MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersFunctionconfigure_sink
(url: str, **fields: JsonValue)
tests/integration/_support/otlp_sink.py:343
↓ 8 callersFunctionconfigure_state_path
The receipt describing settings_path: the default file keeps CONFIGURE_STATE_PATH, and any other file (a CLAUDE_CONFIG_DIR) gets its own beside it
litellm/proxy/client/cli/commands/claude_settings.py:124
↓ 8 callersFunctionconfigured_injection_points
(value: object)
litellm/integrations/anthropic_cache_control_hook.py:341
↓ 8 callersMethodconnect
`http` is the host's pooled client; the SDK sends every request through it.
litellm-rust/crates/cache-azure-blob/src/cache.rs:35
↓ 8 callersFunctionconnection_for
The connection configured right now, so a UI edit takes effect without a restart.
litellm/integrations/zerobus/logger.py:74
↓ 8 callersFunctionconsume_file_usage
( cache: "InternalUsageCache", limits: tuple[ScopedFileUsageLimit, ...], window_seconds: int,
litellm/proxy/openai_files_endpoints/file_usage_caps.py:154
↓ 8 callersFunctioncontext_secret_vault
Where this invocation reads and writes secret material; injectable through ctx.obj for tests
litellm/proxy/client/cli/commands/auth.py:221
↓ 8 callersFunctionconvert_to_anthropic_image_obj
Input: "image_url": "data:image/jpeg;base64,{base64_image}", Return: "source": { "type": "base64", "media_type": "image/
litellm/litellm_core_utils/prompt_templates/factory.py:878
↓ 8 callersFunctioncopy
({className:s=null,width:o=15,height:i=16,...a})
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctioncount
(request: Request)
tests/integration/providers/test_count_tokens_error_shapes_wire.py:176
↓ 8 callersMethodcount
(self, where: Optional[Dict[str, Any]] = None)
tests/unit/proxy/memory/test_memory_endpoints.py:119
↓ 8 callersFunctioncount_capability_routers
How many of ``deployments`` (router model_list entries or config.yaml rows) claim ``capability``.
litellm/router_strategy/auto_router/auto_router_model_naming.py:351
↓ 8 callersFunctioncount_in
( table: CountTable, field: str, values: Iterable[Hashable], *, where: Mapping[str, object
litellm/repositories/chunked_in.py:105
↓ 8 callersFunctioncounted
Group ``g``'s ``kind`` usage this minute, as ``health().usage`` reports it.
tests/unit/test_router/core/test_legacy_members.py:118
↓ 8 callersMethodcreate
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:5
↓ 8 callersFunctioncreateMockTeamData
(overrides = {})
ui/litellm-dashboard/src/components/team/TeamInfo.test.tsx:276
↓ 8 callersMethodcreate_backend_model
Register a chat deployment for a guardrail test to run against (deleted on teardown). The guardrails under test here gate on prompt/output
tests/e2e/guardrails/guardrails_client.py:219
↓ 8 callersMethodcreate_initial_state
Create initial state in Redis for a polling request Uses OpenAI ResponsesAPIResponse object: https://platform.openai.com/doc
litellm/proxy/response_polling/polling_handler.py:52
↓ 8 callersMethodcreate_litellm_proxy_request_started_span
(self, start_time: datetime, headers: dict[str, str])
tests/unit/proxy/auth/test_user_api_key_auth_request_flow.py:11808
↓ 8 callersFunctioncreate_mcp_server
Create a new mcp server record in the db
litellm/proxy/mcp_server/db.py:1079
↓ 8 callersMethodcreate_org
(self, body: OrgNewBody)
tests/e2e/management/management_client.py:593
↓ 8 callersMethodcreate_rate_limit_descriptors
( self, *, user_api_key_dict: UserAPIKeyAuth, data: Mapping[str, str],
tests/unit/llms/anthropic/messages/test_caller_model_checks.py:142
↓ 8 callersFunctioncreate_scratch_org
( db: ManagementDatabase, scratch_prefix: str, *, max_budget: float | None = None, tpm_lim
tests/integration/_support/actors.py:343
↓ 8 callersMethodcreate_skill
( data: NewSkillRequest, user_id: str | None = None, user_api_key_dict: UserAPIKeyAuth
litellm/llms/litellm_proxy/skills/handler.py:67
↓ 8 callersFunctioncreate_versioned_prompt_spec
Helper function to create a PromptSpec with versioned prompt_id from a DB prompt entry. Args: db_prompt: The DB prompt object (from
litellm/proxy/prompts/prompt_endpoints.py:149
↓ 8 callersMethodcredential_hits
(self)
tests/integration/security/_sweeps.py:568
↓ 8 callersFunctioncredential_less_arize
An operator with no Arize account and no generic OTLP collector or headers.
tests/unit/integrations/otel/test_otel_v2_destinations.py:3260
↓ 8 callersFunctioncz
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0_6jqgnorqxl2.js:1
↓ 8 callersFunctiond
()
litellm/proxy/_experimental/out/_next/static/chunks/2j96ftcthirif.js:161
↓ 8 callersFunctiond
litellm/proxy/_experimental/out/_next/static/chunks/1f2vcab0yti03.js:57
↓ 8 callersFunctiond
litellm/proxy/_experimental/out/_next/static/chunks/2jxpy6eth1zvy.js:1
↓ 8 callersFunctiondecisions_text
(value: DecisionsJSON)
litellm/llms/base_llm/decisions/transformation.py:71
↓ 8 callersMethoddecrypt
(self, CiphertextBlob: bytes)
litellm/secret_managers/secret_manager_handler.py:46
↓ 8 callersMethoddeepgram_listen_passthrough_handler
( self, websocket_messages: Sequence[Mapping[str, object]], logging_obj: LiteLLMLoggin
litellm/proxy/pass_through_endpoints/llm_provider_handlers/deepgram_listen_passthrough_logging_handler.py:59
↓ 8 callersFunctiondefaultJevClassifierConfig
(provider: OssClassifierProvider = "jev")
ui/litellm-dashboard/src/components/add_model/jev_classifier_config.ts:61
↓ 8 callersFunctiondefault_video_cost_calculator
Default video cost calculator for video generation Args: model (str): Model name duration_seconds (float): Duration of the g
litellm/cost_calculator.py:3129
↓ 8 callersMethoddelete_cache
(self, key: str)
tests/unit/router_strategy/test_least_busy.py:599
↓ 8 callersFunctiondelete_team_models
Delete every BYOK model owned by the given teams, from the DB and the router. The DB rows are removed inside a single transaction, so deleti
litellm/proxy/management_endpoints/model_management_endpoints.py:2434
↓ 8 callersFunctiondelete_user
Delete a user according to SCIM v2 protocol
litellm/proxy/management_endpoints/scim/scim_v2.py:2007
↓ 8 callersFunctiondeployment
(name: str, model: str, api_base: str, **extra: JsonValue)
tests/integration/_support/safeguards_rig.py:175
↓ 8 callersFunctiondeployment
( model_id: str, classifier: str, *, model: str = "solver", tuned: bool = False, confi
tests/unit/proxy/management_helpers/test_auto_router_availability.py:15
↓ 8 callersFunctiondisable_team_logging
Disable all logging callbacks for a team Callbacks registered through POST /team/{team_id}/callback and the Admin UI are cleared, so re-
litellm/proxy/management_endpoints/team_callback_endpoints.py:623
↓ 8 callersFunctiondisabled_capabilities
()
litellm/proxy/mcp_server/capabilities.py:82
↓ 8 callersFunctiondiscard_staged_json
Throw a staged file away when the change it was part of is abandoned
litellm/litellm_core_utils/private_json.py:78
↓ 8 callersMethoddomFromPos
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 8 callersMethoddone
( self, event: Mapping[str, object], level_error: BaseException | None, hop_er
litellm/router_rust/invoke/walk.py:384
↓ 8 callersMethoddrain
(self)
tests/unit/harness/sandbox/test_docker.py:26
↓ 8 callersFunctiondrain_spend_logs_queue
( prisma_client: PrismaClient, db_writer_client: "AsyncHTTPHandler | None", proxy_logging_obj: Pro
litellm/proxy/utils.py:9221
↓ 8 callersFunctioneO
litellm/proxy/_experimental/out/_next/static/chunks/37cr8te-omsl0.js:1
↓ 8 callersFunctioneO
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/14v3irtjifjt2.js:1
↓ 8 callersFunctionedit_mcp_server
Updates the MCP Server in the db. Partial update: a field left out of the payload keeps its stored value, and a field sent as null i
litellm/proxy/management_endpoints/mcp_management_endpoints.py:3206
↓ 8 callersFunctionee
(e)
litellm/proxy/_experimental/out/_next/static/chunks/2k-fkubkt19cc.js:1
↓ 8 callersMethodemit_guardrail_span
(self, entry)
tests/unit/integrations/otel/test_otel_v2_logger.py:3009
↓ 8 callersFunctionencode
(chunk: &ChatCompletionChunk)
litellm-rust/crates/llms/src/base_llm/chat/streaming.rs:26
↓ 8 callersFunctionencode_tool_call_id_with_signature
Embed thought signature into tool call ID for OpenAI client compatibility. Args: tool_call_id: The tool call ID (e.g., "call_abc123.
litellm/litellm_core_utils/prompt_templates/factory.py:1236
↓ 8 callersFunctionencode_upstream_scope
(server_id: str, permission: str)
litellm/proxy/mcp_server/oauth_utils.py:865
↓ 8 callersMethodencrypt
(original_id: str)
litellm/proxy/hooks/responses_id_security.py:396
↓ 8 callersMethodenforce_mcp_server_rate_limits
( self, user_api_key_dict: UserAPIKeyAuth | None, server: "MCPServer", )
litellm/proxy/utils.py:5323
↓ 8 callersMethodenqueue
(self, record: bytes)
litellm/tracing/exporter.py:162
↓ 8 callersFunctionenqueue_spend_logs
Queue spend logs for the next flush, held under ``SPEND_LOG_QUEUE_MAX_BYTES``. ``at_head`` replays a batch the DB refused, so it flushes before t
litellm/proxy/utils.py:8597
↓ 8 callersFunctionenroll_microsoft_subject
(subject: object, user_id: object, client: object)
litellm/proxy/management_endpoints/sso/agent_subject_enrollment.py:40
↓ 8 callersFunctionensure_response_additional_headers
(response: object)
litellm/litellm_core_utils/add_retry_fallback_headers.py:148
↓ 8 callersFunctionensure_unique_openapi_operation_ids
( openapi_schema: JsonObject, reserved_operation_ids: set[str] | None = None, )
litellm/proxy/proxy_server.py:2098
↓ 8 callersFunctionenv_status
(gateway: Gateway, key: str, identity: str)
tests/integration/mcp/test_mcp_user_env_vars.py:61
↓ 8 callersMethodenvironment
(self)
tests/integration/providers/test_device_code_login_guard_boot.py:67
↓ 8 callersFunctionerror_type
(response: httpx.Response)
tests/integration/authorization/_hidden_alias_budget.py:149
↓ 8 callersFunctionestimate_cost
Estimate cost for a given model and token counts. This endpoint uses the same cost calculation logic as actual requests, including any c
litellm/proxy/management_endpoints/cost_tracking_settings.py:579
↓ 8 callersFunctionestimate_image_tokens
Estimate image policies from at most 48 KiB of inline headers, without fetching media.
litellm/litellm_core_utils/token_counter.py:597
↓ 8 callersMethodevents_for_query
Every ingested event the search query matches (failure payloads carry no prompt to mark, so failure scenarios query indexed attributes
tests/e2e/logging/datadog_reader.py:130
↓ 8 callersFunctioneventstream_event
(event_type: str, payload: JsonValue, message_type: str = "event")
tests/code_coverage_tests/test_provider_cache.py:916
↓ 8 callersMethodevict_local
(self, model_id: str)
litellm/redis/stores/router_cooldowns/__init__.py:36
↓ 8 callersFunctionexpected
(marker: str)
tests/integration/routing/test_reasoning_effort_levels_wire.py:101
↓ 8 callersFunctionextract_custom_tool_names
Extract names of ``type: "custom"`` tools, at the top level or one level inside a ``namespace`` tool.
litellm/responses/litellm_completion_transformation/custom_tools.py:75
↓ 8 callersMethodextract_error_message
Extract error message from various provider response formats. Handles: - Bedrock: {"detail": {"message": "..."}} - A
litellm/anthropic_interface/exceptions/exception_mapping_utils.py:75
↓ 8 callersMethodextract_fields
Extract field values from data using JSONPath-like expressions. Supports simple expressions like: - "query" -> data["query"]
litellm/proxy/pass_through_endpoints/jsonpath_extractor.py:16
↓ 8 callersFunctionextract_images_from_message
Extract images from a message. For data URLs (e.g., "data:image/png;base64,iVBOR..."), only the base64 data portion is extracted. This i
litellm/litellm_core_utils/prompt_templates/common_utils.py:1362
↓ 8 callersFunctionextract_model_id_from_unified_id
Extract model ID from a unified resource ID. Args: unified_id: The unified resource ID (decoded or encoded) Returns: Mo
litellm/llms/base_llm/managed_resources/utils.py:184
↓ 8 callersFunctionextract_model_name_from_bedrock_arn
Extract the model name from an AWS Bedrock ARN. Returns the string after the last '/' if 'arn' is in the input string.
litellm/llms/bedrock/common_utils.py:1192
↓ 8 callersFunctioney
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 8 callersFunctionf
(e,t,n)
litellm/proxy/_experimental/out/_next/static/chunks/0dvgjd47fte1d.js:1
↓ 8 callersFunctionfake_sagemaker_session
(response_body: object)
tests/unit/llms/sagemaker/test_sagemaker_embedding_openai.py:40
↓ 8 callersMethodfile_content
( self, _is_async: bool, file_content_request: FileContentRequest, api_base: s
litellm/llms/openai/openai.py:1875
↓ 8 callersFunctionfinalize_cost
(amount: float, breakdown: CostBreakdown | None, allowance_discount: float = 0.0)
litellm/litellm_core_utils/llm_cost_calc/finalization.py:41
↓ 8 callersMethodfind_invalid_scope_entries
Validate the concrete scope entries of a policy attachment. Returns an error for every non-wildcard entry that does not resolve to a
litellm/proxy/policy_engine/policy_validator.py:172
↓ 8 callersMethodfind_many
( self, where: Mapping[str, object] | None = None, order: Mapping[str, str] | None = N
litellm/proxy/policy_engine/policy_registry.py:114
↓ 8 callersMethodfind_many
( self, *, where: Mapping[str, str | int], order: Mapping[str, str] = ...,
litellm/proxy/prompts/prompt_endpoints.py:92
↓ 8 callersMethodfind_unique
(self, where: Mapping[str, object])
litellm/proxy/management_endpoints/organization_endpoints.py:124
↓ 8 callersMethodfind_unique
(self, *, where: Mapping[str, object])
litellm/proxy/management_endpoints/model_management_endpoints.py:275
↓ 8 callersMethodfinish_span
Stamp attributes + status on an already-started ``span`` and end it. The counterpart to :meth:`start_span` for callers that own a span's
litellm/integrations/otel/emitter.py:270
↓ 8 callersMethodflush_queue
(self)
litellm/integrations/datadog/datadog.py:445
↓ 8 callersFunctionfollowup_request
(request: Mapping[str, JsonValue], response: Mapping[str, JsonValue])
tests/integration/translation/chat_completions/cross_model/contracts.py:345
↓ 8 callersFunctionformatGuardrailMode
(raw: unknown)
ui/litellm-dashboard/src/app/(dashboard)/guardrails/_components/guardrail_info_helpers.tsx:229
↓ 8 callersMethodforward_headers_from_request
Helper to forward headers from original request. Also handles 'x-pass-' prefixed headers which are always forwarded with the
litellm/passthrough/utils.py:59
↓ 8 callersMethodfromJSON
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 8 callersFunctionfromURIReference
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersMethodfrom_json
(cls, raw: object)
tests/e2e/cli_harness/npm_version_resolver.py:33
↓ 8 callersFunctionfunction
(name: str)
tests/integration/_support/tool_search.py:35
↓ 8 callersFunctiong
(e,s)
litellm/proxy/_experimental/out/_next/static/chunks/0-i21ejarohtj.js:1
↓ 8 callersFunctiongemini_deployment
(scenario: Scenario, wire_url: str, **extra: JsonValue)
tests/integration/providers/_gemini_tts_voice_support.py:163
↓ 8 callersFunctiongemini_frame
(text: str)
tests/integration/observability/test_presidio_streaming_output.py:27
← previousnext →9,201–9,300 of 202,479, ranked by callers