moved s3 variables to .env

added README content
renamed vectorstore dir

.gitignore

@@ -164,5 +164,6 @@ cython_debug/
 *.bin
 *.pickle
 chroma_db/*
+vectorstore/*
 bin
 obj

README.md

@@ -1 +1,82 @@
-# docu-qachat-demo
+# docu-qachat-demo
+---
+title: Docs Qachat
+emoji: 🚀
+colorFrom: gray
+colorTo: gray
+sdk: gradio
+sdk_version: 4.2.0
+app_file: app.py
+pinned: false
+---
+
+# Docs QAchat 🚀
+
+## Overview
+Docs QAchat is an advanced Documentation AI helper, demonstrating a fine-tuned 7b model's capabilities in aiding users with software documentation. This application integrates technologies like Retrieval-Augmented Generation (RAG), LangChain, Gradio UI, Chroma DB, and FAISS to offer insightful documentation assistance. It's designed to help users navigate and utilize software tools efficiently by retrieving relevant documentation pages and maintaining conversational flow.
+
+## Key Features
+- **AI-Powered Documentation Retrieval:** Utilizes various fine-tuned 7b models for precise and context-aware responses.
+- **Rich User Interface:** Features a user-friendly interface built with Gradio.
+- **Advanced Language Understanding:** Employs LangChain for implementing RAG setups and sophisticated natural language processing.
+- **Efficient Data Handling:** Leverages Chroma DB and FAISS for optimized data storage and retrieval.
+- **Retrieval Chain with Prompt Tuning:** Includes a retrieval chain with a prompt template for prompt tuning.
+- **Conversation Memory:** Incorporates BufferMemory for short-term conversation memory, enhancing conversational flow.
+
+## Models Used
+This setup is tested with the following models:
+- `mistralai/Mistral-7B-v0.1`
+- `mistralai/Mistral-7B-Instruct-v0.1`
+- `HuggingFaceH4/zephyr-7b-beta`
+- `HuggingFaceH4/zephyr-7b-alpha`
+- `tiiuae/falcon-7b-instruct`
+- `microsoft/Orca-2-7b`
+- `teknium/OpenHermes-2.5-Mistral-7B`
+
+## Prerequisites
+- Python 3.8 or later
+- [Additional prerequisites as needed]
+
+## Installation
+1. Clone the repository:
+   ```bash
+   git clone https://github.com/yourusername/Docs-QAchat.git
+   ```
+2. Navigate to the project directory:
+   ```bash
+   cd Docs-QAchat
+   ```
+3. Install required packages:
+   ```bash
+   pip install -r requirements.txt
+   ```
+
+## Configuration
+1. Create a `.env` file in the project root.
+2. Add the following environment variables to the `.env` file:
+   ```
+   HUGGINGFACEHUB_API_TOKEN=""
+   AWS_S3_LOCATION=""
+   AWS_S3_FILE=""
+   VS_DESTINATION=""
+   ```
+
+## Usage
+Start the application by running:
+```bash
+python app.py
+```
+[Include additional usage instructions and examples]
+
+## Contributing
+Contributions to Docs QAchat are welcome. [Include contribution guidelines]
+
+## Support
+For support, contact [Support Contact Information].
+
+## Authors and Acknowledgement
+- [Name]
+- Acknowledgements to the contributors of the used models and technologies.
+
+## License
+This project is licensed under the [License] - see the LICENSE file for details.

app.py

@@ -7,6 +7,7 @@ import boto3
 from botocore import UNSIGNED
 from botocore.client import Config
 # access .env file
+import os
 from dotenv import load_dotenv
 #from bs4 import BeautifulSoup
 # HF libraries
@@ -24,9 +25,12 @@ from langchain.memory import ConversationBufferMemory
 #import logging
 import zipfile
 
-# load HF Token
+# load .env variables
 config = load_dotenv(".env")
-
+HUGGINGFACEHUB_API_TOKEN=os.getenv('HUGGINGFACEHUB_API_TOKEN')
+AWS_S3_LOCATION=os.getenv('AWS_S3_LOCATION')
+AWS_S3_FILE=os.getenv('AWS_S3_FILE')
+VS_DESTINATION=os.getenv('VS_DESTINATION')
 
 model_id = HuggingFaceHub(repo_id="HuggingFaceH4/zephyr-7b-beta", model_kwargs={
     "temperature":0.1, 
@@ -43,8 +47,8 @@ embeddings = HuggingFaceHubEmbeddings(repo_id=model_name)
 s3 = boto3.client('s3', config=Config(signature_version=UNSIGNED))
 
 ## Chroma DB
-s3.download_file('rad-rag-demos', 'vectorstores/chroma.sqlite3', './chroma_db/chroma.sqlite3')
-db = Chroma(persist_directory="./chroma_db", embedding_function=embeddings)
+s3.download_file(AWS_S3_LOCATION, AWS_S3_FILE, VS_DESTINATION)
+db = Chroma(persist_directory="./vectorstore", embedding_function=embeddings)
 db.get()
 
 ## FAISS DB