mirror of
https://github.com/simstudioai/sim.git
synced 2026-02-07 21:25:38 -05:00
552dc56fc3
* feat(confluence): added more confluence endpoints * update license * updated * updated docs
62 lines
2.7 KiB
Plaintext
62 lines
2.7 KiB
Plaintext
---
|
|
title: Mistral Parser
|
|
description: Extract text from PDF documents
|
|
---
|
|
|
|
import { BlockInfoCard } from "@/components/ui/block-info-card"
|
|
|
|
<BlockInfoCard
|
|
type="mistral_parse_v3"
|
|
color="#000000"
|
|
/>
|
|
|
|
{/* MANUAL-CONTENT-START:intro */}
|
|
The Mistral Parse tool provides a powerful way to extract and process content from PDF documents using [Mistral's OCR API](https://mistral.ai/). This tool leverages advanced optical character recognition to accurately extract text and structure from PDF files, making it easy to incorporate document data into your agent workflows.
|
|
|
|
With the Mistral Parse tool, you can:
|
|
|
|
- **Extract text from PDFs**: Accurately convert PDF content to text, markdown, or JSON formats
|
|
- **Process PDFs from URLs**: Directly extract content from PDFs hosted online by providing their URLs
|
|
- **Maintain document structure**: Preserve formatting, tables, and layout from the original PDFs
|
|
- **Extract images**: Optionally include embedded images from the PDFs
|
|
- **Select specific pages**: Process only the pages you need from multi-page documents
|
|
|
|
The Mistral Parse tool is particularly useful for scenarios where your agents need to work with PDF content, such as analyzing reports, extracting data from forms, or processing text from scanned documents. It simplifies the process of making PDF content available to your agents, allowing them to work with information stored in PDFs just as easily as with direct text input.
|
|
{/* MANUAL-CONTENT-END */}
|
|
|
|
|
|
## Usage Instructions
|
|
|
|
Integrate Mistral Parse into the workflow. Can extract text from uploaded PDF documents, or from a URL.
|
|
|
|
|
|
|
|
## Tools
|
|
|
|
### `mistral_parser`
|
|
|
|
#### Input
|
|
|
|
| Parameter | Type | Required | Description |
|
|
| --------- | ---- | -------- | ----------- |
|
|
| `filePath` | string | No | URL to a PDF document to be processed |
|
|
| `file` | file | No | Document file to be processed |
|
|
| `fileUpload` | object | No | File upload data from file-upload component |
|
|
| `resultType` | string | No | Type of parsed result \(markdown, text, or json\). Defaults to markdown. |
|
|
| `includeImageBase64` | boolean | No | Include base64-encoded images in the response |
|
|
| `pages` | array | No | Specific pages to process \(array of page numbers, starting from 0\) |
|
|
| `imageLimit` | number | No | Maximum number of images to extract from the PDF |
|
|
| `imageMinSize` | number | No | Minimum height and width of images to extract from the PDF |
|
|
| `apiKey` | string | Yes | Mistral API key \(MISTRAL_API_KEY\) |
|
|
|
|
#### Output
|
|
|
|
| Parameter | Type | Description |
|
|
| --------- | ---- | ----------- |
|
|
| `pages` | array | Array of page objects from Mistral OCR |
|
|
| `model` | string | Mistral OCR model identifier |
|
|
| `usage_info` | json | Usage statistics from the API |
|
|
| `document_annotation` | string | Structured annotation data |
|
|
|
|
|