data_juicer_agents.tools.retrieve.retrieve_operators.backend module#

data_juicer_agents.tools.retrieve.retrieve_operators.backend.init_dj_func_info()[source]#: Initialize dj_func_info at agent startup

data_juicer_agents.tools.retrieve.retrieve_operators.backend.refresh_dj_func_info()[source]#: Refresh dj_func_info during agent runtime (for manual updates)

data_juicer_agents.tools.retrieve.retrieve_operators.backend.get_dj_func_info()[source]#: Get current dj_func_info (lifecycle-aware)

async data_juicer_agents.tools.retrieve.retrieve_operators.backend.retrieve_ops_lm(user_query, limit=20)[source]#: Tool retrieval using language model - returns list of tool names

async data_juicer_agents.tools.retrieve.retrieve_operators.backend.retrieve_ops_lm_items(user_query, limit=20)[source]#: Tool retrieval using language model - returns validated tool metadata.

data_juicer_agents.tools.retrieve.retrieve_operators.backend.retrieve_ops_vector(user_query, limit=20)[source]#: Tool retrieval using vector search with smart caching - returns list of tool names

async data_juicer_agents.tools.retrieve.retrieve_operators.backend.retrieve_ops_with_meta(user_query: str, limit: int = 20, mode: str = 'auto') → dict[source]#: Tool retrieval with source/trace metadata.

async data_juicer_agents.tools.retrieve.retrieve_operators.backend.retrieve_ops(user_query: str, limit: int = 20, mode: str = 'auto') → list[source]#

Tool retrieval with configurable mode

Parameters:

user_query – User query string
limit – Maximum number of tools to retrieve
mode – Retrieval mode - “llm”, “vector”, or “auto” (default: “auto”) - “llm”: Use language model only - “vector”: Use vector search only - “auto”: Try LLM first, fallback to vector search on failure

Returns:

List of tool names