Company Data Enrichment Tool 🏢

Instantly enrich company lists with actionable business data using Bright Data Web Scraper API, Google Gemini AI, and Streamlit. Perfect for lead generation, market research, or competitor analysis. Just upload your CSV—get CEO, funding, products, and more in minutes.

---

enrichiq-demo.mp4

Features 🚀

• Automated enrichment. Collect 13+ data points per company, including CEO, funding, and products.
• CSV upload. Process multiple company records in a single upload.
• Progress tracking. Monitor enrichment progress as the tool processes data.
• User-friendly interface. Clean, professional dashboard for easy data access.

For even more powerful research and data enrichment, try Deep Lookup. This tool searches across more than 1,000 public sources and returns ready-to-use structured data using natural language queries.

End-to-end workflow 🔄

1. User input. Upload a CSV with company names via the Streamlit interface.
2. Data preparation. Pandas checks for valid company names and removes duplicates.
3. Web scraping. Requests send data to the Bright Data Web Scraper API. Bright Data scrapes web sources for company information.
4. AI processing. Google Gemini AI standardizes formats and removes inconsistencies.
5. Results display. Enriched data appears in an interactive Streamlit table. Download results or continue enriching more fields.

Data fields ℹ️

Each company record may include, based on public data availability:

• Leadership. CEO, Founders, Executives.
• Company Info. LinkedIn URL, Services, Contact Email, Headquarters, and Founded.
• Financials. Funding, Investors, Trustpilot Rating (if available).
• Updates. News, Products, Open Roles (if listed).

Prerequisites 🛠️

• Python 3.9+ 🐍
• Bright Data API key 🔑
• Google Gemini API key 🔑

Quick start ⚙️

Step 1 – clone the repository

git clone https://github.com/triposat/ai-company-enrichment.git

Step 2 – navigate to the folder

cd ai-company-enrichment

Step 3 – create and activate a virtual environment

# Create virtual environment
python -m venv .venv

# Activate virtual environment
# Windows:
.venv\Scripts\activate
# macOS/Linux:
source .venv/bin/activate

Step 4 – install dependencies

pip install -r requirements.txt

Step 5 – create a .env file with

BRIGHT_DATA_API_KEY=your_bright_data_api_key_here
GEMINI_API_KEY=your_gemini_api_key_here
DATASET_ID=your_dataset_id_here

Step 6 – run the app

streamlit run app.py

Step 7

Upload a CSV with a “Company Name” column and select fields to enrich.

Next steps

To master AI data enrichment, leverage Bright Data’s powerful tools and support:

• Power your AI models with advanced Web Access APIs for seamless data access.
• Explore the ultimate MCP tool to connect your AI to the web and enjoy 5,000 MCP requests every month for free.
• Use pre-collected datasets with billions of records for high-quality data.
• Integrate with AI platforms like n8n and CrewAI to connect and build AI agents.
• Learn more about AI data solutions in Bright Data’s blogs page.

For expert guidance, contact Bright Data’s support team.