Commit graph

3821 commits

Author SHA1 Message Date
sabaimran
0eb000c3ea Add health checks for the django ORM 2024-07-07 16:11:28 +05:30
sabaimran
6f8a65c529 References, mobile friendly chat sessions and file filter 2024-07-07 15:42:29 +05:30
Debanjum Singh Solanky
a31cd0dec1 Fix async batch delete of indexed entries 2024-07-06 22:45:26 +05:30
Debanjum
08b379c2ab
Fix, Improve Indexing, Deleting Files (#840)
### Fix
- Fix degrade in speed when indexing large files
- Resolve org-mode indexing bug by splitting current section only once by heading
- Improve summarization by fixing formatting of text in indexed files

### Improve
- Improve scaling user, admin flows to delete all entries for a user
2024-07-06 19:52:42 +05:30
Debanjum Singh Solanky
4a471979eb Upgrade sentence-transformer package to version 3.0.1
Add einops dependency for some sentence transformer models like the
nomic-embed
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
d693baccbc Make it optional to set the encoder, cross-encoder configs via admin UI 2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
1baebb8d0e Identify markdown headings by any whitespace character after ^#+
Previously only markdown headings with space characters after # would
be considered a heading. So ^##\t wouldn't be considered a valid heading
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
010486fb36 Split current section once by heading to resolve org-mode indexing bug
- Split once by heading (=first_non_empty) to extract current section body
  Otherwise child headings with same prefix as current heading will
  cause the section split to go into infinite loop
- Also add check to prevent getting into recursive loop while trying
  to split entry into sub sections
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
6a135b1ed7 Fix degrade in speed of indexing large files. Improve summarization
Adding files to the DB for summarization was slow, buggy in two ways:
- We were updating same text of modified files in DB = no of chunks
  per file times

- The `" ".join(file_content)' code was breaking each character in the
  file content by a space. This formats the original file content
  incorrectly before storing in the DB

Because this code ran in the main file indexing path, it was slowing down
file indexing. Knowledge bases with larger files were impacted more strongly
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
e6ffb6b52c Improve scaling user flow to delete all entries
- Delete entries by batch to improve efficiency of query at scale
- Share code to delete all user entries between it's async, sync methods
- Add indicator to show when files being deleted on web config page
2024-07-06 19:35:59 +05:30
Debanjum Singh Solanky
1ab59865b5 Improve scaling admin flow to delete all entries for user 2024-07-06 19:35:59 +05:30
Debanjum
05138cbd0a
Use DOM Scripting, Add CSP to Web config pages. Disable CSP in Obsidian plugin (#834)
- Add CSP to web config pages. Load phone no. validation js, css from S3
- Construct config page elements on Web via DOM scripting
- Disable CSP in Khoj Obsidian as it interferes with Obsidian functionality

- Other miscellaneous voice message level improvements (rate limit, listening animation)
2024-07-06 19:30:09 +05:30
Debanjum Singh Solanky
9bdb48807b Ratelimit text to speech model. Validate share chat url domain
- Do not log auth error message on server when Resend setup as Magic
  links for sign-in are now supported
2024-07-06 12:53:19 +05:30
Debanjum Singh Solanky
b334db0fca Add CSP to web config pages. Load phone no validation js, css from S3 2024-07-06 12:48:28 +05:30
Debanjum Singh Solanky
2f034f807a Construct config page elements on Web via DOM scripting.
Minimize isage of innerHTML to prevent DOM clobbering and unintended
escape by user Input
2024-07-06 12:48:28 +05:30
Debanjum Singh Solanky
69c9e8cc08 Disable CSP in Khoj Obsidian as it interferes with Obsidian functionality
The Khoj CSP interferes with other Obsidian features and plugins as
CSP is applied page wide.

For now chat message sanitization via Dompurify should suffice.

Enable CSP when can scope it to only the Khoj Obsidian plugin.
2024-07-05 16:10:08 +05:30
Debanjum Singh Solanky
a353d883a0 Make it optional to set the encoder, cross-encoder configs via admin UI
Upgrade sentence-transformer, add einops dependency for some sentence
transformer models like nomic
2024-07-05 16:09:30 +05:30
Debanjum Singh Solanky
6d59ad7fc9 Add listening circle animation to speak button in Obsidian plugin
Use icon active focus as color of animation button
2024-07-05 14:00:53 +05:30
sabaimran
aec44a0b89 Add dark mode toggle! And improve experience for train of thought 2024-07-04 18:29:21 +05:30
Debanjum Singh Solanky
516af86575 Fix add, remove of the text to speech loader element in Obsidian 2024-07-04 17:38:45 +05:30
sabaimran
465ef0b772 Add a loading experience when waiting for khoj response 2024-07-04 13:49:51 +05:30
Debanjum Singh Solanky
814aca6d69 Skip summarize when not triggered via slash cmd and can't summarize
Maybe better to fallback to non-summarize behavior if summarize intent
is just inferred but we can't actually summarize because the single
file added to conversation isn't satisfied
2024-07-04 13:31:00 +05:30
Debanjum
4446de00d3
Enable Voice, Keyboard Shortcuts in Khoj Obsidian Plugin (#837)
- Simplify quick jump between Khoj side pane and main editor view using keyboard shortcuts
- Enable voice chat in Obsidian to make interactions with Khoj more seamless
2024-07-04 13:28:29 +05:30
sabaimran
5ea8b16f84 Fix missing method error 2024-07-04 12:08:22 +05:30
sabaimran
d61bddf56c Fix retrieving image model by prefetching the openai config in the async method 2024-07-04 11:58:33 +05:30
sabaimran
a129b017b9 Fix image generation on server -- use default config when not set by user 2024-07-04 09:13:23 +05:30
sabaimran
34118078bf kill the emojis 2024-07-04 00:30:21 +05:30
sabaimran
d5ba916978 Working example of streaming, intersection observer, other UI updates 2024-07-04 00:30:01 +05:30
sabaimran
78d1a29bc1 Finish up filte filter side panel menu 2024-07-02 23:32:36 +05:30
sabaimran
6fa2dbc042 Do not use the custom configured max prompt size to send message to anthropic 2024-07-02 21:59:06 +05:30
sabaimran
8a6722ba97 Add basic implementation for chat side panel components 2024-07-02 21:56:43 +05:30
Debanjum Singh Solanky
afcfc60637 Merge DB migrations post merge of SD3 via API support PR 2024-07-02 17:54:58 +05:30
Debanjum
c015eeb5dd
Improve Online Search: Parallelize Search, Use Jina Reader API by default (#832)
- Overview
  Khoj wil be able to do online search out of the box, even for self-hosted users
  - Default to Jina search, reader API when no Serper.dev, Olostep API keys
  - Run online searches in parallel to process multiple queries faster

- Details
  - Jina provides a [reader API](https://github.com/jina-ai/reader) for online search and web page reading
     It requires no API key. This provides a good default to enable 
     online search for self-hosted readers requiring no additional setup. 

  - Jina search API also returns webpage contents with the results, so
     just use those directly when Jina Search API used instead of
     trying to read webpages separately. The extract relevant content from
     webpage step using a chat model is still used from the
    `read_webpage_and_extract_content' func in this case.

  - Parse search results from Jina search API into same format as
     Serper.dev for accurate rendering of online references by clients

  - Run online searches in parallel with AsyncIO to process multiple queries faster
2024-07-02 17:44:51 +05:30
Debanjum
826c3dc9cc
Enable using Stable Diffusion 3 for Image Generation via API (#830)
- Support Stable Diffusion 3 via API
  Server Admin needs to setup model similar to DALLE-3 via Django Admin Panel
- Use shorter prompt generator to prompt SD3 to create better images
- Allow users to set paint model to use from web client config page
2024-07-02 17:28:50 +05:30
Debanjum Singh Solanky
d5ceff2691 Update tests and documentation with Jina reader API usage and info
Update offline, openai chat actor, director tests to not require
Serper to run the online command tests

Update documentation for self-hosted online search to mention no setup
is required by default. But improvements can be made by using
Serper.dev or Olostep
2024-07-02 17:19:09 +05:30
Debanjum Singh Solanky
553beae848 No need to set OpenAI API key from environment variable explicitly
It is unnecessary as the OpenAI client automatically tries to use API
key from OPENAI_API_KEY env var when the api_key field is unset
2024-07-02 17:19:09 +05:30
Debanjum Singh Solanky
a038e4911b Default to Jina search, reader API when no Serper.dev, Olostep API keys
Jina AI provides a search and webpage reader API that doesn't require
an API key. This provides a good default to enable online search for
self-hosted readers requiring no additional setup.

Jina search API also returns webpage contents with the results, so
just use those directly when Jina Search API used instead of
trying to read webpages separately. The extract relvant content from
webpage step using a chat model is still used from the
`read_webpage_and_extract_content' func in this case.

Parse search results from Jina search API into same format as
Serper.dev for accurate rendering of online references by clients
2024-07-02 17:19:08 +05:30
Debanjum Singh Solanky
ff44734774 Run online searches in parallel to process multiple queries faster 2024-07-02 17:19:08 +05:30
sabaimran
0ee7cc8c47 Change overall architecure of how information is flowing for better statefulness 2024-07-02 12:39:54 +05:30
sabaimran
541ce04ebc Checkpoint: Updated sidebar panel with new components
- Add non-functional UI elements for chat, references, feedback buttons, rename/share session, mic, attachment, websocket connection
2024-07-02 11:18:50 +05:30
Raghav Tirumale
8eccd8a5e4
Support Indexing Images via OCR (#823)
- Added support for uploading .jpeg, .jpg, and .png files to Khoj from Web, Desktop app
- Updating indexer to generate raw text and entries using RapidOCR
- Details
  * added support for indexing images via ocr
  * fixed pyproject.toml
  * Update src/khoj/processor/content/images/image_to_entries.py
     Co-authored-by: Debanjum <debanjum@gmail.com>
  * Update src/khoj/processor/content/images/image_to_entries.py
     Co-authored-by: Debanjum <debanjum@gmail.com>
  * removed redudant try except blocks
  * updated desktop js file to support image formats
  * added tests for jpg and png
  * Fix processing for image to entries files
  * Update unit tests with working image indexer
  * Change png test from version verificaition to open-cv verification

---------

Co-authored-by: Debanjum <debanjum@gmail.com>
Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-07-01 06:00:00 -07:00
Debanjum Singh Solanky
cffc14a46a Trigger voice chat via keyboard shortcut in Khoj side pane
Quickly trigger voice chat from Khoj side pane using Keyboard shortcuts
2024-07-01 18:06:09 +05:30
Debanjum Singh Solanky
3723904512 Toggle jump between Khoj side pane & previous editor via cmd, kbd shortcut
Improve quick navigation to, from Khoj side pane using Keyboard
shortcut or Obsidian command
2024-07-01 18:05:59 +05:30
Debanjum Singh Solanky
fbb95ca342 Put cursor on chat input when focus on chat view in Obsidian
This should improve fluidity of keyboard interactions with Khoj on
Obsidian.

Open Khoj chat view via keybinding or command pallete and ask
question using only the keyboard, with no mouse clicks required
2024-07-01 18:05:55 +05:30
Debanjum Singh Solanky
093e276908 Enable Voice chat in Khoj Obsidian plugin
- Automatically carry out voice chats with Khoj from within Obsidian
  When send voice message, Khoj will auto respond with voice as well
- Listen to past Khoj messages as speech
- Add circular loading spinner to use while message is being converted
  to speech
2024-07-01 18:02:28 +05:30
sabaimran
c83b8f2768
Allow just one worker to be the background schedule leader (#836)
* Add a leader election mechanism to circumvent runtime issues for multiple schedulers

- Reduce the load on the DB and risk of issues on the service side by limiting the execution environment to one elected leader at a given time. This one is responsible for managing all of the execution of the jobs, though all workers are capable of adding and removing jobs

* Set a max duration for the schedule leader position (12 hrs), add some error if automation not added successfully
2024-06-28 13:13:25 +05:30
sabaimran
80fe5ce182 Fix user not authenticated interpretation error 2024-06-27 21:13:54 +05:30
Raghav Tirumale
24a0d8b073
Add OS Level Shortcut Window for Quick Access to Khoj Desktop (#815)
* rough sketch of desktop shortcuts. many bugs to fix still

* working MVP of desktop shortcut khoj

* UI fixes

* UI improvements for editable shortcut message

* major rendering fix to prevent clipboard text from getting lost

* UI improvements and bug fixes

* UI upgrades: custom top bar, edit sent message and color matching

* removed debug javascript file

* font reverted to Noto Sans

* cleaning up the code and removing diffs

* UX fixes

* cleaning up unused methods from html

* front end for button to send user back to main window to continue conversation

* UX fix for window and continue conversation support added

* migrated common js functions into chatutils.js

* Fix window closing issue in macos by

1. Use a helper function to determine if the window is open by seeing if there's a browser window with shortcut.html loaded
2. Use the  event listener on the window to handle teardown

* removed extra comment and renamed continue convo button

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2024-06-27 07:20:13 -07:00
sabaimran
870d9ecdbf
Add a fact checker feature with updated styling (#835)
- Add an experimental feature used for fact-checking falsifiable statements with customizable models. See attached screenshot for example. Once you input a statement that needs to be fact-checked, Khoj goes on a research spree to verify or refute it.
- Integrate frontend libraries for [Tailwind](https://tailwindcss.com/) and [ShadCN](https://ui.shadcn.com/) for easier UI development. Update corresponding styling for some existing UI components. 
- Add component for model selection 
- Add backend support for sharing arbitrary packets of data that will be consumed by specific front-end views in shareable scenarios
2024-06-27 18:45:38 +05:30
sabaimran
3b7a9358c3
Add our first view via Next.js for Agents (#817)
Initialize our migration to use Next.js for front-end views via Agents. This includes setup for getting authenticated users, reading in available agents, setting up a pop-up modal when you're clicking on an agent, and allowing users to start new conversations with agents.

Best attempt at an in-place migration, though there are some noticeable differences.

Also adds view for chat that are not being used, but in experimental phase.
2024-06-27 13:56:16 +05:30