RAG Quick Start

Learn how to configure retrieval behavior for AI agents with knowledge bases.

Diagram

A knowledge-centric workflow where RAG (Retrieval Augmented Generation) agents interact with vector databases to store and retrieve information efficiently, enabling sophisticated question-answering and information retrieval capabilities.

Quick Start

Install Package
Install PraisonAI Agents with knowledge support:
bash
```
pip install "praisonaiagents[knowledge]"
```
Set API Key
Set your OpenAI API key:
bash
```
export OPENAI_API_KEY=xxxxx
```

Create Script

Create a new file app.py:

python

from praisonaiagents import Agent

agent = Agent(
    name="Knowledge Agent",
    instructions="You answer questions based on the provided knowledge.",
    knowledge=["small.pdf"], # Indexing
)

agent.start("What is KAG in one line?") # Retrieval

Data Indexing and Retrieval Agents

Diagram

The simplest way to create a knowledge-based agent is without any configuration:

python

from praisonaiagents import Agent

agent = Agent(
    name="Knowledge Agent",
    instructions="You answer questions based on the provided knowledge.",
    knowledge=["small.pdf"] # Indexing
)

agent.start("What is KAG in one line?") # Retrieval

Advanced Configuration

For more control over the knowledge base, you can specify a configuration:

python

from praisonaiagents import Agent

config = {
    "vector_store": {
        "provider": "chroma",
        "config": {
            "collection_name": "praison",
            "path": ".praison",
        }
    }
}

agent = Agent(
    name="Knowledge Agent",
    instructions="You answer questions based on the provided knowledge.",
    knowledge={
        "sources": ["small.pdf"],
        **config
    }
)

agent.start("What is KAG in one line?") # Retrieval

Multi-Agent Knowledge System

For more complex scenarios, you can create a knowledge-based system with multiple agents:

python

from praisonaiagents import Agent, Task, AgentTeam
import logging
import os

# Configure logging
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
logger = logging.getLogger(__name__)

# Define the configuration for the Knowledge instance
config = {
    "vector_store": {
        "provider": "chroma",
        "config": {
            "collection_name": "praison",
            "path": ".praison",
        }
    }
}

# Create an agent with knowledge capabilities
knowledge_agent = Agent(
    name="KnowledgeAgent",
    role="Information Specialist",
    goal="Store and retrieve knowledge efficiently",
    backstory="Expert in managing and utilizing stored knowledge",
    knowledge={
        "sources": ["sample.pdf"],
        **config
    }
)

# Define a task for the agent
knowledge_task = Task(
    name="knowledge_task",
    description="Who is Mervin Praison?",
    expected_output="Answer to the question",
    agent=knowledge_agent # Agent
)

# Create and start the agents
agents = AgentTeam(
    agents=[knowledge_agent],
    tasks=[knowledge_task],
    process="sequential",
    memory={"user_id": "user1"} # User ID
)

# Start execution
result = agents.start() # Retrieval

Retrieval Agents

Install Package
Retrieval uses a vector store, so install the knowledge extra:
bash
```
pip install "praisonaiagents[knowledge]"
```
Set API Key
Set your OpenAI API key as an environment variable in your terminal:
bash
```
export OPENAI_API_KEY=your_api_key_here
```

Create a file

Create a new file rag_agent.py with the basic setup:

python

from praisonaiagents import Agent, Task, AgentTeam

# Define the configuration for the Knowledge instance
config = {
    "vector_store": {
        "provider": "chroma",
        "config": {
            "collection_name": "praison",
            "path": ".praison"
        }
    }
}

# Create an agent
rag_agent = Agent(
    name="RAG Agent",
    role="Information Specialist",
    goal="Retrieve knowledge efficiently",
    llm="gpt-4o-mini"
)

# Define a task for the agent
rag_task = Task(
    name="RAG Task",
    description="What is KAG?",
    expected_output="Answer to the question",
    agent=rag_agent,
    context=[config] # Retrieval : Vector Database provided as context
)

# Build Agents
agents = AgentTeam(
    agents=[rag_agent],
    tasks=[rag_task],
    memory={"user_id": "user1"}
)

# Start Agents
agents.start()

Start Agents
Type this in your terminal to run your agents:
bash
```
python rag_agent.py
```

Adding Knowledge to RAG Agents

python

from praisonaiagents import Agent

config = {
    "vector_store": {
        "provider": "chroma",
        "config": {
            "collection_name": "praison",
            "path": ".praison",
        }
    }
}

agent = Agent(
    name="Knowledge Agent",
    instructions="You answer questions based on the provided knowledge.",
    knowledge={
        "sources": ["small.pdf"],
        **config
    }
)

agent.start("What is KAG in one line?") # Retrieval

Understanding RAG Agents

What are RAG Agents?

RAG (Retrieval Augmented Generation) agents enable: – Efficient knowledge retrieval – Semantic search capabilities – Persistent knowledge storage – Context-aware responses