agents.rag.enhanced_memory_react

Enhanced Memory RAG with ReAct Pattern.

RAG system that maintains conversation memory and uses ReAct (Reasoning + Acting) pattern for complex multi-step queries requiring reasoning and tool use.

Classes

EnhancedResponse	Enhanced response with memory integration.
MemoryAnalysis	Memory analysis result.
MemoryEntry	Memory entry structure.
MemoryType	Types of memory.
ReActStep	ReAct pattern steps.
ReActStepResult	Result from a ReAct step.

Functions

create_enhanced_memory_react_rag(documents[, ...])	Create an enhanced memory-aware RAG with ReAct pattern.
create_memory_react_with_tools(documents[, llm_config])	Create memory ReAct RAG with tool integration.
create_simple_memory_react_rag(documents[, llm_config])	Create a simplified memory-aware ReAct RAG.
get_enhanced_memory_react_io_schema()	Get I/O schema for enhanced memory ReAct RAG.

Module Contents

class agents.rag.enhanced_memory_react.EnhancedResponse(/, **data)

Bases: pydantic.BaseModel

Enhanced response with memory integration.

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)

class agents.rag.enhanced_memory_react.MemoryAnalysis(/, **data)

Bases: pydantic.BaseModel

Memory analysis 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)

class agents.rag.enhanced_memory_react.MemoryEntry(/, **data)

Bases: pydantic.BaseModel

Memory entry structure.

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)

class agents.rag.enhanced_memory_react.MemoryType

Bases: str, enum.Enum

Types of memory.

Initialize self. See help(type(self)) for accurate signature.

class agents.rag.enhanced_memory_react.ReActStep

Bases: str, enum.Enum

ReAct pattern steps.

Initialize self. See help(type(self)) for accurate signature.

class agents.rag.enhanced_memory_react.ReActStepResult(/, **data)

Bases: pydantic.BaseModel

Result from a ReAct step.

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.enhanced_memory_react.create_enhanced_memory_react_rag(documents, llm_config=None, name='Enhanced Memory ReAct RAG')

Create an enhanced memory-aware RAG with ReAct pattern.

Parameters:

• documents (list[langchain_core.documents.Document])

• llm_config (haive.core.models.llm.base.LLMConfig | None)

• name (str)

Return type:

haive.agents.chain.ChainAgent

agents.rag.enhanced_memory_react.create_memory_react_with_tools(documents, llm_config=None)

Create memory ReAct RAG with tool integration.

Parameters:

• documents (list[langchain_core.documents.Document])

• llm_config (haive.core.models.llm.base.LLMConfig | None)

Return type:

haive.agents.chain.ChainAgent

agents.rag.enhanced_memory_react.create_simple_memory_react_rag(documents, llm_config=None)

Create a simplified memory-aware ReAct RAG.

Parameters:

• documents (list[langchain_core.documents.Document])

• llm_config (haive.core.models.llm.base.LLMConfig | None)

Return type:

haive.agents.chain.ChainAgent

agents.rag.enhanced_memory_react.get_enhanced_memory_react_io_schema()

Get I/O schema for enhanced memory ReAct RAG.

Return type:

dict[str, list[str]]