Update README.md
Browse files
README.md
CHANGED
@@ -1,14 +1,159 @@
|
|
1 |
---
|
2 |
title: Convert To Json
|
3 |
emoji: π¬π
π
|
4 |
-
colorFrom:
|
5 |
-
colorTo:
|
6 |
sdk: gradio
|
7 |
-
sdk_version: 5.33.
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
11 |
short_description: Convert Free Text Into Json Using AI
|
12 |
---
|
13 |
|
|
|
|
|
14 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
title: Convert To Json
|
3 |
emoji: π¬π
π
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: green
|
6 |
sdk: gradio
|
7 |
+
sdk_version: 5.33.1
|
8 |
app_file: app.py
|
9 |
pinned: false
|
10 |
license: mit
|
11 |
short_description: Convert Free Text Into Json Using AI
|
12 |
---
|
13 |
|
14 |
+
youtube : https://youtu.be/PtWkJHNmo9k
|
15 |
+
|
16 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
17 |
+
# π Osmosis Structure - Text to JSON Converter
|
18 |
+
|
19 |
+
A powerful web application that converts unstructured text into well-formatted JSON using the Osmosis Structure 0.6B model. This tool is specifically designed for structured data extraction and format conversion tasks.
|
20 |
+
|
21 |
+
## π Features
|
22 |
+
|
23 |
+
- **Intelligent Text Processing**: Automatically identifies and extracts key information from unstructured text
|
24 |
+
- **Schema Support**: Optionally provide a JSON schema to structure the output according to your needs
|
25 |
+
- **Customizable Generation**: Fine-tune the output with adjustable parameters:
|
26 |
+
- Temperature
|
27 |
+
- Max tokens
|
28 |
+
- Top-p sampling
|
29 |
+
- Top-k sampling
|
30 |
+
- **User-Friendly Interface**: Clean and intuitive Gradio interface
|
31 |
+
- **Example Templates**: Pre-configured examples to help you get started
|
32 |
+
- **GPU Acceleration**: Optimized for GPU when available
|
33 |
+
|
34 |
+
## π Quick Start
|
35 |
+
|
36 |
+
1. Clone the repository:
|
37 |
+
```bash
|
38 |
+
git clone https://github.com/yourusername/Convert-to-Json.git
|
39 |
+
cd Convert-to-Json
|
40 |
+
```
|
41 |
+
|
42 |
+
2. Install dependencies:
|
43 |
+
```bash
|
44 |
+
pip install -r requirements.txt
|
45 |
+
```
|
46 |
+
|
47 |
+
3. Run the application:
|
48 |
+
```bash
|
49 |
+
python app.py
|
50 |
+
```
|
51 |
+
|
52 |
+
## π» Usage
|
53 |
+
|
54 |
+
### Basic Usage
|
55 |
+
|
56 |
+
1. Enter your unstructured text in the input field
|
57 |
+
2. (Optional) Provide a JSON schema to structure the output
|
58 |
+
3. Adjust generation parameters if needed
|
59 |
+
4. Click "Convert" or press Enter
|
60 |
+
5. View the structured JSON output
|
61 |
+
|
62 |
+
### Example Input
|
63 |
+
|
64 |
+
```text
|
65 |
+
The conference will be held on June 10-12, 2024 at the Grand Hotel in San Francisco.
|
66 |
+
Registration fee is $500 for early bird (before May 1) and $650 for regular registration.
|
67 |
+
Contact info@conference.com for questions.
|
68 |
+
```
|
69 |
+
|
70 |
+
### Example Schema
|
71 |
+
|
72 |
+
```json
|
73 |
+
{
|
74 |
+
"type": "object",
|
75 |
+
"properties": {
|
76 |
+
"event_start_date": {
|
77 |
+
"type": "string",
|
78 |
+
"format": "date"
|
79 |
+
},
|
80 |
+
"event_end_date": {
|
81 |
+
"type": "string",
|
82 |
+
"format": "date"
|
83 |
+
},
|
84 |
+
"location": {
|
85 |
+
"type": "string"
|
86 |
+
},
|
87 |
+
"registration_fees": {
|
88 |
+
"type": "object",
|
89 |
+
"properties": {
|
90 |
+
"early_bird_price": {
|
91 |
+
"type": "number"
|
92 |
+
},
|
93 |
+
"regular_price": {
|
94 |
+
"type": "number"
|
95 |
+
},
|
96 |
+
"early_bird_deadline": {
|
97 |
+
"type": "string",
|
98 |
+
"format": "date"
|
99 |
+
}
|
100 |
+
}
|
101 |
+
},
|
102 |
+
"contact_email": {
|
103 |
+
"type": "string"
|
104 |
+
}
|
105 |
+
}
|
106 |
+
}
|
107 |
+
```
|
108 |
+
|
109 |
+
### Example Output
|
110 |
+
|
111 |
+
```json
|
112 |
+
{
|
113 |
+
"event_start_date": "2024-06-10",
|
114 |
+
"event_end_date": "2024-06-12",
|
115 |
+
"location": "Grand Hotel, San Francisco",
|
116 |
+
"registration_fees": {
|
117 |
+
"early_bird_price": 500.0,
|
118 |
+
"regular_price": 650.0,
|
119 |
+
"early_bird_deadline": "2024-05-01"
|
120 |
+
},
|
121 |
+
"contact_email": "info@conference.com"
|
122 |
+
}
|
123 |
+
```
|
124 |
+
|
125 |
+
## βοΈ Generation Parameters
|
126 |
+
|
127 |
+
- **Max Tokens**: Controls the maximum length of the generated output (default: 512)
|
128 |
+
- **Temperature**: Controls randomness in generation (default: 0.6)
|
129 |
+
- Lower values (e.g., 0.3) make output more focused and deterministic
|
130 |
+
- Higher values (e.g., 0.9) make output more diverse and creative
|
131 |
+
- **Top-p**: Nucleus sampling parameter (default: 0.95)
|
132 |
+
- **Top-k**: Number of highest probability tokens to consider (default: 20)
|
133 |
+
|
134 |
+
## π οΈ Technical Details
|
135 |
+
|
136 |
+
- **Model**: Osmosis Structure 0.6B parameters
|
137 |
+
- **Architecture**: Qwen3 (specialized for structured data)
|
138 |
+
- **Purpose**: Converting unstructured text to structured JSON format
|
139 |
+
- **Optimizations**: Fine-tuned for data extraction and format conversion tasks
|
140 |
+
|
141 |
+
## π€ Contributing
|
142 |
+
|
143 |
+
Contributions are welcome! Please feel free to submit a Pull Request. For major changes, please open an issue first to discuss what you would like to change.
|
144 |
+
|
145 |
+
## π License
|
146 |
+
|
147 |
+
This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
|
148 |
+
|
149 |
+
## π Acknowledgments
|
150 |
+
|
151 |
+
- Thanks to the Hugging Face team for their excellent tools and resources
|
152 |
+
- Special thanks to Yuvi Sharma and all the folks at Hugging Face for the community grant
|
153 |
+
|
154 |
+
## π Join Our Community
|
155 |
+
|
156 |
+
- Join our active builder's community on [Discord](https://discord.gg/qdfnvSPcqP)
|
157 |
+
- Follow us on [Hugging Face](https://huggingface.co/MultiTransformer)
|
158 |
+
- Check out our [GitHub](https://github.com/tonic-ai)
|
159 |
+
- Contribute to [MultiTonic](https://github.com/MultiTonic)
|