MCPcopy Create free account

hub / github.com/BerriAI/litellm / functions

Functions68,180 in github.com/BerriAI/litellm

↓ 9 callersFunctionget_bedrock_chat_config
Helper function to get the appropriate Bedrock chat config based on model and route. Args: model: The model name/identifier Ret
litellm/llms/bedrock/common_utils.py:1102
↓ 9 callersMethodget_bedrock_model_id
( optional_params: dict, provider: Optional[BEDROCK_INVOKE_PROVIDERS_LITERAL], model:
litellm/llms/bedrock/base_aws_llm.py:421
↓ 9 callersMethodget_cache
(self, key, **kwargs)
litellm/caching/in_memory_cache.py:207
↓ 9 callersFunctionget_config_param
Cached read of a LiteLLM_Config row; returns row, _ConfigRow shim, or None.
litellm/proxy/utils.py:2737
↓ 9 callersFunctionget_credentials_for_model
Retrieve API credentials for a model from the LLM Router. Args: llm_router: LiteLLM Router instance model_id: Model name or
litellm/proxy/openai_files_endpoints/common_utils.py:257
↓ 9 callersFunctionget_datadog_hostname
()
litellm/integrations/datadog/datadog_handler.py:19
↓ 9 callersFunctionget_form_data
Read form data from request Handles when OpenAI SDKs pass form keys as `timestamp_granularities[]="word"` instead of `timestamp_granularitie
litellm/proxy/common_utils/http_parsing_utils.py:269
↓ 9 callersFunctionget_key_models
Returns: - List of model name strings - Empty list if no models set - If model_access_groups is provided, only return models that are
litellm/proxy/auth/model_checks.py:96
↓ 9 callersMethodget_litellm_managed_vector_store_from_registry
Returns the vector store from the registry
litellm/vector_stores/vector_store_registry.py:207
↓ 9 callersMethodget_model_info
curl http://localhost:11434/api/show -d '{ "name": "mistral" }'
litellm/llms/ollama/completion/transformation.py:222
↓ 9 callersMethodget_objects
Get user, org, end-user, and team-membership objects. Returns ``(..., effective_user_id)``: JWT claim unless fuzzy lookup matched a l
litellm/proxy/auth/handle_jwt.py:1426
↓ 9 callersMethodget_prompt
Get a prompt template by ID and optional version. Args: prompt_id: The base prompt ID version: Optional vers
litellm/integrations/dotprompt/prompt_manager.py:258
↓ 9 callersMethodget_provider_audio_transcription_config
( model: str, provider: LlmProviders, )
litellm/utils.py:7952
↓ 9 callersMethodget_provider_video_config
( model: Optional[str], provider: LlmProviders, )
litellm/utils.py:8526
↓ 9 callersFunctionget_shared_realtime_ssl_context
Lazily create the SSL context reused by realtime websocket clients so we avoid import-order cycles during startup while keeping a single shar
litellm/llms/custom_httpx/http_handler.py:349
↓ 9 callersFunctionget_stored_api_key
Get the stored API key from token file. If expected_base_url is provided, the key is only returned when it was originally issued for that URL
litellm/proxy/client/cli/commands/auth.py:56
↓ 9 callersFunctionget_valid_models
Returns a list of valid LLMs based on the set environment variables Args: check_provider_endpoint: If True, will check the provider'
litellm/utils.py:6875
↓ 9 callersFunctionget_vendor_from_model
Return the OCI vendor enum for a model name. OCI GenAI uses two ``apiFormat`` values: - ``"COHERE"`` for Cohere models (``cohere.*``) -
litellm/llms/oci/chat/transformation.py:240
↓ 9 callersMethodget_vertex_ai_project
(litellm_params: dict)
litellm/llms/vertex_ai/vertex_llm_base.py:1123
↓ 9 callersMethodhandle_async_request
( self, request: httpx.Request, )
litellm/llms/custom_httpx/aiohttp_transport.py:292
↓ 9 callersMethodhandle_guardrail_response
Parse the Akto guardrail response. Returns (allowed, reason).
litellm/proxy/guardrails/guardrail_hooks/akto/akto.py:298
↓ 9 callersFunctionhandle_messages_with_content_list_to_str_conversion
Handles messages with content list conversion
litellm/litellm_core_utils/prompt_templates/common_utils.py:84
↓ 9 callersMethodhandle_non_streaming
Handle non-streaming A2A request. Args: request_id: A2A JSON-RPC request ID params: A2A MessageSendParams co
litellm/a2a_protocol/providers/base.py:18
↓ 9 callersFunctionhas_non_string_content
Return True if any inspected content is not a plain string. Used by hooks whose mask/redact path operates on string offsets and therefore can
litellm/proxy/guardrails/_content_utils.py:189
↓ 9 callersFunctioni
(e,r,n)
litellm/proxy/_experimental/out/_next/static/chunks/0.4.bbjx7y007.js:1
↓ 9 callersFunctionie
(t,e,r,n)
litellm/proxy/_experimental/out/_next/static/chunks/03~yq9q893hmn.js:1
↓ 9 callersMethodisEmpty
()
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callersFunctionisJSONReferenceLikeElement
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callersFunctionis_otel_v2_enabled
()
litellm/integrations/otel/model/config.py:52
↓ 9 callersMethodis_tool_search_used
Check if tool search tools are present in the tools list.
litellm/llms/anthropic/common_utils.py:169
↓ 9 callersFunctionj
(t,e,r)
litellm/proxy/_experimental/out/_next/static/chunks/0ys10755n8os_.js:1
↓ 9 callersFunctionlQ
(t,e,r)
litellm/proxy/_experimental/out/_next/static/chunks/0ys10755n8os_.js:1
↓ 9 callersMethodlist_tools
List available tools from the server. Args: raise_on_error: When True, re-raise exceptions instead of returning a
litellm/experimental_mcp_client/client.py:478
↓ 9 callersMethodlist_tools
List all tools available across all MCP Servers. Args: user_api_key_auth: User authentication mcp_auth_heade
litellm/proxy/_experimental/mcp_server/mcp_server_manager.py:1501
↓ 9 callersMethodload_all
Scan GitLab for all .prompt files under prompts_path, load and parse each, and return the mapping of repo file path -> JSON-like dict
litellm/integrations/gitlab/gitlab_prompt_manager.py:669
↓ 9 callersFunctionm
()
litellm/proxy/_experimental/out/_next/static/chunks/0.4.bbjx7y007.js:1
↓ 9 callersMethodmap_openai_params
Map OpenAI parameters to Moonshot AI parameters Handles Moonshot AI specific limitations: - tool_choice doesn't support "req
litellm/llms/moonshot/chat/transformation.py:110
↓ 9 callersMethodmap_openai_params
( self, non_default_params: dict, optional_params: dict, model: str, d
litellm/llms/fireworks_ai/chat/transformation.py:197
↓ 9 callersMethodmean
(self)
litellm/router_strategy/adaptive_router/bandit.py:36
↓ 9 callersFunctionmilvus_proxy_route
Enable using Milvus `/vectors` endpoint as a pass-through endpoint.
litellm/proxy/pass_through_endpoints/llm_passthrough_endpoints.py:426
↓ 9 callersMethodmodel_dump
(self)
tests/test_litellm/proxy/guardrails/guardrail_hooks/test_noma_v2.py:246
↓ 9 callersMethodmount
()
litellm/proxy/_experimental/out/_next/static/chunks/0n.a~e5dwfnkn.js:1
↓ 9 callersFunctionn
()
litellm/proxy/_experimental/out/_next/static/chunks/0c4pfjjue0uc-.js:1
↓ 9 callersFunctionn
({config:e,src:t,width:s,quality:i})
litellm/proxy/_experimental/out/_next/static/chunks/16.oisvgwzo8s.js:2
↓ 9 callersMethodnew
Build a router from a `model_list` using the default `simple-shuffle` strategy.
litellm-rust/crates/core/src/router/mod.rs:29
↓ 9 callersFunctionnew_team
(session, i, user_id=None, member_list=None, model_aliases=None)
tests/test_team.py:286
↓ 9 callersFunctiono
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/101az3fsw7lje.js:1
↓ 9 callersFunctionoV
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/04jvxoid~vpxj.js:1
↓ 9 callersFunctionoptionally_handle_anthropic_oauth
Handle Anthropic OAuth token detection and header setup. If an OAuth token is detected in the Authorization header, extracts it and sets
litellm/llms/anthropic/common_utils.py:66
↓ 9 callersMethodpass_through_async_success_handler
( self, httpx_response: httpx.Response, response_body: Optional[dict], logging
litellm/proxy/pass_through_endpoints/success_handler.py:255
↓ 9 callersMethodpoll_logs_for_key
( self, key: str, *, min_rows: int = 1, predicate: Callable[[list[Spen
tests/e2e/spend_tracking/spend_e2e_client.py:119
↓ 9 callersMethodprocess_output_response
Process output response by applying guardrails to text content. Args: response: LiteLLM ModelResponse object
litellm/llms/openai/chat/guardrail_translation/handler.py:290
↓ 9 callersFunctionproxy_startup_event
(app: FastAPI)
litellm/proxy/proxy_server.py:774
↓ 9 callersFunctionr
(e)
litellm/proxy/_experimental/out/_next/static/chunks/036wlkuzplhfz.js:1
↓ 9 callersMethodrecord_turn
Apply one turn, push session snapshot + bandit deltas to the queue.
litellm/router_strategy/adaptive_router/adaptive_router.py:359
↓ 9 callersMethodrecreate_prisma_client
Recreate both writer and reader Prisma clients. The writer reconnect path in PrismaClient calls `self.db.recreate_prisma_client(...)`
litellm/proxy/db/routing_prisma_wrapper.py:146
↓ 9 callersFunctionredact_message_input_output_from_logging
Removes messages, prompts, input, response from logging. This modifies the data in-place only redacts when litellm.turn_off_message_logging =
litellm/litellm_core_utils/redact_messages.py:269
↓ 9 callersMethodregister
Register a key so the replenisher starts warming it. Idempotent. The gateway calls this once per known deployment at startup; the pool only warms keys
litellm-rust/crates/ai-gateway/src/io/realtime_pool.rs:246
↓ 9 callersFunctionrequestAnimationFrame
(...e)
litellm/proxy/_experimental/out/_next/static/chunks/15.9ylrtxojbj.js:1
↓ 9 callersFunctionresolve_embedding_router
Return ``llm_router`` iff it serves ``embedding_model`` as a deployment.
litellm/caching/_embedding_router.py:21
↓ 9 callersFunctionrewrite_path_ids
Walk URL path segments and resolve any passthrough managed IDs to raw provider IDs. Returns *path* unchanged when no managed IDs are found.
litellm/proxy/pass_through_endpoints/managed_id_rewriter.py:1059
↓ 9 callersFunctionrr
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/04jvxoid~vpxj.js:1
↓ 9 callersFunctionrule
(name, baseline, slack)
tests/test_litellm/test_ruff_strict_gate.py:14
↓ 9 callersMethodrun
( &self, context: CallLifecycleContext, request: InitialReq, hooks: &Hooks,
litellm-rust/crates/core/src/call_lifecycle/mod.rs:100
↓ 9 callersFunctionry
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/04jvxoid~vpxj.js:1
↓ 9 callersMethodsend
( self, path: str, *, headers: BaseModel, json: BaseModel, par
tests/e2e/transport.py:28
↓ 9 callersMethodset
(t,e)
litellm/proxy/_experimental/out/_next/static/chunks/0ys10755n8os_.js:1
↓ 9 callersFunctionset_request_from_trusted_proxy
(mock_request)
tests/litellm/proxy/_experimental/mcp_server/test_discoverable_endpoints.py:11
↓ 9 callersMethodset_session_routing
Store a routing override for a session. Called by guardrails when they detect sensitive data and want to route the session t
litellm/proxy/hooks/sensitive_data_routing.py:113
↓ 9 callersMethodshould_retry_this_error
1. raise an exception for ContextWindowExceededError if context_window_fallbacks is not None 2. raise an exception for ContentPolicyV
litellm/router.py:6506
↓ 9 callersFunctionsign_with_manual_credentials
Sign a request using manually provided OCI credentials (user/fingerprint/tenancy/key).
litellm/llms/oci/common_utils.py:246
↓ 9 callersFunctionsj
(e)
litellm/proxy/_experimental/out/_next/static/chunks/04jvxoid~vpxj.js:1
↓ 9 callersMethodstore_message
Store message in list
litellm/litellm_core_utils/realtime_streaming.py:164
↓ 9 callersMethodstore_unified_object_id
( self, unified_object_id: str, file_object: Union[LiteLLMBatch, LiteLLMFineTuningJob,
enterprise/litellm_enterprise/proxy/hooks/managed_files.py:150
↓ 9 callersMethodsuccess_handler
(self, *args, **kwargs)
tests/llm_responses_api_testing/test_responses_hooks.py:40
↓ 9 callersFunctiontL
(e,t,r,n,o)
litellm/proxy/_experimental/out/_next/static/chunks/0.4.bbjx7y007.js:143
↓ 9 callersFunctiontS
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0c4pfjjue0uc-.js:1
↓ 9 callersFunctiontm
(e)
litellm/proxy/_experimental/out/_next/static/chunks/04jvxoid~vpxj.js:1
↓ 9 callersMethodtoBaseURI
(s)
litellm/proxy/swagger/swagger-ui-bundle.js:2
↓ 9 callersMethodtransform_create_file_request
Transform OpenAI-style file creation request into Manus's two-step format. Manus API spec (https://open.manus.im/docs/openai-compati
litellm/llms/manus/files/transformation.py:156
↓ 9 callersMethodtransform_realtime_response
Transform Bedrock Nova Sonic response to OpenAI realtime format. Args: message: Bedrock format message (JSON string)
litellm/llms/bedrock/realtime/transformation.py:994
↓ 9 callersMethodtransform_request
Transform the overall request to be sent to the API. Returns: dict: The transformed request. Sent as the body of the API
litellm/llms/moonshot/chat/transformation.py:194
↓ 9 callersMethodtransform_request
( self, model: str, messages: List["AllMessageValues"], optional_params: dict,
litellm/completion_extras/litellm_responses_transformation/transformation.py:374
↓ 9 callersMethodtransform_response
( self, model: str, raw_response: Response, model_response: ModelResponse,
litellm/llms/ollama/completion/transformation.py:238
↓ 9 callersMethodtransform_retrieve_file_response
Transform retrieve file response.
litellm/llms/manus/files/transformation.py:302
↓ 9 callersMethodtransform_vertex_ai_batch_response_to_openai_batch_response
( cls, response: VertexBatchPredictionResponse )
litellm/llms/vertex_ai/batches/transformation.py:45
↓ 9 callersMethodtransform_video_status_retrieve_response
Transform the Veo operation status response. Veo returns: { "name": "operations/generate_1234567890",
litellm/llms/gemini/videos/transformation.py:374
↓ 9 callersMethodtranslate_anthropic_tools_to_openai
Translate Anthropic tools to OpenAI format. Returns: Tuple of (translated_tools, tool_name_mapping) - tool_n
litellm/llms/anthropic/experimental_pass_through/adapters/transformation.py:720
↓ 9 callersMethodtranslate_completion_to_generate_content
Transform litellm completion response to Google GenAI generate_content format Args: response: ModelResponse from litellm
litellm/google_genai/adapters/transformation.py:460
↓ 9 callersMethodtranslate_system_message
Translate system message to anthropic format. Removes system message from the original list and returns a new list of anthropic syst
litellm/llms/anthropic/chat/transformation.py:1557
↓ 9 callersFunctiontw
(e,t,n,r)
litellm/proxy/_experimental/out/_next/static/chunks/04jvxoid~vpxj.js:1
↓ 9 callersMethodupdate_from_kwargs
(self, **kwargs)
tests/test_litellm/llms/xai/test_xai_key_fallback.py:20
↓ 9 callersFunctionv
(e)
litellm/proxy/_experimental/out/_next/static/chunks/0teffxf7o_863.js:1
↓ 9 callersMethodvalidate_environment
( self, headers: dict, model: str, messages: List[AllMessageValues], o
litellm/llms/anthropic/common_utils.py:607
↓ 9 callersFunctionvalidate_team_org_change
Validate that a team can be moved to an organization. - The org must have access to the team's models - The team budget cannot be greate
litellm/proxy/management_endpoints/team_endpoints.py:1461
↓ 9 callersFunctionwalk_user_text
Rewrite every text fragment in place via ``visit``. Mutates ``data["messages"]`` and ``data["input"]``. Returns the number of fragments visit
litellm/proxy/guardrails/_content_utils.py:100
↓ 8 callersFunctionC
(t)
litellm/proxy/_experimental/out/_next/static/chunks/101az3fsw7lje.js:1
↓ 8 callersFunctionI
(e,s)
litellm/proxy/_experimental/out/_next/static/chunks/0lstohw6r.qs..js:1
↓ 8 callersFunctionP
(e,t)
litellm/proxy/_experimental/out/_next/static/chunks/0.4.bbjx7y007.js:39
↓ 8 callersFunctionVe
(s,o)
litellm/proxy/swagger/swagger-ui-bundle.js:2
← previousnext →2,001–2,100 of 68,180, ranked by callers