# Chat with PDF

Indexes a PDF into a vector store and answers questions over it with page-cited retrieval and stratified sampling.

> For the complete documentation index, see [llms.txt](/llms.txt). Markdown variants are available by appending `.md` to any URL or sending an `Accept: text/markdown` header. An agent skill is available at [/.well-known/agent-skills/site-skill.md](/.well-known/agent-skills/site-skill.md).



<DocsBaseSwitcher base="mastra" agent="chat-with-pdf" />

<AgentPreview
  agent="chat-with-pdf"
  framework="mastra"
  inputFields="[
  {
    name: &#x22;url&#x22;,
    label: &#x22;PDF URL&#x22;,
    placeholder: &#x22;https://example.com/whitepaper.pdf&#x22;,
    type: &#x22;text&#x22;,
  },
  {
    name: &#x22;question&#x22;,
    label: &#x22;Question&#x22;,
    placeholder: &#x22;What does the paper conclude about latency?&#x22;,
    type: &#x22;text&#x22;,
  },
]"
/>

## Summary [#summary]

The **Chat with PDF Agent** lets you ask questions about a PDF and get answers
grounded in the document, with a page citation for every claim. It indexes the
PDF into a vector store, retrieves only the relevant chunks per question using
stratified sampling across page ranges, and can also generate comprehension
quizzes from real passages. Reach for it to turn manuals, papers, and reports
into something you can query.

## Installation [#installation]

<CodeTabs>
  <TabsList>
    <TabsTrigger value="cli">
      Command
    </TabsTrigger>

    <TabsTrigger value="manual">
      Manual
    </TabsTrigger>
  </TabsList>

  <TabsContent value="cli">
    ```bash
    npx shadcn@latest add @agentcn/mastra/chat-with-pdf
    ```
  </TabsContent>

  <TabsContent value="manual">
    <Steps>
      <Step>
        Install the following dependencies:
      </Step>

      ```bash
      npm install @mastra/core @mastra/libsql @mastra/rag pdf-parse
      ```

      <Step>
        Copy and paste the following code into your project.
      </Step>

      <ComponentSource src="registry/mastra/chat-with-pdf/config.ts" title="config.ts" />

      <ComponentSource src="registry/mastra/chat-with-pdf/instructions.md" title="instructions.md" />

      <ComponentSource src="registry/mastra/chat-with-pdf/memory.ts" title="memory.ts" />

      <ComponentSource src="registry/mastra/chat-with-pdf/lib/vector-store.ts" title="lib/vector-store.ts" />

      <ComponentSource src="registry/mastra/chat-with-pdf/tools/list_documents.ts" title="tools/list_documents.ts" />

      <ComponentSource src="registry/mastra/chat-with-pdf/tools/query_pdf.ts" title="tools/query_pdf.ts" />

      <ComponentSource src="registry/mastra/chat-with-pdf/workflows/index_pdf.ts" title="workflows/index_pdf.ts" />

      <Step>
        Update the import paths to match your project setup.
      </Step>
    </Steps>
  </TabsContent>
</CodeTabs>

## Composition [#composition]

```text
├── config.ts              # Agent definition (model + config)
├── instructions.md        # Detailed assistant instructions
├── memory.ts              # Memory instance for conversation history
├── lib/
│   └── vector-store.ts    # LibSQLVector store + index management
├── tools/
│   ├── list_documents.ts  # List all indexed PDF documents
│   └── query_pdf.ts       # Query with stratified page sampling
└── workflows/
    └── index_pdf.ts       # 3-step workflow: download → chunk → embed
```

## Customization [#customization]

* **Swap the vector store.** `lib/vector-store.ts` uses `@mastra/libsql` — replace it with
  Pinecone, Qdrant, Chroma, or pgvector by swapping the vector store import.
* **Tune chunking.** Adjust the `splitIntoChunks` step's `maxSize` and `overlap` in `workflows/index_pdf.ts`.
* **Swap the embedding model.** Change the model in tools and workflows from `openai/text-embedding-3-small`.
* **Add quizzes.** The instructions already support quiz generation from
  retrieved passages — extend them with your preferred format.
* **Add more tools.** Create additional tools in `tools/` — they'll be auto-discovered.