Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
@@ -9,4 +9,60 @@ app_file: app.py
|
|
9 |
pinned: false
|
10 |
---
|
11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
12 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
|
|
9 |
pinned: false
|
10 |
---
|
11 |
|
12 |
+
# π§ Research Paper Summarizer
|
13 |
+
|
14 |
+

|
15 |
+

|
16 |
+
[](https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer)
|
17 |
+
|
18 |
+
Welcome to the **Research Paper Summarizer** β a powerful tool designed to automatically extract and summarize text from research paper images or PDFs, while identifying key subdomains and technical topics covered in the document.
|
19 |
+
|
20 |
+
---
|
21 |
+
|
22 |
+
## π Live Demo
|
23 |
+
|
24 |
+
β‘οΈ **Try it now on Hugging Face Spaces**:
|
25 |
+
π [https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer](https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer)
|
26 |
+
|
27 |
+
---
|
28 |
+
|
29 |
+
## π Features
|
30 |
+
|
31 |
+
- π· Upload **research paper screenshots** or **PDFs**
|
32 |
+
- π Automatic **OCR-based text extraction** using `EasyOCR`
|
33 |
+
- π§ Summarization and **key subdomain detection** using `LLaMA 3` via `Langchain + Groq API`
|
34 |
+
- β
Simple and clean **Gradio interface**
|
35 |
+
|
36 |
+
---
|
37 |
+
|
38 |
+
## π How It Works
|
39 |
+
|
40 |
+
1. **Upload** a research paper image or PDF.
|
41 |
+
2. The system performs **OCR** to extract readable text.
|
42 |
+
3. A custom prompt is sent to **LLaMA 3** using the `Groq API`.
|
43 |
+
4. The app returns:
|
44 |
+
- A concise **summary**
|
45 |
+
- A list of **key subdomains & topics** covered
|
46 |
+
|
47 |
+
---
|
48 |
+
|
49 |
+
## π Tech Stack
|
50 |
+
|
51 |
+
- π§ **[LLaMA 3-70B](https://huggingface.co/meta-llama)** via Groq API
|
52 |
+
- π§Ύ **EasyOCR** for image-to-text
|
53 |
+
- βοΈ **Langchain** for structured prompt engineering
|
54 |
+
- πΌ **OpenCV** and **pdf2image** for input handling
|
55 |
+
- π **Gradio** for UI
|
56 |
+
- βοΈ **Deployed on Hugging Face Spaces**
|
57 |
+
|
58 |
+
---
|
59 |
+
|
60 |
+
## π¦ Requirements
|
61 |
+
|
62 |
+
To run this app locally, install the following:
|
63 |
+
|
64 |
+
```bash
|
65 |
+
pip install -r requirements.txt
|
66 |
+
|
67 |
+
|
68 |
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|