> ## 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.

# Document Readers: PDF, DOCX, PPTX, Excel

> Knowledge auto-detects file types and selects the right reader.

Knowledge auto-detects file types and selects the right reader. You can also specify a reader explicitly for more control.

```python documents.py theme={null}
"""
Document Readers: PDF, DOCX, PPTX, Excel
==========================================
Knowledge auto-detects file types and selects the right reader.
You can also specify a reader explicitly for more control.

Supported document formats:
- PDF: Text extraction with optional OCR
- DOCX: Microsoft Word documents
- PPTX: PowerPoint presentations
- Excel: .xlsx and .xls spreadsheets

See also: 02_data.py for CSV/JSON, 03_web.py for web sources.
"""

import asyncio

from agno.agent import Agent
from agno.knowledge.embedder.openai import OpenAIEmbedder
from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.excel_reader import ExcelReader

# Other available readers (used via auto-detection or explicit import):
# from agno.knowledge.reader.docx_reader import DocxReader
# from agno.knowledge.reader.pdf_reader import PDFReader
# from agno.knowledge.reader.pptx_reader import PPTXReader
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="document_readers",
        url=qdrant_url,
        search_type=SearchType.hybrid,
        embedder=OpenAIEmbedder(id="text-embedding-3-small"),
    ),
)

agent = Agent(
    model=OpenAIResponses(id="gpt-5.2"),
    knowledge=knowledge,
    search_knowledge=True,
    markdown=True,
)

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

if __name__ == "__main__":

    async def main():
        # --- PDF: auto-detected by file extension ---
        print("\n" + "=" * 60)
        print("READER: PDF (auto-detected)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="CV",
            path="cookbook/07_knowledge/testing_resources/cv_1.pdf",
        )
        agent.print_response("What skills does Jordan Mitchell have?", stream=True)

        # --- Excel: explicit reader for more control ---
        print("\n" + "=" * 60)
        print("READER: Excel (explicit reader)")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Products",
            path="cookbook/07_knowledge/testing_resources/sample_products.xlsx",
            reader=ExcelReader(),
        )
        agent.print_response("What products are listed?", stream=True)

        # --- PDF from URL: auto-detected ---
        print("\n" + "=" * 60)
        print("READER: PDF from URL")
        print("=" * 60 + "\n")

        await knowledge.ainsert(
            name="Recipes",
            url="https://agno-public.s3.amazonaws.com/recipes/ThaiRecipes.pdf",
        )
        agent.print_response("What Thai recipes are available?", 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 openpyxl qdrant-client xlrd
    ```
  </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 `documents.py`, then run:

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

Full source: [cookbook/07\_knowledge/05\_integrations/readers/01\_documents.py](https://github.com/agno-agi/agno/blob/main/cookbook/07_knowledge/05_integrations/readers/01_documents.py)