agents.memory_v2.rag_memory_agent¶

RAG-based Memory Agent using BaseRAGAgent with advanced retrievers.

This module provides memory-capable agents built on BaseRAGAgent with: 1. Time-weighted retrieval for temporal memory access 2. Multi-modal memory storage (conversation, preferences, facts) 3. Knowledge graph-enhanced retrieval 4. Real-time memory updates and ingestion 5. Vector store persistence across different backends

All built using BaseRAGAgent as the foundation with custom retrievers.

Classes¶

`ConversationMemoryAgent`	Memory agent for conversation history using BaseRAGAgent.
`FactualMemoryAgent`	Memory agent for factual information using BaseRAGAgent.
`MemoryRAGConfig`	Configuration for RAG-based memory agents.
`PreferencesMemoryAgent`	Memory agent for user preferences using BaseRAGAgent.
`UnifiedMemoryRAGAgent`	Unified memory agent coordinating multiple specialized memory agents.

Functions¶

`create_conversation_memory_agent`([...])	Factory function to create conversation memory agent.
`create_factual_memory_agent`([vector_store_provider, ...])	Factory function to create factual memory agent.
`create_postgresql_memory_agent`(connection_string[, ...])	Create memory agent with PostgreSQL persistence.
`create_supabase_memory_agent`(supabase_url, supabase_key)	Create memory agent with Supabase persistence.
`create_unified_memory_agent`([user_id, llm_config, ...])	Factory function to create unified memory agent.
`demo`()	Demo.

Module Contents¶

class agents.memory_v2.rag_memory_agent.ConversationMemoryAgent(config, name='conversation_memory')¶

Memory agent for conversation history using BaseRAGAgent.

Initialize conversation memory agent.

Parameters:

config (MemoryRAGConfig)
name (str)

async add_conversation(messages)¶

Add conversation messages to memory.

Parameters:: messages (list[langchain_core.messages.BaseMessage])
Return type:: None

async initialize()¶

Initialize the underlying RAG agent.

Return type:: None

async retrieve_conversation_context(query, k=None)¶

Retrieve relevant conversation context.

Parameters:

query (str)
k (int | None)

Return type:

list[langchain_core.documents.Document]

class agents.memory_v2.rag_memory_agent.FactualMemoryAgent(config, name='factual_memory')¶

Memory agent for factual information using BaseRAGAgent.

Initialize factual memory agent.

Parameters:

config (MemoryRAGConfig)
name (str)

async add_memories(memories)¶

Add multiple factual memories.

Parameters:: memories (list[agents.memory_v2.memory_state_original.EnhancedMemoryItem])
Return type:: None

async add_memory(memory)¶

Add a factual memory.

Parameters:: memory (agents.memory_v2.memory_state_original.EnhancedMemoryItem)
Return type:: None

async initialize()¶

Initialize the underlying RAG agent.

Return type:: None

async retrieve_facts(query, k=None)¶

Retrieve relevant factual memories.

Parameters:

query (str)
k (int | None)

Return type:

list[dict[str, Any]]

class agents.memory_v2.rag_memory_agent.MemoryRAGConfig(/, **data)¶

Bases: pydantic.BaseModel

Configuration for RAG-based memory agents.

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)

model_config¶: Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].

class agents.memory_v2.rag_memory_agent.PreferencesMemoryAgent(config, name='preferences_memory')¶

Memory agent for user preferences using BaseRAGAgent.

Initialize preferences memory agent.

Parameters:

config (MemoryRAGConfig)
name (str)

async add_preference(preference)¶

Add a user preference.

Parameters:: preference (agents.memory_v2.memory_state_original.EnhancedMemoryItem)
Return type:: None

async check_preference_conflict(new_preference)¶

Check if new preference conflicts with existing ones.

Parameters:: new_preference (str)
Return type:: dict[str, Any]

async get_preferences_for(context)¶

Get relevant preferences and generate summary.

Parameters:: context (str)
Return type:: str

async initialize()¶

Initialize the underlying RAG agent.

Return type:: None

class agents.memory_v2.rag_memory_agent.UnifiedMemoryRAGAgent(config, user_id=None)¶

Unified memory agent coordinating multiple specialized memory agents.

Initialize unified memory agent.

Parameters:

config (MemoryRAGConfig)
user_id (str | None)

classmethod as_tool(name=None, description=None, **config_kwargs)¶

Convert this agent to a tool for use in other agents.

Parameters:

name (str | None)
description (str | None)

async get_memory_summary()¶

Get summary of all stored memories.

Return type:: dict[str, Any]

async initialize()¶

Initialize all memory agents.

Return type:: None

async process_conversation(messages)¶

Process conversation and extract memories.

Parameters:: messages (list[langchain_core.messages.BaseMessage])
Return type:: dict[str, Any]

async retrieve_context(query, memory_types=None)¶

Retrieve relevant context from all memory types.

Parameters:

query (str)
memory_types (list[str] | None)

Return type:

dict[str, Any]

agents.memory_v2.rag_memory_agent.create_conversation_memory_agent(vector_store_provider=VectorStoreProvider.FAISS, embedding_model='sentence-transformers/all-mpnet-base-v2', enable_time_weighting=True, name='conversation_memory')¶

Factory function to create conversation memory agent.

Parameters:

vector_store_provider (haive.core.engine.vectorstore.VectorStoreProvider)
embedding_model (str)
enable_time_weighting (bool)
name (str)

Return type:

ConversationMemoryAgent

agents.memory_v2.rag_memory_agent.create_factual_memory_agent(vector_store_provider=VectorStoreProvider.FAISS, embedding_model='sentence-transformers/all-mpnet-base-v2', similarity_threshold=0.7, name='factual_memory')¶

Factory function to create factual memory agent.

Parameters:

vector_store_provider (haive.core.engine.vectorstore.VectorStoreProvider)
embedding_model (str)
similarity_threshold (float)
name (str)

Return type:

FactualMemoryAgent

agents.memory_v2.rag_memory_agent.create_postgresql_memory_agent(connection_string, user_id=None, table_name='user_memories')¶

Create memory agent with PostgreSQL persistence.

Parameters:

connection_string (str)
user_id (str | None)
table_name (str)

Return type:

UnifiedMemoryRAGAgent

agents.memory_v2.rag_memory_agent.create_supabase_memory_agent(supabase_url, supabase_key, user_id=None)¶

Create memory agent with Supabase persistence.

Parameters:

supabase_url (str)
supabase_key (str)
user_id (str | None)

Return type:

UnifiedMemoryRAGAgent

agents.memory_v2.rag_memory_agent.create_unified_memory_agent(user_id=None, llm_config=None, vector_store_provider=VectorStoreProvider.FAISS, embedding_model='sentence-transformers/all-mpnet-base-v2')¶

Factory function to create unified memory agent.

Parameters:

user_id (str | None)
llm_config (haive.core.engine.aug_llm.AugLLMConfig)
vector_store_provider (haive.core.engine.vectorstore.VectorStoreProvider)
embedding_model (str)

Return type:

UnifiedMemoryRAGAgent

async agents.memory_v2.rag_memory_agent.demo()¶: Demo.