Janaka Abeywardhana

Add Slack as a data source. Docq admins should be able select Slack as a data source, autheN and authZ Docq with a Slack org they have access to, then...

When the browser width is reduced the "New chat" button falls off the end of the screen. File drop zone doesn't hold correctly. Width change on small width breakpoint Icon...

## Current The Web API only supports JWT token authentication based on user authentication. There's limited support for scenarios where a client app needs access the API without a user...

CORE API: add custom error handler class that returns json

1

Currently we are using the built in HTTP exception class. This gets returned by Tornado as a HTML page.

fix: G Drive integration + integration docs improvements

5

## Description Fixes/Implements #(issue/feature) ## Type of change - [x] Bug fix (non-breaking change which fixes an issue) - [ ] New feature (non-breaking change which adds functionality) - [...

RFC: [WIP] Change persistence folder structure

1

## Situation Data persistence on disk isn't consistently separated by scope of ownership. Current filesystem structure: - `/index/PERSONAL/{user_id}/` - index files for Ask Your Docs feature - `/index/SHARED/{org_id}/{space_id}/` - index...

BUG: in Docq production SaaS logins session isn't persisting refresh ## Recreation - Login to https://app.docq.ai - click on an option - refresh browser - login page is presented

## Current If a response references files from multiple spaces the users isn't show which Space the source came from. This is particularly important if the same file exists in...

## Current if a user want's to repeat a previous message / instruction they have to re-type or copy and paste. This is inefficient. ## Solution Track input entered in...

CORE: Sophisticated PDFReader with Image and Table extraction

1

## Current The LlamaIndex PDFReader (part of the SimpleDirectoryReader) currently only handles simple (naive) text extraction. It uses the `pypdf` package. It iterates through pages (`pypdf.pdfreader.pages`) then uses the `page.extract_text()`...