Prompt injection: hidden threat to AI web scraping?
Large language models, and the tools and apps built on them, are vulnerable to unwanted prompts. If you like being in control of your AIs, prompt injection will give you nightmares.
Category
AI
Learn about various AI tools that you can use with Apify to enhance your web scraping and automation workflow. Data extraction is crucial for training AI models, so read on and see how Apify can help you build extensive datasets.
15 Posts
Product matching AI: pricing intelligence powered by web scraping
Many retailers at some point run into the same challenge - how to do scalable product matching across multiple online stores. This tutorial will show you how to use our AI-model-based Product Matcher.
How to use Google Lens API to extract image data and find matching images
“Google but for pictures” as one might call it, short of some AI sorcery, Google Lens is not just your pocket-sized document scanner.
Unlocking JavaScript secrets: reverse engineering code with ChatGPT
Discover how ChatGPT can unravel the secrets of minified JavaScript and transform it into a human-readable format, making it accessible for web scraping, security research, and reverse engineering obfuscated scripts.
What is a vector database?
Vector databases are all the rage these days. The reason is simple: they’ve rapidly become a popular way to add long-term memory to LLMs such as GPT-4, LLaMDA, and LLaMA. Learn how vector databases can store ML embeddings to integrate with tools like ChatGPT.
What is LangChain?
The real power of LLMs lies in their integration with other sources of computation or knowledge. That’s why LangChain is the ideal tool for developing applications powered by language models.
What is data ingestion for large language models?
Data ingestion for LLMs is super easy… said no one ever! The fact is, it’s a complex process that involves collecting, preprocessing, and preparing data. Find out how to go about gathering and processing the data for your own large language models.
How I use GPT Scraper to let ChatGPT access the internet
Do you dream of letting ChatGPT roam the net? GPT Scraper uses web scraping to do just that, with the help of the OpenAI API.
AI and copyright: the legal landscape
Is AI-generated content protected by copyright law? And can copyrighted content be used to train AI? We explore the legal landscape for answers.
