mirror of
https://github.com/danswer-ai/danswer.git
synced 2025-09-28 21:05:17 +02:00
6891e4f1980596ca91eb99eeb5813d0abac774fd
Introducing permissioning, standardize onboarding for connectors, re-make the data model for connectors / credentials / index-attempts, making all environment variables optional, a bunch of small fixes + improvements. Co-authored-by: Weves <chrisweaver101@gmail.com>
Standardize connectors + permissioning + new frontend for admin pages + small fixes / improvements (#75)
Standardize connectors + permissioning + new frontend for admin pages + small fixes / improvements (#75)
Standardize connectors + permissioning + new frontend for admin pages + small fixes / improvements (#75)
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, Google Drive, among others.
💃 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.
- Connectors to Slack, GitHub, GoogleDrive, Web scrapping, with more to come.
- Management Dashboard to manage connectors and set up features such as live update fetching.
- One line Docker Compose deployment of all services to host Danswer anywhere.
Upcoming
- Chat/Conversation support.
- Extend current user Auth flows to support document level access management.
- Support for custom endpoints for Generative AI models or even self-host options.
- Custom Deep Learning NLP model to classify user intent to customize prompts for code generation, summarization, etc.
- Templates to easily build custom connectors.
Languages
Python
65.3%
TypeScript
30.4%
JavaScript
2.2%
HTML
0.8%
CSS
0.8%
Other
0.5%