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

# Basic RAG: Context Injection

> The simplest way to give an agent access to documents.

The simplest way to give an agent access to documents. Content is automatically retrieved and injected into the system prompt before the agent responds.

```python basic_rag.py theme={null}
"""
Basic RAG: Context Injection
=============================
The simplest way to give an agent access to documents. Content is automatically
retrieved and injected into the system prompt before the agent responds.

This pattern works well for simple Q&A over documents. The agent doesn't need
to decide whether to search - it always gets relevant context.

Steps:
1. Create a Knowledge base with a vector database
2. Load a document
3. Create an Agent with add_knowledge_to_context=True
4. Ask questions - context is injected automatically

See also: 02_agentic_rag.py for agent-driven search decisions.
"""

import asyncio

from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.models.openai import OpenAIResponses
from agno.vectordb.qdrant import Qdrant
from agno.vectordb.search import SearchType

# ---------------------------------------------------------------------------
# Setup
# ---------------------------------------------------------------------------

qdrant_url = "http://localhost:6333"

knowledge = Knowledge(
    vector_db=Qdrant(
        collection="basic_rag",
        url=qdrant_url,
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------

# Traditional RAG: context is fetched and injected into the prompt automatically.
# The agent doesn't get a search tool - it just sees the relevant context.
agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    knowledge=knowledge,
    add_knowledge_to_context=True,
    search_knowledge=False,
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Demo
# ---------------------------------------------------------------------------

if __name__ == "__main__":

    async def main():
        await knowledge.ainsert(
            url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf"
        )

        print("\n" + "=" * 60)
        print("Basic RAG: Context injected into prompt automatically")
        print("=" * 60 + "\n")

        agent.print_response(
            "How do I make chicken and galangal in coconut milk soup",
            stream=True,
        )

    asyncio.run(main())
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno fastembed openai qdrant-client
    ```
  </Step>

  <Step title="Export your OpenAI API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export OPENAI_API_KEY="your_openai_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:OPENAI_API_KEY="your_openai_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Run Qdrant">
    ```bash theme={null}
    docker run -d --name qdrant -p 6333:6333 qdrant/qdrant:latest
    ```
  </Step>

  <Step title="Run the example">
    Save the code above as `basic_rag.py`, then run:

    ```bash theme={null}
    python basic_rag.py
    ```
  </Step>
</Steps>

Full source: [cookbook/07\_knowledge/01\_getting\_started/01\_basic\_rag.py](https://github.com/agno-agi/agno/blob/main/cookbook/07_knowledge/01_getting_started/01_basic_rag.py)