This takes the load of the task scheduling chat actor / prompt from
having to artifically differentiate query to create scheduled task
from a scheduled task run.
- The task scheduling actor was having trouble calculating the
timezone. Giving the actor a scratchpad to improve correctness by
thinking step by step
- Add more examples to reduce chances of the inferred query looping to
create another reminder instead of running the query and sharing
results with user
- Improve task scheduling chat actor test with more tests and
by ensuring unexpected words not present in response
There's a difference between running a scheduled task and notifying
the user about the results of running the scheduled task.
Decide to notify the user only when the results of running the
scheduled task satisfy the user's requirements.
Use sync version of send_message_to_model_wrapper for scheduled tasks
- Store scheduled job state in Postgres so job schedules persist
across app restarts
- Use Process Locks to only allow single worker to process a given job
type. This prevents duplicating job runs across all workers
- Detect when user intends to schedule a task, aka reminder
Add new output mode: reminder. Add example of selecting the reminder
output mode
- Extract schedule time (as cron timestring) and inferred query to run
from user message
- Use APScheduler to call chat with inferred query at scheduled time
- Handle reminder scheduling from both websocket and http chat requests
- Support constructing scheduled task using chat history as context
Pass chat history to scheduled query generator for improved context
for scheduled task generation
Previously the make delete API response failed, after deleting token.
Required a page refresh to see that the API token was actually gone.
This was happening because the response type of the delete token API
endpoint isn't a string, so it failed FastAPI response validation
checks.
- Allow self-hosted users to customize their open ai base url. This allows you to easily use a proxy service and extend support for other models.
- This also includes a migration that associates any existing openai chat model configuration with an openai processor configuration
- Make changing model a paid/subscriber feature
- Removes usage of langchain's OpenAI wrapper for better control over parsing input/output
- Allow passing completion args through completion_with_backoff
- Pass model_kwargs in a separate arg to simplify this
- Pass model in `model_name' kwarg from the send_message_to_model func
`model_name' kwarg is used by langchain, not `model' kwarg
- Make valid file extension checking case insensitive on Desktop app
- Skip indexing non-existent folders on Desktop app
- Pass auth headers to fix lazy load of chat messages on Desktop app
- Set chat-message height to height of content in web, desktop
Previous cross-encoder model was a few years old, newer models should
have improved in quality. Model size increases by 50% compared to
previous for better performance, at least on benchmarks
Most newer, better embeddings models add a query, docs prefix when
encoding. Previously Khoj admins couldn't configure these, so it
wasn't possible to use these newer models.
This change allows configuring the kwargs passed to the query, docs
encoders by updating the search config in the database.
Improve tool, online search, webpage links, docs search chat actor
prompts. Ensure works with hermes-2-pro and llama-3.
Be more specific about generating JSON and not saying anything else.
- Improve extract question prompts to explicitly request JSON list
- Use llama-3 chat format if HF repo_id mentions llama-3. The
llama-cpp-python logic for detecting when to use llama-3 chat format
isn't robust enough currently
* Changed the styling of the link that takes a user to the settings page into a button
* added an indicator that shows if a user is connected to the server or not
* made a class name more descriptive and also made the text in first run message more intuitive
* changed the command to install dependencies in the README.md
* changed the class name of the first run message text to be more descriptive
* added icons in the desktop UI that shows if a file is synced successfully or not
* made the link class name in the homepage more descriptive
* fixed the hover issue on status box in the chat header pane
* fixed hovering issue on status box on macOS
- User configured max tokens limits weren't being passed to
`send_message_to_model_wrapper'
- One of the load offline model code paths wasn't reachable. Remove it
to simplify code
- When max prompt size isn't set infer max tokens based on free VRAM
on machine
- Use min of app configured max tokens, vram based max tokens and
model context window
- User configured max tokens limits weren't being passed to
`send_message_to_model_wrapper'
- One of the load offline model code paths wasn't reachable. Remove it
to simplify code
- When max prompt size isn't set infer max tokens based on free VRAM
on machine
- Use min of app configured max tokens, vram based max tokens and
model context window
To access the Khoj admin panel from a non HTTPS custom domain the
`KHOJ_NO_SSL' and `KHOJ_DOMAIN' env vars need to be explictly set.
See the updated setup docs for details.
Resolves#662
### Store Generated Images as WebP
- 78bac4ae Add migration script to convert PNG to WebP references in database
- c6e84436 Update clients to support rendering webp images inline
- d21f22ff Store Khoj generated images as webp instead of png for faster loading
### Lazy Fetch Chat Messages to Improve Time, Data to First Render
This is especially helpful for long conversations with lots of images
- 128829c4 Render latest msgs on chat session load. Fetch, render rest as they near viewport
- 9e558577 Support getting latest N chat messages via chat history API
### Intelligently set Context Window of Offline Chat to Improve Performance
- 4977b551 Use offline chat prompt config to set context window of loaded chat model
### Fixes
- 148923c1 Fix to raise error on hitting rate limit during Github indexing
- b8bc6bee Always remove loading animation on Desktop app if can't login to server
- 38250705 Fix `get_user_photo` to only return photo, not user name from DB
### Miscellaneous Improvements
- 689202e0 Update recommended CMAKE flag to enable using CUDA on linux in Docs
- b820daf3 Makes logs less noisy
- Reduces time to first render when loading long chat sessions
- Limits size of first page load, when loading long chat sessions
These performance improvements are maximally felt for large chat
sessions with lots of images generated by Khoj
Updated web and desktop app to support these changes for now
Previously you couldn't configure the n_ctx of the loaded offline chat
model. This made it hard to use good offline chat model (which these
days also have larger context) on machines with lower VRAM
- Show telemetry enabled/disabled state on init, not every 2 minutes
- Convert no docs synced logs to debug level instead of warning
Having synced docs isn't as important to use Khoj now, unlike before
- Magika on Desktop app was too bloated (100Mb to 250Mb) and broke
install for some reason. Not sure why it was causing the app install
to fail but do not have time to currently investigate
- Just use file extensions whitelist it's good enough for now. Let
server handle the deeper identification of file type
### Index more text file types
- Index all text, code files in Github repos. Not just md, org files
- Send more text file types from Desktop app and improve indexing them
- Identify file type by content & allow server to index all text files
### Deprecate Github Indexing Features
- Stop indexing commits, issues and issue comments in a Github repo
- Skip indexing Github repo on hitting Github API rate limit
### Fixes and Improvements
- **Fix indexing files in sub-folders from Desktop app**
- Standardize structure of text to entries to match other entry processors
- Show internet search, webpage read, image query, image generation steps
- Standardize, improve rendering of the intermediate steps on the web app
Benefits:
1. Improved transparency, allow users to see what Khoj is doing behind
the scenes and modify their query patterns to improve response quality
2. Reduced websocket connection keep alive timeouts for long running steps
- `file-type' doesn't handle mis-labelled files or files without
extensions well
- Only show supported file types in file selector dialog on Desktop app
Use Magika to get list of text file extensions. Combine with other
supported extensions to get complete list of supported file extensions.
Use it to limit selectable files in the File Open dialog.
Note: Folder selector will index text files with no extensions as well
* Don't trigger any re-indexing on server initailization
* Integrate Resend to send welcome emails when a new user signs up
- Only send if this is the first time they've signed in
- Configure welcome email with basic styling, as more complex designs don't work and style tag did not work
### Enable copying chat messages. Improve copy button behavior and styling
- Add button to copy chat messages on Desktop, Web apps
- Improve copy button's icon, hover color & click animation in Desktop, Web apps
### Improve Navigation, Chat Session Panes on Desktop, Web apps
- Dynamically generate navigation menu based on user info from server
- Create API endpoint to get authenticated user information
- Collapse navigation tabs into icons on mobile. Add spacing to them
- Add Chat navigation tab back to top pane on Web app
- Use proper icons for Search, Chat and Agents tab on navigation pane
### Miscellaneous Improvements
- Make current chat expand to full width when session panel collapsed on Desktop App
- Add chat session loading spinner to Desktop App (same as Web app)
### Fixes
- Show title bar in Khoj desktop app on Windows to simplify close, minimize etc.
- Only render first run setup message once if error or server not running
- Fix showing Search navigation tab from Agent pages on web client
The username and location in system prompt should disambiguate user
context from user's actual message for the chat model.
It doesn't need to be told to not mention the context or acknowledge
the context instructions in it's response, as it understands that this
information is just context and not part of the user's actual message.
- Move new conversation button to right of "Conversation" title
- Reduce size of chat message loading ellipsis animation
- Add loading animation for chat session
The `has_documents' flag wasn't being passed. So the search tab
always showing up as empty instead of being dynamically enabled if
documents had been indexed.
- `fs.readdir' func in node version 18.18.2 has buggy `recursive' option
See nodejs/node#48640, effect-ts/effect#1801 for details
- We were recursing down a folder in two ways on the Desktop app.
Remove `recursive: True' option to the `fs.readdirSync' method call
to recurse down via app code only
Add process_single_plaintext_file func etc with similar signatures as
org_to_entries and markdown_to_entries processors
The standardization makes modifications, abstractions easier to create
Sleep until rate limit passed is too expensive, as it keeps a
app worker occupied.
Ideally we should schedule job to contine after rate limit wait time
has passed. But this can only be added once we support jobs scheduling.
Normal indexing quickly Github hits rate limits. Purpose of exposing
Github indexer is for indexing content like notes, code and other
knowledge base in a repo.
The current indexer doesn't scale to index metadata given Github's
rate limits, so remove it instead of giving a degraded experience of
partially indexed repos
- Allow syncing more file types from desktop app to index on server
- Use `file-type' package to identify valid text file types on Desktop app
- Split plaintext entries into smaller logical units than a whole file
Since the text splitting upgrades in #645, compiled chunks have more
logical splits like paragraph, sentence.
Show those (potentially) smaller snippets to the user as references
- Tangential Fix:
Initialize unbound currentTime variable for error log timestamp
- Use Magika's AI for a tiny, portable and better file type
identification system
- Existing file type identification tools like `file' and `magic'
require system level packages, that may not be installed by default
on all operating systems (e.g `file' command on Windows)
## Major
- Parse markdown, org parent entries as single entry if fit within max tokens
- Parse a file as single entry if it fits with max token limits
- Add parent heading ancestry to extracted markdown entries for context
- Chunk text in preference order of para, sentence, word, character
## Minor
- Create wrapper function to get entries from org, md, pdf & text files
- Remove unused Entry to Jsonl converter from text to entry class, tests
- Dedupe code by using single func to process an org file into entries
Resolves#620
* Add support for using OAuth2.0 in the Notion integration
* Add notion to the admin page
* Remove unnecessary content_index and image search/setup references
* Trigger background job to start indexing Notion after user configures it
* Add a log line when a new Notion integration is setup
* Fix references to the configure_content methods
`re.MULTILINE' should be passed to the `flags' argument, not the
`max_splits' argument of the `re.split' func
This was messing up the indexing by only allowing a maximum of
re.MULTILINE splits. Fixing this improves the search quality to
previous state
More content indexed per entry would result in an overall scores
lowering effect. Increase default search distance threshold to counter that
- Details
- Fix expected results post indexing updates
- Fix search with max distance post indexing updates
- Minor
- Remove openai chat actor test for after: operator as it's not expected anymore
- Major
- Do not split org file, entry if it fits within the max token limits
- Recurse down org file entries, one heading level at a time until
reach leaf node or the current parent tree fits context window
- Update `process_single_org_file' func logic to do this recursion
- Convert extracted org nodes with children into entries
- Previously org node to entry code just had to handle leaf entries
- Now it recieve list of org node trees
- Only add ancestor path to root org-node of each tree
- Indent each entry trees headings by +1 level from base level (=2)
- Minor
- Stop timing org-node parsing vs org-node to entry conversion
Just time the wrapping function for org-mode entry extraction
This standardizes what is being timed across at md, org etc.
- Move try/catch to `extract_org_nodes' from `parse_single_org_file'
func to standardize this also across md, org
These changes improve context available to the search model.
Specifically this should improve entry context from short knowledge trees,
that is knowledge bases with sparse, short heading/entry trees
Previously we'd always split markdown files by headings, even if a
parent entry was small enough to fit entirely within the max token
limits of the search model. This used to reduce the context available
to the search model to select appropriate entries for a query,
especially from short entry trees
Revert back to using regex to parse through markdown file instead of
using MarkdownHeaderTextSplitter. It was easier to implement the
logical split using regexes rather than bend MarkdowHeaderTextSplitter
to implement it.
- DFS traverse the markdown knowledge tree, prefix ancestry to each entry
These changes improve entry context available to the search model
Specifically this should improve entry context from short knowledge trees,
that is knowledge bases with small files
Previously we split all markdown files by their headings,
even if the file was small enough to fit entirely within the max token
limits of the search model. This used to reduce the context available
to select the appropriate entries for a given query for the search model,
especially from short knowledge trees
- Previous simplistic chunking strategy of splitting text by space
didn't capture notes with newlines, no spaces. For e.g in #620
- New strategy will try chunk the text at more natural points like
paragraph, sentence, word first. If none of those work it'll split
at character to fit within max token limit
- Drop long words while preserving original delimiters
Resolves#620
This was earlier used when the index was plaintext jsonl file. Now
that documents are indexed in a DB this func is not required.
Simplify org,md,pdf,plaintext to entries tests by removing the entry
to jsonl conversion step
- Convert extract_org_entries function to actually extract org entries
Previously it was extracting intermediary org-node objects instead
Now it extracts the org-node objects from files and converts them
into entries
- Create separate, new function to extract_org_nodes from files
- Similarly create wrapper funcs for md, pdf, plaintext to entries
- Update org, md, pdf, plaintext to entries tests to use the new
simplified wrapper function to extract org entries
- Move green server connected dot to the bottom. Show status when
disconnected from server
- Move "New conversation" button to right of the "Conversation" title
- Center alignment of the new conversation and connection status buttons
- Overview
- Extract more structured date variants (e.g with dot(.) & slash(/) separators, 2-digit year)
- Extract some natural, partial dates as well from entries
- Capability
Add ability to extract the following additional date forms:
- Natural Dates: 21st April 2000, February 29 2024
- Partial Natural Dates: March 24, Mar 2024
- Structured Dates: 20/12/24, 20.12.2024, 2024/12/20
Note: Previously only YYYY-MM-DD ISO-8601 structured date form was extracted for date filters
- Performance
Using regexes is MUCH faster than using the `dateparser' python library
It's a little crude but gives acceptable performance for large datasets
- Much faster than using dateparser
- It took 2x-4x for improved regex to extracts 1-15% more dates
- Whereas It took 33x to 100x for dateparser to extract 65% - 400% more dates
- Improve date extractor tests to test deduping dates, natural,
structured date extraction from content
- Extract some natural, partial dates and more structured dates
Using regex is much faster than using dateparser. It's a little
crude but should pay off in performance.
Supports dates of form:
- (Day-of-Month) Month|AbbreviatedMonth Year|2DigitYear
- Month|AbbreviatedMonth (Day-of-Month) Year|2DigitYear
Previously we just extracted dates in YYYY-MM-DD format from content
for date filterings during search.
Use dateparser to extract dates across locales and natural language
This should improve notes returned as context when chat searches
knowledge base with date filters
Fallback to regex for date parsing from content if dateparser fails
- Limit natural date extractor capabilities to improve performance
- Assume language is english
Language detection otherwise takes a REALLY long time
- Do not extract unix timestamps, timezone
- This isn't required, as just using date and approximating dates as UTC
- When setting up the default agent, configure every conversation that doesn't have an agent to use the Khoj agent
- Fix reverse migration for the locale removal migration
Previously we were skipping the extract questions step for offline
chat as default offline chat model wasn't good enough to output proper
json given the time it took to extract questions.
The new default offline chat models gives json much more regularly and
with date filters, so the extract questions step becomes useful given
the impact on latency
- Benefits of moving to llama-cpp-python from gpt4all:
- Support for all GGUF format chat models
- Support for AMD, Nvidia, Mac, Vulcan GPU machines (instead of just Vulcan, Mac)
- Supports models with more capabilities like tools, schema
enforcement, speculative ddecoding, image gen etc.
- Upgrade default chat model, prompt size, tokenizer for new supported
chat models
- Load offline chat model when present on disk without requiring internet
- Load model onto GPU if not disabled and device has GPU
- Load model onto CPU if loading model onto GPU fails
- Create helper function to check and load model from disk, when model
glob is present on disk.
`Llama.from_pretrained' needs internet to get repo info from
HuggingFace. This isn't required, if the model is already downloaded
Didn't find any existing HF or llama.cpp method that looked for model
glob on disk without internet
* Initial pass at backend changes to support agents
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications
* Customize default behaviors for conversations without agents or with default agents
* Add a new web client route for viewing all agents
* Use agent_id for getting correct agent
* Add web UI views for agents
- Add a page to view all agents
- Add slugs to manage agents
- Add a view to view single agent
- Display active agent when in chat window
- Fix post-login redirect issue
* Fix agent view
* Spruce up the 404 page and improve the overall layout for agents pages
* Create chat actor for directly reading webpages based on user message
- Add prompt for the read webpages chat actor to extract, infer
webpage links
- Make chat actor infer or extract webpage to read directly from user
message
- Rename previous read_webpage function to more narrow
read_webpage_at_url function
* Rename agents_page -> agent_page
* Fix unit test for adding the filename to the compiled markdown entry
* Fix layout of agent, agents pages
* Merge migrations
* Let the name, slug of the default agent be Khoj, khoj
* Fix chat-related unit tests
* Add webpage chat command for read web pages requested by user
Update auto chat command inference prompt to show example of when to
use webpage chat command (i.e when url is directly provided in link)
* Support webpage command in chat API
- Fallback to use webpage when SERPER not setup and online command was
attempted
- Do not stop responding if can't retrieve online results. Try to
respond without the online context
* Test select webpage as data source and extract web urls chat actors
* Tweak prompts to extract information from webpages, online results
- Show more of the truncated messages for debugging context
- Update Khoj personality prompt to encourage it to remember it's capabilities
* Rename extract_content online results field to webpages
* Parallelize simple webpage read and extractor
Similar to what is being done with search_online with olostep
* Pass multiple webpages with their urls in online results context
Previously even if MAX_WEBPAGES_TO_READ was > 1, only 1 extracted
content would ever be passed.
URL of the extracted webpage content wasn't passed to clients in
online results context. This limited them from being rendered
* Render webpage read in chat response references on Web, Desktop apps
* Time chat actor responses & chat api request start for perf analysis
* Increase the keep alive timeout in the main application for testing
* Do not pipe access/error logs to separate files. Flow to stdout/stderr
* [Temp] Reduce to 1 gunicorn worker
* Change prod docker image to use jammy, rather than nvidia base image
* Use Khoj icon when Khoj web is installed on iOS as a PWA
* Make slug required for agents
* Simplify calling logic and prevent agent access for unauthenticated users
* Standardize to use personality over tuning in agent nomenclature
* Make filtering logic more stringent for accessible agents and remove unused method:
* Format chat message query
---------
Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
### Overview
Khoj can now read website directly without needing to go through the search step first
### Details
- Parallelize simple webpage read and extractor
- Rename extract_content online results field to web pages
- Tweak prompts to extract information from webpages, online results
- Test select webpage as data source and extract web urls chat actors
- Render webpage read in chat response references on Web, Desktop apps
- Pass multiple webpages with their urls in online results context
- Support webpage command in chat API
- Add webpage chat command for read web pages requested by user
- Create chat actor for directly reading webpages based on user message
Previously even if MAX_WEBPAGES_TO_READ was > 1, only 1 extracted
content would ever be passed.
URL of the extracted webpage content wasn't passed to clients in
online results context. This limited them from being rendered
- Fallback to use webpage when SERPER not setup and online command was
attempted
- Do not stop responding if can't retrieve online results. Try to
respond without the online context
* Initial pass at backend changes to support agents
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications
* Customize default behaviors for conversations without agents or with default agents
* Use agent_id for getting correct agent
* Merge migrations
* Simplify some variable definitions, add additional security checks for agents
* Rename agent.tuning -> agent.personality
- Use the conversation id of the retrieved conversation rather than the
potentially unset conversation id passed via API
- await creating new chat when no chat id provided and no existing
conversations exist
- Move some common methods into separate functions to make the UI components more efficient
- The normal HTTP-based chat connection will still work and serves as a fallback if the websocket is unavailable
- Convert to a model of calling the search API directly with a function call (rather than using the API method)
- Gracefully handle websocket connection disconnects
- Ensure that the rest of the response is still saved, as it is currently, if the user disconects from the client
- Setup unchangeable context at the beginning of the session when the connection is established (like location, username, etc)
The recently added after: operator to online search actor was too
restrictive, gave worse results than when just use natural language
dates in search query
Previously was assuming the system prompt is being always passed as
the first message. So expected there to be at least 2 messages in logs.
This broke chat actors querying with single long non system message.
A more robust way to extract system prompt is via the message role
instead
- Ask for Confirmation before deleting chat session in Desktop, Web app
- Save chat session rename on hitting enter in title edit input box
- No need to flash previous conversation cleared status message
- Move chat session delete button after rename button in Desktop app
- Add prompt for the read webpages chat actor to extract, infer
webpage links
- Make chat actor infer or extract webpage to read directly from user
message
- Rename previous read_webpage function to more narrow
read_webpage_at_url function
### Major
- Enforce json mode response from OpenAI chat actors prev using string lists
- Use `gpt-4-turbo-preview' as default chat model, extract questions actor
- Make Khoj read khoj website to respond with accurate, up-to-date information about itself
- Dedupe query in notes prompt. Improve OAI chat actor, director tests
### Minor
- Test data source, output mode selector, web search query chat actors
- Improve notes search actor to always create a non-empty list of queries
- Construct available data sources, output modes as a bullet list in prompts
- Use consistent agent name across static and dynamic examples in prompts
- Add actor's name to extract questions prompt to improve context for guidance
Previously only the notes references would get rendered post response
streaming when when both online and notes references were used to
respond to the user's message
- Allow passing response format type to OpenAI API via chat actors
- Convert in-context examples to use json objects instead of str lists
- Update actors outputting str list to request output to be json_object
- OpenAI's json mode enforces the model to output valid json object
- Remove stale tests
- Improve tests to pass across gpt-3.5 and gpt-4-turbo
- The haiku creation director was failing because of duplicate query in
instantiated prompt
- Remove the option for Notes search query generation actor to return
no queries. Whether search should be performed is decided before,
this step doesn't need to decide that
- But do not throw warning if the response is a list with no elements
- Add examples where user queries requesting information about Khoj
results in the "online" data source being selected
- Add an example for "general" to select chat command prompt
Previously the examples constructed from chat history used "Khoj" as
the agent's name but all 3 prompts using the func used static examples
with "AI:" as the pertinent agent's name
- Add example to read khoj.dev website for up-to-date info to setup,
use khoj, discover khoj features etc.
- Online search should use site: and after: google search operators
- Show example of adding the after: date filter to google search
- Give local event lookup example using user's current location in
query
- Remove unused select search content type prompt
- Add a page to view all agents
- Add slugs to manage agents
- Add a view to view single agent
- Display active agent when in chat window
- Fix post-login redirect issue
### Major
- Read web pages in parallel to improve chat response time
- Read web pages directly when Olostep proxy not setup
- Include search results & web page content in online context for chat response
### Minor
- Simplify, modularize and add type hints to online search functions
Previously if a web page was read for a sub-query, only the extracted
web page content was provided as context for the given sub-query. But
the google results themselves have relevant snippets. So include them
- Simplify content arg to `extract_relevant_info' function. Validate,
clean the content arg inside the `extract_relevant_info' function
- Extract `search_with_google' function outside the parent function
- Call the parent function a more appropriate `search_online' instead
of `search_with_google'
- Simplify the `search_with_google' function using list comprehension.
Drop empty search result fields from chat model context for response
to reduce cost and response latency
- No need to show stacktrace when unable to read webpage, basic error
is enough
- Add type hints to online search functions to catch issues with mypy
- Time reading webpage, extract info from webpage steps for perf
analysis
- Deduplicate webpages to read gathered across separate google
searches
- Use aiohttp to make API requests non-blocking, pair with asyncio to
parallelize all the online search webpage read and extract calls
- Add a db model for Agents, attaching them to conversations
- When an agent is added to a conversation, override the system prompt to tweak the instructions
- Agents can be configured with prompt modification, model specification, a profile picture, and other things
- Admin-configured models will not be editable by individual users
- Add unit tests to verify agent behavior. Unit tests demonstrate imperfect adherence to prompt specifications
- Trigger
SentenceTransformer Cross Encoder models now run fast on GPU enabled machines, including Mac ARM devices since UKPLab/sentence-transformers#2463
- Details
- Use cross-encoder to rerank search results by default on GPU machines and when using an inference server
- Only call search API when pause in typing search query on web, desktop apps
Wait for 300ms since stop typing before calling search API.
This smooths out UI jitter when rendering search results, especially
now that we're reranking for every search query on GPU enabled devices
Emacs already has 300ms debounce time. More convoluted to add
debounce time to Obsidian search modal, so not updating that yet
Latest sentence-transformer package uses GPU for cross-encoder. This
makes it fast enough to enable reranking on machines with GPU.
Enabling search reranking by default allows (at least) users with GPUs
to side-step learning the UI affordance to rerank results
(i.e hitting Cmd/Ctrl-Enter or ENTER).
- Fix
`get_conversation_by_user' shouldn't return new conversation if
conversation with requested id not found.
It should only return new conversation if no specific conversation
is requested and no conversations found for user at all
- Repro
- Delete a new chat, this calls loadChat via window.onload which
calls server /chat/history API endpoint with conversationId set to
that of just deleted conversation sporadically
The call to GET chat/history API with conversationId set occurs
when window.onload triggers before the conversationId is deleted
by the delete button after the DELETE /chat/history API call (via race)
- In such a scenario, get_conversation_by_user called by
chat/history API with conversationId of deleted conversation
returns a new conversation
- Miscellaneous
- Chat history load should be logged as call to that chat_history api,
not the "chat" api
- Show status updates of clearing conversation history in chat input
- Simplify web, desktop client code by removing unnecessary new variables
* Upload generated images to s3, if AWS credentials and bucket is available.
- In clients, render the images via the URL if it's returned with a text-to-image2 intent type
* Make the loading screen more intuitve, less jerky and update the programmatic copy button
* Update the loading icon when waiting for a chat response
* Add additional styling changes for showing UI changes when dragging file to the main screen
* Add a loading spinner when file upload is in progress, and don't index github/notion when indexing files
* Add an explicit icon for file uploading in the chat button menu
* Add appropriate dragover styling when picking a file from the file picker/browser
* Add a loading screen when retrieving chat history. Fix width of the chat window. Put attachment icon to the left of chat input
* Make major improvements to the image generation flow
- Include user context from online references and personal notes for generating images
- Dynamically select the modality that the LLM should respond with
- Retun the inferred context in the query response for the dekstop, web chat views to read
* Add unit tests for retrieving response modes via LLM
* Move output mode unit tests to the actor suite, rather than director
* Only show the references button if there is at least one available
* Rename aget_relevant_modes to aget_relevant_output_modes
* Use a shared method for generating reference sections, simplify some of the prompting logic
* Make out of space errors in the desktop client more obvious
- Open external links using the default link handler registered on OS
for the link type, e.g http:// -> firefox, mailto: thunderbird etc
- Confirm before opening non-http URL using an external app
- Improve render of inferred query in image chat messages in Web, Desktop apps
- Add inferred queries to image chat responses in Obsidian client
- Fix rendering images from Khoj response in Obsidian client
* Simplify and clarify prompt for selecting toolset dynamically
* Add error handling around call to OLOSTEP api
* Fix conversation admin page
* Skip adding none or empty entries in the chunking method
- Improve
- Only send files modified since their last sync for indexing on server from the Obsidian client
- Fix
- Invalidate static asset browser cache in Web client when Khoj version changes
Previously we'd send all files in vault and let the server
deduplicate.
This changes takes inspiration from the desktop app, and only pushes
files which were modified after their previous sync with the server.
This should reduce the processing load on the server
* Retrieve, create, and save conversations differently if they're coming from a client application
- Not all of our client apps will necessarily maintain state over the conversation IDs available to a user. For some (single-threaded conversations), it should just use a single conversation. Fix the code to do so
* Simplify conversation retrieval logic
* Keep 0 padding below chat response
* Add order_by sorting to retrieving the conversation without id
### Improvements to Chat UI on Web, Desktop apps
- Improve styling of chat session side panel
- Improve styling of chat message bubble in Desktop, Web app
- Add frosted, minimal chat UI to background of Login screen
- Improve PWA install experience of Khoj
### Fixes to Chat UI on Web, Desktop apps
- Fix creating new chat sessions from the Desktop app
- Only show 3 starter questions even when consecutive chat sessions created
### Other Improvements
- Update Khoj cloud trial period to a fortnight instead of a week
- Document using venv to handle dependency conflict on khoj pip install
Resolves#276
- Resolve PWA issues thrown by Chrome/Edge
- Add screenshot samples showcasing remember, browse and draw features
- This can provide a richer app store like experience when
installing Khoj PWA on Mobile or Desktop
- Add wide and narrow screenshots to show Mobile vs Desktop UX
- Add higher resolution favicon for PWA
- Use single web manifest instead of separate ones for Chat, Search
- Update manifest description with more details about Khoj features
Reset starter question suggestions before appending in web, desktop app
Otherwise previously it'd keep adding to existing starter question
suggestions on each new session creation if multiple consecutive new
chat sessions created.
This would result in more than the 3 expected starter questions being
displayed at a time
- Make collapse, expand toggle arrow point in the direction the action
will expand the side panel in
- Make the collapsed side panel reduce to a 1px sliver
- Improve rate limit error message wording
- Make the "too many requests" error message more robust. Should throw
that exception fix self.request >= self.subscribed_requests because
upgrading wouldn't fix this rate limiting
- Respect newline with pre-line but not for bullets to improve
formatting of responses by Khoj
- Respect bold font by loading tajawal font with other weights
- Reduce bottom margin in chat message bubble, its taking too much space
* Document original query when subqueries can't be generated
* Only add messages to the chat message log if it's non-empty
* When changing the search model, alert the user that all underlying data will be deleted
* Adding more clarification to the prompt input for username, location
* Check if has_more is in the notion results before getting next_cursor
* Update prompt template for user name/location, update confirmation message when changing search model
* Display given_name field only if it is not None
* Add default slugs in the migration script
* Ensure that updated_at is saved appropriately, make sure most recent chat is returned for default history
* Remove the bin button from the chat interface, given deletion is handled in the drop-down menus
* Refresh the side panel when a new chat is created
* Improveme tool retrieval prompt, don't let /online fail, and improve parsing of extract questions
* Fix ending chat response by offline chat on hitting a stop phrase
Previously the whole phrase wouldn't be in the same response chunk, so
chat response wouldn't stop on hitting a stop phrase
Now use a queue to keep track of last 3 chunks, and to stop responding
when hit a stop phrase
* Make chat on Obsidian backward compatible post chat session API updates
- Make chat on Obsidian get chat history from
`responseJson.response.chat' when available (i.e when using new api)
- Else fallback to loading chat history from
responseJson.response (i.e when using old api)
* Fix detecting success of indexing update in khoj.el
When khoj.el attempts to index on a Khoj server served behind an https
endpoint, the success reponse status contains plist with certs. This
doesn't mean the update failed.
Look for :errors key in status instead to determine if indexing API
call failed. This fixes detecting indexing API call success on the
Khoj Emacs client, even for Khoj servers running behind SSL/HTTPS
* Fix the mechanism for populating notes references in the conversation primer for both offline and online chat
* Return conversation.default when empty list for dynamic prompt selection, send all cmds in telemetry
* Fix making chat on Obsidian backward compatible post chat session API updates
New API always has conversation_id set, not `chat' which can be unset
when chat session is empty.
So use conversation_id to decide whether to get chat logs from
`responseJson.response.chat' or `responseJson.response' instead
---------
Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
This will reduce khoj dependencies to install for self-hosting users
- Move auth production dependencies to prod python packages group
- Only enable authentication API router if not in anonymous mode
- Improve error with requirements to enable authentication when not in
anonymous mode
* Add location metadata to chat history
* Add support for custom configuration of the user name
* Add region, country, city in the desktop app's URL for context in chat
* Update prompts to specify user location, rather than just location.
* Add location data to Obsidian chat query
* Use first word for first name, last word for last name when setting profile name
* Have Khoj dynamically select which conversation command(s) are to be used in the chat flow
- Intercept the commands if in default mode, and have Khoj dynamically guess which tools would be the most relevant for answering the user's query
* Remove conditional for default to enter online search mode
* Add multiple-tool examples in the prompt, make prompt for tools more specific to info collection
* Add chat sessions to the desktop application
* Increase width of the main chat body to 90vw
* Update the version of electron
* Render the default message if chat history fails to load
* Merge conversation migrations and fix slug setting
* Update the welcome message, use the hostURL, and update background color for chat actions
* Only update the window's web contents if the page is config
* Enable support for multiple chat sessions within the web client
- Allow users to create multiple chat sessions and manage them
- Give chat session slugs based on the most recent message
- Update web UI to have a collapsible menu with active chats
- Move chat routes into a separate file
* Make the collapsible side panel more graceful, improve some styling elements of the new layout
* Support modification of the conversation title
- Add a new field to the conversation object
- Update UI to add a threedotmenu to each conversation
* Get the default conversation if a matching one is not found by id
- Removed node-fetch dependency to work on mobile.
- Fix CORS issue for Khoj (streaming) chat on Obsidian mobile
- Verified Khoj plugin, search, chat work on Obsidian mobile.
## Details
### Major
- Allow calls to Khoj server from Obsidian mobile app to fix CORS issue
- Chat stream using default `fetch' not `node-fetch' in obsidian plugin
### Minor
- Load chat history after other elements in chat modal on Obsidian are rendered
- Scroll to bottom of chat modal on Obsidian across mobile & desktop
- Obsidian mobile uses capacitor js. Requests from it have origin as
http://localhost on Android and capacitor://localhost on iOS
- Allow those Obsidian mobile origins in CORS middleware of server
- Can now expect date awareness chat quality test to pass
- Prevent offline chat model from printing verbatim user Notes and
special tokens
- Make it ask follow-up questions if it needs more context
- Put Whatsapp card back in Client section.
- Fixes side spacing on cards
- Improve Whatsapp card row gaps
- Hide notification banner on web app load. Previously it showed up as
a yellow dot on smaller displays
* Fix subscription state detection for users based on phone numbers, emails
* Fix unit tests for api_user4
* Use a single method for determining subscription from user
* Pass user object, rather than user.email for getting subscription state
* Fix license in pyproject.toml. Remove unused utils.state import
* Use single debug mode check function. Disable telemetry in debug mode
- Use single logic to check if khoj is running in debug mode.
Previously there were 3 different variants of the check
- Do not log telemetry if KHOJ_DEBUG is set to true. Previously didn't
log telemetry even if KHOJ_DEBUG set to false
* Respect line breaks in user, khoj chat messages to improve formatting
* Disable Whatsapp config section on web client if Twilio not configured
Simplify Whatsapp configuration status checking js by standardizing
external input to lower case
* Disable Phone API when Twilio not setup and rate limit calls to it
- Move phone api to separate router and only enable it if Twilio enabled
- Add rate-limiting to OTP and verification calls
* Add slugs for phone rate limiting
---------
Co-authored-by: sabaimran <narmiabas@gmail.com>
* Store rate limiter-related metadata in the database for more resilience
- This helps maintain state even between server restarts
- Allows you to scale up workers on your service without having to implement sticky routing
* Make the usage exceeded message less abrasive
* Fix rate limiter for specific conversation commands and improve the copy
* Add retries in case the embeddings API fails
* Improve error handling in the inference endpoint API request handler
- retry only if HTTP exception
- use logger to output information about errors
* Initailize changes to incporate web scraping logic after getting SERP results
- Do some minor refactors to pass a symptom prompt to the openai model when making a query
- integrate Olostep in order to perform the webscraping
* Fix truncation error with new line, fix typing in olostep code
* Use the authorization header for the token
* Add a small hint/indicator for how to use Khojs other modalities in the welcome prompt
* Add more detailed error message if Olostep query fails
* Add unit tests which invoke Olostep in chat director
* Add test for olostep tool
* Improve subqueries for online search and prompt generation for image
- Include conversation history so that subqueries or intermediate prompts are generated with the appropriate context
* Allow users to configure phone numbers with the Khoj server
* Integration of API endpoint for updating phone number
* Add phone number association and OTP via Twilio for users connecting to WhatsApp
- When verified, store the result as such in the KhojUser object
* Add a Whatsapp.svg for configuring phone number
* Change setup hint depending on whether the user has a number already connected or not
* Add an integrity check for the intl tel js dependency
* Customize the UI based on whether the user has verified their phone number
- Update API routes to make nomenclature for phone addition and verification more straightforward (just /config/phone, etc).
- If user has not verified, prompt them for another verification code (if verification is enabled) in the configuration page
* Use the verified filter only if the user is linked to an account with an email
* Add some basic documentation for using the WhatsApp client with Khoj
* Point help text to the docs, rather than landing page info
* Update messages on various callbacks and add link to docs page to learn more about the integration
## Major
### Move to single click audio chat UX on Obsidian, Desktop, Web clients
New default UX has 1 long-press on mobile, 2-click on desktop to send transcribed audio message
- New Audio Chat Flow
1. Record audio while microphone button pressed
2. Show auto-send 3s countdown timer UI for audio chat message
Provide a visual cue around send button for how long before audio
message is automatically sent to Khoj for response
3. Auto-send msg in 3s unless stop send message button clicked
- Why
- Removes the previous default of 3 clicks required to send audio message
The record > stop > send process to send audio messages was unclear and effortful
- Still allows stopping message from being sent, to make correction to transcribed audio
- Removes inadvertent long audio transcriptions if forget to press stop while recording
### Improve chat input pane actions & icons on Obsidian. Desktop, Web clients
- Use SVG icons in chat footer on web, desktop app
- Move delete icon to left of chat input. This makes it harder to inadvertently click it
- Add send button to chat input pane
- Color chat message send button to make it primary CTA
- Make chat footer shorter. Use no or round border on action buttons
## Minor
- Stop rendering empty starter questions element when no questions present
- Add round border, hover color to starter questions in web, desktop apps
- Fix auto resizing chat input box when transcribed text added
- Convert chat input into a text area in the Obsidian client
- Capabillity
New default UX has 1 long-press to send transcribed audio message
- Removes the previous default of 3 clicks required to send audio message
- The record > stop > send process to send audio messages was unclear
- Still allows stopping message from being sent, if users want to make
correction to transcribed audio
- Removes inadvertent long audio transcriptions if user forgets to
press stop when recording
- Changes
- Record audio while microphone button pressed
- Show auto-send 3s countdown timer UI for audio chat message
Provide a visual cue around send button for how long before audio
message is automatically sent to Khoj for response
- Auto-send msg in 3s unless stop send message button clicked
- Capabillity
New default UX has 1 long-press to send transcribed audio message
- Removes the previous default of 3 clicks required to send audio message
- The record > stop > send process to send audio messages was unclear
- Still allows stopping message from being sent, if users want to make
correction to transcribed audio
- Removes inadvertent long audio transcriptions if user forgets to
press stop when recording
- Changes
- Record audio while microphone button pressed
- Show auto-send 3s countdown timer UI for audio chat message
Provide a visual cue around send button for how long before audio
message is automatically sent to Khoj for response
- Auto-send msg in 3s unless stop send message button clicked
- Capabillity
New default UX has 1 long-press to send transcribed audio message
- Removes the previous default of 3 clicks required to send audio message
- The record > stop > send process to send audio messages was unclear
- Still allows stopping message from being sent, if users want to make
correction to transcribed audio
- Removes inadvertent long audio transcriptions if user forgets to
press stop when recording
- Changes
- Record audio while microphone button pressed
- Show auto-send 3s countdown timer UI for audio chat message
Provide a visual cue around send button for how long before audio
message is automatically sent to Khoj for response
- Auto-send msg in 3s unless stop send message button clicked
- Move delete icon to left of chat input. This makes it harder to
inadvertently click
- Add send button to chat footer. Enter being the only way to send
messages is not intuitive, outside standard modern UI patterns
- Color chat message send button to make it primary CTA on web client
- Make chat footer shorter. Use no or round border on action buttons
- Use SVG icons in chat footer on web
- Move delete icon to left of chat input. This makes it harder to
inadvertently click
- Add send button to chat footer. Enter being the only way to send
messages is not intuitive, outside standard modern UI patterns
- Color chat message send button to make it primary CTA on web client
- Make chat footer shorter. Use no or round border on action buttons
- Use SVG icons in chat footer on web
- Move delete icon to left of chat input. This makes it harder to
inadvertently click
- Add send button to chat footer. Enter being the only way to send
messages is not intuitive, outside standard modern UI patterns
- Color chat message send button to make it primary CTA on web client
- Make chat footer shorter. Use no or round border on action buttons
* Add support for a first party client app
- Based on a client id and client secret, allow a first party app to call into the Khoj backend with a phone number identifier
- Add migration to add phone numbers to the KhojUser object
* Add plus in front of country code when registering a phone number.
- Decrease free tier limit to 5 (from 10)
- Return a response object when handling stripe webhooks
* Fix telemetry method which references authenticated user's client app
* Add better error handling for null phone numbers, simplify logic of authenticating user
* Pull the client_secret in the API call from the authorization header
* Add a migration merge to resolve phone number and other changes
The actual issue was that `get_or_create_user_by_email' tried to
create a subscription even if it already existed.
With updated logic:
- New subscription is only created when it doesn't already exist in
`get_or_create_user_by_email'
- `set_user_subscription' just updates the subscription state as
user subscription object creation is already managed by
`get_or_create_user_by_email'. So the other conditionals are
unnecessary
- Issue
Users with Dataview plugin would have error as its markdown
post-processor expects the sourcePath to be a string
This prevents Khoj from responding to chat messages in the Obsidian
chat modal. Search via Obsidian still works but it throws the same
dataview plugin error
- Fix
Pass a string as sourcePath to markdownRenderer to fix failing chat response
and stop throwing dataview errors on search
Resolves#614, Resolves#606
- Update health API to pass authenticated users their info
- Improve Khoj server status check in Khoj Obsidian client
- Show Khoj Obsidian commands even if no connection to server
- Show Khoj chat by default in Obsidian side pane instead of search
Server connection check can be a little flaky in Obsidian. Don't gate
the commands behind it to improve usability of Khoj.
Previously the commands would get disabled when server connection
check failed, even though server was actually accessible
- Update server connection status on every edit of khoj url, api key in
settings instead of only on plugin load
The error message was stale if connection fixed after changes in
Khoj plugin settings to URL or API key, like on plugin install
- Show better welcome message on first plugin install.
Include API key setup instruction
- Show logged in user email on Khoj settings page
- Issue: Users with Dataview plugin would have error as its markdown
post-processor expects the sourcePath to be a string
This prevents Khoj from responding to chat messages in the Obsidian
chat modal. Search via Obsidian still works but it throws the same
dataview error
- Fix: Pass a string as sourcePath to markdownRenderer to fix
failing chat response
Resolves#614, Resolves#606
* Add support for custom inference endpoints for the cross encoder model
- Since there's not a good out of the box solution, I've deployed a custom model/handler via huggingface to support this use case.
* Use langchain.community for pdf, openai chat modules
* Add an explicit stipulation that the api endpoint for crossencoder inference should be for huggingface for now
This allows Khoj clients to get email address associated with
user's API token for display in client UX
In anonymous mode, default user information is passed
### Major
- Short-circuit API rate limiter for unauthenticated user
Calls by unauthenticated users were failing at API rate limiter as it
failed to access user info object. This is a bug.
API rate limiter should short-circuit for unauthenicated users so a
proper Forbidden response can be returned by API
Add regression test to verify that unauthenticated users get 403
response when calling the /chat API endpoint
### Minor
- Remove trailing slash to normalize khoj url in obsidian plugin settings
- Move used /api/config API controllers into separate module
- Delete unused /api/beta API endpoint
- Fix error message rendering in khoj.el, khoj obsidian chat
- Handle deprecation warnings for subscribe renew date, langchain, pydantic & logger.warn
- Use /api/health for server up check instead of api/config/default
- Remove unused `khoj--post-new-config' method
- Remove the now unused /config/data GET, POST API endpoints
* Support using hosted Huggingface inference endpoint for embeddings generation
* Since the huggingface inference endpoint is model-specific, make the URL an optional property of the search model config
* Handle ECONNREFUSED error in desktop app
* Drive API key via the search model config model and use more generic names
- Ensure langchain less than 0.2.0 is used, to prevent breaking
ChatOpenAI, PyMuPDF usage due to their deprecation after 0.2.0
- Set subscription renewal date to a timezone aware datetime
- Use logger.warning instead of logger.warn as latter is deprecated
- Use `model_dump' not deprecated dict to get all configured content_types
Calls by unauthenticated users were failing at API rate limiter as it
failed to access user info object. This is a bug.
API rate limiter should short-circuit for unauthenicated users so a
proper Forbidden response can be returned by API
Add regression test to verify that unauthenticated users get 403
response when calling the /chat API endpoint
FastAPI API endpoints only support uploading 1000 files at a time.
So split all files to index into groups of 1000 for upload to
index/update API endpoint
FastAPI API endpoints only support uploading 1000 files at a time.
So split all files to index into groups of 1000 for upload to
index/update API endpoint
Make usage of the first offline/openai chat model as the default LLM
to use for background tasks more explicit
The idea is to use the default/first chat model for all background
activities, like user message to extract search queries to perform.
This is controlled by the server admin.
The chat model set by the user is used for user-facing functions like
generating chat responses
Previously you could only index org-mode files and directories from
khoj.el
Mark the `khoj-org-directories', `khoj-org-files' variables for
deprecation, since `khoj-index-directories', `khoj-index-files'
replace them as more appropriate names for the more general case
Resolves#597
- Fix streaming chat response in Obsidian client
- Fix first-run, chat error message in obsidian, desktop and web clients
- Set Khoj app version to latest version in Docker images
- Tag Khoj Docker image built on release with the `latest` tag
This align docker image release cadence with client, server releases
- Honor this setting across the relevant places where embeddings are used
- Convert the VectorField object to have None for dimensions in order to make the search model easily configurable
- Improve the prompt before sending it for image generation
- Update the help message to include online, image functionality
- Improve styling for the voice, trash buttons
The source URL returned by OpenAI would expire soon. This would make
the chat sessions contain non-accessible images/messages if using
OpenaI image URL
Get base64 encoded image from OpenAI and store directly in
conversation logs. This resolves the image link expiring issue
- All search models are loaded into memory, and stored in a dictionary indexed by name
- Still need to add database migrations and create a UI for user to select their choice. Presently, it uses the default option
- Move it out to conversation.utils from generate_chat_response function
- Log new optional intent_type argument to capture type of response
expected. This can be type responses by Khoj e.g speech, image. It
can be used to render responses by Khoj appropriately on clients
- Make user_message_time argument optional, set the time to now by
default if not passed by calling function
- Wasn't able to login to the admin panel when KHOJ_DEBUG was not True. Fix this error so self-hosted users can get unblocked from accessing the admin settings
- Don't force users to set their KHOJ_DJANGO_SECRET_KEY
- Use new style references for Khoj chat modal in Obsidian
- Khoj Chat responses in Obsidian had regressed to not show references
for new questions after modal has been opened. Now even those are
rendered, and use new references style
- Render chat response as markdown while it's being streamed
- Add transcription button with mic icon
- Collect audio recording on pressing mic
- Process and send audio recording to server for transcription
- Extract the functionality to flash status in chat input for reuse
- Allow server admin to configure offline speech to text model during
initialization
- Use offline speech to text model to transcribe audio from clients
- Set offline whisper as default speech to text model as no setup api key reqd
- Extract flashing status message in chat input placeholder into
reusable function
- Use emoji prefixes for status messages
- Improve alt text of transcribe button to indicate what the button does
- Conflicts:
- src/interface/desktop/chat.html
Combine and use common class names for speak component
- src/khoj/database/adapters/__init__.py
Combine imports
- src/khoj/interface/web/chat.html
Combine and use common class names for speak component
- src/khoj/routers/api.py
Combine imports
- Add a dependency on the indexer API endpoint that rounds up the amount of data indexed and uses that to determine whether the next set of data should be processed
- Delete any files that are being removed for adminstering the calculation
- Show current amount of data indexed in the config page
- Ignore errors in deleting network requests to khoj server
- Also delete open network connection to khoj server on auto reindex
Otherwise when server is unreachable a bunch of failed network
connections accrue in the processes list
- Make auto-update of content index user configurable from khoj.el
- Handle server unavailable error on auto-index schedule job in khoj.el
Resolves#567
- Append chat message to chat logs as TextNodes in web, desktop clients
- Simplify Code to Identify Files from Github, Notion on Web, Desktop Client
- Use file source to find entries from github, notion on web, desktop client
- Pass file source to clients via text search API response
- Make Django Logs Follow Khoj Log Format, Verbosity
- Handle image search setup related warning
- Format Django initializing outputs using Khoj logger format
- Use `KHOJ_HOST` env var to set allowed/trusted domains to host Khoj
Ideally should rename model_directory to config_directory or some such
but the current image search code will need to be migrated soon. So
changing the variable name and creating a migration script for old
khoj.yml files using model-directory variable isn't worth it
Remove the explicity set of number of threads to use by pytorch. Use
the default used by it.
- Collect STDOUT from the `migrate', `collectstatic' commands and
output using the Khoj logger format and verbosity settings
- Only show Django `collectstatic' command output in verbose mode
- Fix showing the Initializing Khoj log line by moving it after logger
level set
Previously it was only searching for PDF and Markdown files. This was
meant to show only content from current vault as results.
But it has not scaled well as other clients also allow syncing PDF and
markdown files now. So remove this content type filter for now.
A proper solution would limit by using file/dir filters on server or
client side.
- Our pypi package currently does not work because the django app and associated database is not included. To remedy this issue, move the app into the src/khoj folder. This has the added benefit of improved organization of the codebase, as all server related code is now in a single folder
- Update associated file paths and system references
### Overview
The parent hierarchy of org-mode entries can store important context.
This change updates OrgNode to track parent headings for each org entry and adds the parent outline for each entry to the index
### Details
- Test search uses ancestor headings as context for improved results
- Add ancestor headings of each org-mode entry to their compiled form
- Track ancestor headings for each org-mode entry in org-node parser
Resolves#85
- Update docs to show how to use Khoj Cloud
- Move self-hosting Khoj to separate section
- Add page to setup Desktop app
- Set default URL to Khoj Cloud URL in Obsidian, Emacs clients
- Upgrade FastAPI to >= latest version. Required upgrade of FastAPI.
Earlier version didn't support wrapping common query params in class
- Use per fixture app instead of a global FastAPI app in conftest
- Upgrade minimum required Django version
- Fix no notes chat director test with updated no notes message
No notes message was updated in commit 118f1143
- Use the knowledgeGraph, answerBox, peopleAlsoAsk and organic responses of serper.dev to provide online context for queries made with the /online command
- Add it as an additional tool for doing Google searches
- Render the results appropriately in the chat web window
- Pass appropriate reference data down to the LLM
- Adds support for multiple users to be connected to the same Khoj instance using their Google login credentials
- Moves storage solution from in-memory json data to a Postgres db. This stores all relevant information, including accounts, embeddings, chat history, server side chat configuration
- Adds the concept of a Khoj server admin for configuring instance-wide settings regarding search model, and chat configuration
- Miscellaneous updates and fixes to the UX, including chat references, colors, and an updated config page
- Adds billing to allow users to subscribe to the cloud service easily
- Adds a separate GitHub action for building the dockerized production (tag `prod`) and dev (tag `dev`) images, separate from the image used for local building. The production image uses `gunicorn` with multiple workers to run the server.
- Updates all clients (Obsidian, Emacs, Desktop) to follow the client/server architecture. The server no longer reads from the file system at all; it only accepts data via the indexer API. In line with that, removes the functionality to configure org, markdown, plaintext, or other file-specific settings in the server. Only leaves GitHub and Notion for server-side configuration.
- Changes license to GNU AGPLv3
Resolves#467Resolves#488Resolves#303Resolves#345Resolves#195Resolves#280Resolves#461Closes#259Resolves#351Resolves#301Resolves#296
- Link to Django admin panel for user to create Chat Models on their
Khoj server
- This should only get hit when user is not using Khoj cloud, as Khoj
cloud would already have Chat models configured
- While sigmoid normalization isn't required for reranking.
Normalizing score to distance metrics for both encoder and cross
encoder scores is useful to reason about them
- Softmax wasn't required as don't need probabilities, sigmoid is good
enough to get distance metric
- Expose ability to modify search model via Django admin interface
- Previously the bi_encoder and cross_encoder models to use were set
in code
- Now it's user configurable but with a default config generated by
default
- During the migration, the confidence score stopped being used. It
was being passed down from API to some point and went unused
- Remove score thresholding for images as image search confidence
score different from text search model distance score
- Default score threshold of 0.15 is experimentally determined by
manually looking at search results vs distance for a few queries
- Use distance instead of confidence as metric for search result quality
Previously we'd moved text search to a distance metric from a
confidence score.
Now convert even cross encoder, image search scores to distance metric
for consistent results sorting
Remove the Results Count button from the web app. It's hanging weirdly
with not much context to its purpose.
Reintroduce it in the Search card when created under the Features section
Reduce user confusion by joining config update with index updation for
each content type.
So only a single click required to configure any content type instead
of two clicks on two separate pages
- Notes prompt doesn't need to be so tuned to question answering. User
could just want to talk about life. The notes need to be used to
response to those, not necessarily only retrieve answers from notes
- System and notes prompts were forcing asking follow-up questions a
little too much. Reduce strength of follow-up question asking
The Chat models sometime output reference notes directly in the chat
body in unformatted form, specifically as Notes:\n['. Prevent that.
Reference notes are shown in clean, formatted form anyway
- Make mutable syncing variable not a const
- Show next sync time to make users aware of data sync is automated
- Keep a single Save button to reduce confusion. It does what Save All
previously did. Intent to manual sync should Save All
- Default to using app.khoj.dev as default Khoj URL to ease setup
- Add fields to mark users as subscribed to a specific plan and
subscription renewal date in DB
- Add ability to unsubscribe a user using their email address
- Expose webhook for stripe to callback confirming payment
Previously hitting configure or disable wouldn't update the state of
the content cards. It needed page refresh to see if the content was
synced correctly.
Now cards automatically get set to new state on hitting disable button
on card or global configure buttons
Lock syncing to server if a sync is already in progress.
While the sync save button gets disabled while sync is in progress,
the background sync job can still trigger a sync in parallel. This
sync lock prevents that
Remove the table of all files indexed by Khoj. This seems overkill and
doesn't match the UI semantics of the other data sources like Github,
Notion.
Create instead a data source card for computer files with the same
update, disable semantics of the Github and Notion data source cards
Users can disable each data source from its card on the main config page.
They can see/delete individual files indexed from the computer data source
once they click into the computer files data source card on the config page
This will be useful for updating, deleting entries by their data
source. Data source can be one of Computer, Github or Notion for now
Store each file/entries source in database
Major
- Ensure search results logic consistent across migration to DB, multi-user
- Manually verified search results for sample queries look the same across migration
- Flatten indexing code for better indexing progress tracking and code readability
Minor
- a4f407f Test memory leak on MPS device when generating vector embeddings
- ef24485 Improve Khoj with DB setup instructions in the Django app readme (for now)
- f212cc7 Arrange remaining text search tests in arrange, act, assert order
- 022017d Fix text search tests to test updated indexing log messages
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
- 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
