@@ -6,7 +6,7 @@ description: Extract text from PDF documents
66import { BlockInfoCard } from " @/components/ui/block-info-card"
77
88<BlockInfoCard
9- type = " mistral_parse_v2 "
9+ type = " mistral_parse_v3 "
1010 color = " #000000"
1111/>
1212
@@ -35,8 +35,6 @@ Integrate Mistral Parse into the workflow. Can extract text from uploaded PDF do
3535
3636### ` mistral_parser `
3737
38- Parse PDF documents using Mistral OCR API
39-
4038#### Input
4139
4240| Parameter | Type | Required | Description |
@@ -56,27 +54,8 @@ Parse PDF documents using Mistral OCR API
5654| Parameter | Type | Description |
5755| --------- | ---- | ----------- |
5856| ` pages ` | array | Array of page objects from Mistral OCR |
59- | ↳ ` index ` | number | Page index \( zero-based\) |
60- | ↳ ` markdown ` | string | Extracted markdown content |
61- | ↳ ` images ` | array | Images extracted from this page with bounding boxes |
62- | ↳ ` id ` | string | Image identifier \( e.g., img-0.jpeg\) |
63- | ↳ ` top_left_x ` | number | Top-left X coordinate in pixels |
64- | ↳ ` top_left_y ` | number | Top-left Y coordinate in pixels |
65- | ↳ ` bottom_right_x ` | number | Bottom-right X coordinate in pixels |
66- | ↳ ` bottom_right_y ` | number | Bottom-right Y coordinate in pixels |
67- | ↳ ` image_base64 ` | string | Base64-encoded image data \( when include_image_base64=true\) |
68- | ↳ ` dimensions ` | object | Page dimensions |
69- | ↳ ` dpi ` | number | Dots per inch |
70- | ↳ ` height ` | number | Page height in pixels |
71- | ↳ ` width ` | number | Page width in pixels |
72- | ↳ ` tables ` | array | Extracted tables as HTML/markdown \( when table_format is set\) . Referenced via placeholders like \[ tbl-0.html\] |
73- | ↳ ` hyperlinks ` | array | Array of URL strings detected in the page \( e.g., \[ "https://...", "mailto:..."\]\) |
74- | ↳ ` header ` | string | Page header content \( when extract_header=true\) |
75- | ↳ ` footer ` | string | Page footer content \( when extract_footer=true\) |
76- | ` model ` | string | Mistral OCR model identifier \( e.g., mistral-ocr-latest\) |
77- | ` usage_info ` | object | Usage and processing statistics |
78- | ↳ ` pages_processed ` | number | Total number of pages processed |
79- | ↳ ` doc_size_bytes ` | number | Document file size in bytes |
80- | ` document_annotation ` | string | Structured annotation data as JSON string \( when applicable\) |
57+ | ` model ` | string | Mistral OCR model identifier |
58+ | ` usage_info ` | json | Usage statistics from the API |
59+ | ` document_annotation ` | string | Structured annotation data |
8160
8261
0 commit comments