "user")
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_handler.py:1817
↓ 14 callersFunction_v1_models
(user_api_key_dict: UserAPIKeyAuth, **kwargs)
tests/unit/proxy/test_model_list_callback_filter.py:144
↓ 14 callersFunction_violation_response
(url: str = CHAT_URL)
tests/unit/proxy/guardrails/guardrail_hooks/_cisco_ai_defense_test_utils.py:92
↓ 14 callersFunction_wire_tx
Model the prisma seam the partition DDL uses. Every statement this manager issues, DDL and catalog query alike, runs inside db.tx() so i
tests/unit/proxy/db/db_transaction_queue/test_spend_logs_partition_manager.py:32
↓ 14 callersFunction_wires
(classifier: Callable[[Request], Reply] | None = None)
tests/integration/routing/test_complexity_router_databricks_classifier.py:151
↓ 14 callersFunctionaL
()
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 14 callersMethodacancel_batch
( self, cancel_batch_data: CancelBatchRequest, openai_client: AsyncOpenAI, )
litellm/llms/openai/openai.py:2296
↓ 14 callersMethodaclose
(self)
litellm/llms/custom_httpx/aiohttp_transport.py:196
↓ 14 callersMethodacount_tokens
Count tokens using Google Gen AI Studio countTokens endpoint. Args: contents: The content to count tokens for (Google Ge
litellm/llms/gemini/count_tokens/handler.py:155
↓ 14 callersMethodadd_job
( self, func: Callable[[], Awaitable[None]], /, **trigger: str | int, # kwarg
litellm/integrations/ternary/ternary_logger.py:28
↓ 14 callersFunctionadd_new_member
Add a new member to a team - add team id to user table - add team member to team member table, linked to a budget when one resolves
litellm/proxy/management_helpers/utils.py:443
↓ 14 callersMethodagent
(self)
tests/integration/spend/test_daily_activity_key_metadata_query_timeout.py:464
↓ 14 callersFunctionaget_user_provider_credentials
Map each per-user credential name to the caller's stored GitHub connection. Cached values are the stored ciphertext or the ``_NOT_CONNECTED`` mar
litellm/proxy/credential_endpoints/user_provider_credentials.py:297
↓ 14 callersFunctionanswer
(marker: str)
tests/integration/providers/_tool_search_support.py:80
↓ 14 callersMethodappend
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 14 callersFunctionapply_redacted_messages_back
Write redacted messages back to whichever field(s) the caller used. Mask/anonymize paths take a synthesised messages list (from :func:`build_
litellm/proxy/guardrails/_content_utils.py:487
↓ 14 callersMethodaread
(self, file_path: str, offset: int = 0, limit: int = 2000)
litellm/llms/deepagents/harness/sandbox_backend.py:209
↓ 14 callersMethodas_str
(&self)
litellm-rust/crates/secrets-types/src/value.rs:31
↓ 14 callersFunctionassert_listing_shape
Every listing is one foundation-models GET plus `pages` inference-profiles GETs; returns the listing count.
tests/integration/_support/bedrock_discovery.py:238
↓ 14 callersFunctionassistants_wire
(respond: Callable[[Request], Reply], port: int = 0)
tests/integration/providers/_assistants_route_errors_support.py:269
↓ 14 callersMethodasync_get_cache
( self, key, parent_otel_span: Span | None = None, *, raise_on_error: bool = False, **kwargs )
litellm/caching/redis_cache.py:1671
↓ 14 callersMethodasync_pre_call_hook
Runs before the LLM API call to validate and potentially modify input. Uses 'PROMPT' messageType as this is input to the model.
litellm/proxy/guardrails/guardrail_hooks/lasso/lasso.py:184
↓ 14 callersMethodasync_set_cache
Internal method to check the type of the result & cache used and adds the result to the cache accordingly Args: result:
litellm/caching/caching_handler.py:1207
↓ 14 callersMethodasync_store
( &self, cache: &dyn ExactResponseCache, request: &ResponseCacheRequest, respo
litellm-rust/crates/cache-response/src/buffer.rs:21
↓ 14 callersMethodattempt
Refuses a blocked key before any credential is looked at; otherwise hands back the attempt to settle.
litellm/proxy/auth/login_throttle.py:325
↓ 14 callersMethodbackend_to_client
Forward events from backend WebSocket to the client.
litellm/responses/streaming_iterator.py:2742
↓ 14 callersFunctionbedrock_realtime_peer
Serve scripted `turns` on a loopback TLS h2 endpoint; yield the peer. `cert` is the self-signed pair the owned proxy already trusts via SSL_CERT_
tests/integration/_support/bedrock_realtime_peer.py:514
↓ 14 callersFunctionbind_admission_counter_keys
Idempotent: call again after the token gains ids (end user, team org) so those counters join the MGET.
litellm/proxy/spend_tracking/spend_counter_batch.py:253
↓ 14 callersFunctionbuild_effective_auth_contexts
Every auth context a management or listing surface must resolve a UI session token through: one per real team backing the session, plus the sessio
litellm/proxy/mcp_server/ui_session_utils.py:136
↓ 14 callersFunctionbuild_where_clause
(scope: DailyActivityScope, *, start_index: int = 1)
litellm/repositories/daily_activity_sql.py:66
↓ 14 callersFunctionby_name
(exporter: InMemorySpanExporter)
tests/unit/integrations/otel/test_otel_v2_destinations.py:5110
↓ 14 callersFunctioncall
(server: RecordingServer, asynchronous: bool, **kwargs: object)
tests/test_litellm_rust/ocr/data.py:38
↓ 14 callersFunctioncall
(method: str, body: bytes = b"")
tests/unit/proxy/mcp_server/test_mcp_server_tool_calls_and_headers.py:4114
↓ 14 callersMethodcaller_admission_credential
( headers: Headers, user_api_key_auth: UserAPIKeyAuth, *, custom_key_header_na
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:1954
↓ 14 callersMethodchat
Drive a chat call, optionally opting into named guardrails for this request only (the per-request `guardrails` selector). With `guardrails`
tests/e2e/guardrails/guardrails_client.py:381
↓ 14 callersMethodclear
(self)
litellm/llms/vertex_ai/context_caching/known_cached_contents.py:150
↓ 14 callersFunctionclient_for
(*skills: LiteLLM_SkillsTable, uploads: PluginUploadRepository | None = None)
tests/unit/proxy/discovery_endpoints/test_agent_skills_endpoints.py:72
↓ 14 callersMethodclose
(self, code: int = 1000, reason: str = "")
tests/unit/proxy/test_openai_ws_passthrough_routes.py:72
↓ 14 callersMethodclose
(self, code: int = 1000, reason: str = "")
tests/unit/proxy/pass_through_endpoints/test_deepgram_ws_passthrough_routes.py:60
↓ 14 callersFunctioncollect
(handler: CLIHarnessHandler, ctx: SessionContext, prompt: str)
tests/unit/llms/pi/harness/test_transformation.py:246
↓ 14 callersFunctioncomplete
( request: ChatCompletionsRequest<'_>, )
litellm-rust/crates/inference-chat/tests/request.rs:34
↓ 14 callersFunctionconnect
( server: &FakeQdrant, vectors: impl IntoIterator<Item = (&'static str, Vec<f32>)>, )
litellm-rust/crates/cache-qdrant-semantic/tests/qdrant.rs:84
↓ 14 callersMethodcontains
(&self, name: &str)
litellm-rust/crates/python-bridge/src/marshal.rs:164
↓ 14 callersFunctioncontinuation_core
(make_core: MakeCore, **arguments: object)
tests/unit/test_router/core/test_streaming_characterization_chat.py:386
↓ 14 callersFunctioncount_request_tokens
( request: TokenCountRequest, call_endpoint: bool = False, messages_format: TokenCountMessagesForm
litellm/proxy/proxy_server.py:15989
↓ 14 callersMethodcreate
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 14 callersMethodcreate_mcp_client
( self, server: MCPServer, mcp_auth_header: str | dict[str, str] | None = None,
litellm/proxy/mcp_server/mcp_server_manager.py:4377
↓ 14 callersMethodcreate_posthog_event_payload
Helper function to create a PostHog event payload for logging Args: kwargs (Dict[str, Any]): request kwargs containing s
litellm/integrations/posthog.py:158
↓ 14 callersFunctioncreate_standard_logging_payload
()
tests/unit/integrations/test_posthog.py:25
↓ 14 callersMethodcredentials
(self)
litellm/proxy/mcp_server/oauth2_flow_backfill.py:84
↓ 14 callersMethodcurrent
()
litellm-rust/crates/tracing/src/lib.rs:73
↓ 14 callersMethodde_anonymize_event_stream
( self, body_bytes: bytes, proxy_logging_obj: "ProxyLogging", user_api_key_dic
litellm/llms/pass_through/guardrail_translation/handler.py:222
↓ 14 callersMethoddeployment_model_info
Model info for a deployment, merged with the pricing map (was ``get_deployment_model_info``; ``cached=True`` was ``cached_deployment_
litellm/router_api.py:384
↓ 14 callersFunctiondiagnose_zero_cost
( usage: Usage, pricing_model: str, pricing_entry: Mapping[str, object], calculation_failed: b
litellm/litellm_core_utils/llm_cost_calc/zero_cost_diagnostic.py:108
↓ 14 callersFunctiondigest_no_key_table_holds
()
tests/integration/_support/daily_activity.py:81
↓ 14 callersMethoddomSelectionRange
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 14 callersFunctiondrain_contract_requests
(wire: Wire)
tests/integration/providers/test_responses_lifecycle_wire.py:73
↓ 14 callersFunctione_
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 14 callersFunctionea
()
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 14 callersFunctionecho_tool
(name: str)
tests/integration/_support/mcp.py:397
↓ 14 callersFunctionendpoint
(scenario: str)
tests/integration/_support/sagemaker_embedding.py:35
↓ 14 callersFunctionengine_call
(return_value: _T | None = None)
tests/unit/proxy/db/fake_prisma_engine.py:15
↓ 14 callersFunctionerror_message
(response: httpx.Response)
tests/integration/providers/_dashscope_video_support.py:206
↓ 14 callersFunctiones
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 14 callersMethodexchange
( self, subject_token: str, server: ServerSpec, config: TokenExchangeConfig, *, tenant_id: str = ""
litellm/proxy/mcp_server/outbound_credentials/token_exchanger.py:251
↓ 14 callersFunctionexpand_wildcard_deployments_for_model_info
Expand wildcard deployments into one row per known provider model. PR #30025 changed /model/info to read from llm_router.model_list (correct,
litellm/proxy/auth/model_checks.py:636
↓ 14 callersMethodextract_response_content
( self, completion_response: dict )
litellm/llms/anthropic/chat/transformation.py:2790
↓ 14 callersFunctionfetch_sso_identity_assertion
The stored assertion for ``user_id``, or ``None`` when absent, undecryptable (salt-key rotation), or unparseable. Expiry is not judged here; the r
litellm/proxy/mcp_server/outbound_credentials/sso_assertion_store.py:397
↓ 14 callersMethodfilter_tools
Filter tools semantically based on query. Args: query: User query to match against tools available_tools: Fu
litellm/proxy/mcp_server/semantic_tool_filter.py:268
↓ 14 callersFunctionfinal_label
(marker: str)
tests/integration/providers/_cache_control_marks_support.py:61
↓ 14 callersMethodfindAll
(e={})
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 14 callersFunctionfind_canary
Every canary found in ``blob``, one ``Match`` per slot with the shallowest encoding seen. Decoding is bounded: at most ``_MAX_DEPTH`` nested laye
tests/integration/security/_canary.py:184
↓ 14 callersMethodfind_credential
(credential_name: str)
litellm/litellm_core_utils/credential_accessor.py:17
↓ 14 callersMethodfind_many
(self, where: Mapping[str, object])
litellm/proxy/mcp_server/toolset_db.py:61
↓ 14 callersMethodfinite
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2j7hjtph8n74b.js:1
↓ 14 callersMethodfire_deferred_stream_logging
Fire the deferred streaming logging callback after the full streaming pipeline (including guardrail end-of-stream blocks) has complet
litellm/proxy/utils.py:5250
↓ 14 callersFunctionflush_post_call_redis_batches
Called where the success and failure callbacks of a request have all run.
litellm/caching/redis_batch.py:679
↓ 14 callersFunctionframes
( input: S, codec: D, )
litellm-rust/crates/framer/src/framed.rs:10
↓ 14 callersFunctionfrom_py
(value: &Bound<'_, PyAny>)
litellm-rust/crates/host-python/src/marshal.rs:21
↓ 14 callersMethodfrom_request
( cls, request: Request, general_settings: Mapping[str, object] | None, redis_
litellm/proxy/auth/login_throttle.py:290
↓ 14 callersMethodgenerate
(self, **kwargs)
tests/unit/llms/openai/test_openai.py:2379
↓ 14 callersFunctiongetLocalStorageItem
(key: string)
ui/litellm-dashboard/src/utils/localStorageUtils.ts:7
↓ 14 callersMethodget_api_base
(api_base: str | None = None)
litellm/llms/gemini/common_utils.py:413
↓ 14 callersMethodget_api_key
(api_key: str | None = None)
litellm/llms/gemini/common_utils.py:417
↓ 14 callersFunctionget_api_key_metadata
( prisma_client: PrismaClient, api_keys: AbstractSet[str], spend_logs_window: SpendLogsWindow | None = Non
litellm/proxy/management_endpoints/common_daily_activity.py:615
← previousnext →4,401–4,500 of 202,479, ranked by callers