Ali Abdullah
commited on
Update README.md
Browse files
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
|
| 12 |
---
|
| 13 |
|
| 14 |
-
# π§ AI Chatbot with File, Web,
|
| 15 |
|
| 16 |
-
A multimodal AI assistant that can answer questions using
|
| 17 |
-
|
| 18 |
-
-
|
| 19 |
-
-
|
| 20 |
-
-
|
|
|
|
| 21 |
|
| 22 |
---
|
| 23 |
|
| 24 |
## π Features
|
| 25 |
|
| 26 |
- Chat with files (PDF, DOCX, TXT, CSV)
|
| 27 |
-
-
|
| 28 |
-
-
|
| 29 |
-
-
|
| 30 |
-
-
|
| 31 |
|
| 32 |
---
|
| 33 |
|
| 34 |
## π οΈ Tech Stack
|
| 35 |
|
| 36 |
-
- [Gradio
|
| 37 |
-
- [
|
| 38 |
-
- [
|
| 39 |
-
- [
|
| 40 |
-
- [
|
| 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 |
-
|
| 51 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
# π§ 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 |
+
- π Uploaded documents (`.txt`, `.pdf`, `.docx`, `.csv`)
|
| 19 |
+
- π Any public website URL (RAG retrieval)
|
| 20 |
+
- πΌοΈ Images via OCR (Tesseract)
|
| 21 |
+
- π§ Audio files via transcription (Whisper)
|
| 22 |
|
| 23 |
---
|
| 24 |
|
| 25 |
## π 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 |
## π 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
|