- Capabillity
New default UX has 1 long-press to send transcribed audio message
- Removes the previous default of 3 clicks required to send audio message
- The record > stop > send process to send audio messages was unclear
- Still allows stopping message from being sent, if users want to make
correction to transcribed audio
- Removes inadvertent long audio transcriptions if user forgets to
press stop when recording
- Changes
- Record audio while microphone button pressed
- Show auto-send 3s countdown timer UI for audio chat message
Provide a visual cue around send button for how long before audio
message is automatically sent to Khoj for response
- Auto-send msg in 3s unless stop send message button clicked
- Move delete icon to left of chat input. This makes it harder to
inadvertently click
- Add send button to chat footer. Enter being the only way to send
messages is not intuitive, outside standard modern UI patterns
- Color chat message send button to make it primary CTA on web client
- Make chat footer shorter. Use no or round border on action buttons
- Issue
Users with Dataview plugin would have error as its markdown
post-processor expects the sourcePath to be a string
This prevents Khoj from responding to chat messages in the Obsidian
chat modal. Search via Obsidian still works but it throws the same
dataview plugin error
- Fix
Pass a string as sourcePath to markdownRenderer to fix failing chat response
and stop throwing dataview errors on search
Resolves#614, Resolves#606
Server connection check can be a little flaky in Obsidian. Don't gate
the commands behind it to improve usability of Khoj.
Previously the commands would get disabled when server connection
check failed, even though server was actually accessible
- Update server connection status on every edit of khoj url, api key in
settings instead of only on plugin load
The error message was stale if connection fixed after changes in
Khoj plugin settings to URL or API key, like on plugin install
- Show better welcome message on first plugin install.
Include API key setup instruction
- Show logged in user email on Khoj settings page
- Issue: Users with Dataview plugin would have error as its markdown
post-processor expects the sourcePath to be a string
This prevents Khoj from responding to chat messages in the Obsidian
chat modal. Search via Obsidian still works but it throws the same
dataview error
- Fix: Pass a string as sourcePath to markdownRenderer to fix
failing chat response
Resolves#614, Resolves#606
### Major
- Short-circuit API rate limiter for unauthenticated user
Calls by unauthenticated users were failing at API rate limiter as it
failed to access user info object. This is a bug.
API rate limiter should short-circuit for unauthenicated users so a
proper Forbidden response can be returned by API
Add regression test to verify that unauthenticated users get 403
response when calling the /chat API endpoint
### Minor
- Remove trailing slash to normalize khoj url in obsidian plugin settings
- Move used /api/config API controllers into separate module
- Delete unused /api/beta API endpoint
- Fix error message rendering in khoj.el, khoj obsidian chat
- Handle deprecation warnings for subscribe renew date, langchain, pydantic & logger.warn
FastAPI API endpoints only support uploading 1000 files at a time.
So split all files to index into groups of 1000 for upload to
index/update API endpoint
The source URL returned by OpenAI would expire soon. This would make
the chat sessions contain non-accessible images/messages if using
OpenaI image URL
Get base64 encoded image from OpenAI and store directly in
conversation logs. This resolves the image link expiring issue
- Use new style references for Khoj chat modal in Obsidian
- Khoj Chat responses in Obsidian had regressed to not show references
for new questions after modal has been opened. Now even those are
rendered, and use new references style
- Render chat response as markdown while it's being streamed
- Add transcription button with mic icon
- Collect audio recording on pressing mic
- Process and send audio recording to server for transcription
- Extract the functionality to flash status in chat input for reuse
Previously it was only searching for PDF and Markdown files. This was
meant to show only content from current vault as results.
But it has not scaled well as other clients also allow syncing PDF and
markdown files now. So remove this content type filter for now.
A proper solution would limit by using file/dir filters on server or
client side.
- Adds support for multiple users to be connected to the same Khoj instance using their Google login credentials
- Moves storage solution from in-memory json data to a Postgres db. This stores all relevant information, including accounts, embeddings, chat history, server side chat configuration
- Adds the concept of a Khoj server admin for configuring instance-wide settings regarding search model, and chat configuration
- Miscellaneous updates and fixes to the UX, including chat references, colors, and an updated config page
- Adds billing to allow users to subscribe to the cloud service easily
- Adds a separate GitHub action for building the dockerized production (tag `prod`) and dev (tag `dev`) images, separate from the image used for local building. The production image uses `gunicorn` with multiple workers to run the server.
- Updates all clients (Obsidian, Emacs, Desktop) to follow the client/server architecture. The server no longer reads from the file system at all; it only accepts data via the indexer API. In line with that, removes the functionality to configure org, markdown, plaintext, or other file-specific settings in the server. Only leaves GitHub and Notion for server-side configuration.
- Changes license to GNU AGPLv3
Resolves#467Resolves#488Resolves#303Resolves#345Resolves#195Resolves#280Resolves#461Closes#259Resolves#351Resolves#301Resolves#296
