Commit graph

1770 commits

Author SHA1 Message Date
sabaimran
b5972e9311 Use OCR to extract image text in PDFs 2023-11-04 17:15:28 -07:00
Debanjum Singh Solanky
8273bf26b7 Fix multi-line chat input and output render on web, desktop clients
- Remove spurious whitespace in chat input box on page load being
  added because text area element was ending on newline
- Do not insert newline in message when send message by hitting enter key
  This would be more evident when send message with cursor in the
  middle of the sentence, as a newline would be inserted at the cursor
  point
- Remove chat message separator tokens from model output. Model
  sometimes starts to output text in it's chat format
2023-11-04 01:09:35 -07:00
Debanjum Singh Solanky
2f1756cc15 Do not use icon for each file, folder to index in desktop app.
Other minor fixes based on PR feedback
2023-11-04 00:13:10 -07:00
Debanjum Singh Solanky
e8f568d79c Make splash screen wider, opaque and fix it's spinner radius
Radius should be such that final spin doesn't extend out of the circle
Opaque background improves contrast for better visual
2023-11-03 23:59:21 -07:00
Debanjum Singh Solanky
3ef05f4803 Use css var for main font color in search, chat page of desktop app 2023-11-03 23:59:21 -07:00
Debanjum Singh Solanky
a19cbde2d7 Add About page for Khoj to Desktop app. Expose it via system tray
- Pass current khoj version from package.json to about page via
  electron IPC between backend js and frontend page
- Update Khoj information in default About screen as well, in case
  it's exposed anywhere else
2023-11-03 23:59:21 -07:00
Debanjum Singh Solanky
a327294ee9 Rename khoj.js to utils.js in web and desktop client apps 2023-11-03 18:13:37 -07:00
Debanjum Singh Solanky
db57eeaefe Console log a welcome message on loading Desktop client 2023-11-03 05:15:41 -07:00
Debanjum Singh Solanky
6fae6fb2a4 Merge branch 'features/multi-user-support-khoj' into improve-client-app-theming 2023-11-03 04:58:41 -07:00
Debanjum Singh Solanky
4cd76311ad Slow down spinning at end of splash sequence. Make animation bigger 2023-11-03 04:28:17 -07:00
Debanjum Singh Solanky
34661c33a2 Show splash screen on starting desktop app 2023-11-03 03:19:08 -07:00
Debanjum Singh Solanky
126d3f4563 Render each file, folder to index row with icon in desktop app
Make the file, folders to index look less like an editable field
2023-11-03 02:48:42 -07:00
Debanjum Singh Solanky
80ae132cad Update Desktop, Obsidian client color theme to lighter yellow
- Update background color to a different shade of white
- Make primary and primary hover colors less intense and more aligned
  with lantern flame shade
- Add water, leaf, flower color variables
2023-11-03 02:48:42 -07:00
sabaimran
fb6ebd19fc
Fix refactor bugs, CSRF token issues for use in production (#531)
Fix refactor bugs, CSRF token issues for use in production
* Add flags for samesite settings to enable django admin login
* Include tzdata to dependencies to work around python package issues in linux
* Use DJANGO_DEBUG flag correctly
* Fix naming of entry field when creating EntryDate objects
* Correctly retrieve openai config settings
* Fix datefilter with embeddings name for field
2023-11-02 23:02:38 -07:00
Debanjum Singh Solanky
345856e7be Merge branch 'master' of github.com:khoj-ai/khoj into features/multi-user-support-khoj
Merge changes to use latest GPT4All with GPU, GGUF model support into
khoj multi-user support rearchitecture branch
2023-11-02 22:44:25 -07:00
Debanjum Singh Solanky
041074ccd6 Make chat the landing page for the desktop app
Chat, unlike search, doesn't knowledge base indexing setup.
So you can get started with chat much faster.
2023-11-02 20:42:21 -07:00
Debanjum Singh Solanky
3801105b2a Make chat the landing page for the web app
Chat, unlike search, doesn't knowledge base indexing setup.
So you can get started with chat much faster.
2023-11-02 20:42:21 -07:00
Debanjum Singh Solanky
0d4e7d46c2 Fix color and size of profile picture circle in nav pane 2023-11-02 20:42:21 -07:00
Debanjum Singh Solanky
4fbe8ac6b1 Console log a welcome message on loading web client 2023-11-02 20:42:21 -07:00
Debanjum Singh Solanky
9fc6c97139 Use Khoj standard font family, weight in web client settings page 2023-11-02 20:42:21 -07:00
Debanjum Singh Solanky
b6f07099cd Simplify login page styling on web client
- Center all elements: icon, text and button
- Use khoj icon not logo-text
- Simplify login title text
2023-11-02 20:42:21 -07:00
Debanjum Singh Solanky
7b7f6d3bc8 Update web client theme to a lighter
- Update background color to a different shade of white
- Make primary and primary hover colors less intense and more aligned
  with lantern flame shade
- Add water, leaf, flower color variables
2023-11-02 20:42:21 -07:00
sabaimran
fe860aaf83 Merge branch 'features/multi-user-support-khoj' of github.com:khoj-ai/khoj into features/multi-user-support-khoj 2023-11-02 14:56:01 -07:00
sabaimran
2c9496bcf1 Add additional null checks in the migrate_server_pg script 2023-11-02 14:55:58 -07:00
sabaimran
20df0f5330 Use url_path_for for creating the login page URL in the application 2023-11-02 14:55:14 -07:00
sabaimran
fd11b78552
Fix migration script error when openai not available (#530) 2023-11-02 11:28:08 -07:00
sabaimran
fe6720fa06
[Multi-User Part 8]: Make conversation processor settings server-wide (#529)
- Rather than having each individual user configure their conversation settings, allow the server admin to configure the OpenAI API key or offline model once, and let all the users re-use that code.
- To configure the settings, the admin should go to the `django/admin` page and configure the relevant chat settings. To create an admin, run `python3 src/manage.py createsuperuser` and enter in the details. For simplicity, the email and username should match.
- Remove deprecated/unnecessary endpoints and views for configuring per-user chat settings
2023-11-02 10:43:27 -07:00
Debanjum Singh Solanky
12b3eeae9e Use Khoj fonts on config page of web and desktop apps too
Previously pico.css font-families were being selected for the config
page. This was different from the fonts used by index.html, chat.html

This improves spacing issue of heading further
2023-11-01 17:50:50 -07:00
Debanjum Singh Solanky
022d695309 Switch to narrow view below width of 700px on web client
This makes the dropdown menu align better to the profile picture in
mobile view
2023-11-01 17:49:44 -07:00
Debanjum Singh Solanky
6a0adfbfbb Default to profile picture with Initial if user has no profile picture 2023-11-01 17:49:44 -07:00
Tuan Nguyen
354605e73e
Autofocus to chat input when openning chat (#524) 2023-11-01 16:09:45 -07:00
Debanjum Singh Solanky
d92a2d03a7 Rename Files, Classes from X_To_JSONL to more appropriate X_To_Entries
These content processors are converting content into entries in DB
instead of entries in JSONL file
2023-11-01 14:51:33 -07:00
Debanjum Singh Solanky
2ad2055bcb Remove user null check in API controllers that require authentication 2023-11-01 14:38:19 -07:00
Debanjum Singh Solanky
7ac5a4766d Match spacing of navigation header pane in config vs search/chat pages 2023-11-01 14:38:19 -07:00
Debanjum Singh Solanky
2e3a4a6a9b Use Jinja macro to deduplicate navigation header HTML 2023-11-01 14:38:12 -07:00
Debanjum Singh Solanky
c631b61a81 Put colors shared by index, chat html into khoj css global variables 2023-11-01 02:13:24 -07:00
Debanjum Singh Solanky
f585a71744 Put logout, settings under dropdown menu with logged in user's profile picture
- Create dropdown menu. Put settings page, logout action under it
- Make user's profile picture the dropdown menu heading
- Create khoj.js to store shared js across web client
  It currently stores the dropdown menu open, close functionality
- Put shared styling for khoj dropdown menu under khoj.css
2023-11-01 02:13:24 -07:00
Debanjum Singh Solanky
58a7171911 Show truncated API key for identification & restrict table width
- Use a function to generate API Key table row HTML, to dedup logic
- Show delete, copy icon hints on hover
- Reduce length of copied message to not expand table width
- Truncating API key helps keep the API key table width within width
  of smaller width displays
2023-10-31 23:10:26 -07:00
Debanjum Singh Solanky
9cebd7f856 Add emoji icons to Search, Chat, Settings items in nav menu of Web client
Emoji icons have already been added to the Search, Chat and Settings
top navigation menu in the desktop client. This change adds these to
the web client as well
2023-10-31 22:38:44 -07:00
Debanjum Singh Solanky
f77336ba61 Add key icon for API keys table in Web client config page 2023-10-31 19:01:09 -07:00
Debanjum Singh Solanky
87e6b1eab9 Rename TextEmbeddings to TextEntries for improved readability
Improves readability as name has closer match to underlying
constructs
2023-10-31 18:55:59 -07:00
Debanjum Singh Solanky
bcbee05a9e Rename DbModels Embeddings, EmbeddingsAdapter to Entry, EntryAdapter
Improves readability as name has closer match to underlying
constructs

- Entry is any atomic item indexed by Khoj. This can be an org-mode
  entry, a markdown section, a PDF or Notion page etc.

- Embeddings are semantic vectors generated by the search ML model
  that encodes for meaning contained in an entries text.

- An "Entry" contains "Embeddings" vectors but also other metadata
  about the entry like filename etc.
2023-10-31 18:50:54 -07:00
sabaimran
54a387326c
[Multi-User Part 6]: Address small bugs and upstream PR comments (#518)
- 08654163cb: Add better parsing for XML files
- f3acfac7fb: Add a try/catch around the dateparser in order to avoid internal server errors in app
- 7d43cd62c0: Chunk embeddings generation in order to avoid large memory load
- e02d751eb3: Addresses comments from PR #498 
- a3f393edb4: Addresses comments from PR #503 
- 66eb078286: Addresses comments from PR #511 
- Address various items in https://github.com/khoj-ai/khoj/issues/527
2023-10-31 17:59:53 -07:00
sabaimran
5f3f6b7c61
[Multi-User Part 5]: Add a production Docker file and use a gunicorn configuration with it (#514)
- Add a productionized setup for the Khoj server using `gunicorn` with multiple workers for handling requests
- Add a new Dockerfile meant for production config at `ghcr.io/khoj-ai/khoj:prod`; the existing Docker config should remain the same
2023-10-26 13:15:31 -07:00
Debanjum
9acc722f7f
[Multi-User Part 4]: Authenticate using API Tokens (#513)
###  New
- Use API keys to authenticate from Desktop, Obsidian, Emacs clients
- Create API, UI on web app config page to CRUD API Keys
- Create user API keys table and functions to CRUD them in Database

### 🧪 Improve
- Default to better search model, [gte-small](https://huggingface.co/thenlper/gte-small), to improve search quality
- Only load chat model to GPU if enough space, throw error on load failure
- Show encoding progress, truncate headings to max chars supported
- Add instruction to create db in Django DB setup Readme

### ⚙️ Fix
- Fix error handling when configure offline chat via Web UI
- Do not warn in anon mode about Google OAuth env vars not being set
- Fix path to load static files when server started from project root
2023-10-26 12:33:03 -07:00
sabaimran
4b6ec248a6
[Multi-User Part 3]: Separate chat sesssions based on authenticated users (#511)
- Add a data model which allows us to store Conversations with users. This does a minimal lift over the current setup, where the underlying data is stored in a JSON file. This maintains parity with that configuration.
- There does _seem_ to be some regression in chat quality, which is most likely attributable to search results.

This will help us with #275. It should become much easier to maintain multiple Conversations in a given table in the backend now. We will have to do some thinking on the UI.
2023-10-26 11:37:41 -07:00
sabaimran
a8a82d274a
[Multi-User Part 2]: Add login pages and gate access to application behind login wall (#503)
- Make most routes conditional on authentication *if anonymous mode is not enabled*. If anonymous mode is enabled, it scaffolds a default user and uses that for all application interactions.
- Add a basic login page and add routes for redirecting the user if logged in
2023-10-26 10:17:29 -07:00
sabaimran
216acf545f
[Multi-User Part 1]: Enable storage of settings for plaintext files based on user account (#498)
- Partition configuration for indexing local data based on user accounts
- Store indexed data in an underlying postgres db using the `pgvector` extension
- Add migrations for all relevant user data and embeddings generation. Very little performance optimization has been done for the lookup time
- Apply filters using SQL queries
- Start removing many server-level configuration settings
- Configure GitHub test actions to run during any PR. Update the test action to run in a containerized environment with a DB.
- Update the Docker image and docker-compose.yml to work with the new application design
2023-10-26 09:42:29 -07:00
Debanjum Singh Solanky
9677eae791 Expose CLI flag to disable using GPU for offline chat model
- Offline chat models outputing gibberish when loaded onto some GPU.
  GPU support with Vulkan in GPT4All seems a bit buggy

- This change mitigates the upstream issue by allowing user to
  manually disable using GPU for offline chat

Closes #516
2023-10-25 17:51:46 -07:00
Debanjum Singh Solanky
0f1ebcae18 Upgrade to latest GPT4All. Use Mistral as default offline chat model
GPT4all now supports gguf llama.cpp chat models. Latest
GPT4All (+mistral) performs much at least 3x faster.

On Macbook Pro at ~10s response start time vs 30s-120s earlier.
Mistral is also a better chat model, although it hallucinates more
than llama-2
2023-10-22 19:04:23 -07:00
sabaimran
963cd165eb Resolve merge conflicts 2023-10-19 14:39:05 -07:00
Debanjum Singh Solanky
8346e1193c Release Khoj version 0.13.0 2023-10-18 03:43:54 -07:00
Debanjum Singh Solanky
6631fc38db Delete plaintext config via API. Catch any offline model loading exception 2023-10-18 03:37:45 -07:00
Debanjum Singh Solanky
53abd1a506 Mark sync completed on desktop client, even when no files to send
Previously Sync spinner on desktop config screen would hang when no
files to send to server & the Sync button had been manually triggered
2023-10-18 01:30:56 -07:00
Debanjum Singh Solanky
71b0012e8c Set offline chat config to default value if unset on server load 2023-10-18 00:59:43 -07:00
Debanjum Singh Solanky
cf1cdc3fe1 Disambiguate input_filter variable names in fs_syncer functions 2023-10-17 23:32:10 -07:00
Debanjum Singh Solanky
e3cd8b4150 Only index files returned by input-filter globs in fs_syncer
Ignore .org, .pdf etc. suffixed directories under `input-filter' from
being evaluated as files.

Explicitly filter results by input-filter globs to only index files,
not directory for each text type

Add test to prevent regression

Closes #448
2023-10-17 23:32:10 -07:00
Debanjum Singh Solanky
51363d280d Do not configure khoj server for pull based indexing from khoj.el
Do not make khoj server pull update index on Obsidian plugin load.
Index is updated on push from plugin instead now/
2023-10-17 21:47:19 -07:00
Debanjum Singh Solanky
d9d133dfb9 Read text files as utf-8, instead of default os locale
On Windows, the default locale isn't utf8. Khoj had regressed to
reading files in OS specified locale encoding, e.g cp1252, cp949 etc.

It now explicitly uses utf8 encoding to read text files for indexing

Resolves #495, resolves #472
2023-10-17 21:47:19 -07:00
Debanjum
3d4576ae38
Fix encoding binary files for sync from the Desktop, Obsidian client (#506)
- Fix encoding binary files like PDFs for sync from Desktop client
- Fix encoding binary files like PDFs for sync from Obsidian client
2023-10-17 15:37:22 -07:00
Debanjum Singh Solanky
c8293998d9 Fix encoding binary files like PDFs for sync from Obsidian client
Use readBinary to read binary files like PDFs instead of read
2023-10-17 15:08:30 -07:00
sabaimran
ba60c869c9 Fix encoding binary files like PDFs for sync from Desktop client
Use readFileSync, Buffer to pass appropriately formatted binary data
2023-10-17 15:08:23 -07:00
Andrew Spott
3d7381446d
Changed globbing. Now doesn't clobber a users glob if they want to a… (#496)
* Changed globbing.  Now doesn't clobber a users glob if they want to add it, but will (if just given a directory), add a recursive glob.

Note: python's glob engine doesn't support `{}` globing, a future option is to warn if that is included.

* Fix typo in globformat variable

* Use older glob pattern for plaintext files

---------

Co-authored-by: Saba <narmiabas@gmail.com>
2023-10-17 11:26:06 -07:00
sabaimran
2646c8554d Provide a default value to offline_chat configuration of the conversation processor 2023-10-17 10:35:22 -07:00
Debanjum Singh Solanky
b8976426eb Update offline chat model config schema used by Emacs, Obsidian clients
The server uses a new schema for the conversation config. The Emacs,
Obsidian clients need to use this schema to update the conversation
config
2023-10-17 07:01:35 -07:00
Debanjum
ecc6fbfeb2
Push Files to Index from Emacs, Obsidian & Desktop Clients using Multi-Part Forms (#499)
### Overview
- Add ability to push data to index from the Emacs, Obsidian client
- Switch to standard mechanism of syncing files via HTTP multi-part/form. Previously we were streaming the data as JSON
  - Benefits of new mechanism
    - No manual parsing of files to send or receive on clients or server is required as most have in-built mechanisms to send multi-part/form requests
    - The whole response is not required to be kept in memory to parse content as JSON. As individual files arrive they're automatically pushed to disk to conserve memory if required
    - Binary files don't need to be encoded on client and decoded on server

### Code Details
### Major
- Use multi-part form to receive files to index on server
- Use multi-part form to send files to index on desktop client
- Send files to index on server from the khoj.el emacs client
  - Send content for indexing on server at a regular interval from khoj.el
- Send files to index on server from the khoj obsidian client
- Update tests to test multi-part/form method of pushing files to index

#### Minor
- Put indexer API endpoint under /api path segment
- Explicitly make GET request to /config/data from khoj.el:khoj-server-configure method
- Improve emoji, message on content index updated via logger
- Don't call khoj server on khoj.el load, only once khoj invoked explicitly by user
- Improve indexing of binary files
  - Let fs_syncer pass PDF files directly as binary before indexing
  - Use encoding of each file set in indexer request to read file 
- Add CORS policy to khoj server. Allow requests from khoj apps, obsidian & localhost
- Update indexer API endpoint URL to` index/update` from `indexer/batch`

Resolves #471 #243
2023-10-17 06:05:15 -07:00
Debanjum Singh Solanky
6a4f1b2188 Add more client, request details in logs by index/update API endpoint 2023-10-17 05:43:29 -07:00
Debanjum Singh Solanky
5efae1ad55 Update indexer API endpoint query params for force, content type
New URL query params, `force' and `t' match name of query parameter in
existing Khoj API endpoints

Update Desktop, Obsidian and Emacs client to call using these new API
query params. Set `client' query param from each client for telemetry
visibility
2023-10-17 04:58:13 -07:00
Debanjum Singh Solanky
84654ffc5d Update indexer API endpoint URL to index/update from indexer/batch
New URL follows action oriented endpoint naming convention used for
other Khoj API endpoints

Update desktop, obsidian and emacs client to call this new API
endpoint
2023-10-17 04:58:13 -07:00
Debanjum Singh Solanky
e347823ff4 Log telemetry for index updates via push to API endpoint 2023-10-17 04:58:13 -07:00
Debanjum Singh Solanky
05be6bd877 Clicking Update Index in Obsidian settings should push files to index
Use the indexer/batch API endpoint to regenerate content index rather
than the previous pull based content indexing API endpoint
2023-10-17 04:58:13 -07:00
Debanjum Singh Solanky
13a3122bf3 Stop configuring server to pull files to index from Obsidian client
Obsidian client now pushes vault files to index instead
2023-10-17 04:58:13 -07:00
Debanjum Singh Solanky
99a2c934a3 Add CORS policy to allow requests from khoj apps, obsidian & localhost
Using fetch from Khoj Obsidian plugin was failing due to cross-origin
request and method: no-cors didn't allow passing x-api-key custom
header. And using Obsidian's request with multi-part/form-data wasn't
possible either.
2023-10-17 04:58:13 -07:00
Debanjum Singh Solanky
541cd59a49 Let fs_syncer pass PDF files directly as binary before indexing
No need to do unneeded base64 encoding/decoding to pass pdf contents
for indexing from fs_syncer to pdf_to_jsonl
2023-10-17 04:58:13 -07:00
Debanjum Singh Solanky
d27dc71dfe Use encoding of each file set in indexer request to read file
Get encoding type from multi-part/form-request body for each file
Read text files as utf-8 and pdfs, images as binary
2023-10-17 04:58:12 -07:00
Debanjum Singh Solanky
8e627a5809 Pass any files to be deleted to indexer API via Khoj Obsidian plugin
- Keep state of previously synced files to identify files to be deleted
- Last synced files stored in settings for persistence of this data
  across Obsidian reboots
2023-10-17 03:34:49 -07:00
Debanjum Singh Solanky
f2e293a149 Push Vault files to index to Khoj server using Khoj Obsidian plugin
Use the multi-part/form-data request to sync Markdown, PDF files in
vault to index on khoj server

Run scheduled job to push updates to value for indexing every 1 hour
2023-10-17 03:05:30 -07:00
Debanjum Singh Solanky
6baaaaf91a Test request body of multi-part form to update content index from khoj.el 2023-10-16 23:54:32 -07:00
Debanjum Singh Solanky
79b3f8273a Make khoj.el send files to be deleted from index to server 2023-10-16 23:53:02 -07:00
Debanjum Singh Solanky
f64fa06e22 Initialize the Khoj Transient menu on first run instead of load
This prevents Khoj from polling the Khoj server until explicitly
invoked via `khoj' entrypoint function.

Previously it'd make a request to the khoj server every time Emacs or
khoj.el was loaded

Closes #243
2023-10-16 19:11:46 -07:00
Debanjum
b4949f7f0b
Improve Offline Chat Model Experience (#494)
- Make offline chat model user configurable. Use `filename` of any [GPT4All supported  model](https://github.com/nomic-ai/gpt4all/blob/main/gpt4all-chat/metadata/models.json) like below:
- Run GPT4All Chat Model on GPU, when available via [GPT4All Vulcan support](https://blog.nomic.ai/posts/gpt4all-gpu-inference-with-vulkan)
- Use default Llama 2 supported by GPT4All
- Make `tokenizer` and `max-prompt-size` of chat model user configurable. E.g When using chat models not in [this pre-defined list](https://github.com/khoj-ai/khoj/blob/master/src/khoj/processor/conversation/utils.py) that support larger context window or a different tokenizer.

Closes #406, #418
2023-10-16 17:44:49 -07:00
Debanjum Singh Solanky
644c3b787f Scale no. of chat history messages to use as context with max_prompt_size
Previously lookback turns was set to a static 2. But now that we
support more chat models, their prompt size vary considerably.

Make lookback_turns proportional to max_prompt_size. The truncate_messages
can remove messages if they exceed max_prompt_size later

This lets Khoj pass more of the chat history as context for models
with larger context window
2023-10-16 17:22:28 -07:00
Debanjum Singh Solanky
df1d74a879 Use max_prompt_size, tokenizer from config for chat model context stuffing 2023-10-15 16:52:53 -07:00
Debanjum Singh Solanky
116595b351 Use chat_model specified in new offline_chat section of config
- Dedupe offline_chat_model variable. Only reference offline chat
  model stored under offline_chat. Delete the previous chat_model
  field under GPT4AllProcessorConfig

- Set offline chat model to use via config/offline_chat API endpoint
2023-10-15 16:37:49 -07:00
Debanjum Singh Solanky
feb4f17e3d Update chat config schema. Make max_prompt, chat tokenizer configurable
This provides flexibility to use non 1st party supported chat models

- Create migration script to update khoj.yml config
  - Put `enable_offline_chat' under new `offline-chat' section
    Referring code needs to be updated to accomodate this change
  - Move `offline_chat_model' to `chat-model' under new `offline-chat' section
  - Put chat `tokenizer` under new `offline-chat' section
  - Put `max_prompt' under existing `conversation' section
    As `max_prompt' size effects both openai and offline chat models
2023-10-15 16:35:11 -07:00
sabaimran
c125995d94
[Multi-User]: Part 0 - Add support for logging in with Google (#487)
* Add concept of user authentication to the request session via GoogleUser
2023-10-14 19:39:13 -07:00
Debanjum Singh Solanky
247e75595c Use AutoTokenizer to support more tokenizers 2023-10-14 16:54:52 -07:00
Saba
ff2dbadc9d Use computed plaintext_content to set file content rather than calling f.read again 2023-10-14 13:28:34 -07:00
Debanjum Singh Solanky
1ad8b150e8 Add default tokenizer, max_prompt as fallback for non-default offline chat models
Pass user configured chat model as argument to use by converse_offline

The proper fix for this would allow users to configure the max_prompt
and tokenizer to use (while supplying default ones, if none provided)
For now, this is a reasonable start.
2023-10-13 22:48:56 -07:00
Debanjum Singh Solanky
56bd69d5af Improve Llama v2 extract questions actor and associated prompt
- Format extract questions prompt format with newlines and whitespaces
- Make llama v2 extract questions prompt consistent

- Remove empty questions extracted by offline extract_questions actor
- Update implicit qs extraction unit test for offline search actor
2023-10-13 22:48:56 -07:00
sabaimran
09bb3686cc
Strip the incoming query from the slash conversation command (#500)
* Strip the incoming query from the slash conversation command before passing it to the model or for search
* Return q when content index not loaded
* Remove -n 4 from pytest ini configuration to isolate test failures
2023-10-13 21:11:23 -07:00
Debanjum Singh Solanky
96c0b21285 Sync desktop app package.json with other Khoj clients metadata
- Make `bump_version.sh' script set version for the Khoj desktop app too
- Sync Khoj desktop app authors, license, description and version with
  the other interfaces and server
- Update description in packages metadata to match project subtitle on Github
2023-10-13 20:43:55 -07:00
sabaimran
80fb56b8a5 Sync deksktop app package version with the other releases 2023-10-13 19:23:00 -07:00
Debanjum Singh Solanky
b669aa2395 Clean and fix the content indexing code in the Emacs client
- Pass payloads as unibyte. This was causing the request to fail for
  files with unicode characters
- Suppress messages with file content in on index updates
- Fix rendering response from server on index update API call
- Extract code to populate body of index update HTTP request with files
2023-10-13 18:00:37 -07:00
Debanjum Singh Solanky
bea196aa30 Explicitly make GET request to /config/data from khoj.el:khoj-server-configure method
Previously global state of `url-request-method' would affect the
kind of request made to api/config/data API endpoint as it wasn't
being explicitly being set before calling the API endpoint

This was done with the assumption that the default value of GET for
url-request-method wouldn't change globally

But in some cases, experientially, it can get changed. This was
resulting in khoj.el load failing as POST request was being made
instead which would throw error
2023-10-12 20:58:52 -07:00
Debanjum Singh Solanky
292f0420ad Send content for indexing on server at a regular interval from khoj.el
- Allow indexing frequency to be configurable by user
- Ensure there is only one khoj indexing timer running
2023-10-12 20:58:52 -07:00
Debanjum Singh Solanky
fc99431754 Send files to index on server from the khoj.el emacs client
- Add elisp variable to set API key to engage with the Khoj server
- Use multi-part form to POST the files to index to the indexer API
  endpoint on the khoj server
2023-10-12 20:58:52 -07:00
Debanjum Singh Solanky
68018ef397 Use multi-part form to send files to index on desktop client
- Add typing for variables in for loop and other minor formatting clean-up
- Assume utf8 encoding for text files and binary for image, pdf files
2023-10-12 20:58:49 -07:00
Debanjum Singh Solanky
7190b3811d Remove all filter terms in user query from defiltered_query
Previously only the the last filter's terms were getting effectively
applied as the `filter.defilter' operation was being done on
`user_query' but was updating the `defiltered_query'
2023-10-12 20:56:17 -07:00
Debanjum Singh Solanky
60e9a61647 Use multi-part form to receive files to index on server
- This uses existing HTTP affordance to process files
  - Better handling of binary file formats as removes need to url encode/decode
  - Less memory utilization than streaming json as files get
    automatically written to disk once memory utilization exceeds preset limits
  - No manual parsing of raw files streams required
2023-10-11 23:58:23 -07:00
Debanjum Singh Solanky
9ba173bc2d Improve emoji, message on content index updated via logger
Use mailbox closed with flag down once content index completed.

Use standard, existing logger messages in new indexer messages, when
files to index sent by clients
2023-10-11 17:12:03 -07:00
Debanjum Singh Solanky
6aa69da3ef Put indexer API endpoint under /api path segment
Update FastAPI app router, desktop app and to use new url path to
batch indexer API endpoint

All api endpoints should exist under /api path segment
2023-10-09 21:35:58 -07:00
Debanjum Singh Solanky
f6f7a62d80 Wait for user to stop typing to trigger search from khoj.el in Emacs
- Improves user experience by aligning idle time with search latency
  to avoid display jitter (to render results) while user is typing

- Makes the idle time configurable

Closes #480
2023-10-06 12:44:45 -07:00
sabaimran
5c4f0d42b7 Return new default config in API endpoint 2023-10-06 12:30:09 -07:00
sabaimran
052b25af0a Update default configuration passed to Khoj clients to circumvent valiation issues 2023-10-06 12:29:15 -07:00
Debanjum Singh Solanky
a85ff941ca Make offline chat model user configurable
Only GPT4All supported Llama v2 models will work given the prompt
structure is not currently configurable
2023-10-04 20:41:14 -07:00
Debanjum Singh Solanky
d1ff812021 Run GPT4All Chat Model on GPU, when available
GPT4All now supports running models on GPU via Vulkan
2023-10-04 18:42:12 -07:00
Debanjum Singh Solanky
13b16a4364 Use default Llama 2 supported by GPT4All
Remove custom logic to download custom Llama 2 model.
This was added as GPT4All didn't support Llama 2 when it was added to Khoj
2023-10-03 19:01:54 -07:00
sabaimran
4a5ed7f06c
Update Khoj package version for Electron, Desktop app (#492)
* Address package upgrade for Electron application
* Update package version for Electron desktop application
2023-10-03 12:21:32 -07:00
sabaimran
3f962a55c3
Fix Linux Desktop Application (#491)
* Use separate functions for adding files and folders to configuration for indexing
* Add a loading bar while data is syncing
* Bump the minor version for the application
2023-10-03 11:43:19 -07:00
sabaimran
63b3696af0 Release Khoj version 0.12.3 2023-09-26 22:41:11 -07:00
sabaimran
d2f9bca1cf Fix null ref issue in query method and update logic for determining whether khoj is already configured in obsidian 2023-09-26 22:33:44 -07:00
sabaimran
2f18383349 Release Khoj version 0.12.2 2023-09-26 11:59:47 -07:00
sabaimran
588f35b6e9 Add max prompt size for gpt-3.5-turbo-16k 2023-09-26 10:57:35 -07:00
sabaimran
4e370d7a18 Release Khoj version 0.12.1 2023-09-26 09:24:53 -07:00
sabaimran
3675aa348a Update naming of Khoj in manifest.json for Obsidian 2023-09-26 09:24:36 -07:00
sabaimran
a82d1becc3 Release Khoj version 0.12.0 2023-09-26 09:17:56 -07:00
sabaimran
38f0df3d53 Remove unused icons from electron app folder 2023-09-26 07:56:29 -07:00
sabaimran
5e16074b92 Fix comparison for search type in plugins mode 2023-09-25 10:57:17 -07:00
sabaimran
2dd15e9f63
Resolve issues with GPT4All and fix prompt for yesterday extract questions date filter (#483)
- GPT4All integration had ceased working with 0.1.7 specification. Update to use 1.0.12. At a later date, we should also use first party support for llama v2 via gpt4all
- Update the system prompt for the extract_questions flow to add start and end date to the yesterday date filter example.
- Update all setup data in conftest.py to use new client-server indexing pattern
2023-09-18 14:41:26 -07:00
sabaimran
b225d1188c Fix formatting of gpt.py 2023-09-18 11:09:02 -07:00
Jonny-GM
34b202b868
More lenient date searching (#481)
* Modify DateFilter to use compiled entry key
* Instruct search to include date in query
* Minor prompt change
* Prompt fix
2023-09-18 10:46:00 -07:00
sabaimran
16874e1953 Provide force fallback for regeneration 2023-09-12 16:35:07 -07:00
sabaimran
9f42a1a036 Propagate flags to configure index command 2023-09-11 10:33:44 -07:00
sabaimran
343854752c
Improve docker builds for local hosting (#476)
* Remove GPT4All dependency in pyproject.toml and use multiplatform builds in the dockerization setup in GH actions
* Move configure_search method into indexer
* Add conditional installation for gpt4all
* Add hint to go to localhost:42110 in the docs. Addresses #477
2023-09-08 17:07:26 -07:00
sabaimran
dccfae3853
Remove PySide dependency and deprecate desktop builds (#475)
* Remove PySide, gui option from code
* Remove pyside 6 dependency from code
* Remove workflows which build desktop applications
* Update unit tests and update line in documentation
* Remove additional references to pyinstaller, gui
* Add uninstall steps to normal uninstall instructions
2023-09-07 11:36:27 -07:00
sabaimran
76562f4250
Add front-end Electron application for Khoj local file syncing (#473)
* Initial version - setup a file-push architecture for generating embeddings with Khoj
* Use state.host and state.port for configuring the URL for the indexer
* Fix parsing of PDF files
* Read markdown files from streamed data and update unit tests
* On application startup, load in embeddings from configurations files, rather than regenerating the corpus based on file system
* Init: refactor indexer/batch endpoint to support a generic file ingestion format
* Add features to better support indexing from files sent by the desktop client
* Initial commit with Electron application
- Adds electron app
* Add import for pymupdf, remove import for pypdf
* Allow user to configure khoj host URL
* Remove search type configuration from index.html
* Use v1 path for current indexer routes
2023-09-06 12:04:18 -07:00
bholagabbar
205dc90746
Fix notion title bug (#474)
* Update notion_to_jsonl.py
* Fix try-catch block
2023-09-05 10:47:42 -07:00
sabaimran
4854258047
Move to a push-first model for retrieving embeddings from local files (#457)
* Initial version - setup a file-push architecture for generating embeddings with Khoj
* Update unit tests to fix with new application design
* Allow configure server to be called without regenerating the index; this no longer works because the API for indexing files is not up in time for the server to send a request
* Use state.host and state.port for configuring the URL for the indexer
* On application startup, load in embeddings from configurations files, rather than regenerating the corpus based on file system
2023-08-31 12:55:17 -07:00
sabaimran
92cbfef7ab Skip plaintext file indexing if there's a parsing issue and log the file 2023-08-29 14:34:08 -07:00
sabaimran
74409c2c64 Release Khoj version 0.11.4 2023-08-29 11:44:35 -07:00
sabaimran
1b85958bcc trim chat input start 2023-08-28 19:18:10 -07:00
sabaimran
e592f6eac8 Release Khoj version 0.11.3 2023-08-28 14:46:03 -07:00
sabaimran
7c35da9fc4 Fix bug in /chat endpoint for general and update depdendencies 2023-08-28 14:12:11 -07:00
sabaimran
bc09143856 Release Khoj version 0.11.2 2023-08-28 10:16:13 -07:00
Debanjum Singh Solanky
01b310635e Enable passing search query filters via chat and test it 2023-08-28 09:24:32 -07:00
Debanjum Singh Solanky
794bad8bcb Make date_filter.extract_date_range method always return a list type 2023-08-28 00:55:28 -07:00
Debanjum Singh Solanky
d5a2de6222 Add method to extract filter terms from query to all filters
- Test the get_filter_term method in all 3 word, file, date filters
- Make the existing can_filter method by default in base filter abstract class
2023-08-28 00:55:28 -07:00
Debanjum
150105505b
Add Default chat command. Make Khoj ask clarifying questions (#468)
- Make Khoj ask clarifying questions when answer not in provided context
- Add default conversation command to auto switch b/w general, notes modes
- Show filtered list of commands available with the currently input text
- Use general prompt when no references found and not in Notes mode
- Test general and notes slash commands in offline chat director tests
2023-08-28 00:52:57 -07:00
Debanjum Singh Solanky
eb6cd4f8d0 Use general prompt when no references found and not in Notes mode 2023-08-28 00:47:02 -07:00
Debanjum Singh Solanky
edffbad837 Make Khoj ask clarifying questions when answer not in provided context
Previously it would just refuse ask for clarification. This improves
the chat quality score for the existing director tests
2023-08-28 00:47:02 -07:00
Debanjum Singh Solanky
75c1016ec0 Show filtered list of commands available with the currently input text 2023-08-28 00:46:10 -07:00
Debanjum Singh Solanky
74605f6159 Add default conversation command to auto switch b/w general, notes modes
This was the default behavior but behavior regressed when adding slash
commands in PR #463
2023-08-28 00:46:10 -07:00
sabaimran
cbc978ea08 Update help links for notion, github to point to the main docs 2023-08-27 15:02:55 -07:00
sabaimran
b45e1d8c0d
Fix plaintext HTML parsing and rendering (#464)
* Store conversation command options in an Enum
* Move to slash commands instead of using @ to specify general commands
* Calculate conversation command once & pass it as arg to child funcs
* Add /notes command to respond using only knowledge base as context
This prevents the chat model to try respond using it's general world
knowledge only without any references pulled from the indexed
knowledge base
* Test general and notes slash commands in openai chat director tests
---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
2023-08-27 11:24:30 -07:00
Debanjum
7919787fb7
Use Slash Commands and Add Notes Slash Command (#463)
* Store conversation command options in an Enum

* Move to slash commands instead of using @ to specify general commands

* Calculate conversation command once & pass it as arg to child funcs

* Add /notes command to respond using only knowledge base as context

This prevents the chat model to try respond using it's general world
knowledge only without any references pulled from the indexed
knowledge base

* Test general and notes slash commands in openai chat director tests

* Update gpt4all tests to use md configuration

* Add a /help tooltip

* Add dynamic support for describing slash commands. Remove default and treat notes as the default type

---------

Co-authored-by: sabaimran <narmiabas@gmail.com>
2023-08-26 18:11:18 -07:00
sabaimran
e64357698d
Skip indexing single bad markdown, plaintext file (#460) 2023-08-23 15:34:56 -07:00
sabaimran
84bd579077 Format the chat outputted message with code, bolding, or italics. Add a copy button for code. Closes #445. 2023-08-19 20:02:57 -07:00
sabaimran
f9e09ba490 Do not try downloading model from GPT4All if the user is not connected to the internet 2023-08-19 19:09:21 -07:00
Debanjum Singh Solanky
3ff4e19dd2 Release Khoj version 0.11.1 2023-08-16 22:53:29 -07:00
sabaimran
4fb8c2c5e1 Pass a SIGTERM to tell the uvicorn server to exit and gracefully kill the thread 2023-08-16 21:27:05 -07:00
sabaimran
4e03dfea43
Attach the parent to the server thread, allowing the kill signal to trigger a graceful exit (#446) 2023-08-16 19:36:10 -07:00
Debanjum Singh Solanky
26c3977fb9 Remove info hint to reindex khoj on unexpected search results
The index corruption was issue resolved a while ago in #325 and
hasn't cropped up again
2023-08-16 00:58:59 -07:00
sabaimran
def909a913
Revert "Open Web interface within Desktop app in GUI mode" (#444) 2023-08-15 23:26:28 -07:00
sabaimran
6562ec6531 Release Khoj version 0.11.0 2023-08-14 19:25:03 -07:00
sabaimran
0ea901c7c1
Allow indexing to continue even if there's an issue parsing a particular org file (#430)
* Allow indexing to continue even if there's an issue parsing a particular org file
* Use approximation in pytorch comparison in text_search UT, skip additional file parser errors for org files
* Change error of expected failure
2023-08-14 07:56:33 -07:00
sabaimran
7b907add77
Add support for indexing plaintext files (#420)
* Add support for indexing plaintext files
- Adds backend support for parsing plaintext files generically (.html, .txt, .xml, .csv, .md)
- Add equivalent frontend views for setting up plaintext file indexing
- Update config, rawconfig, default config, search API, setup endpoints
* Add a nifty plaintext file icon to configure plaintext files in the Web UI
* Use generic glob path for plaintext files. Skip indexing files that aren't in whitelist
2023-08-09 15:44:40 -07:00
Ellen7ions
26bddcb65c
Add support for starting a new line with shift-enter (#412)
* Add support for starting a new line with shift-enter
* Remove useless comments. Set font-size: medium.
* Update src/khoj/interface/web/chat.html
Update the styling to have the padding, margin and line-height like before.
Co-authored-by: Debanjum <debanjum@gmail.com>
* Update src/khoj/interface/web/chat.html
Make the chat-body scroll to the bottom after resizing
Co-authored-by: Debanjum <debanjum@gmail.com>
---------
Co-authored-by: Debanjum <debanjum@gmail.com>
2023-08-07 19:49:07 -07:00
Debanjum Singh Solanky
97609e4995 Use 500px png of khoj logo instead svg for much smaller asset size
The khoj logo svg was 1.3Mb. The 500px png of it is 38Kb.
Given all usage of khoj-logo are below 230px this should work fine
2023-08-07 18:27:11 -07:00
Debanjum
14a816d173
Open Web interface within Desktop app in GUI mode (#429)
Previously the GUI mode (with khoj --gui or using the desktop app) would open the web interface in the users default web browser. Now the web interface is just rendered within the app itself using PyQT's Webview. This gives it a more proper app like feel
2023-08-07 17:48:30 -07:00
Debanjum Singh Solanky
378b96ec1b Open the khoj app window maximized on startup 2023-08-07 15:39:05 -07:00
Debanjum Singh Solanky
ea734ba1c8 Open app in native view on starting it in GUI mode instead of on web browser
- Opens settings page on first run and landing page after in GUI mode
  Previously was only opening the GUI on linux after first run as it
  doesn't have a system tray
- Both the views are from the web interface but are rendered within
  the app instead of the browser
2023-08-07 13:41:42 -07:00
Debanjum Singh Solanky
9c494705a8 Open the search, chat or config view in app from the system tray menu 2023-08-07 13:41:42 -07:00
Debanjum Singh Solanky
cc36b87345 Render the web interface directly within the desktop app as a webview 2023-08-07 13:41:12 -07:00
Jason Qin
3ef1b7073d
Update obsidian/manifest.json
Closes #426
2023-08-07 10:41:39 -07:00
sabaimran
738cf650b3
Explicitly set Khoj to use the default locale of the user (#425)
- Explicitly set locale using `locale.setLocale(locale.LC_ALL, '')` for localization. Relevant for datetime libraries. See [Python 3 documentation](https://docs.python.org/3/library/locale.html#locale.setlocale).
2023-08-07 09:23:24 -07:00
Muftawo
c8ef619090
fixed reference link to landing page (#417)
* Fixed zsh error no matches found
* Fixed home page 404 error
2023-08-04 10:38:14 -07:00
sabaimran
78012b8111 Avoid null ref issue when setting model state for web UI. Closes #410 2023-08-03 00:39:06 -07:00
sabaimran
0baed742e4
Add checksums to verify the correct model is downloaded as expected (#405)
* Add checksums to verify the correct model is downloaded as expected
- This should help debug issues related to corrupted model download
- If download fails, let the application continue
* If the model is not download as expected, add some indicators in the settings UI
* Add exc_info to error log if/when download fails for llamav2 model
* Simplify checksum checking logic, update key name in model state for web client
2023-08-02 23:26:52 -07:00
Debanjum Singh Solanky
e6e3acdbe4 Release Khoj version 0.10.1 2023-08-01 23:55:13 -07:00
Debanjum Singh Solanky
7c1d70aa17 Bump GPT4All response generation batch size to 512 from 256
A batch size of 512 performs ~20% better on a XPS with no GPU and 16Gb
RAM. Seems worth the tradeoff for now
2023-08-01 23:34:02 -07:00
Debanjum
16c6bfce8e
Improve Quality and Reliability of Offline Chat (#393)
# Incoming
## Major
### Fix Prompt Size Exceeded Issue
- Fix issues related to prompt size, Closes #386. Use the correct tokenizer to calculate whether the input needs to be truncated or not.

### Improve Llama 2 Model Download
- Use the correct download link for LlamaV2 -- should have been using the small model, but was using the medium
- Add better downloading logic to retry download if it failed, Closes #379 

### Fix Segmentation Fault due to Race
- Add a lock around generating chat responses from the offline model to avoid segmentation faults. Closes #367.
- Add a loading symbol to the web chat UI when the model is thinking. Closes #392

### Improve Chat Response Latency
- Improve performance of offline chat by increasing batch size (via `n_batch`) to automatically engage more cores/GPU, using smaller model and fixing prompt vs response token generation numbers. Closes #363

### Fix Fake Dialogue Continuation
- Fix formatting of user query with offline chat, this was contributing to #398
- Stop Llama 2 from Creating Fake Dialogue Continuations. Closes #398

## Minor
- Improve default message for Chat window on web when it's not configured. Include hint to use offline chat.
- Add null check in `perform_chat_checks` method
- Add offline chat director unit tests

## Performance Analysis (Time to First Token)
|  | v0.10.0 | this branch |
|-|-|-|
| Query 1 | 52s | 28s |
| Query 2 | 33s| 42s |
| Query 3 | 67s| 38s|
2023-08-01 22:07:27 -07:00
Debanjum Singh Solanky
44292afff2 Put offline model response generation behind the chat lock as well
Not just the chat response streaming
2023-08-01 21:53:52 -07:00
Debanjum Singh Solanky
1812473d27 Extract new schema version for each migration script into a variable
This should ease readability, indicates which version this
migration script will update the schema to once applied
2023-08-01 21:41:08 -07:00
Debanjum Singh Solanky
b9937549aa Simplify migration scripts management. Make them use static version
- Only make them update config when it's run conditions are satisfies
- Use static schema version to simplify reasoning about run conditions
2023-08-01 21:28:20 -07:00
Debanjum Singh Solanky
185a1fbed7 Remove old chat setup timer. It is mislabelled, irrelevant since streaming 2023-08-01 20:52:00 -07:00
Debanjum Singh Solanky
c2b7a14ed5 Fix context, response size for Llama 2 to stay within max token limits
Create regression text to ensure it does not throw the prompt size
exceeded context window error
2023-08-01 20:52:00 -07:00
Debanjum Singh Solanky
6e4050fa81 Make Llama 2 stop generating response on hitting specified stop words
It would previously some times start generating fake dialogue with
it's internal prompt patterns of <s>[INST] in responses.

This is a jarring experience. Stop generation response when hit <s>

Resolves #398
2023-08-01 20:52:00 -07:00
Debanjum Singh Solanky
aa6846395d Fix offline model migration script to run for version < 0.10.1
- Use same batch_size in extract question actor as the chat actor
- Log final location the chat model is to be stored in, instead of
  it's temp filename while it is being downloaded
2023-08-01 20:51:53 -07:00
Ikko Eltociear Ashimine
49abb9df9c
Fix typo in orgnode.py (#397)
Fix spelling of Ouput in org parser property drawer comment to Output.
2023-08-01 19:54:57 -07:00
sabaimran
f409e16137 Update some of the extract question prompts for llamav2 2023-08-01 12:23:36 -07:00
sabaimran
b11b00a9ff Add log line for time to first response 2023-08-01 10:57:38 -07:00
sabaimran
778df6be71 Add a logline when the offline model migration script runs 2023-08-01 09:27:42 -07:00
sabaimran
3a5d93d673 Add migration script for getting the new offline model 2023-08-01 09:25:05 -07:00
sabaimran
90efc2ea7a Update comments and add explanations 2023-08-01 09:24:03 -07:00
sabaimran
f7e03f6d63 Switch spinner snake case -> camel case 2023-08-01 08:52:25 -07:00
sabaimran
1c52a6993f add a lock around chat operations to prevent the offline model from getting bombarded and stealing a bunch of compute resources
- This also solves #367
2023-08-01 00:23:17 -07:00
sabaimran
6c3074061b Disable the input bar when chat response is in flight 2023-08-01 00:21:39 -07:00
sabaimran
c14cbe926a Add a loading symbol to web chat. Closes #392 2023-07-31 23:35:48 -07:00
sabaimran
8054bdc896 Use n_batch parameter to increase resource consumption on host machine (and implicitly engage GPU) 2023-07-31 23:25:08 -07:00
sabaimran
e55e9a7b67 Fix unit tests and truncation logic 2023-07-31 21:37:59 -07:00
sabaimran
2335f11b00 Add better error handling for download processes incase of failure 2023-07-31 21:07:38 -07:00
sabaimran
209975e065 Resolve merge conflicts: let Khoj fail if the model tokenizer is not found 2023-07-31 19:12:26 -07:00
sabaimran
2d6c3cd4fa Misc. quality improvements for Llama V2
- Fix download url -- was mapping to q3_K_M, but fixed to use q4_K_S
- Use a proper Llama Tokenizer for counting tokens for truncation with Llama
- Add additional null checks when running
2023-07-31 19:11:20 -07:00
sabaimran
ca195097d7 Update chat hint message at first run 2023-07-31 17:46:09 -07:00
Debanjum Singh Solanky
ded606c7cb Fix format of user query during general conversation with Llama 2 2023-07-31 17:21:14 -07:00
Debanjum Singh Solanky
48e5ac0169 Do not drop system message when truncating context to max prompt size
Previously the system message was getting dropped when the context
size with chat history would be more than the max prompt size
supported by the cat model

Now only the previous chat messages are dropped or the current
message is truncated but the system message is kept to provide
guidance to the chat model
2023-07-31 17:21:14 -07:00
sabaimran
88ef86ad5c
Fix typing issues for mypy (#372) 2023-07-30 19:27:48 -07:00
sabaimran
ca2c942b65 Add typing to compiled_references and inferred_queries 2023-07-30 19:10:30 -07:00
sabaimran
3646fd1449 Add a warning to indicate that Khoj is not configured to work with personal data sources 2023-07-30 18:52:10 -07:00
sabaimran
996832dc72 Allow user to chat even if content types aren't configured - use empty references 2023-07-30 18:47:45 -07:00
Debanjum Singh Solanky
53810a0ff7 Create khoj config dir if non-existant, before writing to khoj env file 2023-07-30 01:35:36 -07:00
sabaimran
f65d157244 Release Khoj version 0.10.0 2023-07-28 19:27:47 -07:00
Debanjum Singh Solanky
f76af869f1 Do not log the gpt4all chat response stream in khoj backend
Stream floods stdout and does not provide useful info to user
2023-07-28 19:14:04 -07:00
sabaimran
5ccb01343e
Add Offline chat to Obsidian (#359)
* Add support for configuring/using offline chat from within Obsidian
* Fix type checking for search type
* If Github is not configured, /update call should fail
* Fix regenerate tests same as the update ones
* Update help text for offline chat in obsidian
* Update relevant description for Khoj settings in Obsidian
* Simplify configuration logic and use smarter defaults
2023-07-28 18:47:56 -07:00
Debanjum
b3c1507708
Merge pull request #361 from khoj-ai/configure-offline-chat-from-emacs
- Configure using Offline Chat from Emacs: 
- Enable, Disable Offline Chat from Emacs

- Use: Enable offline chat with `(setq khoj-chat-offline t)' during khoj setup
- Benefits: Offline chat models are better for privacy but not great at answering questions
2023-07-28 18:06:58 -07:00
sabaimran
9f78db0579
Let Offline chat override OpenAI API settings (#362)
* Let Offline chat override OpenAI API settings
* Download the offline model whenever offline chat is enabled
* Add progressbar for download for llamav2 model to track progress
* Change ordering of n due to switch of default processor
* Flip ordering of offline/openai checks when extracting questions from query
2023-07-28 17:26:20 -07:00
Debanjum Singh Solanky
ebfbef1f68 Configure using offline chat from Emacs
Closes #358
2023-07-28 16:07:33 -07:00
sabaimran
29081f4429 Adjust parameters for offline chat 2023-07-27 22:22:09 -07:00
sabaimran
124d97c26d
Replace Falcon 🦅 model with Llama V2 🦙 for offline chat (#352)
* Working example with LlamaV2 running locally on my machine

- Download from huggingface
- Plug in to GPT4All
- Update prompts to fit the llama format

* Add appropriate prompts for extracting questions based on a query based on llama format

* Rename Falcon to Llama and make some improvements to the extract_questions flow

* Do further tuning to extract question prompts and unit tests

* Disable extracting questions dynamically from Llama, as results are still unreliable
2023-07-27 20:51:20 -07:00
Debanjum Singh Solanky
715d56d4f0 Use new schema to update khoj.yml config from khoj.el 2023-07-26 17:34:16 -07:00
sabaimran
8b2af0b5ef
Add support for our first Local LLM 🤖🏠 (#330)
* Add support for gpt4all's falcon model as an additional conversation processor
- Update the UI pages to allow the user to point to the new endpoints for GPT
- Update the internal schemas to support both GPT4 models and OpenAI
- Add unit tests benchmarking some of the Falcon performance
* Add exc_info to include stack trace in error logs for text processors
* Pull shared functions into utils.py to be used across gpt4 and gpt
* Add migration for new processor conversation schema
* Skip GPT4All actor tests due to typing issues
* Fix Obsidian processor configuration in auto-configure flow
* Rename enable_local_llm to enable_offline_chat
2023-07-26 16:27:08 -07:00
sabaimran
23d77ee338
Fix import issues in desktop image builds (#343) 2023-07-26 15:45:52 -07:00
Debanjum Singh Solanky
7722a9c347 Default to using the gpt-3.5-turbo model for chat from khoj.el 2023-07-22 00:29:26 -07:00
Debanjum Singh Solanky
f0d4a4cf9a Revert "Make configure_content functional. Do not pass content index state to it."
This reverts commit 2ddee7e745 as it
broke partial updates of the content index for just the specified
content types
2023-07-21 13:59:09 -07:00
sabaimran
82c725817e Merge branch 'master' of github.com:khoj-ai/khoj 2023-07-21 13:24:05 -07:00
sabaimran
596e11ec6d Use the same function for computing entries for IDs regardless of whether it has prev entries 2023-07-21 13:23:56 -07:00
Debanjum Singh Solanky
2ddee7e745 Make configure_content functional. Do not pass content index state to it. 2023-07-20 23:24:08 -07:00
sabaimran
1610d2ebd9
📝 Add a documentation base for Khoj! (#333)
* Add docs for more organized, accessible information detailing Khoj setup
* Delete duplicated files
* Add a coverpage without enabling it. Add logo and theme
* Remove obsidian README.md
* Add plausible script to index.html via docsify
2023-07-20 22:34:25 -07:00
Debanjum Singh Solanky
3e59be7f1d Release Khoj version 0.9.0 2023-07-18 19:59:27 -07:00
Debanjum Singh Solanky
d078e7b1f6 Clean up search type usage in khoj server, tests and Readme 2023-07-18 19:57:55 -07:00
Debanjum Singh Solanky
4d910936b7 Fix triggering index update on khoj server from khoj.el 2023-07-18 19:57:54 -07:00
Debanjum Singh Solanky
5c7d7f558d Make AI model used for Khoj chat configurable from khoj.el
- Fix bug. Set the unused model-name to a standad default value
2023-07-18 19:57:54 -07:00
Debanjum
5f2be2a9bb
Merge pull request #298 from HyunggyuJang/patch-1
Encode config as utf-8 during setup in khoj.el. This will allow utf-8 encoded files etc to be passed in config
2023-07-18 17:54:11 -07:00
Debanjum Singh Solanky
429e1b4b48 Regenerate index to apply corruption fixes on first run of new khoj 2023-07-18 16:10:47 -07:00
Debanjum Singh Solanky
83e1088d42 Manage khoj.yml config migrations on app start. Version the schema
- Add version to khoj.yml schema
  Versioning the khoj.yml config schema will simplify future migrations
2023-07-18 16:10:10 -07:00
Debanjum Singh Solanky
71e8ddd9a2 Check if PDF is configured before showing it as an option in khoj.el 2023-07-17 15:49:20 -07:00
Debanjum
d00c5da8b7
Merge pull request #325 from khoj-ai/stablize-simplify-content-indexing
## Stabilize and Simplify Content Indexing

### Major Updates
- 9bcca43 Unify logic to update entries when indexing from scratch or incrementally
- 89c7819 Unify logic to update embeddings when indexing from scratch or incrementally
- 6a0297c Stable sort new entries when marking entries for update
- 58d86d7 Unify logic to configure server from API or on server start
- Create tests to ensure old entries, embeddings in index are unaffected on adding new entries
  - Refer: 1482fd4, 7669b85, 88d1a29 
  - ad41ef3 Make normalization of embeddings configurable to test this in c73feeb

### Minor Updates
- 1673bb5 Add todo state to compiled form of each entry
- 6e70b91 Remove unused `dump_jsonl` helper method 
- 7ad9603 Improve naming of lock
- b02323a Improve naming text search test methods

Resolves #190
2023-07-17 14:51:10 -07:00
Debanjum Singh Solanky
3e3a1ecbc8 Start app even if server init fails to let user fix it
Show stacktrace on error to help debugging
2023-07-17 14:33:02 -07:00
Debanjum Singh Solanky
ef6a0044f4 Drop embeddings of deleted text entries from index
Previously the deleted embeddings would continue to be in the index,
even after the entry was deleted
2023-07-16 03:47:05 -07:00
Debanjum Singh Solanky
ad41ef3991 Make normalizing embeddings configurable 2023-07-16 02:16:33 -07:00
Debanjum Singh Solanky
89c7819cb7 Unify logic to generate embeddings from scratch and incrementally
This simplifies the `compute_embeddings' method and avoids potential
later divergence in handling the index regenerate vs update scenarios
2023-07-16 01:45:53 -07:00
Debanjum Singh Solanky
6a0297cc86 Stable sort new entries when marking entries for update 2023-07-16 01:45:53 -07:00
Debanjum Singh Solanky
6e70b914c2 Remove unused dump_jsonl method
The entries index is stored ingzipped jsonl files for each content type
2023-07-16 01:45:53 -07:00
Debanjum Singh Solanky
9bcca43299 Use single func to handle indexing from scratch and incrementally
Previous regenerate mechanism did not deduplicate entries with same key
So entries looked different between regenerate and update
Having single func, mark_entries_for_update, to handle both scenarios
will avoid this divergence

Update all text_to_jsonl methods to use the above method for
generating index from scratch
2023-07-16 01:45:53 -07:00
Debanjum Singh Solanky
1673bb5558 Add todo state to compiled form of each org-mode entry 2023-07-16 01:45:53 -07:00
Debanjum Singh Solanky
7ad96036b0 Improve lock name to config_lock instead of search_index_lock
It is used to lock updates to all app config state, including processor
2023-07-16 01:45:53 -07:00
Debanjum Singh Solanky
58d86d7876 Use single func to configure server via API and on server start
Improve error messages on failure to configure server components
2023-07-16 01:45:53 -07:00
sabaimran
a15711e635 Fix null type checks in get /config 2023-07-15 15:53:56 -07:00
sabaimran
e590d75b20
Start Khoj even when config is not valid (#320)
* Add icon to indicate bad config, start Khoj even if there was an issue setting up the index
2023-07-15 14:11:54 -07:00
sabaimran
49ab201c30
Fix issues importing PySide in Docker container (#322)
* Rather than installing PyQT dependencies, remove codepaths that require pyqt files in no-gui mode
2023-07-15 13:33:13 -07:00
sabaimran
ba47f2ab39 Merge branch 'master' of github.com:debanjum/khoj 2023-07-14 22:28:05 -07:00
sabaimran
874cffd256 Add additional support for parsing notion workspaces 2023-07-14 22:27:56 -07:00
Debanjum
52f68167ce
Merge pull request #317 from khoj-ai/reduce-memory-consumption-by-search-model-duplication
Reuse Search Models across Content Types to reduce Memory Consumption

- Memory consumption now only scales with search models used, not with content types. 
  Previously each content type had it's own copy of the search ML models. 
  That'd result in 300+ Mb per enabled text content type

- Split model state into 2 separate state objects, `search_models` and `content_index`. 
  This allows loading text_search and image_search models first
  and then reusing them across all content_types in content_index

- The change should cut down memory utilization quite a bit for most users.
  I see a >50% drop in memory utilization on my Khoj instance. 
  But this will vary for each user based on the amount of content indexed vs number of plugins enabled.

- This change does not solve the RAM utilization scaling with size of the index,
  as the whole content index is still kept in RAM while Khoj is running

Should help with #195, #301 and #303
2023-07-14 19:54:12 -07:00
Debanjum Singh Solanky
f08e9539f1 Release lock after updating index even if update fails to prevent deadlock
Wrap acquire/release locks in try/catch/finally when updating content
index and search models to prevent lock not being released on error
and causing a deadlock
2023-07-14 16:57:27 -07:00
sabaimran
37f7f9fd1d
Add additional telemetry for system understanding (#316)
* Add additional telemetry in order to understand which data sources are the most useful
* Make actions side by side in the configuration page
* Restore main run command
* Update links to point to wiki pages for Github, Notion integrations
* Stanardize nomenclature of the api_type to use _config suffix

Remove header fields that aren't actually helpful for understanding config usage
2023-07-14 10:14:07 -07:00
Debanjum Singh Solanky
86e2bec9a0 Reuse Search Models across Content Types to Reduce Memory Consumption
- Memory consumption now only scales with search models used, not with
  content types as well. Previously each content type had it's own
  copy of the search ML models. That'd result in 300+ Mb per enabled
  content type

- Split model state into 2 separate state objects, `search_models' and
  `content_index'.
  This allows loading text_search and image_search models first and then
  reusing them across all content_types in content_index

- This should cut down memory utilization quite a bit for most users.
  I see a ~50% drop in memory utilization.

  This will, of course, vary for each user based on the amount of
  content indexed vs number of plugins enabled

- This does not solve the RAM utilization scaling with size of the index.
  As the whole content index is still kept in RAM while Khoj is running

Should help with #195, #301 and #303
2023-07-14 01:27:22 -07:00
Debanjum
b2718d330c
Merge pull request #304 from migrate-from-pyqt-to-pyside
Migrate from PyQT6 to PySide6
2023-07-13 11:54:47 -07:00
sabaimran
31e933207f Set default values for sys.stdout if they're unavailable 2023-07-12 22:22:49 -07:00
Debanjum Singh Solanky
9c76150895 Migrate from PyQT6 to PySide6 2023-07-11 18:43:44 -07:00
HyunggyuJang
88c42b3043
Encode data as utf-8
otherwise it will complain, see 1c85531090
2023-07-11 17:06:05 +09:00
Debanjum Singh Solanky
f664a74e77 Update Khoj server to run on non standard port, 42110 instead of 8000
Resolves #295
2023-07-10 21:27:58 -07:00
sabaimran
effb52f859 Fix demo rendering with the new header 2023-07-10 21:16:19 -07:00
sabaimran
55f5be7b03 Release Khoj version 0.8.2 2023-07-10 14:39:32 -07:00
sabaimran
9a63f89f33 Merge branch 'master' of github.com:debanjum/khoj 2023-07-10 14:31:19 -07:00
sabaimran
53809298c0 Release Khoj version 0.8.1 2023-07-10 14:30:04 -07:00
tjsousa
5b37e988e6
Allow using configured GPT chat model (#292)
My account doesn't have gpt-4 enabled and it wouldn't work as the default value was always used from extract_questions, where the caller could use the configured model.
2023-07-10 14:24:40 -07:00
Debanjum Singh Solanky
75ff871217 Release Khoj version 0.8.0 2023-07-10 13:37:51 -07:00
Debanjum Singh Solanky
979088b3dc Add tooltip helper text on web settings page buttons
- Provide more details on what clicking configure, initialize buttons
  or changing the results count slider does
- This shows up on user hovering over those buttons
2023-07-10 13:32:41 -07:00
Debanjum Singh Solanky
255781e135 Use relative link on logo to jump to correct page on local and cloud 2023-07-10 13:22:20 -07:00
Debanjum Singh Solanky
b2d229c116 Move header pane style to base khoj.css for reuse. Fix logo size 2023-07-10 13:10:17 -07:00
Debanjum Singh Solanky
20cb314171 Open the Khoj config page in the browser on first run 2023-07-10 12:10:20 -07:00
sabaimran
07cf5a214a
Check if PDF files are present in the Obsidian vault before initializing the Khoj configuration (#293) 2023-07-10 10:33:04 -07:00
sabaimran
7364bac8ae Make the header take up less space
- Use a single row for the header
- Needed custom styling for each page because each of them are different in subtle ways, unfortunately
2023-07-09 22:31:37 -07:00
sabaimran
62704cac09
Add a plugin which allows users to index their Notion pages (#284)
* For the demo instance, re-instate the scheduler, but infrequently for api updates
- In constants, determine the cadence based on whether it's a demo instance or not
- This allow us to collect telemetry again. This will also allow us to save the chat session
* Conditionally skip updating the index altogether if it's a demo isntance
* Add backend support for Notion data parsing
- Add a NotionToJsonl class which parses the text of Notion documents made accessible to the API token
- Make corresponding updates to the default config, raw config to support the new notion addition
* Add corresponding views to support configuring Notion from the web-based settings page
- Support backend APIs for deleting/configuring notion setup as well
- Streamline some of the index updating code
* Use defaults for search and chat queries results count
* Update pagination of retrieving pages from Notion
* Update state conversation processor when update is hit
* frequency_penalty should be passed to gpt through kwargs
* Add check for notion in render_multiple method
* Add headings to Notion render
* Revert results count slider and split Notion files by blocks
* Clean/fix misc things in the function to update index
- Use the successText and errorText variables appropriately
- Name parameters in function calls
- Add emojis, woohoo
* Clean up and further modularize code for processing data in Notion
2023-07-09 15:29:26 -07:00
Debanjum
77755c0284
Fix Packaging the Khoj Desktop Apps (#289)
* Add langchain static files and pytorch metadata to Khoj native app

* Add pillow static files, metadata & hidden imports to Khoj native app

* Fix path to web interface static files on Khoj native app

* Add tiktoken hidden imports to make chat work from Khoj native app

* Fix Khoj native app to run with GUI mode enabled

This got broken when we moved from using the --no-gui flag to using
--gui in https://github.com/khoj-ai/khoj/pull/263
2023-07-09 10:21:16 -07:00
sabaimran
4c135ea316
Make streaming optional for the /chat endpoint (#287)
* Update the /chat endpoint to conditionally support streaming

- If streams are enabled, return the threadgenerator as it does currently
- If stream is disabled, return a JSON response with the response/compiled references separated out
- Correspondingly, update the chat.html UI to use the streamed API, as well as Obsidian
- Rename chat/init/ to chat/history

* Update khoj.el to use the /history endpoint

- Update corresponding unit tests to use stream=true

* Remove & from call to /chat for obsidian

* Abstract functions out into a helpers.py file and clean up some of the error-catching
2023-07-09 10:12:09 -07:00
Debanjum Singh Solanky
0a86220d42 Use default values, delete content config on disable and update state 2023-07-07 20:36:16 -07:00
Debanjum Singh Solanky
362063f5fe By default, connect to Khoj server over IPv4 from Obsidian plugin 2023-07-07 20:36:16 -07:00
Debanjum Singh Solanky
571e8c2548 Add rerank, index corruption hint on search page of web interface
Similar to the hint alrady in the Obsidian search modal
Closes #272
2023-07-07 20:36:16 -07:00
Debanjum Singh Solanky
61e131f95c Hide unused model field from chat settings on web interface 2023-07-07 18:43:53 -07:00
Debanjum Singh Solanky
af30d01e85 Move to newer chat models to extract questions & summarize chats
Deprecate usage of the older gpt3 models in-place of the newer chat
based models
- text-davinci-003 is only 50% cheaper than gpt4 and less reliable for
  question extraction
- Using gpt-3.50turbo for summarization should reduce cost of chat

- Keep conversation.chat_session as a list instead of a string
- Update completion_with_backoff func to use ChatML format
2023-07-07 17:32:27 -07:00
Debanjum Singh Solanky
171ce19e1f Update date filter to allow quoting values in single quotes 2023-07-07 17:13:47 -07:00
Debanjum Singh Solanky
e588f7c528 Deprecate unused beta search and answer API endpoints 2023-07-07 16:38:07 -07:00
Debanjum Singh Solanky
c9fc4d1296 Revert to using cross-encoder to improve search results used by chat 2023-07-07 15:31:34 -07:00
Debanjum Singh Solanky
11f0a9f196 Fix chat tests since streaming. Pass args correctly to chat methods
- Fix testing gpt converse method after it started streaming responses
- Pass stop in model_kwargs dictionary and api key in openai_api_key
  parameter to chat completion methods. This should resolve the arg
  warning thrown by OpenAI module
2023-07-07 15:23:44 -07:00
Debanjum Singh Solanky
48870d9170 Fix parsing questions generated by extract_questions actor into list
The previous json parsing was failing to handle questions with date
filters

Fix the chat actor tests to run without throwing error with freezegun
complaining about importing transformers.local_llama model

Remove quote escapes from date filter examples provided to
extract_questions actor
2023-07-07 15:18:55 -07:00
Debanjum Singh Solanky
279662620b Move results count to settings page on web. Use it for search & chat
- Before
  Only the search interface had the results count configuration option

- After
  - The results count is set on the settings page instead of the
    search page
  - Both search and chat can use the configured results count instead
    of just search
2023-07-07 14:08:08 -07:00
Debanjum Singh Solanky
2ec8da89e8 Remove Update button from Khoj Search page on the Web interface
The settings page on the Khoj web interface already has a configure
button. Don't need the Update button on the search page as well
2023-07-07 12:49:58 -07:00
Debanjum Singh Solanky
bf427cd8dd Set no. of results used to generate chat response from Khoj Emacs 2023-07-07 12:34:50 -07:00
Debanjum Singh Solanky
1d77fe712c Set no. of results used to generate chat response from Khoj Obsidian 2023-07-07 12:32:32 -07:00
Debanjum Singh Solanky
2f31de5ed5 Set no. of references to use for chat configurable in Chat API 2023-07-07 12:29:36 -07:00
Debanjum Singh Solanky
d97682fdac Use tooltip, placeholders to guide Khoj setup via web settings page 2023-07-06 21:37:48 -07:00
Debanjum Singh Solanky
f5cf09424b Use more descriptive field names for content type settings on Khoj web
Resolves #281
2023-07-06 20:47:39 -07:00
Debanjum Singh Solanky
a2c668268f Use node-fetch >=3.1.0 in khoj obsidian plugin to avoid security vulnerability 2023-07-06 13:05:52 -07:00
sabaimran
d688ddf92c
Re-instate the scheduler for the demo instances (#279)
* For the demo instance, re-instate the scheduler, but infrequently for api updates

- In constants, determine the cadence based on whether it's a demo instance or not
- This allow us to collect telemetry again. This will also allow us to save the chat session

* Conditionally skip updating the index altogether if it's a demo isntance
2023-07-06 11:01:32 -07:00
Debanjum Singh Solanky
8f36572a9b Improve typing, null checks in controllers and gpt functions 2023-07-05 20:49:25 -07:00
Debanjum
6c2a8a5bce
️ Stream Responses by Khoj Chat on Web, Obsidian
- What
   - Stream chat responses from OpenAI API to Web, Obsidian clients
      - Implement using a callback function which manages a queue where new tokens can be placed as they come on. As the thread is read from, tokens are removed.
      - When the final token has been processed, add the `compiled_references` to the queue to be rendered by the `chat` client
      - When the thread has been closed, save the accumulated conversation log in the user's history using a `partial func`
      - Incrementally decode tokens on the front end and add them as they appear from the streamed response

- Why
This significantly reduces perceived latency and OpenAI API request timeouts for Chat

Closes https://github.com/khoj-ai/khoj/issues/257
2023-07-05 20:02:11 -07:00
Debanjum Singh Solanky
e111eda6ae Make client, app_config optional in telemetry logger for correct typing 2023-07-05 18:57:38 -07:00
Debanjum Singh Solanky
e562114f6b Improve comments, var names in js for chat streaming on web interface 2023-07-05 18:57:27 -07:00
Debanjum Singh Solanky
46269ddfd3 Fix chat logging messages to get context without flooding logs 2023-07-05 18:27:06 -07:00
Debanjum Singh Solanky
0ba838b53a Show temp status message in Khoj Obsidian chat while Khoj is thinking
- Scroll to bottom after adding temporary status message and
references too
2023-07-05 18:02:43 -07:00
Debanjum Singh Solanky
8271abe729 Use optional chaining operator to extract khojBannerSubmit from conditional 2023-07-05 18:02:43 -07:00
Debanjum Singh Solanky
c12ec1fd03 Show temp status message in Khoj web chat while Khoj is thinking
- Scroll to bottom after adding temporary status message and
references too
2023-07-05 18:02:30 -07:00
sabaimran
257a421e45 Bonus: add try-catch logic around telemetry upload in case of JSON serializability issues 2023-07-05 15:12:18 -07:00
sabaimran
4e6b66b139 Add support for streaming chat response from OpenAI to Obsidian
- I needed to installed node-fetch to accomplish this, as the built-in request object from Obsidian doesn't seem to support streaming and the built-in fetch object is very sensitive to any and all cross origin requests
2023-07-05 15:01:22 -07:00
sabaimran
3ff5074cf5 Log the end-to-end time of generating a streamed response from OpenAI 2023-07-05 14:59:44 -07:00
sabaimran
68e635cc32 Remove additional comments and debug statements 2023-07-05 11:33:56 -07:00
sabaimran
67a8795b1f Clean-up commented out code 2023-07-05 11:24:40 -07:00
sabaimran
79b1b1d350 Save streamed chat conversations via partial function passed to the ThreadGenerator 2023-07-04 17:33:52 -07:00
sabaimran
afd162de01 Add reference notes to result response from GPT when streaming is completed
- NOTE: results are still not being saved to conversation history
2023-07-04 12:47:50 -07:00
sabaimran
8f491d72de Initial code with chat streaming working (warning: messy code) 2023-07-04 10:14:39 -07:00
Debanjum Singh Solanky
5889eceba4 Make text selectable in Khoj chat modal on Obsidian
Previously the text in the Khoj chat modal couldn't be copied as it
was not selectable

Resolves #206
2023-07-03 23:24:04 -07:00
sabaimran
89354def9b Update request timeout window to 20 seconds 2023-07-03 22:28:18 -07:00
sabaimran
b1940519c3 Log error if unable to decode chunk from Github 2023-07-03 16:29:32 -07:00
Debanjum Singh Solanky
ecf9730cd7 Disable Chat, Search on Web if Khoj not configured & show next steps 2023-07-03 16:04:32 -07:00
sabaimran
017e8c1aef
Skip indexing a PDF that has an indexing error (#274) 2023-07-03 15:55:11 -07:00
sabaimran
a6f313589e Release Khoj version 0.7.1 2023-07-03 12:26:41 -07:00
sabaimran
8bfd5828e6 Remove deprecation notice since we're opening the web UI by default 2023-07-03 12:01:09 -07:00
sabaimran
92d81d3b16
Initialize the search.model field to SearchModels() and fix Reinitialize API call (#273) 2023-07-03 11:32:44 -07:00
sabaimran
61403138d5
Merge pull request #269 from khoj-ai/features/simplify-configuration-steps
Simplify some common configuration steps
2023-07-03 00:16:51 -07:00
sabaimran
ea3dc2cfa3 Simplify rendering of content type pages and logic of selecting config 2023-07-03 00:15:29 -07:00
sabaimran
260272dca2 Check if state.config is populated before configuring via the update method 2023-07-03 00:10:56 -07:00
sabaimran
bf8914d0c8 Fix default config initialization for for chat.html 2023-07-03 00:00:47 -07:00
Debanjum
faad1297f4
Drop Support for Org Music, Ledger Content Types
Removing unused content types will reduce khoj code to manage

- 0f993b3 Drop support for Ledger as a separate content type
   Khoj will soon get a generic text indexing content type in Index plain text files #237.
   This along with a file filter should suffice for searching through Ledger transactions

- c9db532 Remove unused org-music as an indexable content type from Khoj
   Org-music was just a custom content type that worked with org-music.
   It was mostly only useful for me.
2023-07-02 17:48:29 -07:00
Debanjum Singh Solanky
0f993b332e Drop support for Ledger as a separate content type
Khoj will soon get a generic text indexing content type. This along
with a file filter should suffice for searching through Ledger
transactions, if required.

Having a specific content type for niche use-case like ledger isn't
useful. Removing unused content types will reduce khoj code to manage.
2023-07-02 16:57:49 -07:00
sabaimran
fa218ff5aa Fix call to update for Reinitialize button 2023-07-02 16:31:30 -07:00
sabaimran
a8b83da872 Merge branch 'master' of github.com:debanjum/khoj into features/simplify-configuration-steps 2023-07-02 16:21:54 -07:00
Debanjum Singh Solanky
c9db5321e7 Remove unused org-music as an indexable content type from Khoj
Org-music was just a custom content type that worked with org-music.
It was mostly only useful for me.

Cleaning up that code will reduce number of content types for khoj to
manage.
2023-07-02 16:21:21 -07:00
sabaimran
b86a3bb0c5 Merge branch 'master' of github.com:debanjum/khoj into fix/obsidian-setup-issues 2023-07-02 16:21:05 -07:00
sabaimran
a52c1c8380 Use built-in app.vault to determine whether there are any PDF files within 2023-07-02 16:20:43 -07:00
sabaimran
eff1436857 Overwrite existing PDFs in Obsidian as well, make if-block more legible 2023-07-02 16:17:25 -07:00
Debanjum Singh Solanky
30459ee4ba Fix Khoj subtitle in desktop entry, pyproject, cli and Obsidian Readme 2023-07-02 16:09:07 -07:00
sabaimran
1a1b044d12 Simplify settings pages for configuration
- Add one-click disablement
- Remove fields that probably don't need to be edited (our implementation details)
- Add a green tick if a given field is configured
2023-07-02 16:04:05 -07:00
sabaimran
e4c445f805 Add try-except-finally blocks around configure calls in /update 2023-07-02 13:35:02 -07:00
sabaimran
4b02a8c788 Fix PDF setup in Obsidian plugin and force Obsidian configuration for markdown 2023-07-02 12:37:24 -07:00
sabaimran
2a7e4f2b71 Escape special characters in the URL when adding a link to the remote file 2023-07-02 09:13:28 -07:00
sabaimran
c747562897 Update the GUI to just be a simple box with a button for the web UI 2023-07-01 20:37:21 -07:00
sabaimran
bab7f39d47 Move logic to open the web browser into the GUI section 2023-07-01 20:11:27 -07:00
sabaimran
36537606da Update unit test and preserve prior operational ordering in main.py 2023-07-01 20:02:35 -07:00
sabaimran
ea9ae4ae28 Configure Khoj to automatically open the browser to their web home page when Khoj is up 2023-07-01 19:46:31 -07:00
sabaimran
d2083dd395 Remove bespoke processing for GithubToJsonl file demo 2023-07-01 19:09:22 -07:00
sabaimran
a71440f62a Update the guidance in the error message if config is not set 2023-07-01 19:09:00 -07:00
sabaimran
7db97d8aa9 Fix: don't try to render the search_type.ALL 2023-07-01 19:08:19 -07:00
sabaimran
f0f6390366 Make --no-gui the default behavior of Khoj and update corresponding documentation 2023-07-01 19:07:59 -07:00
Debanjum Singh Solanky
d77e05c279 Release Khoj version 0.7.0 2023-07-01 05:44:22 -07:00
Debanjum Singh Solanky
30d87a9a01 Update color of Khoj chat in Obsidinan plugin to Lantern theme 2023-07-01 02:18:47 -07:00
Debanjum Singh Solanky
51826d28d6 Ensure clicking Update in Khoj Obsidian indexes PDF files too 2023-07-01 02:18:47 -07:00
sabaimran
dac2d14380 Handle file names appropriately for md files and render commits in github results 2023-07-01 01:20:58 -07:00
sabaimran
dbe713604d Fix error in tests for markdown_to_jsonl 2023-07-01 00:49:40 -07:00
sabaimran
931aab4464 Handle case for when headers value is None 2023-07-01 00:37:30 -07:00
sabaimran
d01afb3ee4 Fix path issues for URL-based markdown files 2023-07-01 00:25:11 -07:00
sabaimran
31655447e7 Add the sign-up list to the chat page as well and update copy 2023-06-30 21:43:01 -07:00
sabaimran
796102c74e Add separate configuration if the given Khoj instance is meant for demo
- In theory, this will be suitable for any Khoj instance that's meant for external-facing purposes (as in, outside of the user's network)
- Prevent re-indexing for Github data if this is a demo instance
- Fix up some issues with the CSS which made settings page small in mobile
- In the frontend views for Khoj, add a button to get on the waitlist and links to the landing page
2023-06-30 20:38:55 -07:00
sabaimran
db3026739d Resolve diffs in api.py to make /chat endpoint async with new request parameter 2023-06-30 00:25:37 -07:00
sabaimran
ef72508914 Try/catch around github file decoding, await call to search in chat API, fix img width 2023-06-30 00:23:21 -07:00
Debanjum Singh Solanky
b950889f47 Fix org-mode web renderer to handle results containing list in block
- Break out of rendering list if at end of org block in org.js
- This would previous hang rendering results in web interface

Should try fix this upstream in org.js as well
2023-06-29 19:01:25 -07:00
sabaimran
780c769567 Add additional request headers to improve telemetry 2023-06-29 18:51:24 -07:00
sabaimran
6c10d68262
Merge pull request #253 from khoj-ai/features/github-issues-indexing
Support indexing Github issues as well as corresponding comments
2023-06-29 16:02:47 -07:00
sabaimran
b2dd946c6d Rename issue to entry method for accuracy 2023-06-29 15:23:50 -07:00
Debanjum Singh Solanky
51dfa48e2b Have Khoj support Python 3.11 as Pytorch supports it now
- Previously Khoj could only support Python upto 3.10 due to pytorch.
  But lots of folks had python 3.11 installed by default on their machines.

  This required installing python 3.10 and dealing with virtual envs.

  With Torch >= 2.0.1 now able to support python 3.11, at least one
  class of installation troubles for Khoj should drop. See
  https://github.com/pytorch/pytorch/issues/86566 for reference

- Preliminary testing indicates using the new torch 2.x may reduce
  search time by 25% (from 80ms to 60ms on Mac M1)

- Update Docs to not require mentioning python <=3.10 required
- Update Github test workflow to run khoj tests with python 3.11 too
2023-06-29 15:13:26 -07:00
sabaimran
65bf894302 Interpret org files as a list and put them in separate divs. Update styling of search results to separate into cards 2023-06-29 15:12:48 -07:00
Debanjum Singh Solanky
d212298573 Make Configure button on web interface incrementally update by default
We should add a way to force index everything.

But force indexing should not be the default when user is just trying
update content to index
2023-06-29 14:52:51 -07:00
Debanjum Singh Solanky
da2de21339 Only return requested result count even if search in multiple content types
- Set results_count to default value at start so it is an int, never None
2023-06-29 14:49:05 -07:00
sabaimran
77672ac0ae Demarcate different results with a border box
- Add back support for searching by type Github
- Remove custom class name in markdown js file
2023-06-29 14:14:25 -07:00
sabaimran
6edc32f2f4 Accept current changes to include issues in rendering flow 2023-06-29 12:25:29 -07:00
sabaimran
ab7dabe74f Explicitly use Union type for function parameters for lint checks 2023-06-29 11:44:30 -07:00
sabaimran
fecf6700d2 Limit small image rendering to just the avatar images 2023-06-29 11:27:18 -07:00
sabaimran
70e550250a Add an additional data source for issues from Github repositories + quality of life updates
- Use a request session to reduce the overhead of setting up a new connection with the Github URL each request
- Use the streaming feature for the REST api to reduce some of the memory footprint
2023-06-29 10:59:54 -07:00
Debanjum Singh Solanky
5f2717cc4b Use logger.warning since logger.warn is deprecated 2023-06-28 22:15:27 -07:00
Debanjum Singh Solanky
56ce97ef9e Use async/await in tests for query method of text and image search
The text, image search query method has become async. So async/await
is required to get results correctly in tests etc
2023-06-28 22:07:02 -07:00
Debanjum Singh Solanky
b1767f93d6 Get any configured asymmetric search model to encode query for search
- Set image_search.query to async to use it with multi-threading
  This is same as text_search.query being set to an async method
- Exit search early if no search_model is defined in state.model
2023-06-28 22:07:02 -07:00
Debanjum Singh Solanky
8eae7c898c Put each result under org heading when query for "all" content type in khoj.el
- Add "all" as default content type when no content type retrieved
  from server
2023-06-28 22:07:02 -07:00
Debanjum Singh Solanky
630bf995f1 Style each result based on its content type in same view on Khoj web
- So when searching across content types (with content-type = "all")
  org-mode results get rendered differently than markdown, PDF etc. results

- Set div class for each result separately instead of a single uber div
  for styling. This allows styling div of each result based on the
  content-type of that result

- No need to create placeholder "all" content type on web interface as
  server is passing an all content type by itself
2023-06-28 22:07:01 -07:00
Debanjum Singh Solanky
1773a78339 Fix createRequestUrl method signature to fetch results from khoj web 2023-06-28 12:10:45 -07:00
Debanjum Singh Solanky
212b1a96c8 Create "all" search type for search across all content types on khoj server
Allows moving logic to handle search across all content types to
server from clients
2023-06-28 11:34:26 -07:00
Debanjum Singh Solanky
0636ceaf14 Merge branch 'master' of github.com:khoj-ai/khoj into parallelize-search-across-all-asymmetric-text-content-types
Conflicts:
- src/khoj/routers/api.py: Use theirs
2023-06-27 16:10:32 -07:00
Debanjum Singh Solanky
510bb7e684 Use typing union in text_search for python 3.8 compatible type hinting 2023-06-27 15:59:50 -07:00
Debanjum Singh Solanky
1b11d5723d Extract search request URL builder into js function in web interface 2023-06-27 15:50:41 -07:00
Debanjum Singh Solanky
09f739b8cc Null check config, log warning instead of error when configuring search 2023-06-27 15:48:48 -07:00
sabaimran
9d62d66a77 Simplify construction of repo shorthand in GithubToJsonl 2023-06-27 15:05:03 -07:00
sabaimran
227169ebde Support configuration of multiple Github repositories in the settings interface
- Add cards to configure each of the Github repositories
- Fix a bug in the API which caused all other settings to be wiped when updating one of the content types
- Provide an error message to the user if they have a misconfiguration in their chat settings
2023-06-27 14:10:09 -07:00
sabaimran
37a1f15c38 Add backend support for indexing multiple repositories
- Add support for indexing org files as well as markdown files from the Github repository and update corresponding search view
- Support indexing a list of repositories
2023-06-27 12:06:15 -07:00
sabaimran
ddd550e6f4 Add call to use X-CSRFToken in relevant POST methods 2023-06-26 12:38:00 -07:00
sabaimran
35e24d7851 Fix null checking in state for content config API and telemetry API 2023-06-26 11:37:34 -07:00
sabaimran
5e39421f56 Merge branch 'master' of github.com:debanjum/khoj 2023-06-25 11:41:47 -07:00
sabaimran
4410a3bb4b Limit max width of the pre tag to 100% of the screen width 2023-06-25 11:41:15 -07:00
sabaimran
ffe66b848a Use a single column tempalte for config plugins when in mobile 2023-06-25 11:27:41 -07:00
Debanjum Singh Solanky
b1890aa050 Null check intermediary objects when config not fully initialized 2023-06-24 15:34:18 -07:00
Debanjum Singh Solanky
946af0889d Improve showing status message on saving config via web interface
- Show success/failure status message much closer to the save button
  Previously status message was shown on top of the page, which wasn't
  always in view and wasn't easily seen
- Improve the status message to more clearly show next steps on success
2023-06-24 00:49:57 -07:00
Debanjum Singh Solanky
40d1abfe50 Update the new /config APIs to configure Khoj for first time users
- Setup state.config and sub-components from unset state
- Setup search types with default settings
2023-06-24 00:45:30 -07:00
Debanjum Singh Solanky
edabede93a Fix post configuration state update on error or success on config html 2023-06-23 14:52:25 -07:00
Debanjum Singh Solanky
4744d69221 Resolve button name, anchor tag feedback. Add status message to settings page
- Use "Configure" name for settings config action
- Use more standard anchor tag instead of button
- Add configure status message
2023-06-23 09:48:38 -07:00
Debanjum Singh Solanky
26abafa658 Highlight currently active tab in web interface for orientation 2023-06-22 00:33:28 -07:00
Debanjum Singh Solanky
2728c714d7 Put pico.css in local assets. Move common css styling into khoj.css 2023-06-22 00:33:11 -07:00
Debanjum Singh Solanky
20a37697de Add Khoj header with navigation pane to Search and Chat Interfaces 2023-06-22 00:33:11 -07:00
Debanjum Singh Solanky
c467a0cbb0 Update UI of config sub pages to use khoj lantern theme styling 2023-06-22 00:33:11 -07:00
Debanjum Singh Solanky
0ce2ec590a Update main config page on khoj server to match khoj lantern theme 2023-06-21 20:25:25 -07:00
Debanjum Singh Solanky
d30a9ddd33 Use Khoj Logo on Search, Chat pages of Web Interface 2023-06-21 12:34:53 -07:00
Debanjum Singh Solanky
6d4aad57e1 Use new Khoj Lantern Logo in Web, Emacs, Obsidian UIs and Docs 2023-06-21 01:57:22 -07:00
Debanjum Singh Solanky
69d4fa6525 Rename project links across repo from debanjum/khoj to khoj-ai/khoj 2023-06-21 00:13:21 -07:00
Debanjum Singh Solanky
5c4eb950d5 Search across all content types via khoj.el on Emacs
If no content-type selected in transient menu option, khoj.el queries
khoj server without content-type parameter (t) set.

This results in search across all enabled asymmetric search text
content types
2023-06-20 23:39:56 -07:00
Debanjum Singh Solanky
2cd3e799d3 Improve null and type checks 2023-06-20 23:30:59 -07:00
Debanjum Singh Solanky
d5fb4196de Update web interface to allow querying all content types at once 2023-06-20 22:21:50 -07:00
Debanjum Singh Solanky
5c7c8d1f46 Use async/await to fix parallelization of search across content types 2023-06-20 22:21:50 -07:00
Debanjum Singh Solanky
1192e49307 Pass default value matching argument types expected by text_search methods 2023-06-20 22:21:50 -07:00
Debanjum Singh Solanky
0144e610d6 Only search across content types that work with asymmetric search 2023-06-20 22:21:46 -07:00
Debanjum Singh Solanky
f6a7aa6c96 Style Khoj chat on web interface with new lantern theme
- Color khoj chat message with new yellow theme color
- Update Khoj chat emoji to lantern
- Add page type to title of pages on web interface
2023-06-20 01:39:33 -07:00
Debanjum Singh Solanky
6d94d6e75a Encode the asymmetric, symmetric search queries in parallel for speed
Use timer to measure time to encode queries and total search time
2023-06-20 01:18:17 -07:00
Debanjum Singh Solanky
d292dc03b3 Use new Khoj Logotype in Web interface 2023-06-20 01:13:06 -07:00
Debanjum Singh Solanky
db07362ca3 Encode user query as same across search types to speed up query time
- Add new filter abstract method to remove filter terms from query
- Use the filter method to remove filter terms, encode this defiltered
  query and pass it to the query methods of each search types

TODO: Encoding query is still taking 100-200 ms unlike before. Need to
investigate why
2023-06-19 23:29:54 -07:00
Debanjum Singh Solanky
285d17af2a Search in parallel across all enabled content types requested via API
- Update API to return content from all enabled content types when type
  is not set to specific type in HTTP request param
- To do this efficiently run the search queries in parallel threads
2023-06-19 23:29:06 -07:00
Debanjum Singh Solanky
79d325fbb6 Fix triggering @general queries in Khoj Chat 2023-06-19 23:05:33 -07:00
Debanjum Singh Solanky
e97a20d70c Set conversation type if query param set, else return chat history
Only initialize variables if query is not empty, to avoid unnecessary
compute, variable null checks etc.

Fixes #230
2023-06-19 19:59:16 -07:00
sabaimran
4722a2c16d Add Github configuration page and success notifications 2023-06-18 10:06:45 -07:00
sabaimran
668135c763 Merge branch 'master' of github.com:debanjum/khoj into features/pretty-config-page 2023-06-18 08:35:09 -07:00
sabaimran
81183a1fe1 Address misc PR comments and update logo in all clients
- Rename the new logo to reflect accuracy on size (e.g., 128x128)
- Update the icns file for Mac
- Update nomenclature in settings pages
2023-06-18 08:34:58 -07:00
Debanjum Singh Solanky
a44cde2865 Show hint to re-index vault if wonky results in Obsidian search modal
Remove spurious indentation in Obsidian styles.css

Resolves #207
2023-06-18 04:53:51 -07:00
Debanjum Singh Solanky
595cc5b0f5 Use printer icon for PDF logs. Only split lines if file at web link in web interface 2023-06-18 02:26:03 -07:00
Debanjum Singh Solanky
e31a540a5e Get all md files recursively in repository by passing recursive param
Previously the `get_markdown_files' method was only getting files at
root of the repository

Fix, improve logger messages in github to jsonl processor
2023-06-18 01:47:15 -07:00
Debanjum Singh Solanky
6fdac24416 Set page size to 100 to reduce requests required to Github API to 1/3
- Default is 30. So number of paginated requests required to get all
  items (commits, files) will reduce by 67%

- No need to increase page size for the get tree Github API request from
  `get_markdown_files'

  Get tree Github API doesn't support pagination and return 100K items
  in response. This should be way more than enough for our current
  use-cases
2023-06-18 01:44:36 -07:00
Debanjum Singh Solanky
87975e589a Fix passing auth token to Github API to increase rate limits by x85
- Previously wasn't prefixing "token" to PAT token in Auth header
  This resulted in the request being considered unauthenticated

- Unauthenticated requests to Github API are limited to 60 requests/hour
  Authenticated requests to Github API are allowed 5000 requests/hour
2023-06-18 01:19:26 -07:00
Debanjum Singh Solanky
9c70af960c Extract logic to get file content from Github into a separate method 2023-06-18 01:19:13 -07:00
Debanjum Singh Solanky
10d4c38ce9 Extract Wait for rate limit reset logic into a function for reuse 2023-06-18 01:06:46 -07:00
sabaimran
aad7f825e0 Remove music configuration 2023-06-17 21:23:56 -07:00
sabaimran
5f97afbfac Ignore type checks from mypy in subindexed fields 2023-06-17 16:53:36 -07:00
sabaimran
c2d46de8bc Add endpoint for regenerating directly from the config page and add music content-type 2023-06-17 15:47:33 -07:00
sabaimran
ded3100caf Update the configuration page to make config management easier
- Add a central configuration management page to make management of config details easier
- Add relevant api endpoints both for client and server to update/request data as necessary
- Attempt to update the favicon
2023-06-17 15:21:28 -07:00
Debanjum Singh Solanky
3f24e53b6e Render URL as link in web interface if file param of result is a web link 2023-06-17 04:26:40 -07:00
Debanjum Singh Solanky
63ec84ad78 Store Github URL of Markdown files on Github in file jsonl param 2023-06-17 04:23:01 -07:00
Debanjum Singh Solanky
0c1c7583b5 Handle pagination, API rate limits. Get all commits from Github repo 2023-06-17 04:21:39 -07:00
Debanjum Singh Solanky
31d17d0b22 Index commits message from repository with the github plugin 2023-06-17 02:59:54 -07:00
Debanjum Singh Solanky
c29c141a7e Use Github Rest API to index Markdown files in Github Repository
The Llama_Hub Github plugin is fairly limited.

The Github Rest API is well supported and can easily be extended to
index commit messages, issues, discussions, PRs etc.
2023-06-17 02:16:13 -07:00
Saba
ac96f43b1b Remove try-catch specific to Github plugin; consolidate GUI logic 2023-06-16 23:46:25 -07:00
Saba
019d3732de Rename orgmode_search to org_search 2023-06-13 16:06:54 -07:00
Saba
08d79f5ba4 Unify types used in Github and other text-based configs. Fix typing issues 2023-06-13 15:52:36 -07:00
Saba
a6cd96a6a9 Add a Github plugin which can be used to read from a Github repository 2023-06-13 14:40:06 -07:00
Debanjum
c68cde4803
Log clients calling API endpoints on Khoj server
- Make API endpoints on Khoj server accept `client` as request parameter
  - Khoj API endpoints: /chat, /search, /update
- Make Khoj clients set `client` request param when calling the API endpoints on the Khoj server
  - Khoj clients: Emacs, Obsidian and Web
- Also log khoj server_version running to telemetry server
2023-06-09 18:36:49 +05:30
sabaimran
59fa48036f
Merge pull request #224 from debanjum/fix/message-exceeds-prompt-size
Pass truncated message as string in ChatMessage when exceeding max prompt size
2023-06-08 17:32:53 -07:00
Debanjum Singh Solanky
139a3ba060 Update server to log new server version field to telemetry db 2023-06-08 14:14:21 +05:30
Saba
5d5ebcbf7c Rename truncate messages method and update unit tests to simplify assertion logic 2023-06-06 23:25:43 -07:00
Saba
7119ed0849 Run pre-commit script 2023-06-05 19:29:23 -07:00
Saba
6212d7c2e8 Remove debug line 2023-06-05 19:00:25 -07:00
Saba
f65ff9815d Move message truncation logic into a separate function. Add unit tests with factory boy. 2023-06-05 18:58:29 -07:00
Debanjum Singh Solanky
eb6175e9b0 Update description field in webmanifest of Khoj, Khoj Chat PWA 2023-06-06 01:53:42 +05:30
Debanjum Singh Solanky
bb2363f324 Set client request param when calling khoj server APIs from Web 2023-06-06 00:05:00 +05:30
Debanjum Singh Solanky
caab55fbdd Set client request param when calling khoj server APIs from Obsidian 2023-06-06 00:04:46 +05:30
Debanjum Singh Solanky
de2494154f Set client request param when calling khoj server APIs from Emacs 2023-06-06 00:02:10 +05:30
Debanjum Singh Solanky
168c11cea7 Make server API endpoints accept client as query param
- The chat, search and update API will accept client as request param.
- This will allow logging the client from which these APIs was called.
2023-06-05 23:57:08 +05:30
Debanjum Singh Solanky
8617cf1389 Push telemetry to Posthog to grok Khoj usage 2023-06-05 22:47:49 +05:30
Debanjum Singh Solanky
d13db2e666 Make old telemetry server forward requests to new server 2023-06-05 13:06:45 +05:30
Saba
5f4223efb4 Increase timeout to OpenAI call 2023-06-04 20:49:47 -07:00
Saba
0e63a90377 Fix the mechanism to retrieve the message content 2023-06-04 20:25:37 -07:00
Saba
f0efe0177e Pass truncated message as string in ChatMessage when exceeding max prompt size 2023-06-04 19:33:46 -07:00
Saba
068ee0ac5e Swap elif with else, as usage of this method does not use openai_api_key 2023-06-04 02:25:08 -07:00
Saba
6508379d7b Use api_key keyword argument to set the openai_api_key parameter for GPT 2023-06-04 00:57:00 -07:00
Debanjum Singh Solanky
7af8a56434 Remove filename from reference before rendering references in khoj.el
Fixes bug where actual reference heading in next line jumping out of
references footnote section
2023-06-02 10:42:44 +05:30
Debanjum Singh Solanky
ec280067ef Do not retrieve relevant notes when having a general chat with Khoj
- This improves latency of @general chat by avoiding unnecessary
  compute
- It also avoids passing references in API response when they haven't
  been used to generate the chat response. So interfaces don't have to
  add logic to not render them unnecessarily
2023-06-02 10:42:44 +05:30
Debanjum Singh Solanky
90439a8db1 Update Khoj subtitle to AI personal assistant for your digital brain 2023-06-02 10:42:44 +05:30
Debanjum Singh Solanky
e9ed7a19fd Update search prompt to extract PDF search type. Fix extract_question prompt 2023-06-02 10:06:03 +05:30
Debanjum Singh Solanky
bbe3bf9733 Render PDF search results in Khoj Obsidian interface
- Make plugin update khoj server config to index PDF files in vault too
- Make Obsidian plugin update index for PDF files in vault too
- Show PDF results in Khoj Search modal as well
  - Ensure combined results are sorted by score across both types
- Jump to PDF file when select it PDF search result from modal
2023-06-01 21:42:48 +05:30
Debanjum Singh Solanky
e3892945d4 Render PDF search results in Khoj.el Emacs interface 2023-06-01 21:42:48 +05:30
Debanjum Singh Solanky
85144006a1 Render PDF search results in khoj web interface 2023-06-01 21:42:48 +05:30
Debanjum Singh Solanky
acd14a5e41 Wire up PDF to jsonl processor to Khoj server layer (API, config)
- Specify PDF content to index via khoj.yml
- Index PDF content on app start, reconfigure
- Expose PDF as a search type via API
2023-06-01 21:42:48 +05:30
Debanjum Singh Solanky
286b500f66 Create PDF to JSONL processor using PyPDF and LangChain
Switch `pydantic' to >= 1.9.1 else `langchain.document_loaders' starts
throwing typing error for python 3.8, 3.9
2023-06-01 21:41:49 +05:30
Debanjum Singh Solanky
1b3effd8e6 Fork Markdown to JSONL processor as start template for PDF to Jsonl Processor 2023-06-01 09:13:31 +05:30
Debanjum Singh Solanky
1cd9ecd449 Truncate last message if still over max supported prompt size by model 2023-06-01 08:50:59 +05:30
Debanjum Singh Solanky
ed4d0f9076 Simplify argument names used in khoj openai completion functions
- Match argument names passed to khoj openai completion funcs with
  arguments passed to langchain calls to OpenAI
- This simplifies the logic in the khoj openai completion funcs
2023-06-01 08:50:59 +05:30
Debanjum Singh Solanky
703a7c89c0 Reduce retry count and request timeout for faster response or failure
- Fix bug where both LangChain and Khoj retry requests 6 times each.
  So a total of 12 requests at >1minute intervals for each chat
  response in case of OpenAI API being down

- Retrying too many times when the API is failing doesn't help
- The earlier 60 second request timeout was spacing out the interval
  between retries way too much. This slowed down chat response times
  quite a bit when API was being flaky

- With these updates you'll know if call to chat API failed in under a
  minute
2023-06-01 08:50:59 +05:30
Debanjum Singh Solanky
18081b3bc6 Use LangChain to call GPT over API 2023-06-01 08:50:59 +05:30
Debanjum Singh Solanky
277d2f5c96 Do not add "Notes:" suffix to chat messages when no notes retrieved
This was causing spurious "Notes:" suffix being added to Khoj Chat in
response
2023-06-01 08:50:59 +05:30
Debanjum Singh Solanky
334be4e600 Use LangChain to call OpenAI for Khoj Chat
- Use ChatModel and ChatOpenAI to call OpenAI chat model instead of
  using OpenAI package directly
- This is being done as part of migration to rely on LangChain for
  creating agents and managing their state
2023-06-01 08:50:59 +05:30
Debanjum Singh Solanky
efcf7d1508 Extract prompts as LangChain Prompt Templates into a separate module
Improves code modularity, cleanliness. Reduces bloat in GPT.py module
2023-06-01 08:50:58 +05:30
Debanjum Singh Solanky
b484953bb3 Import app state correctly to generate embeddings with OpenAI model
Resolves #216
2023-05-28 10:21:54 +05:30
Debanjum Singh Solanky
a0d0dbaca7 Fix link to Khoj Obsidian Demo video in Readmes 2023-05-23 04:23:08 +05:30
Debanjum Singh Solanky
ebb5d7b8e5 Release Khoj version 0.6.2 2023-05-17 20:04:20 +05:30
Debanjum Singh Solanky
d02415edcc Write generated server id to env file when env file does not contain it 2023-05-17 19:38:44 +05:30
Debanjum Singh Solanky
dc0626856e Put the telemetry db in a separate directory by default 2023-05-17 18:58:47 +05:30
Debanjum Singh Solanky
e9f04dc644 Add dockerfile to containerize telemetry server 2023-05-17 16:08:21 +05:30
Debanjum Singh Solanky
07b19964d4 Schedule jobs at (co-)prime intervals to reduce overlap in job runs 2023-05-17 16:08:21 +05:30
Debanjum Singh Solanky
d42f0f5055 Add basic telemetry server for khoj 2023-05-17 16:08:21 +05:30
Debanjum Singh Solanky
134cce9d32 Batch upload telemetry data at regular interval instead of while querying 2023-05-17 16:08:21 +05:30
Debanjum Singh Solanky
3ede919c66 Log usage of /search, /chat, /update API endpoints to telemetry server 2023-05-17 16:08:21 +05:30
Debanjum Singh Solanky
f2e89f6f46 Add khoj app helper methods to log app usage to a telemetry server 2023-05-17 16:08:21 +05:30
Debanjum Singh Solanky
9ca61d62ff Enable/disable logging telemetry by setting bool in khoj.yml config
We log usage telemetry by default, unless setting explicitly set in
khoj.yml
2023-05-15 23:26:38 +08:00
Debanjum Singh Solanky
131b8407b5 Allow Khoj Chat to respond to general queries not in reference notes
- Khoj chat will now respond to general queries if:
  1. no relevant reference notes available or
  2. when explicitly induced by prefixing the chat message with "@general"

- Previously Khoj Chat would a lot of times refuse to respond to
  general queries not answerable from reference notes or chat history

- Make chat quality tests more robust
  - Add more equivalent chat response options refusing to answer
  - Force haiku writing to not give any preable, just the haiku
2023-05-12 18:42:40 +08:00
Debanjum Singh Solanky
cc75f986b2 Test text search index only updates on changes to text content 2023-05-12 17:37:34 +08:00
Debanjum Singh Solanky
f9ccce430e Allow configuring OpenAI chat model for Khoj chat
- Simplifies switching between different OpenAI chat models. E.g GPT4
- It was previously hard-coded to use gpt-3.5-turbo. Now it just
  defaults to using gpt-3.5-turbo, unless chat-model field under
  conversation processor updated in khoj.yml
2023-05-03 23:01:13 +08:00
Debanjum Singh Solanky
6b535cc345 Snip prepended heading to avoid crossing model max_token limits
Otherwise if heading > max_tokens than the search models will just see
a heading (with repeated filename) for each compiled entry and not
actual content.

100 characters should be sufficient to include filename (not path) and
entry heading. If longer rather truncate to pass entry unique text to
model for search context
2023-05-03 22:53:13 +08:00
Debanjum Singh Solanky
02aeee60aa Set filename as top heading of org entries for better search context
Previously filename was only being appended to markdown entries.

Test filename getting prepended to compiled entry as heading
2023-05-03 22:53:13 +08:00
Debanjum Singh Solanky
94825a70b9 Set heading of md entries to improve search context for long entries
Otherwise if a markdown entry is longer than max_tokens, the split
entries (apart from first one) do not get their heading context set
2023-05-03 22:53:13 +08:00
Debanjum Singh Solanky
5de04621b5 Set filename as top heading of md entries for better search context
Previously filename was appended to the end of the compiled entry.
This didn't provide appropriate structured context

Test filename getting prepended as heading to compiled entry
2023-05-03 22:50:31 +08:00
Debanjum Singh Solanky
0e3fb59e09 Entries with no md headings should not get heading prefix prepended
Files with no headings would previously get their entry be prefixed
with a markdown heading prefix (#)
2023-05-03 22:50:31 +08:00
Debanjum Singh Solanky
45a991d75c Prepend entry heading to all compiled org snippets to improve search context
All compiled snippets split by max tokens (apart from first) do not
get the heading as context.

This limits search context required to retrieve these continuation
entries
2023-05-03 22:50:31 +08:00
Debanjum Singh Solanky
3386cc92b5 Fix khoj server config update in khoj.el by unquoting list to cl-push to
- cl-push expects a generatlized variable. Else throws (setf quote)
  undefined warning
- This results in the config call failing on calling khoj entrypoint
2023-05-03 15:10:56 +08:00
Debanjum Singh Solanky
948a4274e4 Fix documentation strings and simplify not null checks 2023-05-02 21:47:50 +08:00
Debanjum Singh Solanky
731ef5688f Use cl-pushnew to fix byte-compile errors with using add-to-list 2023-05-02 21:47:38 +08:00
Debanjum Singh Solanky
f046523b33 Improve khoj.el messages to convey state of khoj server
- Remove waiting for server message as it hides the messages from the
  server
- Fix the nil message that were being rendered, by checking before
  showing messages from server
- Consistently prefix messages from khoj with khoj.el
2023-04-28 11:15:13 +08:00
Debanjum Singh Solanky
76df393eb5 Only call khoj server configure API from khoj.el when config updated
Previously khoj.el was calling the server configure API even when
config was same as before.
This had broken the khoj search as you type experience from emacs

Also show more details to user about what in khoj is being configured
2023-04-27 20:45:16 +08:00
Debanjum Singh Solanky
ceae06ae9d Fix khoj.el compilation warnings around unused variables 2023-04-27 20:45:16 +08:00
Debanjum Singh Solanky
8269adf849 Refactor khoj-setup in khoj.el for readability. No functional change 2023-04-27 20:45:00 +08:00
Debanjum Singh Solanky
865d12b6f2 Fix escaping quote in chat references to prevent it breaking out of html 2023-04-27 20:45:00 +08:00
Debanjum Singh Solanky
26cb878327 Add Yarn lockfile for Khoj Obsidian 2023-04-18 00:57:11 +07:00
Debanjum Singh Solanky
e3180d63e6 Sync Khoj Obsidian Tagline with Khoj tagline 2023-04-18 00:56:50 +07:00
Debanjum Singh Solanky
62e6e09521 Release Khoj version 0.6.1 2023-04-17 23:31:35 +07:00
Debanjum Singh Solanky
b079fb31bc Replace Windows path separators in indexName configured via Khoj Obsidian
Resolves #185, #199

- Issue
  IndexName created from Obsidian Absolute Vault path wasn't replacing
  windows path, drive separators with underscore. It was only
  replacing unix path separators

- Fix
  Also replace windows drive and path separators with _ while creating
  IndexName in Khoj Obsidian plugin
2023-04-17 16:55:33 +07:00
Debanjum Singh Solanky
d90df966a9 Make khoj logger use utf-8 encoding when writing to khoj log file
Resolve logger error issue mentioned in #199
2023-04-17 16:55:07 +07:00
Debanjum Singh Solanky
dc3f399f91 Fix to get score associated with SearchResponse in result as string 2023-04-16 20:22:51 +07:00
Debanjum Singh Solanky
d5000c63e1 Update Readmes to use python -m pip install khoj-assistant
Makes it easier to tell pip associated with which python is being
used. Easier to debug when users have different versions of python
installed (e.g 3.10 and 3.11)
2023-04-16 20:17:20 +07:00
Debanjum Singh Solanky
453c84ab79 Add Screenshots of Khoj Chat Interface on Emacs, Obsidian to Readmes 2023-04-07 23:19:47 +07:00
Debanjum Singh Solanky
35aa06067f Release Khoj version 0.6.0
Upload styles.css via release workflow
2023-03-31 18:13:16 +07:00
Debanjum Singh Solanky
5673bd5b96 Keep original formatting in compiled text entry strings
- Explicity split entry string by space during split by max_tokens
- Prevent formatting of compiled entry from being lost
- The formatting itself contains useful information
  No point in dropping the formatting unnecessarily,
  even if (say) the currrent search models don't account for it (yet)
2023-03-30 14:02:46 +07:00
Debanjum Singh Solanky
a2ab68a7a2 Include filename of markdown entries for search indexing
Append originating filename to compiled string of each entry for
better search quality by providing more context to model

Update markdown_to_jsonl tests to ensure filename being added

Resolves #142
2023-03-30 13:51:36 +07:00
Debanjum Singh Solanky
67129964a7 Create Note with Query as title from within Khoj Search Modal
This follows expected behavior for obsidain search modals
E.g Ominsearch and default Obsidian search.

The note creation code is borrowed from Omnisearch.

Resolves #133
2023-03-30 13:51:36 +07:00
Debanjum Singh Solanky
d3257cb24e Style the search result. Use Obsidian theme colors and font-size
Based on PR #135
2023-03-30 12:35:29 +07:00
Debanjum Singh Solanky
40091489c0 For each result: snip it by lines, show filename, remove frontmatter
Based on PR #135
Resolves #134
2023-03-30 12:34:55 +07:00
Debanjum Singh Solanky
240db7b4f0 Add screenshot of Khoj chat on Obsidian to Readme. Fix links 2023-03-30 02:49:05 +07:00
Debanjum Singh Solanky
234be96e53 Fix processor key used to configure chat model in khoj obsidian 2023-03-30 01:47:09 +07:00
Debanjum Singh Solanky
c8c0cfd10e Add Chat features, setup and usage to Khoj Obsidian plugin Readme 2023-03-30 00:32:24 +07:00
Debanjum Singh Solanky
7ecae224e7 Configure OpenAI API Key from the Khoj plugin setting in Obsidian 2023-03-29 23:54:08 +07:00
Debanjum Singh Solanky
3d616c8d65 Use Obsidian font sizes. Improve input field, reference indexing
- Give space in the input field. Too narrow previously
- References should be indexed from 1 instead of 0
- Use Obsidian font size variables to scale fonts in chat appropriately
2023-03-29 22:13:55 +07:00
Debanjum Singh Solanky
23bd737f6b Use chat input element to send message on Enter. No send button required 2023-03-29 22:13:30 +07:00
Debanjum Singh Solanky
81e98c3079 Scroll to bottom of modal on open and message send 2023-03-29 18:12:12 +07:00
Debanjum Singh Solanky
59ff1ae27f Use obsidian theme colors for bg, text. Restrict css namespace via prefix 2023-03-29 18:12:12 +07:00
Debanjum Singh Solanky
001ac7b5eb Style Obsidian Chat Modal like Khoj Chat Web Interface
- Add message sender, date metadata as message footer
- Use css directly from Khoj Chat Web Interface.
  - Modify it to work under a Obsidian modal
  - So replace html, body styling from web interface to instead
    styling new "khoj-chat" class attached to contentEl of modal
2023-03-29 18:12:12 +07:00
Debanjum Singh Solanky
112f388ada Render references next to chat responses by khoj in chat modal 2023-03-28 18:11:03 +07:00
Debanjum Singh Solanky
1d3d949962 Render conversation logs on page load 2023-03-28 14:56:29 +07:00
Debanjum Singh Solanky
cd46a17e5f Add Khoj Chat Modal, Command in Khoj Obsidian to Chat using API 2023-03-28 14:56:29 +07:00
Debanjum Singh Solanky
c0972e09e6 Rename KhojModal to KhojSearchModal, a more specific name for it
In preparation to introduce Khoj chat in Obsidian
2023-03-28 14:56:29 +07:00
Debanjum Singh Solanky
64fff1d372 Release Khoj version 0.5.0 2023-03-28 03:35:59 +07:00
Debanjum Singh Solanky
fc218508f9 Update khoj.el docs and Emacs Readme for chat, simplified setup 2023-03-27 22:02:47 +07:00
Debanjum Singh Solanky
83a7ccd729 Fix docstrings and method ordering in khoj.el 2023-03-27 18:33:09 +07:00
Debanjum Singh Solanky
5c2327ee4f Configure org directories to index from khoj.el
Converts paths to glob style regexes that will index all org files
recursively under the specified list of path

Should help setup for org-roam users from khoj.el
2023-03-27 18:30:53 +07:00
Debanjum Singh Solanky
6e8a40906d Allow disabling automatic server setup. Fix server start vs ready logic
- khoj-auto-setup controls whether to automatically check for and
  setup khoj server from within Emacs
- extract install, start, configure sequence into public, interactive
  method. Allows calling khoj-setup during package load via init.el

- Fix: Do not attempt to configure or wait for server ready if
  user has said no to auto-setup request
- Fix logic to mark server started vs ready
  - Previously the started/running vs ready variables defs were getting
    intertwined
  - Server started indicates server bootup has been triggered
  - Server ready indicates server API ready to accept requests
2023-03-27 17:53:08 +07:00
Debanjum Singh Solanky
526a927bce Fix org entry extraction test, variable prefixed with khoj in khoj.el
Discovered via failing build and test workflows on Github
2023-03-27 16:44:50 +07:00
Debanjum Singh Solanky
7243059507 Track index update asynchronously via moon phase progressbar in khoj.el 2023-03-27 06:01:04 +07:00
Debanjum Singh Solanky
8a9055f918 Restrict server messages show in echo area to main server files 2023-03-27 04:59:55 +07:00
Debanjum Singh Solanky
ae535a06eb Configure Khoj chat using khoj.el by setting OpenAI API key in Emacs 2023-03-27 04:59:54 +07:00
Debanjum Singh Solanky
36b17d4ae0 Generalize the directory from config extraction elisp method 2023-03-27 03:44:03 +07:00
Debanjum Singh Solanky
924424c754 Throw actionable exceptions when content types or chat not configured 2023-03-27 02:47:44 +07:00
Debanjum Singh Solanky
359a2cacef Fix khoj--server-running to work with unconfigured or external server
- If khoj server started outside emacs, khoj--server-ready should be set
to true by khoj--server-running method (instead of waiting for proc msg)

- If khoj server is unconfigured the /config/types endpoint wouldn't
return anything. Using config/data/default allows checking khoj server
running status without requiring it to be configured as well
2023-03-27 02:45:59 +07:00
Debanjum Singh Solanky
d7fb9a596e Auto configure server before loading khoj-menu
If the config hasn't changed there'll be no update. If config has
changed indexing will get triggered asynchronously. But user cannot
make query till indexing done

As easier to know when server ready to configure
2023-03-27 02:44:02 +07:00
Debanjum Singh Solanky
8a21aff438 Make khoj.el server start, stop, restart, setup methods interactive
No need to erase temporary buffers before working on them
2023-03-27 01:53:15 +07:00
Debanjum Singh Solanky
cb40a96c85 Index configured org files from khoj.el
- Set `khoj-org-files-index' to list of files to index
- Defaults to indexing org-agenda-files
- Uses khoj server api to configure org files to index
2023-03-27 01:05:26 +07:00
Debanjum Singh Solanky
50760acc37 Wait for Khoj server to get ready before opening khoj.el transient menu
- Use process filter, sentinel to mark when khoj server is ready or not
- Display server messages for visibility into server boot-up process
- Wait until server ready to open khoj transient menu in Emacs
  Until then khoj features wouldn't work anyway, so avoids confusion
2023-03-26 13:00:01 +07:00
Debanjum Singh Solanky
82eb4bfd0d Setup Khoj server on opening khoj from with Emacs
- Create helper methods to check, stop, restart, setup khoj server
- (Ask to) setup khoj server on calling khoj main entrypoint function
2023-03-26 10:12:06 +07:00
Debanjum Singh Solanky
99d19dcf43 Start Khoj server from Emacs using khoj.el 2023-03-26 09:38:46 +07:00
Debanjum Singh Solanky
c92d79118a Install Khoj server from Emacs using khoj.el 2023-03-26 08:50:03 +07:00
Debanjum Singh Solanky
e281a498b4 Style Khoj search org buffer via elisp instead of in-buffer settings 2023-03-26 06:34:18 +07:00
Debanjum Singh Solanky
4f655d20ae Style Khoj chat directly via elisp instead of via in-buffer settings 2023-03-26 06:03:30 +07:00
Debanjum Singh Solanky
f6ff7b1beb Render foonote reference links as superscript for Khoj Chat on Emacs 2023-03-26 05:33:08 +07:00
Debanjum Singh Solanky
67c850a4ac Add retry logic to OpenAI API queries to increase Chat tenacity
- Move completion and chat_completion into helper methods under utils.py
- Add retry with exponential backoff on OpenAI exceptions using
  tenacity package. This is officially suggested and used by other
  popular GPT based libraries
2023-03-26 05:12:35 +07:00
Debanjum Singh Solanky
ff846f05c5 Clean-up khoj.el based on linting helpers and manual review 2023-03-25 05:47:49 +07:00
Debanjum Singh Solanky
7e36f421f9 Truncate message logs to below max supported prompt size by model
- Use tiktoken to count tokens for chat models
- Make conversation turns to add to prompt configurable via method
  argument to generate_chatml_messages_with_context method
2023-03-25 05:13:56 +07:00
Debanjum Singh Solanky
4725416fbd Use shortcut keybindings in buffer to ease sending messages to Khoj 2023-03-25 05:06:01 +07:00
Debanjum Singh Solanky
508b2176b7 Update Chat API, Logs, Interfaces to store, use references as list
- Remove the need to split by magic string in emacs and chat interfaces
- Move compiling references into string as context for GPT to GPT layer
- Update setup in tests to use new style of setting references
- Name first argument to converse as more appropriate "references"
2023-03-24 22:10:11 +07:00
Debanjum Singh Solanky
b08745b541 Keep chat messages at 1 empty line visible distance in khoj.el
- Clean redundant concat, format string
- Improve variable name to emojified sender
2023-03-24 22:10:11 +07:00
Debanjum Singh Solanky
27217a330d Time chat API sub-components for performance analysis
Time and the search query extraction, search and response generation
components
2023-03-24 20:39:41 +07:00
Debanjum Singh Solanky
5e9558d39d Stylize references shown as footnote links in chat messages
- Render references as superscript
- Show reference definitions on hover over reference links to ease access
- Truncate reference def shown on hover to 70 char
  - Add continuation suffix, ..., when reference definition truncated
2023-03-24 20:38:05 +07:00
Debanjum Singh Solanky
cf28f104c7 Register separate timestamps for user query and response by Khoj Chat 2023-03-24 18:31:58 +07:00
Debanjum Singh Solanky
93e2aff786 Add references as org footnotes instead of links 2023-03-24 18:31:42 +07:00
Debanjum Singh Solanky
d78454d4ad Load Khoj Chat buffer before asking for query to provide context 2023-03-24 13:43:46 +07:00
Debanjum Singh Solanky
863933daaa Resolve build issues found by melpazoid 2023-03-23 02:25:34 +04:00
Debanjum Singh Solanky
e9ca04af0d Require dash, org to run ERT tests for khoj.el 2023-03-23 01:46:26 +04:00
Debanjum Singh Solanky
06df394d6c Style chat messages as org-mode entries in Emacs
- Style Message as Org Entries instead of List
- Put khoj response as child of user query entry
  - Improves color coding for readability
  - Allows folding each back-n-forth
- Put timestamp of message received into property drawer
- Use standardized time format for new and old chat messages
2023-03-22 12:00:43 -06:00
Debanjum Singh Solanky
364e6c11af Render chat history from API in chat buffer on first run
- Generalize the render-chat-response method to handle rendering
  history or chat response from chat API reponse

- Trigger rendering of khoj chat history if Khoj chat buffer not
  created for this session yet
2023-03-22 12:00:35 -06:00
Debanjum Singh Solanky
36b52fdd0a Properly escape reference links before rendering
- Use org-insert-link method to improve link rendering robustness
  Previous simple mechanism to crete org-links would result in links
  escaping out of formating. Use a user-facing org-mode method to
  remove/reduce probability of this

- Replace newlines with space to render reference notes as links
2023-03-22 11:05:38 -06:00
Debanjum Singh Solanky
72f63a6ef7 Add basic chat interface for Khoj on Emacs
- Query khoj chat API to get Khoj Chat response to user message
- Render chat messages as a org-mode list in format:
  - [sender-name]: *[message]*
    - /[receive-date]/
- Add references as org links with context visible on hover,
  but no jump to note
- Require dash library for khoj.el to simplify list manipulation.
  Use `-map-indexed' method from dash
2023-03-22 10:47:55 -06:00
Debanjum Singh Solanky
e4d67694e1 Add search to method, variable names meant for khoj search in khoj.el
In preparation to introduce Khoj chat in Emacs
2023-03-21 21:44:11 -06:00
Debanjum Singh Solanky
2f6284872d Mention Khoj needs Python version 3.10 or lower in docs 2023-03-20 15:18:19 -06:00
Debanjum Singh Solanky
601ff2541b Revert to using GPT to extract search queries from users message
- Reasons:
  - GPT can extract date aware search queries with date filters
    better than ChatGPT given the same prompt.
  - Need quality more than cost savings for now.
  - Need to figure ways to improve prompt for ChatGPT before using it
2023-03-18 17:56:13 -06:00
Debanjum Singh Solanky
e28526bbc9 Extract search queries from users message using ChatGPT as Search Actor
- Reasons
  - ChatGPT should be better at following instructions than GPT
  - At 1/10th the cost, it's much cheaper than using older GPT models
2023-03-18 16:33:24 -06:00
Debanjum Singh Solanky
939d7731da Fix-up Search Actor GPT's response for decoding it as valid JSON 2023-03-18 16:30:55 -06:00
Debanjum Singh Solanky
f63fd0995e Pass more search results as context to Chat Actor to improve inference 2023-03-18 16:30:55 -06:00
Debanjum Singh Solanky
10836dedee Search should return user message if GPT response is not valid JSON
Previously would throw if GPT response is not valid JSON. Better to
return original message to use for search instead
2023-03-18 16:30:55 -06:00
Debanjum Singh Solanky
08f5fb315f Add answers to context for Search Actor to generate relevant queries
Update Search Actor prompt with answers, more precise primer and
two more examples for context

Mark the 3 chat quality tests using answer as context to generate
queries as expected to pass. Verify that the 3 tests pass now, unlike
before when the Search Actor did not have the answers for context
2023-03-18 16:30:55 -06:00
Debanjum Singh Solanky
45cb510421 Loosen search results score thresold used by chat for more context 2023-03-18 16:30:55 -06:00
Debanjum Singh Solanky
d871e04a81 Use past user messages, inferred questions as context to extract questions
- Keep inferred questions in logs
- Improve prompt to GPT to try use past questions as context
- Pass past user message and inferred questions as context to help GPT
  extract complete questions
- This should improve search results quality

- Example Expected Inferred Questions from User Message using History:
  1. "What is the name of Arun's daughter?"
    => "What is the name of Arun's daughter"
  2. "Where does she study?" =>
    => "Where does Arun's daughter study?" OR
    => "Where does Arun's daughter, Reena study?"
2023-03-18 16:30:50 -06:00
Debanjum Singh Solanky
1a5d1130f4 Generate search queries from message to answer users chat questions
The Search Actor allows for
1. Looking up multiple pieces of information from the notes
   E.g "Is Bob older than Tom?" searches for age of Bob and Tom in 2 searches
2. Allow date aware user queries in Khoj chat
   Answer time range based questions
   Limit search to specified timeframe in question using date filter
   E.g "What national parks did I visit last year?" adds
   dt>="2022-01-01" dt<"2023-01-01" to Khoj search

Note: Temperature set to 0. Message to search queries should be deterministic
2023-03-18 16:28:51 -06:00
Debanjum
e75e13d788
Create Tests to Measure Chat Quality, Capabilities
Create Rubric to Test Chat Quality and Capabilities

### Issues
- Previously the improvements in quality of Khoj Chat on changes was uncertain
- Manual testing on my evolving set of notes was slow and didn't assess all expected, desired capabilities

### Fix
1. Create an Evaluation Dataset to assess Chat Capabilities
   - Create custom notes for a fictitious person (I'll publish a book with these soon 😅😋)
   - Add a few of Paul Graham's more personal essays. *[Easy to get as markdown](https://github.com/ofou/graham-essays)*
2. Write Unit Tests to Measure Chat Capabilities
   - Measure quality at 2 separate layers
     - **Chat Actor**: These are the narrow agents made of LLM + Prompt. E.g `summarize`, `converse` in `gpt.py`
     - **Chat Director**: This is the chat orchestration agent. It calls on required chat actors, search through user provided knowledge base (i.e notes, ledger, image) etc to respond appropriately to the users message.  This is what the `/api/chat` API exposes.
   - Mark desired but not currently available capabilities as expected to fail <br />
     This still allows measuring the chat capability score/percentage while only failing capability tests which were passing before on any changes to chat
2023-03-16 11:30:52 -06:00
Debanjum Singh Solanky
7526a50dd4 Extract conversation processor utility funcs from gpt.py into utils.py 2023-03-16 09:30:37 -06:00
Debanjum Singh Solanky
24ddebf3ce Make converse prompt more precise. Fix default arg vals in gpt methods
- Set conversation_log arg default to dict
- Increase default temperature to 0.2 for a little creativity in
  answering
- Make GPT be more reliable in looking at past conversations for
  forming response
2023-03-16 09:30:37 -06:00
Debanjum Singh Solanky
8609e3129e Fix, improve displaying chat messages, sources by Khoj in web interface
Pretty pretty json in conversation logs
2023-03-14 11:24:47 -06:00
Debanjum
6c0e82b2d6
Merge Improve Khoj Chat PR #183 from debanjum/improve-chat-interface
# Improve Khoj Chat
## Main Changes
- Use the new [API](https://openai.com/blog/introducing-chatgpt-and-whisper-apis) for [ChatGPT](https://openai.com/blog/chatgpt) to improve conversation quality and cost
- Improve Prompt to answer query using indexed notes
  - Previously was asking GPT to summarize the notes
  - Both the chat and answer API use this new prompt
- Support Multi-Turn conversations
  - Pass previous messages and associated reference notes to ChatGPT for context
- Show note snippets referenced to generate response
  - Allows fact-checking, getting details
- Simplify chat interface by using only single unified chat type for now

## Miscellaneous
- Replace summarize with answer API. Summarize via API not useful for now
- Only pass Khoj search results above a threshold confidence to GPT for context
  - Allows Khoj to say don't know if it can't find answer to query from notes
  - Allows relying on (only) conversation history to generate response in multi-turn conversation
- Move Chat API out of beta. Update Readme
2023-03-10 19:03:44 -06:00
Debanjum Singh Solanky
cccd225247 Deduplicate and simplify logic to render chat message with reference 2023-03-10 18:58:11 -06:00
Debanjum Singh Solanky
b9caad458e Type score_threshold with union, not |, to support python <3.10 2023-03-10 18:58:11 -06:00
Debanjum Singh Solanky
a71f168273 Move the chat API out of beta. Save chat sessions at 15min intervals 2023-03-10 17:20:52 -06:00
Debanjum Singh Solanky
8bb8824d0c Bump khoj versions in obsidian, emacs files 2023-03-10 15:23:17 -06:00
Debanjum Singh Solanky
e16d0b6d7e Open references notes used for chat on mobile too (by clicking)
Requires clicking the reference as hover doesn't work on mobile
2023-03-09 17:13:07 -06:00
Debanjum Singh Solanky
c3c7b8a951 Make Khoj chat a separate Progressive Web App (PWA) for easier access 2023-03-09 13:45:06 -06:00
Debanjum Singh Solanky
3838f9d8e3 Remove explicitly asking GPT to say I don't know in prompt for now
GPT still mostly says I don't know when answer not in notes or chats

But with this its more inclined to answer general questions not in
chats or notes while informing user that the information is not from
existing chats or notes
2023-03-09 12:11:44 -06:00
Debanjum Singh Solanky
f7b8cdd02e Log prompts being passed to GPT for debugging 2023-03-08 19:17:52 -06:00
Debanjum Singh Solanky
2739a492b4 Log message metadata along with Khoj message instead of user message
References should be attached to khoj chat messsage rather than the
users message in the chat interface
2023-03-08 19:16:24 -06:00
Debanjum Singh Solanky
87d1e1341d Show reference notes used as response context in chat interface 2023-03-08 19:16:24 -06:00
Debanjum Singh Solanky
280061e1fa Do not deduplicate search results used for chat context
- Chat uses compiled form of search results, not the raw entries to
  provide context for chat. The compiled snipped search results
  themselves are unique and using multiple of them for context from
  the same raw note is fine if they cross the score and rank thresholds

  This should improve the context provided for chat

- Also apply score_threshold, no deduplication to the answers API
2023-03-06 23:51:31 -06:00
Debanjum Singh Solanky
672f61529e Make getting deduped search results configurable via Search API 2023-03-06 23:48:46 -06:00
Debanjum Singh Solanky
4fb628975c Fix jumping to note from Khoj Obsidian search modal result on Windows
- Issue
  The file path separator by khoj server and the Obsidian vault were
  different on Windows
- Fix
  Normalize file path to use forward slash(/) to find the matching
  note file in the Obsidian vault for jump to it

Resolves #177
2023-03-05 21:07:54 -06:00
Debanjum Singh Solanky
b6cdc5c7cb Do not expose answer API as a chat type in chat web interface or API
Answer does not rely on past conversations, just the knowledge base.
It is meant for one off interactions, like search rather than a
continuing conversation like chat

For now it is only exposed via API. Later it will be expose in the
interfaces as well

Remove ability to select different chat types from the chat web
interface as there is only a single chat type

Stop appending answers to the conversation logs
2023-03-05 18:21:59 -06:00
Debanjum Singh Solanky
7f994274bb Support multi-turn conversations in chat mode
- Only use decent quality search results, if any, as context
- Pass source results used by previous chat messages as context
- Loosen prompt to allow looking at previous chats and notes to answer
- Pass current date for context

- Make GPT provide reason when it can't answer the question. Gives
  user context to tune their questions
2023-03-05 18:21:39 -06:00
Debanjum Singh Solanky
d73042426d Support filtering for results above threshold score in search API 2023-03-05 18:21:39 -06:00
Debanjum Singh Solanky
45f461d175 Keep search results passed to GPT as context in conversation logs
This will be useful to
1. Show source references used to arrive at answer
2. Carry out multi-turn conversations
2023-03-05 16:00:19 -06:00
Debanjum Singh Solanky
7cad1c9428 Only use past chat message, not session summaries as chat context
Passing only chat messages for current active, and summaries
for past session isn't currently as useful
2023-03-05 16:00:18 -06:00
Debanjum Singh Solanky
ad1f1cf620 Improve and simplify Khoj Chat using ChatGPT
- Set context by either including last 2 chat messages from active
  session or past 2 conversation summaries from conversation logs

- Set personality in system message
- Place personality system message before last completed back & forth
  This may stop ChatGPT forgetting its personality as conversation progresses given:
  - The conditioning based on system role messages is light
  - If system message is too far back in conversation history, the
    model may forget its personality conditioning
  - If system message at end of conversation, the model can think its
    the start of a new conversation
  - Inserting the system message before last completed back & forth should
    prevent ChatGPT from assuming its the start of a new conversation
    while not losing personality conditioning from the system message

- Simplfy the Khoj Chat API to for now just answer from users notes
  instead of trying to infer other potential interaction types.
  - This is the default expected behavior from the feature anyway
  - Use the compiled text of the top 2 search results for context

- Benefits of using ChatGPT
  - Better model
  - 1/10th the price
  - No hand rolled prompt required to make GPT provide more chatty,
    assistant type responses
2023-03-05 01:24:13 -06:00
Debanjum Singh Solanky
9d42b5d60d Use multiple compiled search results for more relevant context to GPT
Increase temperature to allow GPT to collect answer across multiple
notes
2023-03-05 01:24:13 -06:00
Debanjum Singh Solanky
c3b624e351 Introduce improved answer API and prompt. Use by default in chat web interface
- Improve GPT prompt
  - Make GPT answer users query based on provided notes instead
    of summarizing the provided notes
  - Make GPT be truthful using prompt and reduced temperature
  - Use Official OpenAI Q&A prompt from cookbook as starting reference
- Replace summarize API with the improved answer API endpoint
- Default to answer type in chat web interface. The chat type is not
  fit for default consumption yet
2023-03-05 01:24:13 -06:00
Debanjum Singh Solanky
7184508784 Mention Python and Pip need to be installed in Main and Emacs Readme 2023-03-02 21:28:54 -06:00
Debanjum Singh Solanky
211e460398 Output date filter from cache log at debug level. Remove unused imports
Other logs not directly useful to user have already been converted
to debug log levels in 1ae4016. Just forgot to convert this log line too
2023-03-02 15:41:32 -06:00
Debanjum Singh Solanky
b6dbe4dd1d Do not try retrieve an unconfigured core content type in Config GUI
Previous behavior was resulting in a null reference error. As key for
the core content/search type was not present in current config

Fallback to using default config for unconfigured core content type
instead

See #165 for details
2023-03-02 11:09:31 -06:00
Debanjum Singh Solanky
1ae40163a9 Show user friendly information logs by default for context
- Use emojis to make info logs easier to read
- Inform when khoj is ready to use
- Provide information on what khoj is doing while starting up
- Inform when content/search types and processors are setup
- Inform when models are being loaded from the web as this step can
  take time
- Convert all other info logs to be only shown in verbose mode
2023-03-01 16:39:07 -06:00
Debanjum Singh Solanky
fe03ba3dce Index intro text before headings in org files
- Text before headings was not being indexed due to buggy orgnode
  parsing logic
- Resolved indexing intro text from files with and without headings in
  them
- Ensure intro text node has heading set to all title lines collected
  from the file

Resolves #165
2023-03-01 12:11:33 -06:00