agents.rag.adaptive.agent¶

Adaptive RAG Agent.

Dynamic strategy selection based on query complexity. Routes queries to appropriate RAG strategies.

Classes¶

`AdaptiveRAGAgent`	Adaptive RAG that routes queries based on complexity.
`QueryAnalysis`	Analysis of query characteristics.

class agents.rag.adaptive.agent.AdaptiveRAGAgent¶

Bases: haive.agents.multi.base.ConditionalAgent

Adaptive RAG that routes queries based on complexity.

classmethod from_documents(documents, llm_config=None, embedding_model=None, **kwargs)¶

Create Adaptive RAG from documents.

Parameters:

documents (list[langchain_core.documents.Document]) – Documents to index
llm_config (haive.core.models.llm.base.LLMConfig | None) – Optional LLM configuration
embedding_model (str | None) – Optional embedding model
**kwargs – Additional arguments

Returns:

AdaptiveRAGAgent instance

class agents.rag.adaptive.agent.QueryAnalysis(/, **data)¶

Bases: pydantic.BaseModel

Analysis of query characteristics.

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.