MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions202,479 in github.com/BerriAI/litellm

↓ 8 callersMethodgemini_passthrough_handler
( httpx_response: httpx.Response, response_body: dict, logging_obj: LiteLLMLoggingObj,
litellm/proxy/pass_through_endpoints/llm_provider_handlers/gemini_passthrough_logging_handler.py:44
↓ 8 callersFunctiongemini_provider
(reply: Reply)
tests/integration/observability/test_presidio_streaming_output.py:259
↓ 8 callersFunctiongenerate_provider_endpoints_support
( cost_map: Mapping[str, JsonValue], current_json: Mapping[str, JsonValue], )
scripts/generate_provider_endpoints_support.py:181
↓ 8 callersMethodget
( self, url: str, params: dict | None = None, headers: Mapping[str, Any] | Non
litellm/llms/custom_httpx/http_handler.py:1629
↓ 8 callersFunctiongetAgentsList
(accessToken: string, healthCheck: boolean = false)
ui/litellm-dashboard/src/components/networking.tsx:5710
↓ 8 callersMethodgetCurrentQuery
()
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 8 callersFunctiongetExtensions
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctiongetMcpOAuthMode
(s: { auth_type?: string | null; oauth2_flow?: string | null; delegate_auth_to_upstream?: boolean | null
ui/litellm-dashboard/src/components/mcp_tools/types.tsx:256
↓ 8 callersMethodgetQueryData
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0tx19jeq-wskb.js:2
↓ 8 callersMethodget_access_token
(self)
litellm/llms/chatgpt/authenticator.py:96
↓ 8 callersMethodget_access_token
Get access token and project id 1. Check if credentials are already in self._credentials_project_mapping 2. If not, load cre
litellm/llms/vertex_ai/vertex_llm_base.py:937
↓ 8 callersMethodget_account_id
(self, access_token: str | None = None)
litellm/llms/chatgpt/authenticator.py:131
↓ 8 callersMethodget_agent_list
(self)
litellm/proxy/auth/handle_jwt.py:189
↓ 8 callersFunctionget_agent_with_read_through
(agent_id_or_name: str)
litellm/proxy/common_utils/registry_read_through.py:334
↓ 8 callersMethodget_all_attachments
Get all loaded attachments. Returns: List of all PolicyAttachment objects
litellm/proxy/policy_engine/attachment_registry.py:227
↓ 8 callersMethodget_all_callbacks
Get all callbacks from litellm.callbacks, litellm.success_callback, litellm.failure_callback, litellm._async_success_callback, litellm._async
litellm/litellm_core_utils/logging_callback_manager.py:417
↓ 8 callersMethodget_api_key
Resolve xAI API keys while preserving endpoint-specific legacy order. Chat uses xai_key before XAI_API_KEY without adding a generic
litellm/llms/xai/common_utils.py:65
↓ 8 callersFunctionget_authorized_credentials_for_model
``get_credentials_for_model`` gated by ``authorize_model_for_key``.
litellm/proxy/openai_files_endpoints/common_utils.py:512
↓ 8 callersFunctionget_auto_router_classifier_default_prompt
Get the classifier system prompt a router would send, so the dashboard can show it. The prompt's closing line depends on whether prior conve
litellm/proxy/management_endpoints/model_management_endpoints.py:3829
↓ 8 callersMethodget_available_deployment
( self, model: str, messages: list[dict[str, str]] | None = None, input: str |
tests/unit/test_router/test_router.py:18138
↓ 8 callersFunctionget_azure_ad_token_from_entra_id
Get Azure AD token provider from `client_id`, `client_secret`, and `tenant_id` Args: tenant_id: str client_id: str c
litellm/llms/azure/common_utils.py:320
↓ 8 callersMethodget_azure_client
( self, api_key: str | None, api_base: str | None, api_version: str | None,
litellm/llms/azure/assistants.py:40
↓ 8 callersMethodget_bedrock_model_id
( optional_params: dict, provider: BEDROCK_INVOKE_PROVIDERS_LITERAL | None, model: str
litellm/llms/bedrock/base_aws_llm.py:573
↓ 8 callersFunctionget_budget_window_start
(window: object)
litellm/proxy/spend_tracking/budget_reservation.py:1286
↓ 8 callersMethodget_cache
(self, key: str)
litellm/router_utils/pre_call_checks/prompt_caching_deployment_check.py:60
↓ 8 callersMethodget_cache
(self, key: str, **kwargs: object)
tests/unit/test_utils.py:5998
↓ 8 callersFunctionget_chatgpt_client_credential
(headers: Mapping[str, str])
litellm/llms/chatgpt/common_utils.py:316
↓ 8 callersMethodget_combined_callback_list
( self, dynamic_success_callbacks: list[str | Callable[..., object] | CustomLogger] | None,
litellm/litellm_core_utils/litellm_logging.py:5136
↓ 8 callersMethodget_complete_url
Get the complete URL for the RAGFlow API call. Constructs URL based on endpoint type: - Chat: /api/v1/chats_openai/{chat_id}
litellm/llms/ragflow/chat/transformation.py:63
↓ 8 callersMethodget_config_class
(cls, model: str | None)
litellm/llms/bedrock/image_edit/handler.py:63
↓ 8 callersFunctionget_config_general_settings
( field_name: str, user_api_key_dict: UserAPIKeyAuth = Depends(user_api_key_auth), )
litellm/proxy/proxy_server.py:21046
↓ 8 callersMethodget_configured_service_tiers
(self, model_name: str, team_id: str | None = None)
litellm/router_deprecated.py:601
↓ 8 callersMethodget_cost_for_file_search
" OpenAI: $2.50/1k calls Azure: $0.1 USD per 1 GB/Day (storage-based pricing) Doc: https://platform.openai.com/docs/pricing#
litellm/litellm_core_utils/llm_cost_calc/tool_call_cost_tracking.py:703
↓ 8 callersMethodget_credentials
(self, prisma_client: PrismaClient)
litellm/proxy/proxy_server.py:9980
↓ 8 callersFunctionget_daily_activity_aggregated
( *, prisma_client: PrismaClient, table_name: str, entity_id_field: str, entity_id: str |
tests/unit/proxy/management_endpoints/test_common_daily_activity.py:374
↓ 8 callersMethodget_data
(self, *args, **kwargs)
tests/unit/proxy/auth/test_resolvers_store.py:38
↓ 8 callersFunctionget_default_base_url
Pick the host that issued the key: MongoDB-issued keys (``al-`` prefix) are only valid on ai.mongodb.com, every other key on api.voyageai.com
litellm/llms/voyage/common_utils.py:24
↓ 8 callersMethodget_default_injection_points
Default breakpoints when ``litellm.enable_anthropic_prompt_caching`` is on. ``enable_prompt_caching`` is the per-request override (stamped fr
litellm/integrations/anthropic_cache_control_hook.py:1571
↓ 8 callersMethodget_deployments_by_pattern
Get the deployments by pattern Args: model: str custom_llm_provider: Optional[str] Returns:
litellm/litellm_core_utils/pattern_match_deployments.py:263
↓ 8 callersFunctionget_end_user_id_for_cost_tracking
Used for enforcing `disable_end_user_cost_tracking` param. service_type: "litellm_logging" or "prometheus" - used to allow prometheus only d
litellm/utils.py:11730
↓ 8 callersFunctionget_env_int
Parse an environment variable as an integer, falling back to default when it is unset, blank or unparsable. An unparsable value is warned about o
litellm/litellm_core_utils/env_utils.py:52
↓ 8 callersMethodget_error_class
( self, error_message: str, status_code: int, headers: dict | httpx.Headers,
litellm/llms/fal_ai/chat/transformation.py:244
↓ 8 callersMethodget_error_class
(self, error_message: str, status_code: int, headers: dict | httpx.Headers)
litellm/llms/openai/videos/transformation.py:459
↓ 8 callersFunctionget_fallback
Get fallback configuration for a specific model. **Parameters:** - `model`: The model name to get fallbacks for - `fallback_type`: T
litellm/proxy/management_endpoints/fallback_management_endpoints.py:328
↓ 8 callersFunctionget_file_ids_from_messages
Gets file ids from messages
litellm/litellm_core_utils/prompt_templates/file_id_utils.py:612
↓ 8 callersMethodget_job
(self, job_id)
tests/unit/proxy/openai_files_endpoint/test_files_common_utils.py:135
↓ 8 callersFunctionget_key_end_user_budget_id
The default budget a key assigns to end users that carry no budget of their own.
litellm/proxy/auth/auth_checks.py:1737
↓ 8 callersFunctionget_latest_release_info
( client: _AsyncGetClient, cache: InMemoryCache, fetch_lock: asyncio.Lock )
litellm/proxy/ui_crud_endpoints/latest_release_endpoints.py:203
↓ 8 callersFunctionget_litellm_managed_vector_store
Resolve a LiteLLM-managed vector store from the registry or shared cache. Provider-native vector store IDs will not be present in either loc
litellm/proxy/vector_store_endpoints/utils.py:262
↓ 8 callersMethodget_local
This worker's memory copy alone.
litellm/proxy/common_utils/user_api_key_cache.py:160
↓ 8 callersMethodget_mcp_server_access
Get list of allowed MCP servers for the given user/key based on permissions. Permission hierarchy (all rules are intersections):
litellm/proxy/mcp_server/auth/user_api_key_auth_mcp.py:2066
↓ 8 callersFunctionget_model_cost_key
Get the actual key from model_cost, with case-insensitive fallback. WARNING: Only O(1) lookup operations are acceptable. O(n) lookups will c
litellm/utils.py:6873
↓ 8 callersMethodget_model_id_from_response_id
Get the model_id from the response_id
litellm/responses/utils.py:808
↓ 8 callersMethodget_models
List all models available on the Ollama server via /api/tags endpoint.
litellm/llms/ollama/common_utils.py:155
↓ 8 callersFunctionget_order_filtered_deployments
( healthy_deployments: list[dict[str, object]], target_order: int | None = None, )
litellm/utils.py:6419
↓ 8 callersMethodget_pattern
Check if a pattern exists for the given model and custom llm provider Args: model: str custom_llm_provider:
litellm/litellm_core_utils/pattern_match_deployments.py:249
↓ 8 callersFunctionget_provider_affinity_header
(api_base: str | None)
litellm/litellm_core_utils/get_llm_provider_logic.py:1025
↓ 8 callersMethodget_provider_config
Get the provider configuration for a given custom_llm_provider. Args: custom_llm_provider: The provider identifier (e.g.
litellm/a2a_protocol/providers/config_manager.py:18
↓ 8 callersMethodget_provider_image_edit_config
( model: str, provider: LlmProviders, )
litellm/utils.py:11450
↓ 8 callersFunctionget_provider_models
Returns the list of known models by provider
litellm/proxy/auth/model_checks.py:75
↓ 8 callersMethodget_provider_passthrough_config
( model: str, provider: LlmProviders, )
litellm/utils.py:10899
↓ 8 callersMethodget_provider_text_to_speech_config
Get text-to-speech configuration for a given provider.
litellm/utils.py:11633
↓ 8 callersFunctionget_redis_url_from_environment
()
litellm/_redis.py:484
↓ 8 callersFunctionget_regional_uplift_multiplier
Resolve the per-model regional-processing uplift multiplier for a given data-residency region. OpenAI applies a flat percentage uplift (
litellm/litellm_core_utils/llm_cost_calc/utils.py:1411
↓ 8 callersFunctionget_request_route_template
Return the low-cardinality route template, e.g. ``/v1/threads/{thread_id}/runs`` (vs. the literal path from ``get_request_route``). FastA
litellm/proxy/auth/auth_utils.py:1093
↓ 8 callersMethodget_responses
Get a response by ID Uses GET /v1/responses/{response_id} endpoint in the responses API
litellm/llms/custom_httpx/llm_http_handler.py:3633
↓ 8 callersFunctionget_secret_from_manager
( client: &SecretManager, secret_name: &str, _settings: &KeyManagementSettings, environment: &
litellm-rust/crates/secrets/src/handler.rs:70
↓ 8 callersFunctionget_semantic_cache_prompt_from_messages
The text a semantic cache embeds for a request: `get_str_from_messages` plus the text inside Messages API `tool_result` blocks, so a tool tur
litellm/litellm_core_utils/prompt_templates/common_utils.py:376
↓ 8 callersMethodget_service_client
(self)
litellm/integrations/azure_storage/azure_storage.py:383
↓ 8 callersFunctionget_service_tier_from_standard_logging_payload
Resolve the service tier a request ran on, for the Prometheus ``service_tier`` label. The tier the provider actually served wins over the ti
litellm/litellm_core_utils/service_tier_utils.py:51
↓ 8 callersFunctionget_session_id_from_request_data
Extract session_id from request data (litellm_session_id or metadata).
litellm/integrations/custom_guardrail.py:177
↓ 8 callersMethodget_state
Get current polling state from Redis
litellm/proxy/response_polling/polling_handler.py:236
↓ 8 callersFunctionget_storage_backend
Factory function to create a storage backend instance. Backends are configured using the same environment variables as their correspondi
litellm/llms/base_llm/files/storage_backend_factory.py:21
↓ 8 callersMethodget_structured_messages
Convert Responses API request data to OpenAI-spec structured messages. Transforms `input` (string or ResponseInputParam) and optiona
litellm/llms/openai/responses/guardrail_translation/handler.py:781
↓ 8 callersMethodget_sync_custom_stream_wrapper
( self, model: str, custom_llm_provider: str, logging_obj: LiteLLMLoggingObj,
litellm/llms/oci/chat/transformation.py:757
↓ 8 callersFunctionget_usage_object
( completion_response: object, )
litellm/cost_calculator.py:1307
↓ 8 callersMethodget_user_id
(self, token: dict, default_value: str | None)
litellm/proxy/auth/handle_jwt.py:591
↓ 8 callersFunctionget_user_id_from_request
Get the user id from the request
litellm/proxy/management_endpoints/internal_user_endpoints.py:776
↓ 8 callersMethodget_user_role_from_app_roles
Resolve the one role LiteLLM stores for a user from their Entra app roles. Entra does not guarantee `roles` claim ordering, so a use
litellm/proxy/management_endpoints/ui_sso.py:4823
↓ 8 callersMethodget_vector_store_url
Url of one vector store for retrieve, update and delete. Providers whose ``get_complete_url`` adds a query string, like Azure, override this.
litellm/llms/base_llm/vector_store/transformation.py:230
↓ 8 callersFunctionget_vertex_ai_model_route
Determine which handler to use for a Vertex AI model based on the model name. Args: model: The model name (e.g., "llama3-405b", "gem
litellm/llms/vertex_ai/common_utils.py:262
↓ 8 callersFunctionget_web_search_requests_from_usage
Read ``web_search_requests`` from a ``Usage``'s ``server_tool_use``. ``Usage`` deletes unset optional fields from ``__dict__`` (see ``SafeAtt
litellm/litellm_core_utils/llm_cost_calc/utils.py:173
↓ 8 callersFunctiongit_blob_id
(body: bytes)
litellm/litellm_core_utils/get_model_cost_map.py:65
↓ 8 callersFunctionh
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/2_9r2jeem0dh8.js:1
↓ 8 callersFunctionh5
(e,t,n=0)
litellm/proxy/_experimental/out/_next/static/chunks/085r5ieqhajig.js:10
↓ 8 callersFunctionhandle_invalid_parallel_tool_calls
Handle hallucinated parallel tool call from openai - https://community.openai.com/t/model-tries-to-call-unknown-function-multi-tool-use-parallel/
litellm/litellm_core_utils/llm_response_utils/convert_dict_to_response.py:550
↓ 8 callersFunctionhandle_key_type
Handle the key type.
litellm/proxy/management_endpoints/key_management_endpoints.py:985
↓ 8 callersMethodhandle_logging_collected_chunks
( self, all_chunks: Sequence[str], litellm_logging_obj: Logging, model: str,
litellm/llms/vllm/passthrough/transformation.py:88
↓ 8 callersFunctionhandle_messages_with_content_list_to_str_conversion
Returns new messages with each content list flattened to a string, leaving the caller's messages untouched
litellm/litellm_core_utils/prompt_templates/common_utils.py:267
↓ 8 callersFunctionhandle_oauth2_proxy_request
Resolve a ``UserAPIKeyAuth`` from request headers per the admin-set ``oauth2_config_mappings``. The auth model assumes the proxy is depl
litellm/proxy/auth/oauth2_proxy_hook.py:40
↓ 8 callersMethodhandler
()
terraform/provider/litellm/resource_key_test.go:1088
↓ 8 callersFunctionhasCapability
( userRole: string | null | undefined, capability: Capability, isOrgAdmin: boolean = false, )
ui/litellm-dashboard/src/utils/capabilities.ts:27
↓ 8 callersFunctionhasProxyWideSpendView
(userRole: string | null)
ui/litellm-dashboard/src/utils/roles.ts:155
↓ 8 callersFunctionhas_tool_with_name
Check whether a tools list (as sent to an LLM) includes a tool with the given name, regardless of shape: OpenAI-style function tools (``{
litellm/litellm_core_utils/prompt_templates/factory.py:6549
↓ 8 callersFunctionhash
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 8 callersFunctionhashed
(key: str)
tests/integration/spend/_background_responses.py:221
↓ 8 callersFunctionhealth_readiness
Public readiness probe. Returns a low-detail payload safe to expose to unauthenticated load balancers — `status` plus `db` so orchestrators a
litellm/proxy/health_endpoints/_health_endpoints.py:2330
↓ 8 callersFunctionhidden
(stream: object)
tests/unit/test_router/core/test_streaming_characterization_responses.py:84
↓ 8 callersFunctionhigh_detail_image_token_upper_bound
(base_tokens: int = 85, tile_tokens: int | None = None)
litellm/litellm_core_utils/token_counter.py:218
↓ 8 callersFunctionholds_compaction_summary
(input: object)
litellm/responses/litellm_completion_transformation/compaction_items.py:187
← previousnext →9,301–9,400 of 202,479, ranked by callers