### 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
