Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/varunbln/ask-ai
Webapp to ask AI questions regarding college course material
https://github.com/varunbln/ask-ai
Last synced: about 2 months ago
JSON representation
Webapp to ask AI questions regarding college course material
- Host: GitHub
- URL: https://github.com/varunbln/ask-ai
- Owner: varunbln
- Created: 2023-10-03T13:05:12.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2023-10-03T13:46:06.000Z (over 1 year ago)
- Last Synced: 2024-06-06T22:37:33.119Z (7 months ago)
- Language: TypeScript
- Homepage: https://ask-ai.varunbalani.com/
- Size: 27 MB
- Stars: 3
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Ask-AI
Web app to ask AI questions about my college course material.
https://ask-ai.varunbalani.com/
## Behaviour
This project performs Retrieval Augmented Generation(RAG) using embeddings generated from my course material. Embeddings were generated using OpenAI's text embedding model: `text-embedding-ada-002`.
The generated vectors are stored in a Pinecone index with different namespaces corresponding to each subject. When a user enters a query, a similarity search is performed on the stored embeddings
for the selected subjects. The top-k results are returned, and given as context to the chat completion model which uses the context to answer the user's query.
## Tech Stack
- React
- Express
- PostgreSQL with Prisma
- Pinecone as a Vector Database
- Wasp-Lang(https://wasp-lang.dev/)
