Web Weaver 🕷️🕸️

• 🔗Web Weaver takes in a URL (e.g articles from Medium, Guardian, ...) and perform Retrieval-Augmented Generation with provided data using LangChain.js chain in a Next.js project.
• 🪜The chain works in two steps:
  • 1️⃣First, it rephrases the input question into a "standalone" question, dereferencing pronouns based on the chat history.
  • 2️⃣Then, it queries the retriever for documents similar to the dereferenced question and composes an answer.
• 🐙This UI is a modified version of an open source project - you can see the source code and deploy your own version from the GitHub repo!
• 👇Provide me with an URL, click WEAVE WEBSITE, then try asking a question below!
• 💡Need an example? Try this article on LLM Powered Autonomous Agents and ask "What is task decomposition?"