- Improve search speed by ~10x
Tested on corpus of 125K lines, 12.5K entries
- Allow cross-encoder to re-rank results by settings &?r=true when querying /search API
- It's an optional param that default to False
- Earlier all results were re-ranked by cross-encoder
- Making this configurable allows for much faster results, if desired
but for lower accuracy
- Formalize filters into class with can_filter() and filter() methods
- Use can_filter() method to decide whether to apply filter and
create deep copies of entries and embeddings for it
- Improve search speed for queries with no filters
as deep copying entries, embeddings takes the most time
after cross-encodes scoring when calling the /search API
Earlier we would create deep copies of entries, embeddings
even if the query did not contain any filter keywords
- Reason:
Allow natural search on markdown based notes, documentation,
websites etc
- Details:
- Create markdown processor to extract Markdown entries (identified by
Heading) into standard jsonl format required by text_search
- Update API, Configs to support interfacing with new markdown type
- Update Emacs, Web clients to support interfacing with new markdown
type via API
- Update Readme to mentiond markdown is also supported
Closes#35
- The code for both the text search types were mostly the same
It was earlier done this way for expedience while experimenting
- The minor differences were reconciled and merged into a single
text_search type
- This simplifies the app and making it easier to process other
text types
Now that the logic to compile entries is in the processor layer, the
extract_entries method is standard across (text) search_types
Extract the load_jsonl method as a utility helper method.
Use it in (a)symmetric search types
- The logic for compiling a beancount entry (for later encoding) now
completely resides in the org-to-jsonl processor layer
- This allows symmetric search to be generic and not be aware of
beancount specific properties that were extracted by the
beancount-to-jsonl processor layer
- Now symmetric search just expects the jsonl to (at least) have the
'compiled' and 'raw' keys for each entry. What original text the
entry was compiled from is irrelevant to it. The original text
could be location, transaction, chat etc, it doesn't have to care
- The logic for compiling an org-mode entry (for later encoding) now
completely resides in the org-to-jsonl processor layer
- This allows asymmetric search to be generic and not be aware of
org-mode specific properties that were extracted by the org-to-jsonl
processor layer
- Now asymmetric search just expects the jsonl to (at least) have the
'compiled' and 'raw' keys for each entry. What original text the
entry was compiled from is irrelevant to it. The original text
could be mail, chat, markdown, org-mode etc, it doesn't have to care
- Pass Scheduled, Closed Dates of Entries to Include in Embeddings
- The (new?) model seems to understand dates. So can give more
relevant entries if date in natural language mentioned in query
- E.g "Went Surfing with Friends" vs "Went Surfing with Friends in 1984"
will give different results, with the second prioritizing entries
mentioning any entries with closed, scheduled dates from 1984
- While it's true those strings are going to be used to generated
embeddings, the more generic term allows them to be used elsewhere as
well
- Their main property is that they are processed, compiled for
usage by semantic search
- Unlike the 'raw' string which contains the external representation
of the data, as is
- Had already made some progress on this earlier by updating the image
search responses. But needed to update the text search responses to
use lowercase entry and score
- Update khoj.el to consume the updated json response keys for text
search
- Image order returned by glob is OS dependent
- This prevented sharing image embeddings across machines running different OS
- A stable sort order for processed images allows sharing embeddings
across machines.
- Use case:
A more powerful, always on machine actually computes the image embeddings regularly
The client machine just load these periodically to provide semantic search functionality
- Handle case where current image batch smaller than batch_size
- Handle case where no XMP metadata for current image
- return empty strings in such a scenario instead of ". "
Issue:
- Had different schema of extracted entries for symmetric_ledger vs asymmetric
- Entry extraction for asymmetric was dirty, relying on cryptic
indices to store raw entry vs cleaned entry meant to be passed to embeddings
- This was pushing the load of figuring out what property to extract
from each entry to downstream processes like the filters
- This limited the filters to only work for asymmetric search, not for
symmetric_ledger
- Fix
- Use consistent format for extracted entries
{
'embed': entry_string_meant_to_be_passed_to_model_and_get_embeddings,
'raw' : raw_entry_string_meant_to_be_passed_to_use
}
- Result
- Now filters can be applied across search types, and the specific
field they should be applied on can be configured by each search
type
- The all-MiniLM-L6-v2 is more accurate
- The exact previous model isn't benchmarked but based on the
performance of the closest model to it. Seems like the new model
maybe similar in speed and size
- On very preliminary evaluation of the model, the new model seems
faster, with pretty decent results
- The multi-qa-MiniLM-L6-cos-v1 is more extensively benchmarked[1]
- It has the right mix of model query speed, size and performance on benchmarks
- On hugging face it has way more downloads and likes than the msmarco model[2]
- On very preliminary evaluation of the model
- It doubles the encoding speed of all entries (down from ~8min to 4mins)
- It gave more entries that stay relevant to the query (3/5 vs 1/5 earlier)
[1]: https://www.sbert.net/docs/pretrained_models.html
[2]: https://huggingface.co/sentence-transformers
- Avoids having to click the query input box
- Just open page, type whatever and hit enter to do image search
- For other search types select appropriate type from dropdown
- Use shr to render image response from html in result buffer
Earlier was using org-mode. But rendering HTML with shr seems cleaner
- Use Headings to Add highlights
- Use Random to Force fetch of Image. Similar to what was done for Web interface
- Remove trailing elisp brackets from response
- Show query match scores by image model for each image in results
- Metadata match score were consistently giving higher scores by a
factor of ~3x wrt to image match score. This was resulting in all
results being from the metadata match with query and none from the
image match with query.
- Scaling the metadata match scores down by scaling factor seems to
give more consistently give a blend of results from both image and
metadata matches
Adding a random, unused url param at the end of the img.src string
fixes the issue. As the browser thinks it's a new image and doesn't
use the image data that's already cached because of which it wasn't
even making the fetch call for the image
- Allow viewing image results returned by Semantic Search.
Until now there wasn't any interface within the app to view image
search results. For text results, we at least had the emacs interface
- This should help with debugging issues with image search too
For text the Swagger interface was good enough
- Copy images to accessible directory
- Return URL paths to them to ease access
- This is to be used in the web interface to render image results
directly in browser
- Return image, metadata scores for each image in response as well
This should help get a better sense of image scores along both
XMP metadata and whole image axis
- With \t Last Word in Headings was suffixed by \t and so couldn't be
filtered by
- User interacts with raw entries, so run explicit filters on raw entry
- For semantic search using the filtered entry is cleaner, still
- Fix date_filter date_in_entry within query range check
- Extracted_date_range is in [included_date, excluded_date) format
- But check was checking for date_in_entry <= excluded_date
- Fixed it to do date_in_entry < excluded_date
- Fix removal of date filter from query
- Add tests for date_filter
- Default to looking at dates from past, as most notes are from past
- Look for dates in future for cases where it's obvious query is for
dates in the future but dateparser's parse doesn't parse it at all.
E.g parse('5 months from now') returns nothing
- Setting PREFER_DATES_FROM_FUTURE in this case and passing just
parse('5 months') to dateparser.parse works as expected
Details
--
- The filters to apply are configured for each type in the search controller
- Muliple filters can be applied on the query, entries etc before search
- The asymmetric query method now just applies the passed filters to the
query, entries and embeddings before semantic search is performed
Reason
--
This abstraction will simplify adding other pre-search filters. E.g datetime filter
Details
--
- Move explicit_filters function into separate module under search_filter
- Update signature of explicit filter to take and return query, entries, embeddings
- Use this explicit_filter func from search_filters module in query
Reason
--
Abstraction will simplify adding other pre-search filters. E.g datetime filter
- Issue
- Explicit filtering was earlier being done after search by bi-encoder
but before re-ranking by cross-encoder
- This was limiting the quality of results being returned. As the
bi-encoder returned results which were going to be excluded. So the
burden of improving those limited results post filtering was on the
cross-encoder by re-ranking the remaining results based on query
- Fix
- Given the embeddings corresponding to an entry are at the same index
in their respective lists. We can run the filter for blocked,
required words before the search by the bi-encoder model. And limit
entries, embeddings being considered for the current query
- Result
- Semantic search by the bi-encoder gets to return most relevant
results for the query, knowing that the results aren't going to be
filtered out after. So the cross-encoder shoulders less of the
burden of improving results
- Corollary
- This pre-filtering technique allows us to apply other explicit
filters on entries relevant for the current query
- E.g limit search for entries within date/time specified in query
- Use local variable to pass device to asymmetric.setup method via /reload, /regenerate API
- Set default argument to torch.device('cpu') instead of 'cpu' to be more formal
- The reload API adds the ability to separate out the loading of
embeddings from file without having to restart app or (re-)generate embeddings
- Before this the only way to load model from file was by restarting app
- The other way to reload the model embeddings by regenerating them
was to expensive for larger datasets
- This unlocks at least 1 use-case, where
- we regenerate model via an app instance running on a separate server and
- just reload the generated embeddings on the client device
- This allows us to offload the expensive embedding generation
compute to a background server while letting
- This avoids having to (re-)restart application on client device or
be forced to generate embeddings on the client device itself
- But it requires the model relevant files to be synced to the client device
This can be done with any file syncing application like Syncthing
- We can then call /regenerate on server and /reload client on a
regular schedule to keep our data up to date on semantic search
- This is still clunky but it should be commitable
- General enough that it'll work even when a users notes are not in the home directory
- While solving for the special case where:
- Notes are being processed on a different machine and used on a different machine
- But the notes directory is in the same location relative to home on both the machines
- Use Set for Tags instead of dictionary with empty keys
- No Need to store First Tag separately
- Remove properties methods associated with storing first tag separately
- Simplify extraction of tags string in org_to_jsonl
- Split notes_string creation into multiple f-string in separate line
for code readability
- Now that excluding the times line from the raw body of node,
show it in repr so user can see it for reference
- But the model doesn't need to see it for it's embeddings to be
confused by
- Add links to property drawer
- This ensures results returned by semantic search contain these links
- This allows the user to jump to entry within original file for context
- The ID, file+heading based links are more robust to find relevant
entry in original file than the line no based link,
as edits being done by user to original files between embedding regenerations
Sentence Transformer MSMarco Model isn't date aware
So no use of adding scheduled, deadline dates to model embeddings for consideration
This reverts commit a2a08d1354.
- Introduce prompt for GPT to automatically extract user's search intent
- Expose new search api endpoint to use that to set SearchType being
passed to search API
- Currently meant as an experimental API to gauge usefulness,
extendability. Evaluating for phone or voice use-case
To prompt improve readability:
- Remove newline escape sequence and use actual newline directly
- This avoids one long line of text as prompt and
- Remove escaping of double quotes
- Add search query to top of buffer as Beancount comment
- Remove trailing ) from response
- Separate entries by empty line
- Load beancount-mode in semantic search on ledger buffer
- Fix loading entries from jsonl in extract_entries method
- Only extract Title from jsonl of each entry
This is the only thing written to the jsonl for symmetric ledger
- This fixes the trailing escape seq in loaded entries
- Remove the need for semantic-search.el response reader to do pointless complicated cleanup
- Make symmetric_ledger:extract_entries use beancount_to_jsonl:load_jsonl
Both methods were doing similar work
- Make load_jsonl handle loading entries from both gzip and uncompressed jsonl
Conversation logs structure now has session info too instead of just chat info
Session info will allow loading past conversation summaries as context for AI in new conversations
{
"session": [
{
"summary": <chat_session_summary>,
"session-start": <session_start_index_in_chat_log>,
"session-end": <session_end_index_in_chat_log>
}],
"chat": [
{
"intent": <intent-object>
"trigger-emotion": <emotion-triggered-by-message>
"by": <AI|Human>
"message": <chat_message>
"created": <message_created_date>
}]
}
- Allow conversing with user using GPT's contextually aware, generative capability
- Extract metadata, user intent from user's messages using GPT's general understanding
