omvishesh commited on
Commit
17b7da5
Β·
verified Β·
1 Parent(s): 8c38e8a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +56 -0
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
+ # 🧠 Research Paper Summarizer
13
+
14
+ ![Gradio App](https://img.shields.io/badge/Gradio-Interface-blue?logo=gradio)
15
+ ![Status](https://img.shields.io/badge/Status-Deployed-brightgreen)
16
+ [![Hugging Face Spaces](https://img.shields.io/badge/πŸ€—%20View%20on%20Hugging%20Face-orange)](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
+ ## πŸ”— Live Demo
23
+
24
+ ➑️ **Try it now on Hugging Face Spaces**:
25
+ πŸ‘‰ [https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer](https://huggingface.co/spaces/omvishesh/ResearchpaperSummarizer)
26
+
27
+ ---
28
+
29
+ ## πŸ“Œ Features
30
+
31
+ - πŸ“· Upload **research paper screenshots** or **PDFs**
32
+ - πŸ” Automatic **OCR-based text extraction** using `EasyOCR`
33
+ - 🧠 Summarization and **key subdomain detection** using `LLaMA 3` via `Langchain + Groq API`
34
+ - βœ… Simple and clean **Gradio interface**
35
+
36
+ ---
37
+
38
+ ## πŸš€ 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
+ ## πŸ›  Tech Stack
50
+
51
+ - 🧠 **[LLaMA 3-70B](https://huggingface.co/meta-llama)** via Groq API
52
+ - 🧾 **EasyOCR** for image-to-text
53
+ - βš™οΈ **Langchain** for structured prompt engineering
54
+ - πŸ–Ό **OpenCV** and **pdf2image** for input handling
55
+ - 🌐 **Gradio** for UI
56
+ - ☁️ **Deployed on Hugging Face Spaces**
57
+
58
+ ---
59
+
60
+ ## πŸ“¦ 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