---
canonical_url: "https://docs.composio.dev/toolkits/pdf_vector"
markdown_url: "https://docs.composio.dev/toolkits/pdf_vector.md"
product: "platform"
version: null
last_updated: null
---

# PDF Vector

PDF Vector parses documents into markdown, extracts structured data, answers document questions, and searches academic publications and grants.

- **Category:** ai document extraction
- **Auth:** API_KEY
- **Composio-managed OAuth available?** N/A
- **Tools:** 10
- **Triggers:** 0
- **Slug:** `PDF_VECTOR`
- **Version:** 00000000_00

## Tools

### Ask Document

**Slug:** `PDF_VECTOR_ASK_DOCUMENT`

Answer one question from a general, identity, invoice, or bank-statement document. Processing consumes credits; the response reports the actual model and credit cost. The tool never retries with a higher model automatically.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | No | A document supplied through Composio's file input. |
| `model` | string ("auto" | "nano" | "mini" | "pro" | "max") | No | Processing model. Higher models can consume more credits; this tool does not escalate automatically. |
| `base64` | string | No | Base64-encoded document content. Prefer a URL or file for large documents; provide exactly one source. |
| `question` | string | Yes | Question to answer from the document (at least 4 characters). |
| `document_id` | string | No | Optional caller-defined document identifier echoed in the response. |
| `document_url` | string | No | Publicly fetchable URL of the document. Provide exactly one of document_url, file, or base64. |
| `document_type` | string ("general" | "identity" | "invoice" | "bank_statement") | No | Document specialization to use. Choose identity, invoice, or bank_statement only for that document class. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Extract Document Data

**Slug:** `PDF_VECTOR_EXTRACT_DOCUMENT`

Extract schema-constrained structured data from a general, identity, invoice, or bank-statement document. Processing consumes credits and never retries with a higher model automatically.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | No | A document supplied through Composio's file input. |
| `model` | string ("auto" | "nano" | "mini" | "pro" | "max") | No | Processing model. Higher models can consume more credits; this tool does not escalate automatically. |
| `base64` | string | No | Base64-encoded document content. Prefer a URL or file for large documents and provide exactly one source. |
| `prompt` | string | Yes | Extraction instructions describing the fields to return. |
| `document_id` | string | No | Optional caller-defined document identifier echoed in the response. |
| `document_url` | string | No | Publicly fetchable document URL. Provide exactly one of document_url, file, or base64. |
| `document_type` | string ("general" | "identity" | "invoice" | "bank_statement") | No | Document specialization to use. Choose identity, invoice, or bank_statement only for that document class. |
| `output_schema` | object | Yes | JSON Schema that the extracted data must follow. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Fetch Publications

**Slug:** `PDF_VECTOR_FETCH_PUBLICATIONS`

Resolve up to 100 publication identifiers with provider auto-detection and return both resolved records and per-identifier errors.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `ids` | array | Yes | One to 100 DOI, PMID, arXiv, Semantic Scholar, ERIC, Europe PMC, or OpenAlex identifiers. |
| `fields` | array | No | Publication fields to return; omit to use provider defaults. Choices: doi, title, url, providerURL, authors, date, year, totalCitations, totalReferences, abstract, pdfURL, provider, providerData. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Find Citations

**Slug:** `PDF_VECTOR_FIND_CITATIONS`

Find relevant academic citations for each sentence in a paragraph and preserve provider-specific partial errors.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `fields` | array | No | Publication fields to include for each citation; omit for provider defaults. Choices: doi, title, url, providerURL, authors, date, year, totalCitations, totalReferences, abstract, pdfURL, provider, providerData. |
| `paragraph` | string | Yes | Paragraph whose sentences need supporting citations (1-5000 characters). |
| `providers` | array | No | Academic databases to search for citations. Choices: semantic-scholar, pubmed, arxiv, google-scholar, eric, europe-pmc, openalex, crossref. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Find Similar Papers

**Slug:** `PDF_VECTOR_FIND_SIMILAR_PAPERS`

Find papers related to a seed publication using citation-network similarity, optionally including relationship edges.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `id` | string | Yes | Seed publication identifier (1-500 characters). |
| `limit` | integer | No | Maximum similar papers to return (1-100). |
| `fields` | array | No | Publication fields to return for the seed and similar papers. Choices: doi, title, url, providerURL, authors, date, year, totalCitations, totalReferences, abstract, pdfURL, provider, providerData. |
| `include_edges` | boolean | No | Include citing and cited-by identifier edges supporting each similarity result. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Get Paper Graph

**Slug:** `PDF_VECTOR_GET_PAPER_GRAPH`

Retrieve a publication plus one independently offset-controlled page of citing papers and one page of referenced papers.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `id` | string | Yes | Publication identifier for the graph root (1-500 characters). |
| `fields` | array | No | Publication fields to return for the root, citing papers, and referenced papers; omit for provider defaults. Choices: doi, title, url, providerURL, authors, date, year, totalCitations, totalReferences, abstract, pdfURL, provider, providerData. |
| `citations_limit` | integer | No | Maximum citing papers to return (0-1000). |
| `citations_offset` | integer | No | Zero-based offset into citing papers. |
| `references_limit` | integer | No | Maximum referenced papers to return (0-1000). |
| `references_offset` | integer | No | Zero-based offset into referenced papers. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Parse Academic Paper

**Slug:** `PDF_VECTOR_PARSE_ACADEMIC_PAPER`

Resolve an academic identifier or provider URL to a public PDF and parse it to markdown. Processing consumes credits, returns the actual model and credit cost, and never retries with a higher model automatically.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `model` | string ("auto" | "nano" | "mini" | "pro" | "max") | No | Parsing model. Higher models can consume more credits; the tool uses only the selected model and does not escalate automatically. |
| `include_pages` | boolean | No | Include markdown split into individual pages. |
| `publication_id` | string | No | DOI or supported provider identifier. Provide exactly one of publication_id or publication_url. |
| `publication_url` | string | No | Supported provider publication URL. Provide exactly one of publication_url or publication_id. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Parse Document

**Slug:** `PDF_VECTOR_PARSE_DOCUMENT`

Convert a general, identity, invoice, or bank-statement document to markdown. Processing consumes credits; returns the actual model and credit cost and never retries with a higher model automatically.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `file` | object | No | A document supplied through Composio's file input. |
| `model` | string ("auto" | "nano" | "mini" | "pro" | "max") | No | Processing model. Higher models can consume more credits. Identity, invoice, and bank-statement parsing accept only auto, pro, or max. |
| `base64` | string | No | Base64-encoded document content. Prefer a URL or file for large documents; provide exactly one source. |
| `document_id` | string | No | Optional caller-defined document identifier (1-512 characters) echoed in the response. |
| `document_url` | string | No | Publicly fetchable URL of the document. Provide exactly one of document_url, file, or base64. |
| `document_type` | string ("general" | "identity" | "invoice" | "bank_statement") | No | Document specialization to use. Choose identity, invoice, or bank_statement only for that document class. |
| `include_pages` | boolean | No | For general documents only, include markdown split into individual pages. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Publications

**Slug:** `PDF_VECTOR_SEARCH_PUBLICATIONS`

Search academic publications across selected databases and return one offset-controlled page, including any provider-specific partial errors.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum results per provider for this page (1-100). |
| `query` | string | Yes | Publication search query (1-400 characters). |
| `fields` | array | No | Publication fields to return; omit for provider defaults. Choices: doi, title, url, providerURL, authors, date, year, totalCitations, totalReferences, abstract, pdfURL, provider, providerData. |
| `offset` | integer | No | Zero-based result offset for this page; increase it by the number of returned results to request another page. |
| `year_to` | integer | No | Latest publication year, inclusive (1900-2100). |
| `providers` | array | No | Academic databases to search. Choices: semantic-scholar, pubmed, arxiv, google-scholar, eric, europe-pmc, openalex, crossref. |
| `year_from` | integer | No | Earliest publication year, inclusive (1900-2100). |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |

### Search Research Grants

**Slug:** `PDF_VECTOR_SEARCH_RESEARCH_GRANTS`

Search US, EU, and UK research-grant providers and return one explicit offset-controlled page with partial provider errors.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `limit` | integer | No | Maximum results per provider for this page (1-50). |
| `query` | string | Yes | Grant search query (1-400 characters). |
| `fields` | array | No | Grant fields to return; omit for provider defaults. Choices: sourceId, title, url, agency, program, description, eligibility, fundingAmountMin, fundingAmountMax, currency, deadlineDate, openDate, closeDate, grantType, region, keywords, piName, organizationName, provider, providerData. |
| `offset` | integer | No | Zero-based result offset for this page; increase it by the number of returned results to request another page. |
| `providers` | array | No | Grant databases to search; omit to search all supported providers. Choices: grants-gov, nih-reporter, cordis, ukri. |
| `deadline_to` | string | No | Latest grant deadline, inclusive, in YYYY-MM-DD format. |
| `funding_max` | number | No | Maximum funding amount; must be non-negative. |
| `funding_min` | number | No | Minimum funding amount; must be non-negative. |
| `deadline_from` | string | No | Earliest grant deadline, inclusive, in YYYY-MM-DD format. |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `data` | string | Yes | Data from the action execution |
| `error` | string | No | Error if any occurred during the execution of the action |
| `successful` | boolean | Yes | Whether or not the action execution was successful or not |