github/sim
1
1
Fork 0
mirror of https://github.com/simstudioai/sim.git synced 2026-04-28 03:00:29 -04:00
Code Issues Packages Projects Releases Wiki Activity

added mistral v2, files v2, and finalized textract

Browse Source
This commit is contained in:
waleed
2026-01-20 15:02:27 -08:00
parent dcaae1df7c
commit 59578dd140
16 changed files with 368 additions and 188 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
apps/docs/content/docs/en/tools/file.mdx
View File

@@ -6,7 +6,7 @@ description: Read and parse multiple files
import { BlockInfoCard } from "@/components/ui/block-info-card"
<BlockInfoCard
type="file"
type="file_v2"
color="#40916C"
/>
@@ -48,7 +48,7 @@ Parse one or more uploaded files or files from URLs (text, PDF, CSV, images, etc
| Parameter | Type | Description |
| --------- | ---- | ----------- |
| `files` | array | Array of parsed files |
| `combinedContent` | string | Combined content of all parsed files |
| `files` | array | Array of parsed files with content, metadata, and file properties |
| `combinedContent` | string | All file contents merged into a single text string |

12
apps/docs/content/docs/en/tools/mistral_parse.mdx
View File

@@ -6,7 +6,7 @@ description: Extract text from PDF documents
import { BlockInfoCard } from "@/components/ui/block-info-card"
<BlockInfoCard
type="mistral_parse"
type="mistral_parse_v2"
color="#000000"
/>
@@ -57,15 +57,5 @@ Parse PDF documents using Mistral OCR API
| `success` | boolean | Whether the PDF was parsed successfully |
| `content` | string | Extracted content in the requested format \(markdown, text, or JSON\) |
| `metadata` | object | Processing metadata including jobId, fileType, pageCount, and usage info |
| ↳ `jobId` | string | Unique job identifier |
| ↳ `fileType` | string | File type \(e.g., pdf\) |
| ↳ `fileName` | string | Original file name |
| ↳ `source` | string | Source type \(url\) |
| ↳ `pageCount` | number | Number of pages processed |
| ↳ `model` | string | Mistral model used |
| ↳ `resultType` | string | Output format \(markdown, text, json\) |
| ↳ `processedAt` | string | Processing timestamp |
| ↳ `sourceUrl` | string | Source URL if applicable |
| ↳ `usageInfo` | object | Usage statistics from OCR processing |