Skip to content
forked from gustavz/DataChad

Ask questions about any data source by leveraging langchains

Notifications You must be signed in to change notification settings

derluke/DataChad

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DataChad 🤖

This is an app that let's you ask questions about any data source by leveraging embeddings, vector databases, large language models and last but not least langchains

How does it work?

  1. Upload any file or enter any path or url
  2. The data source is detected and loaded into text documents
  3. The text documents are embedded using openai embeddings
  4. The embeddings are stored as a vector dataset to a datalake
  5. A langchain is created consisting of a LLM model (gpt-3.5-turbo by default) and the embedding database index as retriever
  6. When sending questions to the bot this chain is used as context to answer your questions
  7. Finally the chat history is cached locally to enable a ChatGPT like Q&A conversation

Good to know

  • As default context this git repository is taken so you can directly start asking question about its functionality without chosing an own data source.
  • To run locally or deploy somewhere, execute cp .env.template .env and set necessary keys in the newly created secrets file. Another option is to manually set environment variables
  • Yes, Chad in DataChad refers to the well-known meme

About

Ask questions about any data source by leveraging langchains

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%