MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 6 callersMethodclose
(self)
litellm/llms/bedrock/realtime/handler.py:133
↓ 6 callersMethodclose
(self)
tests/unit/litellm_core_utils/test_streaming_handler.py:9517
↓ 6 callersMethodclose
(self)
tests/unit/llms/vertex_ai/audio_transcription/test_vertex_ai_realtime_backend.py:66
↓ 6 callersMethodclose
(self)
tests/unit/integrations/gitlab/test_gitlab_client.py:64
↓ 6 callersFunctioncodex_catalog_rows
`rows` joined with the router's configured metadata, looked up by each entry's internal id so team-scoped rows resolve the way the Anthropic listi
litellm/proxy/common_utils/codex_model_catalog.py:680
↓ 6 callersFunctioncodex_run
(*, exit_code: int, stdout: str, stderr: str)
tests/e2e/codex/run.py:179
↓ 6 callersFunctioncoerce_keepalive_interval
(ping_interval_seconds: float | str | None)
litellm/proxy/common_utils/sse_keepalive.py:22
↓ 6 callersMethodcompact
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2hk8n3azev--d.js:14
↓ 6 callersMethodcompare_versions
Compare two policy versions and return field-by-field diffs. Args: policy_id_a: First policy version ID poli
litellm/proxy/policy_engine/policy_registry.py:995
↓ 6 callersMethodcompletion
( self, *args, **kwargs )
litellm/completion_extras/litellm_responses_transformation/handler.py:164
↓ 6 callersMethodcompletion_prompt_to_str
Normalize OpenAI ``/v1/completions`` ``prompt`` for text DLP. Supports string prompts and list-of-string prompts. List-of-token-id prompts
litellm/proxy/guardrails/guardrail_hooks/microsoft_purview/base.py:409
↓ 6 callersFunctionconfig
(settings: HttpSettings)
litellm-rust/crates/http/src/tls.rs:330
↓ 6 callersFunctionconfigure_background_interaction_settlement
( table: _SettlementTableActions, spend_logs: _SpendLogLookup, spend_logs_kept: Callable[[], bool]
litellm/proxy/spend_tracking/background_interaction_settlement.py:331
↓ 6 callersFunctionconfigure_background_settlement_store
(store: BackgroundSettlementStore)
litellm/interactions/background_cost_polling.py:176
↓ 6 callersFunctionconfigure_proxy
Yields a callable that sets ``oauth2_config_mappings`` and ``trusted_proxy_ranges`` on the proxy_server module for the duration of one te
tests/unit/proxy/auth/test_oauth2_proxy_hook.py:41
↓ 6 callersFunctionconfirmed_history
(database: Database)
tests/e2e/migrations/checks.py:64
↓ 6 callersMethodconnect
( self, uri: str, *, additional_headers: Mapping[str, str], max_size:
litellm/llms/custom_httpx/llm_http_handler.py:314
↓ 6 callersMethodconnect
( cls, *, url: str, headers: dict[str, str], timeout_seconds: float |
tests/unit/responses/test_rust_bridge_websocket.py:31
↓ 6 callersMethodconnection_url
(self)
litellm/llms/valkey/vector_stores/transformation.py:113
↓ 6 callersMethodcontent
(self)
litellm/litellm_core_utils/tokenizer.py:403
↓ 6 callersFunctioncontent_text
(deltas: Sequence[Mapping[str, JsonValue]])
tests/integration/_support/anthropic_thinking.py:200
↓ 6 callersFunctioncontext
(prompt: &str)
litellm-rust/crates/cache-qdrant-semantic/tests/qdrant.rs:72
↓ 6 callersFunctionconvert_mid_conversation_system_turns
( messages: Sequence[Mapping[str, object]], )
litellm/llms/anthropic/messages/native/mid_conversation_system.py:69
↓ 6 callersFunctionconvert_model_response_to_streaming
Convert a ModelResponse to ModelResponseStream. This function transforms a standard completion response into a streaming chunk format by
litellm/llms/base_llm/base_model_iterator.py:42
↓ 6 callersMethodconvert_to_chat_model_response_object
( self, response_object: TextCompletionResponse | None = None, model_response_object:
litellm/llms/openai/completion/transformation.py:83
↓ 6 callersFunctionconvert_usage
(usage_data: Mapping[str, int])
litellm/llms/gigachat/utils.py:10
↓ 6 callersFunctionconverted_stream_requested
(params: Mapping[str, object])
litellm/types/integrations/custom_logger.py:49
↓ 6 callersFunctioncoordination_redis_cache
()
litellm/proxy/common_utils/config_sync_pubsub.py:87
↓ 6 callersFunctioncoordination_resolution
(yaml: &str, environment: &[(&str, &str)])
litellm-rust/crates/gateway/src/redis/surface_tests.rs:41
↓ 6 callersMethodcount
(self)
litellm/integrations/prometheus.py:146
↓ 6 callersMethodcount
(self, where)
tests/unit/proxy/management_endpoints/test_key_management_endpoints.py:17862
↓ 6 callersFunctioncount_live_proxy_workers
The number of workers with a recent heartbeat, or None when the database cannot answer. Callers must treat None as "unknown", not as zero. Al
litellm/proxy/db/proxy_worker_heartbeat.py:93
↓ 6 callersFunctioncount_of
(value: JsonValue)
tests/integration/providers/_gemini_long_decode_support.py:293
↓ 6 callersFunctioncount_tool_upstream
An MCP upstream with one tool, `count`, whose declared output schema wants an integer `n`.
tests/_support/mcp_count_tool_upstream.py:11
↓ 6 callersFunctioncount_values_encrypted_with
(database: SupportsRawQueries, signing_key: str)
litellm/proxy/db/master_key_migration.py:74
↓ 6 callersFunctioncounted_fields
(body: Mapping[str, JsonValue])
tests/integration/providers/_count_tokens_system_lift.py:80
↓ 6 callersFunctioncounters
(cache: Redis, setting: str, holder: str)
tests/integration/management/_batch_file_caps.py:320
↓ 6 callersMethodcreate
(self, data: Mapping[str, object])
litellm/proxy/mcp_server/toolset_db.py:55
↓ 6 callersMethodcreate
(self, *, data: dict[str, object])
tests/unit/proxy/mcp_server/test_db_credentials.py:502
↓ 6 callersMethodcreate
(self, endpoint: str = CHAT_ENDPOINT)
tests/unit/proxy/batches_endpoints/test_litellm_executed_batches.py:358
↓ 6 callersMethodcreate
(self, **kwargs: object)
tests/unit/proxy/common_utils/test_config_sync_pubsub.py:802
↓ 6 callersFunctioncreateTestProps
(userRole = "proxy_admin", userId = "user-1", isTeamAdmin = false)
ui/litellm-dashboard/src/components/add_model/AddModelForm.integration.test.tsx:248
↓ 6 callersMethodcreate_budget
( self, *, max_budget: float | None = None, soft_budget: float | None = None,
tests/e2e/quota_management/budgets/budget_client.py:609
↓ 6 callersFunctioncreate_chunk
(content, finish_reason=None, tool_calls=None)
tests/unit/responses/mcp/test_chat_completions_handler.py:206
↓ 6 callersMethodcreate_client
( self, timeout: float | httpx.Timeout | None, event_hooks: HTTPEventHooks | None,
litellm/llms/custom_httpx/http_handler.py:764
↓ 6 callersMethodcreate_content_filter_guardrail
(self, name: str, blocked_keyword: str, *, default_on: bool = True)
tests/e2e/guardrails/guardrails_client.py:181
↓ 6 callersMethodcreate_datadog_logging_payload
Helper function to create a datadog payload for logging Args: kwargs: request kwargs, read for its standard logging obje
litellm/integrations/datadog/datadog.py:538
↓ 6 callersMethodcreate_follow_up_input
Create follow-up input with tool results in proper format.
litellm/responses/mcp/litellm_proxy_mcp_handler.py:1094
↓ 6 callersMethodcreate_histogram
(self, service: str, type_of_request: str)
litellm/integrations/prometheus_services.py:177
↓ 6 callersMethodcreate_internal_user_audit_log
Create an audit log for an internal user. Parameters: - user_id: str - The id of the user to create the audit log for.
litellm/proxy/hooks/user_management_event_hooks.py:204
↓ 6 callersFunctioncreate_jwt_key_mapping
( data: CreateJWTKeyMappingRequest, user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth), )
litellm/proxy/management_endpoints/jwt_key_mapping_endpoints.py:164
↓ 6 callersFunctioncreate_mock_completion_response
Create a mock ModelResponse (chat completion) with various token details. This simulates responses from different providers that may or may
tests/unit/test_responses_api_bridge_non_stream.py:69
↓ 6 callersFunctioncreate_mock_credentials
Create mock AWS credentials for testing
tests/unit/llms/bedrock/rerank/test_bedrock_rerank_header_forwarding.py:56
↓ 6 callersFunctioncreate_pass_through_endpoints
Create new pass-through endpoint
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:4734
↓ 6 callersFunctioncreate_sync_endpoint_function
Create a sync SDK function from endpoint config. Uses the generic container handler instead of individual handler methods.
litellm/containers/endpoint_factory.py:49
↓ 6 callersMethodcreate_user
( self, *, username: str, email: str, password: str, group: str | None = None, groups: tuple[str, ...]
tests/e2e/idp.py:185
↓ 6 callersFunctioncreated_id
The new resource's id, which Keycloak returns only as the last segment of the Location header on a 201.
tests/e2e/idp.py:100
↓ 6 callersMethodcredentials
( self, id: str, *, form: Literal["params"] = "params", team_id: str | None = None )
litellm/router_api.py:1059
↓ 6 callersFunctioncurrent_billing_time
The pinned billing moment, or now in UTC outside a pinned block.
litellm/_internal_context.py:220
↓ 6 callersFunctioncurrent_binding_proof
( binding: MCPOAuthIdentityBinding, user_id: str, server_id: str, caller_principal_loader: Cal
litellm/proxy/mcp_server/oauth_identity_binding.py:223
↓ 6 callersFunctioncurrent_minute
`get_utc_datetime().strftime("%H-%M")`.
litellm-rust/crates/router-core/src/health.rs:62
↓ 6 callersFunctiondaily_activity_scope
( table: str, entity_id_field: str, entity_id: str | list[str] | None, exclude_entity_ids: lis
litellm/proxy/management_endpoints/common_daily_activity.py:584
↓ 6 callersFunctionde
(t)
litellm/proxy/_experimental/out/_next/static/chunks/0cz1d0mv5g_q7.js:1
↓ 6 callersMethoddecode
(&self, max_bytes: usize)
litellm-rust/crates/llms/src/base_llm/ocr/document.rs:27
↓ 6 callersFunctiondecode_managed_container_id_for_request
Decode a LiteLLM-managed container ID for upstream API calls. Returns: (original_container_id, resolved_provider, updated_litellm_params)
litellm/containers/utils.py:13
↓ 6 callersFunctiondecode_pcm16_append
( audio: JsonValue | None, max_encoded_bytes: int | None = None, error: ProtocolErrorType = Realti
litellm/llms/base_llm/realtime/transcription_protocol.py:181
↓ 6 callersMethoddecode_trusted_assertion
Verify a JWT assertion handed to the gateway's token endpoint with the issuer plumbing JWT auth already trusts, a matching ``issuers`` entry o
litellm/proxy/auth/handle_jwt.py:1322
↓ 6 callersFunctiondecode_user_provider_credential
(stored: str)
litellm/proxy/credential_endpoints/user_provider_credentials.py:76
↓ 6 callersFunctiondefault_deployment_copy
``_try_early_resolve_deployments_for_model_not_in_names``' copy of the default deployment for ``model``, raising what it raises for a value it can
litellm/router_rust/surface/registry.py:2305
↓ 6 callersFunctiondeleteConfigFieldSetting
(accessToken: string, fieldName: string)
ui/litellm-dashboard/src/components/networking.tsx:3200
↓ 6 callersMethoddelete_cache
(self, key: str)
litellm/router_strategy/least_busy.py:220
↓ 6 callersFunctiondelete_cache_team_object
Evict both keys `_cache_team_object` writes. `get_team_object` reads the id key and the JWT `team_alias_jwt_field` path reads the alias key,
litellm/proxy/auth/auth_checks.py:3400
↓ 6 callersFunctiondelete_group
Delete a group according to SCIM v2 protocol
litellm/proxy/management_endpoints/scim/scim_v2.py:3098
↓ 6 callersMethoddelete_group
(self, group_id: str)
tests/e2e/idp.py:207
↓ 6 callersMethoddelete_key
(self, key: str)
tests/e2e/access_control/access_control_client.py:77
↓ 6 callersMethoddelete_many
(self, *, where: Mapping[str, str])
litellm/proxy/prompts/prompt_endpoints.py:105
↓ 6 callersMethoddelete_team_member
(self, team_id: str, user_id: str)
tests/e2e/management/management_client.py:472
↓ 6 callersMethoddelete_vector_store_from_registry
Delete a vector store from the registry
litellm/vector_stores/vector_store_registry.py:505
↓ 6 callersFunctiondeleted_file
(*, deleted: bool = True)
tests/e2e_harness/batches/test_batch_cleanup.py:84
↓ 6 callersFunctiondeliveries
(wire: Wire)
tests/integration/providers/_anthropic_safeguards_beta_support.py:198
↓ 6 callersFunctiondeployment
( scenario: Scenario, group: str, api_base: str | None, *, order: int | None, model: s
tests/integration/routing/test_fallback_hop_foreign_encrypted_reasoning.py:303
↓ 6 callersFunctiondeployment
(id: &str, info: serde_json::Value)
litellm-rust/crates/router-core/src/health.rs:714
↓ 6 callersFunctiondeployment
(id: &str, params: Value, model_info: Value)
litellm-rust/crates/router-core/src/precall.rs:174
↓ 6 callersMethoddeployment
The deployment with this ``model_info.id`` (was ``get_deployment``).
litellm/router_api.py:370
↓ 6 callersFunctiondeployment_ptu_capacity
The sizing row a deployment resolves to: ``model_info.base_model`` first, since an Azure deployment name is arbitrary, then ``litellm_params.model
litellm/llms/azure/ptu_capacity.py:98
↓ 6 callersFunctiondeployment_supports_prefill
(deployment: object)
litellm/router_utils/pre_call_checks/continuation_prefill_check.py:52
↓ 6 callersFunctiondescribe_outcome
(outcome: MigrationOutcome)
litellm/proxy/db/master_key_migration.py:273
↓ 6 callersFunctiondestination_backends
Backends this request resolved a tenant destination for. The fan-out already carries the whole trace to those destinations, so the per-reques
litellm/integrations/otel/plumbing/context.py:499
↓ 6 callersFunctiondetached
``value`` with its plain containers (dict, list, tuple, set) copied, all the way down, so the caller's own objects can't change the router afterwa
litellm/router_config.py:69
↓ 6 callersFunctiondetail_body
(gateway: Gateway, name: str, *, key: str | None = None)
tests/integration/management/test_claude_code_plugin_installation_preference.py:108
↓ 6 callersFunctiondetect_vcr_patch_leak
()
tests/_vcr_conftest_common.py:2090
↓ 6 callersMethoddifference_update
(self, *others: Iterable[object])
litellm/router_rust/surface/indexes.py:234
↓ 6 callersFunctiondiscover_cli_auth
(base_url: str, http: Http)
litellm/proxy/client/cli/commands/pkce_login.py:195
↓ 6 callersFunctiondispatch
(action: TierSetAction)
ui/litellm-dashboard/src/components/add_model/ComplexityRouterConfig.tsx:679
↓ 6 callersMethoddispatch_failure_handlers
Route failure logging to async and/or sync handlers for this request. Mirrors ``dispatch_success_handlers``: the sync ``failure_handler`` nev
litellm/litellm_core_utils/litellm_logging.py:2884
↓ 6 callersFunctiondispatch_success_logging
( logging_obj: LiteLLMLoggingObject, result: object, start_time: datetime.datetime, end_time:
litellm/utils.py:1635
↓ 6 callersFunctiondocker
(*args: str)
tests/e2e/migrations/containers.py:25
↓ 6 callersMethoddomSelection
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 6 callersMethoddrop_partitions_older_than
DROP every partition whose whole range is older than `cutoff`.
litellm/proxy/db/db_transaction_queue/spend_logs_partition_manager.py:314
↓ 6 callersFunctiondrop_policy
(params: Mapping[str, object])
litellm/litellm_core_utils/tool_fields.py:97
← previousnext →12,801–12,900 of 202,479, ranked by callers