- Move khoj message border to left like in web ui
- Remove user, sender emojis and name
- Ensure conversation title always at top of chat sessions view,
even if no chat sessions loaded yet, instead of causing layout shift
on chat sessions load
Improve handling of multiple output modes
- Use the generated descriptions / inferred queries to supply context to the model about what it's created and give a richer response
- Stop sending the generated image in user message. This seemed to be confusing the model more than helping.
- Collect generated assets in a structured objects to provide model context. This seems to help it follow instructions and separate responsibility better
- Also, rename the open ai converse method to converse_openai to follow patterns with other providers
- Use the generated descriptions / inferred queries to supply context to the model about what it's created and give a richer response
- Stop sending the generated image in user message. This seemed to be confusing the model more than helping.
- Also, rename the open ai converse method to converse_openai to follow patterns with other providers
Previously id were used (by default) for model display strings.
This made it hard to select chat model options, server chat settings
etc. in the admin panel dropdowns.
This change uses more recognizable names for the DB objects to ease
selection in dropdowns and display in general on the admin panel.
* Rename OpenAIProcessorConversationConfig to more apt AiModelAPI
The DB model name had drifted from what it is being used for,
a general chat api provider that supports other chat api providers like
anthropic and google chat models apart from openai based chat models.
This change renames the DB model and updates the docs to remove this
confusion.
Using Ai Model Api we catch most use-cases including chat, stt, image generation etc.
Simplify the desktop app
- Make the desktop app mainly a file-syncing client for users who have lots of documents that they need to share with Khoj. This is because the web app provides a fairly robust chat client which can be used by anyone on their computer.
- The chat client in the desktop app had significantly drifted from our current brand / them, and didn't provide enough value add to update. Later, we will make it easier to install the existing web app as a desktop PWA.
Currently, Khoj has terminal states with respect to what assets it outputs. We limit it to image, text, and excalidraw diagram. This limitation is unnecessary and provides undue constraints for creating more dynamic, diverse experiences. For instance, we may want the chat view to morph for document editing or generation, in which case having limited output modes would be a detriment.
This change allows us to emit generated assets and then continue on to more text generation in final response. It forces text response for all messages. It adds a new stream event, GENERATED_ASSETS, which holds content that the AI is emitting in response to the query.
Overview
- The default django admin panel UI looks pretty dated and didn't
have any Khoj specific branding
- Used the Unfold Django admin panel theme for a modern look
- Used the Khoj logo and name in Admin panel title, headings, favicons
Details:
All models shown on Admin panel need to inherit from unfold's
ModelAdmin to get styling applied. So
- Make all models on Admin panel inherit from unfold's ModelAdmin
- Subclassed UserAdmin to inherit from unfold's ModelAdmin
- Deregistered the unused Auth Group model from the Admin panel
We can add it back when its actually used. Avoid confusion for now
- Explicitly register DjangoJobExecution on admin panel and again make
it inherit from the unfold.admin.ModelAdmin
sabaimran