Ali Abdullah commited on
Commit
b6dd802
Β·
verified Β·
1 Parent(s): 0812f0d

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +25 -18
README.md CHANGED
@@ -8,36 +8,37 @@ sdk_version: 5.34.2
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
- short_description: AI Chatbot with RAG β€” Ask from File, Web, Image, or Audio
12
  ---
13
 
14
- # 🧠 AI Chatbot with File, Web, OCR & Audio (Gradio + Groq)
15
 
16
- A multimodal AI assistant that can answer questions using content from:
17
- - πŸ“„ Uploaded `.txt`, `.pdf`, `.docx`, `.csv` files
18
- - 🌐 Any website URL (RAG)
19
- - πŸ–ΌοΈ Images (OCR with Tesseract)
20
- - 🎧 Audio files (transcription with Whisper)
 
21
 
22
  ---
23
 
24
  ## πŸš€ Features
25
 
26
  - Chat with files (PDF, DOCX, TXT, CSV)
27
- - Extract info from websites
28
- - Perform OCR on images
29
- - Transcribe audio to text
30
- - Keeps file and URL-specific chat history
31
 
32
  ---
33
 
34
  ## πŸ› οΈ Tech Stack
35
 
36
- - [Gradio UI](https://gradio.app)
37
- - [Groq LLaMA 3](https://groq.com/)
38
- - [Tesseract OCR](https://github.com/tesseract-ocr)
39
- - [OpenAI Whisper](https://github.com/openai/whisper)
40
- - [FastAPI backend](https://fastapi.tiangolo.com/) (if used locally)
41
 
42
  ---
43
 
@@ -46,6 +47,12 @@ A multimodal AI assistant that can answer questions using content from:
46
  ```bash
47
  git clone https://github.com/your-username/your-repo.git
48
  cd your-repo
 
 
49
  pip install -r requirements.txt
50
- uvicorn main:app --reload # FastAPI backend
51
- python app.py # Gradio frontend
 
 
 
 
 
8
  app_file: app.py
9
  pinned: false
10
  license: mit
11
+ short_description: AI Chatbot using RAG from Files, URLs, Images & Audio
12
  ---
13
 
14
+ # 🧠 AI Chatbot with File, Web, Image & Audio Support (Gradio + Groq)
15
 
16
+ A multimodal AI assistant powered by Groq's LLaMA 3 that can answer questions using:
17
+
18
+ - πŸ“„ Uploaded documents (`.txt`, `.pdf`, `.docx`, `.csv`)
19
+ - 🌐 Any public website URL (RAG retrieval)
20
+ - πŸ–ΌοΈ Images via OCR (Tesseract)
21
+ - 🎧 Audio files via transcription (Whisper)
22
 
23
  ---
24
 
25
  ## πŸš€ Features
26
 
27
  - Chat with files (PDF, DOCX, TXT, CSV)
28
+ - Question answering from website content
29
+ - OCR-based text extraction from images
30
+ - Speech-to-text from audio recordings
31
+ - Maintains separate history for File & URL chat sessions
32
 
33
  ---
34
 
35
  ## πŸ› οΈ Tech Stack
36
 
37
+ - [Gradio](https://gradio.app) β€” User Interface
38
+ - [FastAPI](https://fastapi.tiangolo.com/) β€” API Backend
39
+ - [Groq API](https://groq.com/) β€” LLaMA 3 inference
40
+ - [Tesseract OCR](https://github.com/tesseract-ocr) β€” Image text extraction
41
+ - [Whisper](https://github.com/openai/whisper) β€” Audio transcription
42
 
43
  ---
44
 
 
47
  ```bash
48
  git clone https://github.com/your-username/your-repo.git
49
  cd your-repo
50
+
51
+ # Install dependencies
52
  pip install -r requirements.txt
53
+
54
+ # Start FastAPI backend
55
+ uvicorn main:app --reload
56
+
57
+ # Run Gradio frontend
58
+ python app.py