README.md

AI Search Assistant

A web-based AI assistant that can search the internet to answer questions using LangChain, OpenAI, and Tavily Search.

Features

• Interactive web interface built with Streamlit
• Powered by OpenAI's language models
• Real-time web search capabilities using Tavily Search
• Conversation history tracking
• Customizable search parameters
• Deployment-ready with in-app API key management

How to run locally

1. Create and activate a conda environment:

   conda create -n llmapp python=3.11 -y
   conda activate llmapp
   

2. Install the required packages:

   pip install -r requirements.txt
   

3. (Optional) Set up your API keys in a .env file:

   OPENAI_API_KEY=your_openai_api_key
   TAVILY_API_KEY=your_tavily_api_key
   

   Note: You can also enter API keys directly in the app interface.

4. Run the Streamlit app:

   streamlit run app.py
   

5. Open your browser and navigate to the URL shown in the terminal (typically http://localhost:8501)

Deployment Options

Deploy to Streamlit Cloud

1. Fork this repository to your GitHub account
2. Sign up for Streamlit Cloud
3. Create a new app and connect it to your GitHub repository
4. Deploy the app (no environment variables needed as users will input their API keys)

Deploy to Heroku

1. Create a Heroku account and install the Heroku CLI
2. Create a new Heroku app:

   heroku create your-app-name
   

3. Add a Procfile with the following content:

   web: streamlit run app.py --server.port=$PORT
   

4. Deploy to Heroku:

   git push heroku main
   

Deploy to Hugging Face using Docker

1. Create a Hugging Face account at huggingface.co
2. Install the Hugging Face CLI:

   pip install huggingface_hub
   

3. Login to Hugging Face:

   huggingface-cli login
   

4. Create a new Space on Hugging Face:

   huggingface-cli repo create ai-search-assistant --type space
   

5. Clone your repository:

   git clone https://huggingface.co/spaces/YOUR_USERNAME/ai-search-assistant
   

6. Copy your project files to the cloned repository
7. Add a .gitattributes file with the following content:

   *.7z filter=lfs diff=lfs merge=lfs -text
   *.arrow filter=lfs diff=lfs merge=lfs -text
   *.bin filter=lfs diff=lfs merge=lfs -text
   *.bz2 filter=lfs diff=lfs merge=lfs -text
   *.ckpt filter=lfs diff=lfs merge=lfs -text
   *.ftz filter=lfs diff=lfs merge=lfs -text
   *.gz filter=lfs diff=lfs merge=lfs -text
   *.h5 filter=lfs diff=lfs merge=lfs -text
   *.joblib filter=lfs diff=lfs merge=lfs -text
   *.lfs.* filter=lfs diff=lfs merge=lfs -text
   *.mlmodel filter=lfs diff=lfs merge=lfs -text
   *.model filter=lfs diff=lfs merge=lfs -text
   *.msgpack filter=lfs diff=lfs merge=lfs -text
   *.npy filter=lfs diff=lfs merge=lfs -text
   *.npz filter=lfs diff=lfs merge=lfs -text
   *.onnx filter=lfs diff=lfs merge=lfs -text
   *.ot filter=lfs diff=lfs merge=lfs -text
   *.parquet filter=lfs diff=lfs merge=lfs -text
   *.pb filter=lfs diff=lfs merge=lfs -text
   *.pickle filter=lfs diff=lfs merge=lfs -text
   *.pkl filter=lfs diff=lfs merge=lfs -text
   *.pt filter=lfs diff=lfs merge=lfs -text
   *.pth filter=lfs diff=lfs merge=lfs -text
   *.rar filter=lfs diff=lfs merge=lfs -text
   *.safetensors filter=lfs diff=lfs merge=lfs -text
   *.tar.* filter=lfs diff=lfs merge=lfs -text
   *.tflite filter=lfs diff=lfs merge=lfs -text
   *.tgz filter=lfs diff=lfs merge=lfs -text
   *.wasm filter=lfs diff=lfs merge=lfs -text
   *.xz filter=lfs diff=lfs merge=lfs -text
   *.zip filter=lfs diff=lfs merge=lfs -text
   *.zst filter=lfs diff=lfs merge=lfs -text
   *tfevents* filter=lfs diff=lfs merge=lfs -text
   

8. Create a Dockerfile in your repository (already provided in this project)
9. Add a README.md file with a description of your app
10. Commit and push your changes:

    git add .
    git commit -m "Initial commit"
    git push
    

11. Configure your Space on the Hugging Face website:
    • Go to your Space settings
    • Set the Space SDK to "Docker"
    • Set the Hardware to your preferred option (CPU is sufficient for this app)
    • Save your changes
12. Your app will be built and deployed automatically. You can access it at https://huggingface.co/spaces/YOUR_USERNAME/ai-search-assistant

Usage

1. Enter your OpenAI and Tavily API keys in the sidebar
2. Configure search settings (model and number of results)
3. Enter your question in the text input field
4. Click the "Search" button
5. View the AI's response with information sourced from the web
6. Continue the conversation with follow-up questions

Requirements

• Python 3.11+
• OpenAI API key (Get one here)
• Tavily API key (Get one here)