Skip to content

Releases: gustavz/DataChad

DataChad V2

24 Nov 13:15
@gustavz gustavz
V2
74062ea
Compare
Choose a tag to compare
DataChad V2 Latest
Latest

This is the cut-off point for DataChad V2

How does it work?

  1. Upload any file(s) 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 activeloop's database hub
  5. A langchain is created consisting of a LLM model (gpt-3.5-turbo by default) and the vector store as retriever
  6. When asking questions to the app, the chain embeds the input prompt and does a similarity search of in the vector store and uses the best results as context for the LLM to generate an appropriate response
  7. Finally the chat history is cached locally to enable a ChatGPT like Q&A conversation

Good to know

  • The app only runs on py>=3.10!
  • 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 credentials in the newly created .env file. Other options are manually setting of system environment variables, or storing them into .streamlit/secrets.toml when hosted via streamlit.
  • If you have credentials set like explained above, you can just hit submit in the authentication without reentering your credentials in the app.
  • Your data won't load? Feel free to open an Issue or PR and contribute!
  • Yes, Chad in DataChad refers to the well-known meme
  • DataChad V2 does not support local mode, but many feature will soon come. Stay tuned!
Assets 2
Loading

DataChad V1

30 Aug 07:15
@gustavz gustavz
V1
5687d6c
Compare
Choose a tag to compare
DataChad V1

This is the cut-off point for DataChad V1

How does it work?

  1. Upload any file(s) 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 activeloop's database hub
  5. A langchain is created consisting of a LLM model (gpt-3.5-turbo by default) and the vector store as retriever
  6. When asking questions to the app, the chain embeds the input prompt and does a similarity search of in the vector store and uses the best results as context for the LLM to generate an appropriate response
  7. Finally the chat history is cached locally to enable a ChatGPT like Q&A conversation

Good to know

  • The app only runs on py>=3.10!
  • 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 credentials in the newly created .env file. Other options are manually setting of system environment variables, or storing them into .streamlit/secrets.toml when hosted via streamlit.
  • If you have credentials set like explained above, you can just hit submit in the authentication without reentering your credentials in the app.
  • To enable Local Mode (disabled for the demo) set ENABLE_LOCAL_MODE to True in datachad/constants.py. You need to have the model binaries downloaded and stored inside ./models/
  • Currently supported Local Mode OSS model is GPT4all. To add more models update datachad/models.py
  • If you are running Local Mode all your data stays locally on your machine. No API calls are made. Same with the embeddings database which stores its data to ./data/
  • Your data won't load? Feel free to open an Issue or PR and contribute!
  • Yes, Chad in DataChad refers to the well-known meme
Loading