MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 5 callersFunctioncheck_aws_credentials
Helper function to check if AWS credentials are set
tests/unit/secret_managers/test_aws_secret_manager_v2.py:240
↓ 5 callersFunctioncheck_breaking_changes
(old_schema: Schema, new_schema: Schema)
scripts/check_schema_compatibility.py:48
↓ 5 callersMethodcheck_cache
Checks if content already cached. Currently, checks cache list, for cache key == displayName, since Google doesn't let us set the na
litellm/llms/vertex_ai/context_caching/vertex_ai_context_caching.py:210
↓ 5 callersFunctioncheck_end_user_budget
Check if end user is within their budget limit. Args: end_user_obj: The end user object to check route: The request route
litellm/proxy/auth/auth_checks.py:1962
↓ 5 callersMethodcheck_key_in_limits
( self, user_api_key_dict: UserAPIKeyAuth, cache: DualCache, data: dict,
litellm/proxy/hooks/parallel_request_limiter.py:93
↓ 5 callersFunctioncheck_non_standard_fallback_format
Checks if the fallbacks list is a list of strings or a list of dictionaries. If - List[str]: e.g. ["claude-3-haiku", "openai/o-1"] -
litellm/router_utils/fallback_event_handlers.py:995
↓ 5 callersFunctioncheck_org_key_model_specific_limits
Check if the organization key is allocating model specific limits. If so, raise an error if we're overallocating.
litellm/proxy/management_endpoints/key_management_endpoints.py:2214
↓ 5 callersMethodcheck_pii
Calls Presidio Analyze + Anonymize endpoints for PII Analysis + Masking
litellm/proxy/guardrails/guardrail_hooks/presidio.py:1019
↓ 5 callersMethodcheck_pii
(self, text, output_parse_pii, presidio_config, request_data)
tests/unit/responses/test_responses_websocket_all_providers.py:3186
↓ 5 callersFunctioncheck_require_trace_id_caller_permission
( require_trace_id: bool | None, metadata: Mapping[str, object] | None, user_api_key_dict: UserAPI
litellm/proxy/management_endpoints/common_utils.py:276
↓ 5 callersFunctioncheck_team_key_model_specific_limits
Check if the team key is allocating model specific limits. If so, raise an error if we're overallocating.
litellm/proxy/management_endpoints/key_management_endpoints.py:1952
↓ 5 callersMethodcheck_tool_permission_for_key_team
Check if a tool is allowed based on key/team object_permission.mcp_tool_permissions. Uses MCPRequestHandler.is_tool_allowed_for_serve
litellm/proxy/mcp_server/mcp_server_manager.py:5999
↓ 5 callersFunctionchecks_for_index
The entry-size check a request-log index needs before `CREATE INDEX CONCURRENTLY`.
litellm-proxy-extras/litellm_proxy_extras/migration_data_checks.py:116
↓ 5 callersFunctionchunk
(bytes: &[u8])
litellm-rust/crates/gateway-forward/tests/stream.rs:21
↓ 5 callersFunctionchunks
()
tests/unit/text_completions/test_streaming_iterator.py:66
↓ 5 callersMethodclaim
Atomically claim ``key``. ``"first"`` iff this caller is the first (increment to 1), ``"replayed"`` on a replay (>1), and ``"unavailable"`` wh
litellm/proxy/mcp_server/gateway_dcr_flow.py:1364
↓ 5 callersFunctionclaims
(response: Response)
litellm-rust/crates/gateway-ui/tests/routes.rs:65
↓ 5 callersFunctionclass
(character: char, unicode_classes: &UnicodeClasses)
litellm-rust/crates/token-counter-fast/src/unicode_classes.rs:97
↓ 5 callersFunctionclassify
(rig: Rig, classifier: Responder, **extra: JsonValue)
tests/integration/messages_endpoint/safeguards/test_safeguard_results_classifier_failures.py:85
↓ 5 callersFunctionclaude_code_group_name
Decode a canonical compatibility id only when no configured route claims it.
litellm/proxy/common_utils/model_listing_utils.py:102
↓ 5 callersFunctionclaude_code_view_ids
served id -> Claude Code id for the requested listing view
litellm/proxy/common_utils/model_listing_utils.py:123
↓ 5 callersMethodcleanup_applied
(self, *, retention_days: int = 1, batch_size: int = 1000)
litellm/repositories/accounting_delivery_repository.py:138
↓ 5 callersFunctioncleanup_result
( action: Callable[[], Result[R]], *, wait: Callable[[float], None] = sleep )
tests/e2e/batches/batch_cleanup.py:32
↓ 5 callersMethodclear
(self)
litellm/proxy/route_llm_request.py:85
↓ 5 callersFunctionclear_pid_record
(path: Path | None = None)
litellm/proxy/client/cli/commands/autoroute/process.py:136
↓ 5 callersMethodcli
(&self, args: &[&str])
litellm-rust/crates/redis-testing/src/standalone.rs:49
↓ 5 callersMethodcli_outputs
One redis-cli reply per node, in `nodes()` order.
litellm-rust/crates/redis-testing/src/cluster.rs:78
↓ 5 callersFunctioncli_sso_callback
CLI SSO callback - stores session info for JWT generation on polling
litellm/proxy/management_endpoints/ui_sso.py:2661
↓ 5 callersFunctioncli_sso_complete
(request: Request, login_id: str)
litellm/proxy/management_endpoints/ui_sso.py:810
↓ 5 callersMethodclient_for_context
( &self, context: &AwsOperationContext, )
litellm-rust/crates/secrets-aws/src/secret_manager/client.rs:40
↓ 5 callersFunctionclose
(observed_value: float, expected: float)
tests/integration/streaming/test_mid_stream_fallback_continuation.py:463
↓ 5 callersMethodclose
(self)
litellm/proxy/guardrails/guardrail_hooks/custom_code/bounded_execution.py:84
↓ 5 callersMethodclose
(self, code: int = 1000, reason: str | None = None)
litellm/llms/openai/live/handler.py:92
↓ 5 callersMethodclose
(self)
tests/unit/proxy/guardrails/guardrail_hooks/noma/test_noma.py:95
↓ 5 callersMethodclose
(self)
litellm-rust/crates/spend-clickhouse/tests/storage.rs:46
↓ 5 callersMethodcloseNode
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 5 callersMethodclosePath
()
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 5 callersMethodclose_all_upstream_sessions
(self)
litellm/proxy/mcp_server/mcp_server_manager.py:6502
↓ 5 callersMethodcmp
(&self, other: &Self)
litellm-rust/crates/llms-types/src/providers/anthropic/beta.rs:439
↓ 5 callersFunctioncodex_config_path
(base_env: Mapping[str, str])
litellm/proxy/client/cli/commands/agents.py:399
↓ 5 callersFunctioncoerce_numeric_form_fields
Parse the numeric fields of a form-encoded body back into numbers. ``request.form()`` yields every field as a string, so a provider that put
litellm/proxy/common_utils/http_parsing_utils.py:174
↓ 5 callersFunctioncombine_observed
(sources: tuple[ObservedData, ...], repos: tuple[str, ...])
litellm/proxy/roi_calculator/observed_workspace.py:55
↓ 5 callersFunctioncommit
()
tests/unit/proxy/common_utils/test_reset_budget_job.py:3781
↓ 5 callersFunctioncommit_request_errors_to_db
One bounded statement per chunk, stopping at the first failure. Returns the rows that were not written (the failed chunk and everything after it)
litellm/proxy/db/request_error_tracking.py:203
↓ 5 callersMethodcommon_processing_pre_call_logic
(self, *args: object, **kwargs: object)
tests/unit/proxy/test_proxy_server.py:3572
↓ 5 callersMethodcommunicate
(self, timeout: Optional[float] = None)
tests/unit/litellm_proxy_extras/test_litellm_proxy_extras_utils.py:1931
↓ 5 callersFunctioncomplete_azure_anthropic_url
( api_base: Option<&str>, env_lookup: &dyn Fn(&str) -> Option<String>, )
litellm-rust/crates/llms/src/azure_ai/messages/transformation.rs:112
↓ 5 callersFunctioncomplete_call_tool_result
``to_call_tool_result`` for callers that can never carry an interim result.
litellm/proxy/mcp_server/result_conversion.py:97
↓ 5 callersFunctioncomplexity_router_decision_headers
(request_kwargs: object)
litellm/litellm_core_utils/add_retry_fallback_headers.py:55
↓ 5 callersFunctioncomprehend_medical_proxy_route
Pass-through for Amazon Comprehend Medical, e.g. `POST /comprehendmedical/DetectEntitiesV2`. The request body is forwarded as-is to the AWS
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:1714
↓ 5 callersFunctioncompute_budget_reset_at
Compute the next reset time for a budget duration using injected settings.
litellm/proxy/common_utils/timezone_utils.py:65
↓ 5 callersFunctioncompute_capture_rate
( *, provider: SpendCaptureProvider, start_date: date, end_date: date, captured_by_day: Ma
litellm/proxy/spend_tracking/spend_capture_rate.py:112
↓ 5 callersFunctionconfig_store_info
(gateway: Gateway)
tests/integration/management/test_vector_store_config_ownership.py:46
↓ 5 callersFunctionconnect
( service: &FakeBlobService, account_url: &str, codec: C, handle: Handle, )
litellm-rust/crates/cache-azure-blob/tests/support/mod.rs:191
↓ 5 callersFunctionconnected_proxy_prisma
(database_url: str | None = None)
tests/integration/_support/prisma_clients.py:26
↓ 5 callersFunctionconnected_settings
( repository: ConfigRepository, transport: httpx.AsyncBaseTransport | None = None, selected_id: str | None
litellm/proxy/roi_calculator/oauth.py:348
↓ 5 callersMethodconstruct_dynamic_otel_config
Build a full per-request OTLP config from team/key dynamic Langfuse credentials. Key-scoped credentials must define the export targe
litellm/integrations/langfuse/langfuse_otel.py:531
↓ 5 callersMethodconstruct_request_headers
( self, service_account_json: str | None, vertex_instance: VertexBase | None = None,
litellm/integrations/gcs_bucket/gcs_bucket_base.py:49
↓ 5 callersMethodconstruct_url
( self, api_base: str, query_params: RealtimeQueryParams, )
litellm/llms/openai/realtime/handler.py:170
↓ 5 callersFunctionconsume_async_stream
(create: Callable[[], Awaitable[AsyncIterable[object]]])
tests/rust-python-harness/shared/parity/stream.py:126
↓ 5 callersFunctioncontainer_body
(url: str, prompt: str, **extra: JsonValue)
tests/integration/providers/_sagemaker_chat_container.py:141
↓ 5 callersFunctioncontainer_reply
(identity: str, stream: bool)
tests/integration/providers/_sagemaker_chat_container.py:97
↓ 5 callersFunctioncontains
(statement: str, keyword: str)
tests/code_coverage_tests/check_migrations_no_data_rewrites.py:791
↓ 5 callersFunctioncontains_any
(text: &str, markers: &[&str])
litellm-rust/crates/core-utils/src/exception_mapping_utils/rules.rs:32
↓ 5 callersFunctioncontext
()
litellm-rust/crates/cache-gcs/tests/cache.rs:23
↓ 5 callersFunctioncontext_from_span
A context with ``span`` as the active span (for explicit parenting).
litellm/integrations/otel/plumbing/context.py:221
↓ 5 callersMethodcontinue
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 5 callersFunctionconvert_b64_uid_to_unified_uid
(b64_uid: str)
litellm/proxy/openai_files_endpoints/common_utils.py:162
↓ 5 callersMethodconvert_chat_to_text_completion
Converts a chat completion response to a text completion response format. Note: This is used for huggingface. For OpenAI / Azure Tex
litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py:652
↓ 5 callersFunctionconvert_generic_image_chunk_to_openai_image_obj
Convert a generic image chunk to an OpenAI image object. Input: GenericImageParsingChunk( type="base64", media_type="ima
litellm/litellm_core_utils/prompt_templates/factory.py:858
↓ 5 callersMethodconvert_to_text_completion_object
(self, chunk: ModelResponse | ModelResponseStream)
litellm/text_completions/streaming_iterator.py:35
↓ 5 callersFunctionconvert_vertex_datetime_to_openai_datetime
Converts a Vertex AI / GCS RFC 3339 UTC timestamp to Unix epoch seconds vertex_datetime: str = "2024-12-04T21:53:12.120184Z" returns: in
litellm/llms/vertex_ai/common_utils.py:1128
↓ 5 callersFunctioncooldown
(model_id: &str)
litellm-rust/crates/redis-store/src/router_cooldowns/keys.rs:1
↓ 5 callersFunctioncooldown_config
( directory: Path, settings: Mapping[str, JsonValue], *, model_list: Sequence[Mapping[str, Jso
tests/integration/routing/test_payment_required_cooldown.py:123
↓ 5 callersFunctioncooldown_settings
(cache: OwnedRedis | None)
tests/integration/routing/test_priority_scheduler_queue_cleanup.py:230
↓ 5 callersFunctioncooled
(core: RouterCore, *ids: str)
tests/unit/test_router/core/test_streaming_characterization_outcomes.py:89
↓ 5 callersFunctioncost_of
(usage: tuple[int, int])
tests/integration/providers/_gemini_long_decode_support.py:571
↓ 5 callersMethodcount
(self, where: object = None)
tests/unit/proxy/management_helpers/test_bulk_user_creation.py:48
↓ 5 callersFunctioncount_relayed_prompt_tokens
(model: str, messages: Sequence[Mapping[str, object]] | None)
litellm/proxy/pass_through_endpoints/llm_provider_handlers/openai_passthrough_logging_handler.py:204
↓ 5 callersFunctioncount_release_bullets
Bucket release-note bullets by conventional-commit type or ``other_updates``.
litellm/proxy/ui_crud_endpoints/latest_release_endpoints.py:107
↓ 5 callersMethodcount_tokens
POST /v1/messages/count_tokens (Anthropic-native). Sends the anthropic-version header so the native path accepts it; harmless on the o
tests/e2e/proxy_client.py:1083
↓ 5 callersFunctioncounterLabel
(counter: string)
ui/litellm-dashboard/src/components/GuardrailsMonitor/usageUnits.ts:14
↓ 5 callersFunctioncoverageSpecFixture
(paths map[string][]string)
terraform/provider/tools/endpointaudit/coverage_test.go:11
↓ 5 callersMethodcreate
(self, data: Mapping[str, object])
enterprise/litellm_enterprise/proxy/hooks/managed_files.py:364
↓ 5 callersFunctioncreateGatewayClient
({ accessToken, ...options }: GatewayClientOptions)
ui/litellm-dashboard/src/components/llm_calls/gateway_client.ts:9
↓ 5 callersFunctioncreateGuardrailCall
(accessToken: string, guardrailData: any)
ui/litellm-dashboard/src/components/networking.tsx:4356
↓ 5 callersMethodcreate_and_poll
(self, thread_id, assistant_id, **_kwargs)
tests/unit/llms/openai/test_openai.py:2056
↓ 5 callersFunctioncreate_anthropic_model_list_response
Build the Anthropic-native /v1/models envelope. Clients that send an anthropic-version header parse the Anthropic Models API shape (type/disp
litellm/llms/anthropic/common_utils.py:2812
↓ 5 callersFunctioncreate_draft_mcp_server
Persist a short-lived draft row backing the admin OAuth "Authorize & Fetch Token" flow. The draft lives in the database rather than in proce
litellm/proxy/mcp_server/db.py:1138
↓ 5 callersMethodcreate_follow_up_messages_for_chat
Create follow-up chat messages that include tool execution results.
litellm/responses/mcp/litellm_proxy_mcp_handler.py:1040
↓ 5 callersMethodcreate_model
Register a deployment under `model_name` and return its proxy-assigned model_id, once the model is actually servable on the data plane.
tests/e2e/proxy_client.py:655
↓ 5 callersMethodcreate_project
(self, team_id: str, project_alias: str, models: list[str])
tests/e2e/access_control/access_control_client.py:122
↓ 5 callersFunctioncreate_request
(path: str, base_url: str = "http://testserver")
tests/unit/proxy/auth/test_proxy_routes.py:139
↓ 5 callersFunctioncreate_source
(settings: ROISettings, transport: httpx.AsyncBaseTransport | None = None)
litellm/proxy/roi_calculator/source.py:28
↓ 5 callersFunctioncreate_standard_logging_payload
()
tests/unit/integrations/datadog/test_datadog.py:777
↓ 5 callersMethodcreate_stream_collector
( self, model: str, custom_llm_provider: str, endpoint: str )
litellm/llms/base_llm/passthrough/transformation.py:238
↓ 5 callersMethodcreate_stream_state
(self)
litellm/llms/pi/harness/transformation.py:527
↓ 5 callersMethodcreate_team
(self, body: TeamNewBody)
tests/e2e/proxy_client.py:981
↓ 5 callersFunctioncreate_vector_store_in_db
Helper function to create a vector store in the database. This function handles: - Checking if vector store already exists - Creatin
litellm/proxy/vector_store_endpoints/management_endpoints.py:182
↓ 5 callersMethodcreate_vertex_batch_url
Return the base url for the vertex garden models
litellm/llms/vertex_ai/batches/handler.py:302
← previousnext →15,601–15,700 of 202,479, ranked by callers