zhangjiekui / danswer

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

OpenSource Enterprise Question-Answering

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.

Usage

Danswer provides a fully-featured web UI:

danswer-web.mp4

Or, if you prefer, you can plug Danswer into your existing Slack workflows (more integrations to come 😁):

danswer-slack.mp4

For more details on the admin controls, check out our Full Video Demo!

Deployment

Danswer can easily be tested locally or deployed on a virtual machine with a single docker compose command. Checkout our docs to learn more.

We also have built-in support for deployment on Kubernetes. Files for that can be found here.

💃 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.
• Support for an LLM of your choice (GPT-4, Llama2, Orca, etc.)
• 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.

🔌 Connectors

Danswer currently syncs documents (every 10 minutes) from:

• Slack
• GitHub
• Google Drive
• Confluence
• Jira
• Notion
• Slab
• Linear
• Productboard
• Guru
• Zulip
• Bookstack
• Local Files
• Websites
• With more to come...

🚧 Roadmap

• Chat/Conversation support.
• Organizational understanding.
• Ability to locate and suggest experts.

💡 Contributing

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