MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 23 callersFunction_prisma
()
tests/unit/proxy/guardrails/test_usage_tracking.py:18
↓ 23 callersMethod_prisma
(self, jobs)
tests/unit/proxy/common_utils/test_check_batch_cost.py:2750
↓ 23 callersFunction_request_for
(path: str)
tests/unit/proxy/test_litellm_pre_call_utils.py:9380
↓ 23 callersMethod_reset_all_callbacks
Reset all callbacks to an empty list Note: this is an internal function and should be used sparingly.
litellm/litellm_core_utils/logging_callback_manager.py:404
↓ 23 callersFunction_restore_stream
(guardrail: LLMShieldProxyGuardrail, chunks: list)
tests/unit/proxy/guardrails/guardrail_hooks/test_llm_shield_proxy.py:152
↓ 23 callersFunction_scoped_authorize
( client_id: str, resource: str | None, session_user_id: str | None = "u1", scope: str | None
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:1009
↓ 23 callersFunction_scoped_mcp_server
(name="github", auth_type="oauth2", **kw)
tests/unit/proxy/mcp_server/test_gateway_dcr_flow.py:989
↓ 23 callersFunction_spend_row
(identity: str)
tests/integration/providers/test_bedrock_runtime_chat_completions_wire.py:149
↓ 23 callersFunction_stored_agent_row
(values: Mapping[str, object] | SimpleNamespace)
tests/unit/proxy/agent_endpoints/test_agent_registry.py:1219
↓ 23 callersFunction_stream_chunks
()
tests/unit/proxy/utils/proxy_logging/test_guardrail_pipeline.py:2604
↓ 23 callersFunction_token
(**overrides)
tests/unit/proxy/auth/test_fallback_budget.py:48
↓ 23 callersFunction_tool_search
(**fields: JsonValue)
tests/integration/providers/test_responses_bridge_tool_search_wire.py:101
↓ 23 callersMethod_transform_messages
(self, messages: list[AllMessageValues], model: str)
litellm/llms/openai/openai.py:247
↓ 23 callersFunction_v3_request_calls
(rig: Rig, marker: str, agent: str | None = AUDIT_AGENT)
tests/integration/observability/test_straiker_v3_platform.py:471
↓ 23 callersFunction_validate_ptu_model_info
Enforce the PTU cross-field invariant on the effective model_info. The rules live in litellm_core_utils.ptu_pricing so that config.yaml registrat
litellm/proxy/management_endpoints/model_management_endpoints.py:1106
↓ 23 callersMethodadd_update
Enqueue an update.
litellm/proxy/db/db_transaction_queue/base_update_queue.py:36
↓ 23 callersMethodaliases
model_group_alias as configured (was the ``model_group_alias`` attribute).
litellm/router_api.py:900
↓ 23 callersFunctionanswer
(marker: str)
tests/integration/_support/anthropic_thinking.py:35
↓ 23 callersMethodas_str
(self)
litellm-rust/crates/llms/src/anthropic/common_utils.rs:78
↓ 23 callersMethodasync_build_agentic_loop_plan
( self, tools: Mapping[str, object], model: str, messages: Sequence[Mapping[st
tests/unit/test_router/test_router.py:2911
↓ 23 callersMethodasync_pre_call_hook
( self, user_api_key_dict: UserAPIKeyAuth, cache: DualCache, d
tests/unit/proxy/guardrails/guardrail_hooks/azure/test_azure_prompt_shield.py:445
↓ 23 callersMethodasync_realtime
(self, **kwargs)
tests/unit/llms/bedrock/realtime/test_bedrock_realtime_handler.py:215
↓ 23 callersMethodasync_service_success_hook
(self, service: ServiceTypes, call_type: str, duration: float)
tests/unit/llms/base_llm/auth/test_token_exchange.py:1710
↓ 23 callersFunctionazure_proxy_route
Call any azure endpoint using the proxy. Just use `{PROXY_BASE_URL}/azure/{endpoint:path}` Checks if the deployment id in the url is a
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:2543
↓ 23 callersFunctionb
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 23 callersMethodbackend_calls
(self, requests: Sequence[Request])
tests/integration/_support/safeguards_rig.py:281
↓ 23 callersFunctionblind_spots
Jobs whose published names GitHub decides at run time, which no offline sweep can compare.
tests/code_coverage_tests/check_workflow_job_name_collisions.py:432
↓ 23 callersMethodbody
(self)
tests/unit/proxy/video_endpoints/test_endpoints.py:114
↓ 23 callersMethodbudget
(self, **fields: JsonValue)
tests/integration/_support/client.py:202
↓ 23 callersMethodbudget_alerts
( self, type: Literal[ "token_budget", "user_budget", "sof
litellm/proxy/utils.py:3926
↓ 23 callersMethodcancel
(self)
litellm/llms/vertex_ai/audio_transcription/realtime_backend.py:190
↓ 23 callersMethodchat
(self)
tests/integration/spend/test_shutdown_flush.py:345
↓ 23 callersFunctionchat_body
(model: str, messages: Sequence[JsonValue], **fields: JsonValue)
tests/integration/routing/_prompt_cache_pin_support.py:81
↓ 23 callersMethodchat_stream
( self, key: str, model: str, content: str, *, max_tokens: int | None = None )
tests/e2e/quota_management/spend_tracking/spend_e2e_client.py:286
↓ 23 callersFunctionclear_cli_token
Remove the credential from both stores. Reports whether the keychain is now free of it. The token file goes whatever the keychain answers, so not
litellm/litellm_core_utils/cli_token_utils.py:251
↓ 23 callersMethodclone
(&self)
litellm-rust/crates/model-catalog/src/store/mod.rs:106
↓ 23 callersMethodclone_ref
(&self, py: Python<'_>)
litellm-rust/crates/callbacks-legacy-python/src/logger.rs:24
↓ 23 callersFunctioncomplexity_marker
An ``auto_router/complexity_router`` marker with the shipped tiers and default model ``big``.
tests/unit/test_router/core/gaps_l11100_helpers.py:39
↓ 23 callersMethodcontains
(&self, beta: &AnthropicBeta)
litellm-rust/crates/llms-types/src/providers/anthropic/beta.rs:453
↓ 23 callersFunctioncreated
(identity: str)
tests/integration/_support/responses_stream.py:35
↓ 23 callersFunctiondeployment
( scenario: Scenario, group: str, litellm_params: Mapping[str, JsonValue], *, model_info:
tests/integration/routing/test_payment_required_mapping.py:77
↓ 23 callersFunctioneb
(e,s)
litellm/proxy/_experimental/out/_next/static/chunks/1a2lzi3ursud4.js:1
↓ 23 callersFunctionencoded
(row: dict[str, JsonValue])
tests/integration/providers/_vertex_batch_rows.py:100
↓ 23 callersFunctionendpoint_func
( request: Request, fastapi_response: Response, user_api_key_dict: UserAPI
litellm/proxy/pass_through_endpoints/pass_through_endpoints.py:2349
↓ 23 callersMethodexecute_raw
(self, query: str, *args: object)
tests/integration/spend/test_session_grouped_logs_pages.py:331
↓ 23 callersMethodexecute_tool_calls
Execute tool calls and return results.
litellm/responses/mcp/litellm_proxy_mcp_handler.py:729
↓ 23 callersFunctionfailed
(replicas: tuple[Replica, ...], marker: str)
tests/e2e/migrations/containers.py:125
↓ 23 callersFunctionfetchAvailableModels
(accessToken: string)
ui/litellm-dashboard/src/components/llm_calls/fetch_models.tsx:58
↓ 23 callersFunctionfind_request_attachments
( data: Mapping[str, object], call_type: str, skip_tool_messages: bool, latest_user_message_on
litellm/llms/bedrock/guardrail_attachments.py:80
↓ 23 callersMethodfrom_dict
Create a LiteLLMSendMessageResponse from a dict. Args: response_dict: Dict with A2A response structure reque
litellm/types/agents.py:545
↓ 23 callersMethodgetAll
()
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 23 callersMethodgetQueryCache
()
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 23 callersFunctionget_attachment_registry
Get the global AttachmentRegistry singleton. Returns: The global AttachmentRegistry instance
litellm/proxy/policy_engine/attachment_registry.py:553
↓ 23 callersMethodget_bedrock_invoke_provider
Helper function to get the bedrock provider from the model handles 3 scenarions: 1. model=invoke/anthropic.claude-3-5-sonnet
litellm/llms/bedrock/base_aws_llm.py:534
↓ 23 callersMethodget_cli_jwt_auth_token
Generate a JWT token for CLI authentication with configurable expiration. The expiration time can be controlled via the LITELLM_CLI_
litellm/proxy/auth/auth_checks.py:4110
↓ 23 callersMethodget_credential_values
Safe accessor for credentials.
litellm/litellm_core_utils/credential_accessor.py:24
↓ 23 callersFunctionget_current_spend
Read current spend from the cross-pod spend counter. Reads Redis FIRST (authoritative cross-pod value), not DualCache's async_get_cache
litellm/proxy/proxy_server.py:3401
↓ 23 callersMethodget_deployment
(self, model_id: str)
tests/unit/proxy/policy_engine/test_response_retrieval.py:27
↓ 23 callersMethodget_local
(self, counter: str)
litellm/redis/stores/spend_counters/__init__.py:139
↓ 23 callersMethodget_mcp_server_by_id
(self, server_id: str)
litellm/proxy/mcp_server/server_resolution.py:18
↓ 23 callersMethodhasListeners
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 23 callersFunctioni
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2aatum0yo4cv8.js:1
↓ 23 callersMethodindex
(e)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 23 callersMethodinitialize
(self)
tests/integration/_support/mcp.py:707
↓ 23 callersMethodis_database_service_unavailable_error
True iff the exception means the database could not answer at the infrastructure level (connection refused, socket/interface failure,
litellm/proxy/db/exception_handler.py:442
↓ 23 callersMethodjson
(self)
litellm/llms/compactifai/chat/transformation.py:29
↓ 23 callersMethodjson
(self)
tests/unit/proxy/guardrails/guardrail_hooks/test_presidio.py:60
↓ 23 callersFunctionjwt_key_mapping_cache_key
Cache key under which a JWT-claim-to-key mapping is stored, scoped to one issuer (or the issuer-agnostic/global scope when ``jwt_issuer`` is falsy
litellm/proxy/auth/auth_checks.py:4275
↓ 23 callersMethodlabels
(self, *args, **kwargs)
tests/unit/enterprise/integrations/test_prometheus.py:750
↓ 23 callersMethodload_policies
Load policies from a configuration dictionary. Args: policies_config: Dictionary mapping policy names to policy definiti
litellm/proxy/policy_engine/policy_registry.py:194
↓ 23 callersMethodmap_openai_params
( self, response_api_optional_params: ResponsesAPIOptionalRequestParams, model: str,
litellm/llms/bedrock_mantle/responses/transformation.py:257
↓ 23 callersFunctionmarker_of
(request: Request)
tests/integration/providers/_cache_control_marks_support.py:193
↓ 23 callersMethodmodel_dump
Default to exclude_unset to avoid Pydantic serializer warnings for OpenAIObject-derived types.
litellm/types/utils.py:2303
↓ 23 callersFunctionnamespace
A namespace with the stubs, `StubLogger` and a fresh `logger`, after `script` ran in it.
litellm-rust/crates/callbacks-legacy-python/src/test_support.rs:167
↓ 23 callersFunctionnew_marker
()
tests/integration/routing/test_per_model_rate_limit_fallbacks.py:87
↓ 23 callersFunctionparse
(event: &SseEvent)
litellm-rust/crates/llms/src/base_llm/sse.rs:68
↓ 23 callersFunctionplugin_name
()
tests/integration/management/test_claude_code_plugin_installation_preference.py:37
↓ 23 callersFunctionpoll_and_log_background_interaction_cost
( context: BackgroundInteractionPollContext, fetch_interaction: FetchInteraction = fetch_background_in
litellm/interactions/background_cost_polling.py:509
↓ 23 callersMethodpre_call
(self, input, api_key, model=None, additional_args=None)
litellm/types/utils.py:4882
↓ 23 callersFunctionprint_startup_message
Write a boot-time message meant for the operator's terminal. LITELLM_SUPPRESS_STARTUP_OUTPUT or litellm_settings.suppress_startup_output turns ev
litellm/_logging.py:959
↓ 23 callersFunctionprint_verbose
(print_statement: object)
litellm/litellm_core_utils/streaming_handler.py:253
↓ 23 callersFunctionprovider_texts
(provider: Wire)
tests/integration/observability/azure_dispatch_support.py:187
↓ 23 callersFunctionproxy_startup_event
(app: FastAPI)
litellm/proxy/proxy_server.py:1598
↓ 23 callersFunctionraise_if_required_body_param_missing
( route_type: str, data: Mapping[str, object], llm_router: LitellmRouter | None, )
litellm/proxy/route_llm_request.py:433
↓ 23 callersFunctionregister
( gateway: Gateway, cleanups: Callable[..., object], name: str, url: str, litellm_params:
tests/integration/compatibility/_a2a_peers.py:216
↓ 23 callersMethodrelease_lock
Release the lock if the current pod holds it. Uses an atomic Lua compare-and-delete to prevent TOCTOU races where a stale own
litellm/proxy/db/db_transaction_queue/pod_lock_manager.py:122
↓ 23 callersFunctionresolve
(...rows: AutoRouterDeployment[])
ui/litellm-dashboard/src/components/add_model/auto_setup.test.ts:18
↓ 23 callersFunctionresolve_non_empty
( value: Option<&str>, env_lookup: &dyn Fn(&str) -> Option<String>, names: &[&str], )
litellm-rust/crates/core-utils/src/settings.rs:40
↓ 23 callersMethodresponse_cost_calculator
Calculate response cost using result + logging object variables. used for consistent cost calculation across response headers + logg
litellm/litellm_core_utils/litellm_logging.py:2141
↓ 23 callersFunctionrun
(py: Python<'_>, locals: &Bound<'_, PyDict>, code: &CStr)
litellm-rust/crates/callbacks-legacy-python/src/test_support.rs:175
↓ 23 callersMethodrun
(mut self)
litellm-rust/crates/host-python/src/driver.rs:149
↓ 23 callersMethodsave_config
(self, new_config: Mapping[str, object], include_env_vars: bool = False)
litellm/proxy/proxy_server.py:6096
↓ 23 callersFunctionscenario_identity
( scenario: Scenario, provider: Wire, *, spend_logs_metadata: Mapping[str, object] | None = No
tests/integration/observability/_langfuse_otel_metadata_support.py:327
↓ 23 callersMethodscrollIntoView
()
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:1
↓ 23 callersMethodset
(&self, key: &str, value: V, ttl: Option<Duration>)
litellm-rust/crates/redis-store/src/memory.rs:41
↓ 23 callersFunctionset_auth_context
Set the UserAPIKeyAuth in the auth context variable. Args: user_api_key_auth: UserAPIKeyAuth object mcp_auth
litellm/proxy/mcp_server/server.py:3070
↓ 23 callersFunctionset_hidden_param
(obj: object, key: str, value: object)
litellm/litellm_core_utils/hidden_params.py:142
↓ 23 callersFunctionsettle
Let the tasks a call scheduled run.
tests/unit/test_router/core/test_parity_cooldown_service_model.py:86
↓ 23 callersMethodsetup_canadian_guardrail
Setup guardrail with all Canadian PII patterns (mimics the policy template)
tests/unit/proxy/guardrails/guardrail_hooks/content_filter/test_ca_policy_e2e.py:21
↓ 23 callersMethodsource
(self, key: str)
litellm/proxy/config_resolvers/settings_store.py:107
← previousnext →2,301–2,400 of 202,479, ranked by callers