Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
title: ACReSAL AI - GROQ LLAMA-3 RAG AI Bot
|
| 3 |
+
emoji: 🤖
|
| 4 |
+
colorFrom: green
|
| 5 |
+
colorTo: blue
|
| 6 |
+
sdk: gradio
|
| 7 |
+
sdk_version: 3.26.0
|
| 8 |
+
app_file: app.py
|
| 9 |
+
pinned: false
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
## GROQ and LLAMA-3 Custom RAG Bot
|
| 13 |
+
|
| 14 |
+
This application is a Retrieval-Augmented Generation (RAG) system built with a custom LLM (LLAMA-3) from GROQ. The app allows users to upload a PDF file, process it, and ask questions about the content. The system uses LangChain and Chroma for document retrieval and embedding, and Gradio for the user interface.
|
| 15 |
+
|
| 16 |
+
### Features
|
| 17 |
+
- Upload PDF documents
|
| 18 |
+
- Process and split documents into chunks using LangChain
|
| 19 |
+
- Use HuggingFace embeddings and Chroma for document search
|
| 20 |
+
- Ask questions and receive concise answers based on the content of the PDF
|
| 21 |
+
|
| 22 |
+
### Usage
|
| 23 |
+
1. Upload a PDF file using the "Upload PDF" button.
|
| 24 |
+
2. Once the PDF is processed, you can ask questions about the document's content.
|
| 25 |
+
3. The bot will return answers based on the specific context provided in the PDF.
|
| 26 |
+
|
| 27 |
+
### Running Locally
|
| 28 |
+
|
| 29 |
+
To run the app locally, follow these steps:
|
| 30 |
+
|
| 31 |
+
1. Clone the repository.
|
| 32 |
+
2. Install the required dependencies using the `requirements.txt` file:
|
| 33 |
+
```bash
|
| 34 |
+
pip install -r requirements.txt
|