agents.rag.agentic_router.agent_chain¶
Agentic RAG Router using ChainAgent.
Simplified version using the new ChainAgent approach.
Classes¶
Available RAG strategies. |
|
Strategy selection result. |
Functions¶
|
Create an agentic RAG router using ChainAgent. |
|
Create as a multi-agent system. |
|
Ultra-simple RAG router with just basic routing. |
Get I/O schema for the chain version. |
Module Contents¶
- class agents.rag.agentic_router.agent_chain.RAGStrategy¶
-
Available RAG strategies.
Initialize self. See help(type(self)) for accurate signature.
- class agents.rag.agentic_router.agent_chain.StrategyDecision(/, **data)¶
Bases:
pydantic.BaseModel
Strategy selection result.
Create a new model by parsing and validating input data from keyword arguments.
Raises [ValidationError][pydantic_core.ValidationError] if the input data cannot be validated to form a valid model.
self is explicitly positional-only to allow self as a field name.
- Parameters:
data (Any)
- agents.rag.agentic_router.agent_chain.create_agentic_rag_router_chain(documents, llm_config=None, name='Agentic RAG Router')¶
Create an agentic RAG router using ChainAgent.
Super simple compared to the old implementation!
- agents.rag.agentic_router.agent_chain.create_agentic_router_multi_agent(documents, llm_config=None)¶
Create as a multi-agent system.
- Parameters:
documents (list[langchain_core.documents.Document])
llm_config (haive.core.models.llm.base.LLMConfig | None)
- Return type:
haive.agents.chain.multi_integration.ChainMultiAgent
- agents.rag.agentic_router.agent_chain.create_simple_rag_router_chain(documents, llm_config=None)¶
Ultra-simple RAG router with just basic routing.
- Parameters:
documents (list[langchain_core.documents.Document])
llm_config (haive.core.models.llm.base.LLMConfig | None)
- Return type:
haive.agents.chain.ChainAgent