-> This project is an AI-powered agent that performs web searches, extracts specific information based on user-defined prompts, and displays or downloads the results in a user-friendly interface.
This project is a Streamlit-based AI-powered web scraping and information extraction tool. It allows users to upload a CSV file containing entities (e.g., company names), define a query template, and extract relevant information from Google search results.
It uses OpenAI API for:
1.Processing the scraped search results using OpenAI's GPT-3.5-turbo model.
2. The AI is instructed to extract specific information (e.g., email addresses) from the raw search text.
3. It generates a structured response based on the search results.
Scraper AI is used:
1- It is used to fetch Google search results for the given entity-based query.
2- The project constructs a Google search URL and sends a request via Scraper API to bypass restrictions and retrieve search results.
1- User uploads a CSV file.
2- Selects a column containing entities.
3- Provides a query template (e.g., "Find the email of {company}").
4- The script:
Queries Google via Scraper API.
Extracts text from search results.
Uses OpenAI’s GPT-3.5-turbo to process and extract key data.
5- The extracted information is displayed and can be downloaded as a CSV file.
Achieved the objective of project successfully.
There are no datasets linked
There are no datasets linked
