RAG Scoping & Filtering

Filter retrieval with user_id, agent_id, and run_id for multi-tenant isolation

Scope knowledge retrieval per user, agent, or session so tenants and conversations stay isolated.

from praisonaiagents import Agent, MemoryConfig

agent = Agent(
    name="SupportBot",
    instructions="Answer from the customer's knowledge only.",
    knowledge=["./support_docs/"],
    memory=MemoryConfig(user_id="customer_42"),
)

agent.start("What was the status of my refund request?")

The user asks in a scoped session; retrieval filters by tenant and user so answers stay isolated.

How It Works

Quick Start

1. Simple Usage

   Set user_id via memory config — the agent passes it to every knowledge search:

   from praisonaiagents import Agent, MemoryConfig
   
   agent = Agent(
       name="PersonalAssistant",
       instructions="You are a personal assistant.",
       knowledge=["./documents/"],
       memory=MemoryConfig(user_id="alice"),
   )
   
   agent.start("Find my recent notes about the project")

2. With Configuration

   Combine scopes for multi-tenant SaaS — pass run_id on retrieve for session-specific context:

   from praisonaiagents import Agent, MemoryConfig
   
   session_id = "session_2026_05_30"
   
   agent = Agent(
       name="SupportBot",
       instructions="Answer customer questions using their session history.",
       knowledge=["./support_docs/"],
       memory=MemoryConfig(user_id="customer_42"),
   )
   
   agent.retrieve("Refund status?", run_id=session_id)

How It Works

The agent forwards user_id and agent_id (auto-generated) to the knowledge backend. Vector stores combine filters with $and when multiple scopes are set.

Configuration Options

Backends: ChromaDB supports all scopes; mem0 requires at least one scope identifier.

Best Practices

Related