Skip to content
/ danswer Public
forked from danswer-ai/danswer

Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc.

License

Notifications You must be signed in to change notification settings

syongh/danswer

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OpenSource Enterprise Question-Answering

Documentation Slack Discord License

Danswer allows you to ask natural language questions against internal documents and get back reliable answers backed by quotes and references from the source material so that you can always trust what you get back. You can connect to a number of common tools such as Slack, GitHub, Confluence, amongst others.

Check out our Video Demo!

Features 💃

  • Direct QA powered by Generative AI models with answers backed by quotes and source links.
  • Intelligent Document Retrieval (Semantic Search/Reranking) using the latest LLMs.
  • An AI Helper backed by a custom Deep Learning model to interpret user intent.
  • User authentication and document level access management.
  • Connectors to Slack, GitHub, GoogleDrive, Confluence, local files, and web scraping, with more to come.
  • Option to use Opensource LLMs like Orca, Falcon etc. in place of OpenAI GPT.
  • Management Dashboard to manage connectors and set up features such as live update fetching.
  • One line Docker Compose (or Kubernetes) deployment to host Danswer anywhere.

Upcoming

  • Chat/Conversation support.
  • Templates to easily build custom connectors.
  • Personalized search

💡 Contributing

Looking to contribute? Please check out the Contribution Guide for more details.

About

Ask Questions in natural language and get Answers backed by private sources. Connects to tools like Slack, GitHub, Confluence, etc.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 63.9%
  • TypeScript 34.9%
  • Dockerfile 0.4%
  • Shell 0.4%
  • JavaScript 0.2%
  • CSS 0.1%
  • Mako 0.1%