> ## Documentation Index
> Fetch the complete documentation index at: https://docs.xpander.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Knowledge Base Integration (RAG)

> Learn how to integrate PDF documents and vector search capabilities with your AI agent for Retrieval-Augmented Generation

<AccordionGroup>
  <Accordion title="Prerequisites">
    ### Virtual Environment Setup

    ```bash setup.sh theme={"dark"}
    python3 -m venv .venv
    source .venv/bin/activate
    pip install "xpander-sdk[agno]"
    ```

    ### Environment Setup

    The `.env` file is created when you download your agent code:

    ```bash theme={"dark"}
    xpander init
    ```

    This downloads your agent code from the platform with the `.env` file pre-configured with your keys.
  </Accordion>
</AccordionGroup>

```python knowledge_base_example.py theme={"dark"}
from dotenv import load_dotenv
load_dotenv()

from xpander_sdk import Backend
from agno.agent import Agent
from agno.document.chunking.fixed import FixedSizeChunking
from agno.knowledge.pdf_url import PDFUrlKnowledgeBase
from agno.vectordb.pgvector import PgVector

# Initialize backend and agent
backend = Backend()
agno_agent = Agent(**backend.get_args())

# Get database connection from agent
db = agno_agent.get_db()

# Create knowledge base with PDF documents
knowledge_base = PDFUrlKnowledgeBase(
    urls=["https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"],
    vector_db=PgVector(
        table_name="recipes_fixed_size_chunking", 
        db_url=db.db_url, 
        auto_upgrade_schema=True, 
        schema=db.db_schema
    ),
    chunking_strategy=FixedSizeChunking(),
)

# Load documents into vector database
knowledge_base.load(recreate=True)

# Configure agent with knowledge base
agno_agent.knowledge = knowledge_base
agno_agent.search_knowledge = True

# Query the knowledge base
agno_agent.print_response("How to make Thai curry?", markdown=True)
```

## How to Run

```bash knowledge_base_example.py theme={"dark"}
python knowledge_base_example.py
```

This example shows automatic PDF document parsing and text extraction, vector embeddings creation for semantic search, and Retrieval-Augmented Generation where the agent searches the knowledge base for relevant information and integrates retrieved content seamlessly into LLM responses for enhanced accuracy.

## Production Deployment

For creating and deploying agents to production, see the [Setup and Deployment Guide](/Examples/00-setup-deployment).