Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Open-source platform for extracting structured data from documents using AI.
| Date | Stars |
|---|---|
| 2026-07-24 | 1516 |
| 2026-07-25 | 1517 |
| 2026-07-28 | 1517 |
| 2026-07-30 | 1517 |
| 2026-08-06 | 1517 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<a href="https://discord.gg/w2Ejj36hRU">
<img src="https://user-images.githubusercontent.com/31022056/158916278-4504b838-7ecb-4ab9-a900-7dc002aade78.png" alt="Join us on Discord" width="200px">
</a>
# Documind
**`Documind`** is an advanced document processing tool that leverages AI to extract structured data from PDFs. It is built to handle PDF conversions, extract relevant information, and format results as specified by customizable schemas.
## **Features**
- Extracts structured JSON output from unstructured documents.
- Converts documents into Markdown format.
- Supports custom schemas for data extraction.
- Includes pre-defined templates for common schemas.
- Works with OpenAI and custom LLM setups (Llava and Llama3.2-vision).
- Auto-generates schemas based on document content.
### Try the Hosted Version 🚀
The hosted version provides a seamless experience with fully managed APIs, so you can skip the setup and start extracting data right away. [Join the beta](https://documind.xyz) to get access to the hosted service.
## Roadmap
### ✅ Released Features
- [x] PDF Extraction
- [x] Basic Schema Definition
- [x] Structured JSON Output
- [x] Template Schemas
- [x] Local LLM Integration (Llama3.2)
- [x] Auto-generated Schemas
- [x] Document Formatters (Text and Markdown)
- [x] Multi-file Support (DOCX, PNG, JPG, TXT, HTML)
- [x] Additional Schema Field Types (Boolean and Enum)
### 🚧 Upcoming Features
- [ ] Additional Models (Local and cloud)
- [ ] Image Extraction
- [ ] Advanced Document Formatters
- [ ] Data Classification
- [ ] Use Your Fine-tuned Models
## **Requirements**
Before using **`documind`**, ensure the following software dependencies are installed:
### **System Dependencies**
- **Ghostscript**: **`documind`** relies on Ghostscript for handling certain PDF operations.
- **GraphicsMagick**: Required for image processing within document conversions.
Install both on your system before proceeding:
```bash
# On macOS
brew install ghostscript graphicsmagick
# On Debian/Ubuntu
sudo apt-get update
sudo apt-get install -y ghostscript graphicsmagick
```
### **Node.js & NPM**
Ensure Node.js (v18+) and NPM are installed on your system.
## **Installation**
You can install **`documind`** via npm:
```bash
npm install documind
```
### **Environment Setup**
**`documind`** requires an **`.env`** file to store sensitive information like your OpenAI API key.
Create an **`.env`** file in your project directory and add the following:
```bash
OPENAI_API_KEY=your_openai_api_key
```
## **Usage**
### **Basic Example**
First, import **`documind`** and define your schema. The schema outline what information **`documind`** should look for in each document. Here’s a quick setup to get started.
### **1. Define a Schema**
The schema is an array of objects where each object defines:
- **name**: Field name to extract.
- **type**: Data type (e.g., **`"string"`**, **`"number"`**, **`"array"`**, **`"object"`**).
- **description**: Description of the field.
- **children** (optional): For arrays and objects, define nested fields.
Example schema for a bank statement:
```jsx
const schema = [
{
name: "accountNumber",
type: "string",
description: "The account number of the bank statement."
},
{
name: "openingBalance",
type: "number",
description: "The opening balance of the account."
},
{
name: "transactions",
type: "array",
description: "List of transactions in the account.",
children: [
{
name: "date",
type: "string",
description: "Transaction date."
},
{
name: "creditAmount",
type: "number",
description: "Credit Amount of the transaction."
},
{
name: "debitAmount",
type: "number",
description: "Debit Amount of the transaction."
},
{
name: "description",
type: "string",
description: "Transaction description."
Excerpt of 7,089 characters
Read on GitHub
71
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:028782bb23825b99, topic:ocr, readme:pdf extraction
matched fp:028782bb23825b99, topic:developer-tools