> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Connect AI agents to PDF Vector

The PDF Vector connector lets your AI agent act in each user's PDF Vector account. Each user connects their own PDF Vector access token once, and Scalekit sends it with every call, so your agent never handles credentials. It comes with 19 tools.

**Authentication:** Bearer Token
**Categories:** Files & Documents, AI
**Tools:** 19: 19 read, 0 write, 0 destructive
**Users sign in with:** Access token
**Built by:** Scalekit connector
**Try it:** [Playground in the Scalekit dashboard](https://app.scalekit.com/ws/signup?sk_intent=playground&provider=PDFVECTOR)

## Setup

1. ### Install the SDK

   **Node.js**

   ```bash
   npm install @scalekit-sdk/node dotenv
   ```

   **Python**

   ```bash
   pip install scalekit-sdk-python python-dotenv
   ```

2. ### Set your credentials

   Add your Scalekit credentials to your `.env` file. Find values in **[app.scalekit.com](https://app.scalekit.com)** > **Developers** > **API Credentials**.

   ```sh title=".env"
   SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
   SCALEKIT_CLIENT_ID=<your-client-id>
   SCALEKIT_CLIENT_SECRET=<your-client-secret>
   ```

3. ### Create the PDF Vector connection

   In **AgentKit > Connections**, create a PDF Vector connection. The name you give it is the `connection_name` your code passes. See [Configure connections](/agentkit/connections/).

4. ### Authorize a user and make your first call

   **Node.js** (`quickstart.mts`)

   ```typescript
   import { ScalekitClient } from '@scalekit-sdk/node'
   import 'dotenv/config'
   import { createInterface } from 'node:readline/promises'

   const scalekit = new ScalekitClient(
     process.env.SCALEKIT_ENVIRONMENT_URL,
     process.env.SCALEKIT_CLIENT_ID,
     process.env.SCALEKIT_CLIENT_SECRET,
   )
   const actions = scalekit.actions

   const connector = 'pdfvector'
   const identifier = 'user_123'

   // Generate an authorization link for the user
   const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
   console.log('Authorize PDF Vector:', link)
   const rl = createInterface({ input: process.stdin, output: process.stdout })
   await rl.question('Press Enter after authorizing...')
   rl.close()

   // Make your first call
   const result = await actions.executeTool({
     connector,
     identifier,
     toolName: 'pdfvector_academic_parse',
     toolInput: {},
   })
   console.log(result)
   ```

   ```bash
   npx tsx quickstart.mts
   ```

   **Python** (`quickstart.py`)

   ```python
   import os
   from scalekit import ScalekitClient
   from dotenv import load_dotenv
   load_dotenv()

   scalekit_client = ScalekitClient(
       env_url=os.getenv("SCALEKIT_ENVIRONMENT_URL"),
       client_id=os.getenv("SCALEKIT_CLIENT_ID"),
       client_secret=os.getenv("SCALEKIT_CLIENT_SECRET"),
   )
   actions = scalekit_client.actions

   connection_name = "pdfvector"
   identifier = "user_123"

   # Generate an authorization link for the user
   link_response = actions.get_authorization_link(
       connection_name=connection_name,
       identifier=identifier,
   )
   print("Authorize PDF Vector:", link_response.link)
   input("Press Enter after authorizing...")

   # Make your first call
   result = actions.execute_tool(
       tool_input={},
       tool_name="pdfvector_academic_parse",
       connection_name=connection_name,
       identifier=identifier,
   )
   print(result)
   ```

   ```bash
   python quickstart.py
   ```

   Each user opens the link once and enters their PDF Vector credentials there. See [Authorize a user](/agentkit/tools/authorize/) for the full flow and statuses.

## Tools

Pass the exact name to `execute_tool`, with an input like each tool's example. To ask for a tool that's missing, use the [request form](https://scalekitsupport.portal.usepylon.com/forms/request-a-connector-tool).

**Node.js**

```typescript
const result = await actions.executeTool({
  toolName: 'pdfvector_academic_fetch',
  toolInput: {
    ids: ['10.48550/arXiv.1706.03762', 'arXiv:2005.14165'],
  },
  connector: 'pdfvector',
  identifier: 'user_123',
})
```

**Python**

```python
result = actions.execute_tool(
    tool_name="pdfvector_academic_fetch",
    tool_input={
        "ids": ["10.48550/arXiv.1706.03762", "arXiv:2005.14165"],
    },
    connection_name="pdfvector",
    identifier="user_123",
)
```

`result.data` is the app's response as JSON, and `result.execution_id` (`executionId` in Node.js) is the ID of the call.

### `pdfvector_academic_fetch`

Fetch Academic Papers · Read-only

Fetch academic publications by identifier: DOI, PubMed ID, arXiv ID, Semantic Scholar ID, ERIC ID, Europe PMC ID or OpenAlex ID. Costs 2 credits.
Returns each publication's metadata, such as title, authors, year, abstract, citation counts and PDF link.
Use this to look up known papers. Use pdfvector_academic_search to find papers by topic.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `ids` (`array`, required): Publication identifiers to fetch; the provider is detected automatically. Example: ["10.48550/arXiv.1706.03762", "arXiv:2005.14165"]
- `fields` (`array`, optional): Publication fields to return. All fields except providerData are returned when empty. Example: ["title", "doi", "authors", "year", "abstract", "pdfURL"]

Example input: `{"ids":["10.48550/arXiv.1706.03762","arXiv:2005.14165"]}`

### `pdfvector_academic_find_citations`

Find Citations · Read-only

Find academic papers that support each sentence of a paragraph, using semantic similarity. Costs 2 credits per sentence.
Returns, per sentence, the matching papers with relevance scores and metadata.
Use this to add references to your own text. Use pdfvector_academic_search for a keyword search.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `paragraph` (`string`, required): The text to find citations for. Example: Large language models can be adapted to new tasks with only a few examples provided in the prompt.
- `fields` (`array`, optional): Publication fields to return. All fields except providerData are returned when empty. Example: ["title", "doi", "authors", "year", "abstract", "pdfURL"]
- `providers` (`array`, optional): Databases to search. Defaults to semantic-scholar. Example: ["semantic-scholar", "openalex"]

Example input: `{"paragraph":"<paragraph>"}`

### `pdfvector_academic_paper_graph`

Get Paper Citations and References · Read-only

Get the papers that cite a paper and the papers it references, as full publication objects. Costs 2 or more credits, scaling with results.
Returns citations and references lists with publication metadata and totals.
Use this to explore a citation network. Use pdfvector_academic_similar_papers for related papers ranked by similarity.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `id` (`string`, required): Paper identifier: DOI, Semantic Scholar, arXiv, PubMed or OpenAlex ID, or a URL. Example: 10.48550/arXiv.1706.03762.
- `citations_limit` (`integer`, optional): Maximum citing papers to return, 0 to 1000. Defaults to 100. Example: 50.
- `citations_offset` (`integer`, optional): Citing papers to skip, for paging. Defaults to 0. Example: 0.
- `fields` (`array`, optional): Publication fields to return. All fields except providerData are returned when empty. Example: ["title", "doi", "authors", "year", "abstract", "pdfURL"]
- `references_limit` (`integer`, optional): Maximum referenced papers to return, 0 to 1000. Defaults to 100. Example: 50.
- `references_offset` (`integer`, optional): Referenced papers to skip, for paging. Defaults to 0. Example: 0.

Example input: `{"id":"<id>"}`

### `pdfvector_academic_parse`

Parse Academic Paper · Read-only

Find the public PDF of an academic paper from its identifier or URL and convert it into markdown.
Returns the paper's markdown, page count and credits charged, or NOT_FOUND when no public PDF exists.
Use this to read a paper's full text. Use pdfvector_document_parse for a PDF you already have a URL to.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the result to this URL. Example: https://example.com/hooks/pdfvector.
- `id` (`string`, optional): Publication identifier (DOI, PubMed, arXiv, Semantic Scholar, ERIC, Europe PMC or OpenAlex ID). Send id or url. Example: 10.48550/arXiv.1706.03762.
- `include_pages` (`boolean`, optional): Set true to also return markdown split by page. Example: false.
- `model` (`string`, optional): Model tier for parsing: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Publication page URL from a known provider (DOI, arXiv, PubMed, Semantic Scholar, Springer, Nature, bioRxiv and others). Send id or url. Example: https://arxiv.org/abs/1706.03762.

Example input: `{}`

### `pdfvector_academic_search`

Search Academic Papers · Read-only

Search academic publications across Semantic Scholar, PubMed, arXiv, Google Scholar, ERIC, Europe PMC, OpenAlex and Crossref, ranked by relevance. Costs 2 credits.
Returns publications with title, DOI, authors, year, abstract, citation counts and PDF links.
Use this to find papers on a topic. Use pdfvector_academic_fetch when you already have IDs.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): Search query. Example: transformer attention mechanisms.
- `fields` (`array`, optional): Publication fields to return. All fields except providerData are returned when empty. Example: ["title", "doi", "authors", "year", "abstract", "pdfURL"]
- `limit` (`integer`, optional): Results per database, 1 to 100. Defaults to 20. Example: 20.
- `offset` (`integer`, optional): Results to skip, for paging. Defaults to 0. Example: 0.
- `providers` (`array`, optional): Databases to search. Defaults to semantic-scholar. Example: ["semantic-scholar", "arxiv", "pubmed"]
- `year_from` (`integer`, optional): Only papers published in or after this year. Example: 2020.
- `year_to` (`integer`, optional): Only papers published in or before this year. Example: 2026.

Example input: `{"query":"<query>"}`

### `pdfvector_academic_search_grants`

Search Research Grants · Read-only

Search research grants and funding opportunities across Grants.gov, NIH RePORTER, CORDIS and UKRI. Costs 2 credits.
Returns grants with title, agency, program, funding amounts, deadlines, eligibility, description and links.
Use this to find funding. Use pdfvector_academic_search for publications.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `query` (`string`, required): Search query. Example: machine learning for climate modeling.
- `deadline_from` (`string`, optional): Only grants with a deadline on or after this date (YYYY-MM-DD). Example: 2026-01-01.
- `deadline_to` (`string`, optional): Only grants with a deadline on or before this date (YYYY-MM-DD). Example: 2026-12-31.
- `fields` (`array`, optional): Grant fields to return. All fields except providerData are returned when empty. Example: ["title", "agency", "fundingAmountMax", "deadlineDate", "url"]
- `funding_max` (`number`, optional): Maximum funding amount. Example: 500000.
- `funding_min` (`number`, optional): Minimum funding amount. Example: 50000.
- `limit` (`integer`, optional): Results per database, 1 to 50. Defaults to 10. Example: 10.
- `offset` (`integer`, optional): Results to skip, for paging. Defaults to 0. Example: 0.
- `providers` (`array`, optional): Grant databases to search. Defaults to all four. Example: ["grants-gov", "nih-reporter"]

Example input: `{"query":"<query>"}`

### `pdfvector_academic_similar_papers`

Find Similar Papers · Read-only

Find papers similar to a seed paper using citation network analysis. Costs 3 credits.
Returns papers ranked by similarity score with metadata, and citation edges when requested.
Use this for related reading. Use pdfvector_academic_paper_graph for direct citations and references.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `id` (`string`, required): Seed paper identifier: DOI, Semantic Scholar, arXiv, PubMed or OpenAlex ID, or a URL. Example: 10.48550/arXiv.1706.03762.
- `fields` (`array`, optional): Publication fields to return. All fields except providerData are returned when empty. Example: ["title", "doi", "authors", "year", "abstract", "pdfURL"]
- `include_edges` (`boolean`, optional): Set true to include citing and cited-by edges for drawing a graph. Example: false.
- `limit` (`integer`, optional): Maximum similar papers to return, 1 to 100. Defaults to 30. Example: 30.

Example input: `{"id":"<id>"}`

### `pdfvector_bank_statement_ask`

Ask Bank Statement · Read-only

Answer a natural-language question about a bank statement with PDF Vector's AI.
Returns the answer text with the model tier used and credits charged.
Use this for one question. Use pdfvector_bank_statement_parse for the full text or pdfvector_bank_statement_extract for structured JSON.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `question` (`string`, required): The question to answer about the bank statement. Example: What is the total amount due and when is it due?.
- `base64` (`string`, optional): The bank statement file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for answering: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the bank statement file to process. Send url or base64. Example: https://example.com/statements/2026-10.pdf.

Example input: `{"question":"<question>"}`

### `pdfvector_bank_statement_extract`

Extract Bank Statement Data · Read-only

Extract structured data from a bank statement into JSON that matches a JSON Schema you provide, using PDF Vector's AI.
Returns the extracted data object with the model tier used and credits charged.
Use this to fill your own fields. Use pdfvector_bank_statement_parse for plain markdown.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `prompt` (`string`, required): Instructions telling the AI what to extract. Example: Extract the invoice number, issue date, vendor name and total amount.
- `schema` (`object`, required): JSON Schema of the data to return. Example: {"type": "object", "properties": {"invoice_number": {"type": "string"}, "total": {"type": "number"}}, "required": ["invoice_number"]}
- `base64` (`string`, optional): The bank statement file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for extraction: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the bank statement file to process. Send url or base64. Example: https://example.com/statements/2026-10.pdf.

Example input: `{"prompt":"<prompt>","schema":{}}`

### `pdfvector_bank_statement_parse`

Parse Bank Statement · Read-only

Parse a bank statement into clean markdown text and structured bank statement fields with PDF Vector.
Returns the markdown, page count, the model tier used and credits charged.
Use this to read a whole bank statement. Use pdfvector_bank_statement_ask for one question, or pdfvector_bank_statement_extract for JSON matching your schema.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `base64` (`string`, optional): The bank statement file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for parsing: auto (default), pro (6 credits a page) or max (10 credits a page, highest accuracy). Example: auto. One of: `auto`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the bank statement file to process. Send url or base64. Example: https://example.com/statements/2026-10.pdf.

Example input: `{}`

### `pdfvector_document_ask`

Ask Document · Read-only

Answer a natural-language question about any document (PDF, Word, Excel, PowerPoint, CSV, images, HTML, EPUB and 20+ formats) with PDF Vector's AI.
Returns the answer text with the model tier used and credits charged.
Use this for one question. Use pdfvector_document_parse for the full text or pdfvector_document_extract for structured JSON.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `question` (`string`, required): The question to answer about the document. Example: What is the total amount due and when is it due?.
- `base64` (`string`, optional): The document file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for answering: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the document file to process. Send url or base64. Example: https://arxiv.org/pdf/1706.03762.

Example input: `{"question":"<question>"}`

### `pdfvector_document_extract`

Extract Document Data · Read-only

Extract structured data from any document (PDF, Word, Excel, PowerPoint, CSV, images, HTML, EPUB and 20+ formats) into JSON that matches a JSON Schema you provide, using PDF Vector's AI.
Returns the extracted data object with the model tier used and credits charged.
Use this to fill your own fields. Use pdfvector_document_parse for plain markdown.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `prompt` (`string`, required): Instructions telling the AI what to extract. Example: Extract the invoice number, issue date, vendor name and total amount.
- `schema` (`object`, required): JSON Schema of the data to return. Example: {"type": "object", "properties": {"invoice_number": {"type": "string"}, "total": {"type": "number"}}, "required": ["invoice_number"]}
- `base64` (`string`, optional): The document file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for extraction: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the document file to process. Send url or base64. Example: https://arxiv.org/pdf/1706.03762.

Example input: `{"prompt":"<prompt>","schema":{}}`

### `pdfvector_document_parse`

Parse Document · Read-only

Parse any document (PDF, Word, Excel, PowerPoint, CSV, images, HTML, EPUB and 20+ formats) into clean markdown text with PDF Vector.
Returns the markdown, page count, the model tier used and credits charged.
Use this to read a whole document. Use pdfvector_document_ask for one question, or pdfvector_document_extract for JSON matching your schema.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `base64` (`string`, optional): The document file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `include_pages` (`boolean`, optional): Set true to also return markdown split by page in a pages array. Example: false.
- `model` (`string`, optional): Model tier for parsing: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the document file to process. Send url or base64. Example: https://arxiv.org/pdf/1706.03762.

Example input: `{}`

### `pdfvector_identity_ask`

Ask Identity Document · Read-only

Answer a natural-language question about a passport, driver's license or national ID card with PDF Vector's AI.
Returns the answer text with the model tier used and credits charged.
Use this for one question. Use pdfvector_identity_parse for the full text or pdfvector_identity_extract for structured JSON.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `question` (`string`, required): The question to answer about the identity document. Example: What is the total amount due and when is it due?.
- `base64` (`string`, optional): The identity document file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for answering: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the identity document file to process. Send url or base64. Example: https://example.com/scans/passport.jpg.

Example input: `{"question":"<question>"}`

### `pdfvector_identity_extract`

Extract Identity Document Data · Read-only

Extract structured data from a passport, driver's license or national ID card into JSON that matches a JSON Schema you provide, using PDF Vector's AI.
Returns the extracted data object with the model tier used and credits charged.
Use this to fill your own fields. Use pdfvector_identity_parse for plain markdown.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `prompt` (`string`, required): Instructions telling the AI what to extract. Example: Extract the invoice number, issue date, vendor name and total amount.
- `schema` (`object`, required): JSON Schema of the data to return. Example: {"type": "object", "properties": {"invoice_number": {"type": "string"}, "total": {"type": "number"}}, "required": ["invoice_number"]}
- `base64` (`string`, optional): The identity document file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for extraction: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the identity document file to process. Send url or base64. Example: https://example.com/scans/passport.jpg.

Example input: `{"prompt":"<prompt>","schema":{}}`

### `pdfvector_identity_parse`

Parse Identity Document · Read-only

Parse a passport, driver's license or national ID card into clean markdown text and structured identity document fields with PDF Vector.
Returns the markdown, page count, the model tier used and credits charged.
Use this to read a whole identity document. Use pdfvector_identity_ask for one question, or pdfvector_identity_extract for JSON matching your schema.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `base64` (`string`, optional): The identity document file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for parsing: auto (default), pro (6 credits a page) or max (10 credits a page, highest accuracy). Example: auto. One of: `auto`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the identity document file to process. Send url or base64. Example: https://example.com/scans/passport.jpg.

Example input: `{}`

### `pdfvector_invoice_ask`

Ask Invoice · Read-only

Answer a natural-language question about an invoice with PDF Vector's AI.
Returns the answer text with the model tier used and credits charged.
Use this for one question. Use pdfvector_invoice_parse for the full text or pdfvector_invoice_extract for structured JSON.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `question` (`string`, required): The question to answer about the invoice. Example: What is the total amount due and when is it due?.
- `base64` (`string`, optional): The invoice file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for answering: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the invoice file to process. Send url or base64. Example: https://example.com/invoices/inv-1042.pdf.

Example input: `{"question":"<question>"}`

### `pdfvector_invoice_extract`

Extract Invoice Data · Read-only

Extract structured data from an invoice into JSON that matches a JSON Schema you provide, using PDF Vector's AI.
Returns the extracted data object with the model tier used and credits charged.
Use this to fill your own fields. Use pdfvector_invoice_parse for plain markdown.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `prompt` (`string`, required): Instructions telling the AI what to extract. Example: Extract the invoice number, issue date, vendor name and total amount.
- `schema` (`object`, required): JSON Schema of the data to return. Example: {"type": "object", "properties": {"invoice_number": {"type": "string"}, "total": {"type": "number"}}, "required": ["invoice_number"]}
- `base64` (`string`, optional): The invoice file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for extraction: auto (default) picks one; nano, mini, pro and max trade speed and credits for accuracy. Example: auto. One of: `auto`, `nano`, `mini`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the invoice file to process. Send url or base64. Example: https://example.com/invoices/inv-1042.pdf.

Example input: `{"prompt":"<prompt>","schema":{}}`

### `pdfvector_invoice_parse`

Parse Invoice · Read-only

Parse an invoice into clean markdown text and structured invoice fields with PDF Vector.
Returns the markdown, page count, the model tier used and credits charged.
Use this to read a whole invoice. Use pdfvector_invoice_ask for one question, or pdfvector_invoice_extract for JSON matching your schema.

Read only: yes. Destructive: no. Idempotent (safe to retry): yes.

Inputs:

- `base64` (`string`, optional): The invoice file content, base64-encoded, when it has no public URL. Send url or base64. Example: JVBERi0xLjQKJcfsj6IKNSAwIG9iago8PC9MZW5ndGggNiAwIFI+PgpzdHJlYW0K.
- `callback_url` (`string`, optional): Webhook URL for asynchronous processing. When set, PDF Vector returns 202 at once and POSTs the full result to this URL. Example: https://example.com/hooks/pdfvector.
- `document_id` (`string`, optional): Your own reference ID for this document, used for usage attribution. Example: order-1042.
- `model` (`string`, optional): Model tier for parsing: auto (default), pro (6 credits a page) or max (10 credits a page, highest accuracy). Example: auto. One of: `auto`, `pro`, `max`. Default: `auto`.
- `url` (`string`, optional): Public URL of the invoice file to process. Send url or base64. Example: https://example.com/invoices/inv-1042.pdf.

Example input: `{}`

## Related

Other Files & Documents connectors ([all 76](/agentkit/connectors/?category=files-documents)):

- [Notion](/agentkit/connectors/notion/): Scalekit connector, OAuth, 51 tools
- [Google Sheets](/agentkit/connectors/googlesheets/): Scalekit connector, OAuth, 48 tools
- [Google Drive](/agentkit/connectors/googledrive/): Scalekit connector, OAuth, 47 tools


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |
