- 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
- 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
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
* 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
- 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
* 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
* 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
* 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
* 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
## 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
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
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
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
* 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
- 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
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.
- 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
* 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
* 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
* 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
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
- 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
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
- 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
* 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
- 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
- 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
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.
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.
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.
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
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
- 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
- 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
- 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
- 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
- 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
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.
- 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
- 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
- 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
- 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
- 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
- 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
- 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
- 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
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
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
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
- cl-push expects a generatlized variable. Else throws (setf quote)
undefined warning
- This results in the config call failing on calling khoj entrypoint
- 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
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
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
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)
- 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)
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
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
- 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
- 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
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
- 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
- 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
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
- 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
- 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
- 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
- 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"
- 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
- 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
- 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
- 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
- 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
- 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
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
- 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?"
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
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
- 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
# 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
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
- 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
- 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
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
- 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
- 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
- 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
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
- 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
- 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
