https://github.com/busycaesar/inform.ai

inform.ai is an application that leverages Large Language Models (LLMs) to generate relevant responses by retrieving content related to user queries from the internet. It stores this data in a vector database and uses it to generate accurate answers based on the user's query.
https://github.com/busycaesar/inform.ai

llms rag

Last synced: 2 months ago
JSON representation

inform.ai is an application that leverages Large Language Models (LLMs) to generate relevant responses by retrieving content related to user queries from the internet. It stores this data in a vector database and uses it to generate accurate answers based on the user's query.

• Host: GitHub
• URL: https://github.com/busycaesar/inform.ai
• Owner: busycaesar
• Created: 2025-02-07T21:50:03.000Z (4 months ago)
• Default Branch: Master
• Last Pushed: 2025-02-07T22:07:05.000Z (4 months ago)
• Last Synced: 2025-02-07T22:34:20.982Z (4 months ago)
• Topics: llms, rag
• Language: JavaScript
• Homepage:
• Size: 0 Bytes
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# inform.ai

## Description

inform.ai is an application that uses existing Large Language Models (LLMs) to help users generate relevant responses to their queries. The application fetches data related to user queries from the internet, stores this content in a vector database, and retrieves relevant information from it based on the query. The generated responses are formed by using the retrieved content to accurately address user queries.

In the future, inform.ai will offer features such as providing links to the pages from which the responses are generated, enabling users to verify the information. The platform will also allow users to ask follow-up questions to the generated response. Additionally, users will have the ability to choose from a list of available LLMs, selecting the best fit based on the nature of their query. For example, a distilled model can be selected for simple reasoning tasks, while a more complex model suited for scientific reasoning can be chosen for queries requiring deeper analysis.

## Tech Stack

![Image Alt](https://skillicons.dev/icons?i=react,vite,bootstrap,tailwindcss,flask,docker)

## How it looks?

## Features

- Fetches information related to user queries from the internet, stores it in a vector database, and generates responses using the retrieved content.

## Author

[Dev Shah](https://github.com/busycaesar)