LeadSightAI is a Streamlit-based application designed to help users discover and analyze company information for lead generation and business intelligence. It features a searchable company database and an interactive ChatRAG (Retrieval-Augmented Generation) interface, allowing users to extract insights from company websites. With built-in export options for CSV and Excel, it’s a practical tool for marketers, analysts, and researchers.
- Provide an intuitive interface to filter and explore company data by industry, location, and keywords.
- Offer real-time ChatRAG interactions to dive deeper into company details using web-scraped content.
- Enable easy data export for further analysis or reporting.
- Serve as a foundation for future enhancements in AI-driven lead generation.
- Company Search Dashboard: Filter companies with customizable criteria and view detailed profiles.
- ChatRAG Integration: Engage in conversational queries about selected companies using RAG with OllamaLLM.
- Data Export: Download filtered company data in CSV or Excel formats.
- Dynamic Scraping: Utilize SeleniumURLLoader to fetch and process live website content.
| Component | Tool/Technology | Purpose |
|---|---|---|
| UI Framework | Streamlit | Interactive and responsive dashboard |
| Scraping | SeleniumURLLoader | Extract data from dynamic websites |
| Language Model | OllamaLLM (Llama 3.2:3b) | Power ChatRAG with local LLM |
| Vector Storage | InMemoryVectorStore | Store and retrieve document chunks |
| Data Handling | Pandas | Manage and export company data |
- Explore Companies: Use the dashboard to search and filter companies based on industry, location, or name.
- Select a Company: Click "Chat" to initiate a ChatRAG session for a specific company.
- Scrape Content: The app scrapes the company’s website using SeleniumURLLoader.
- Generate Insights: ChatRAG processes the scraped data with OllamaLLM to answer your questions.
- Export Results: Save filtered company data to CSV or Excel for offline use.
- Clone the repository
git clone https://github.com/yourusername/leadsightai.git
cd leadsightai- Create and activate a virtual environment
python3 -m venv venv
# On macOS/Linux:
source venv/bin/activate
# On Windows:
venv\Scripts\activate- Install dependencies
pip install -r requirements.txt- Pull the Ollama Model
ollama pull llama3.2:3b- Run the app
streamlit run app.py- Python 3.8 or higher
- Internet connection (for live scraping)
- Optional: Update
config.pyto customize OllamaLLM settings
leadsightai/
├── app.py # Main Streamlit app
├── config.py # Configuration for LLM and settings
├── requirements.txt # Required Python packages
├── static/
│ └── styles.css # Custom UI styling
├── modules/
│ ├── data_handling.py # Company data management
│ ├── scraping.py # Website scraping logic
│ ├── chat_rag.py # ChatRAG and LLM pipeline
│ └── ui_components.py # UI components and layout
└── data/
└── company_data.csv # Sample datasetFeel free to fork or submit issues! Created by @kderrylo for exploration and research in lead generation tools using open-source LLMs.