The Langchain HuggingFaceEmbeddings wrapper doesn't support disabling
progressbar, not especially for only query but not documents.
This makes the logs noisy with encoding progressbar for each
incremental queries
No features of the Langchain wrapper for SentenceTransformer was
currently being used anyway for now, and we can always switch back to
it if required
Flatten the nested loops to improve visibilty into indexing progress
Reduce spurious logs, report the logs at aggregated level and update
the logging description text to improve indexing progress reporting
- Given the separation of the client and server now, the web UI will no longer support configuration of local file paths of data to index
- Expose a way to show all the files that are currently set for indexing, along with an option to delete all or specific files
- 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
- 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
- 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
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
- 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
- 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
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
- 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
- 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
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
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.
- 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
### ✨ 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
- 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.
- 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
- 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
- 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
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
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
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
* 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>
### 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
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
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
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.
- 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
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
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
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
- 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
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
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.
- 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
* 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
- 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
- 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
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
- 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
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'
- 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
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
- 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
* 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
- 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
* 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
* 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
* 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
* 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
- 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
* 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>
* 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>
* 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
* 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
* 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>
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
- 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
* 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
# 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|
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
- 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
