Uses longest file path match to find markdown file in vault
corresponding to file of search result returned by Khoj
Allow jumping to search result from khoj plugin modal on Android too
### Details
- 1c813a6 Convert *Results Count* setting to `Slider` from `Text` in plugin settings pane
- 4e1abd1 Disable `Update` button in plugin settings while indexing vault
- 513c86c Set index file paths relative to current or default path on Khoj backend
- 4407e23 Only index current vault on Khoj. Remove `ObsidianVaultPath` setting from plugin
- 86a1e43 Return HTTP Exception on */api/update* API call failure
- 5af2b68 Update plugin notifications for errors. Remove notification for success
Previous mechanism of manually triggering getSuggestions,
renderSuggestions flow was corrupting traversing and opening
reranked search results in KhojModal
Emulate event that would anyway trigger the get & render of results in
modal. This lets obsidian core handle the flow without digging too
deep into obsidian cores handling of the flow. Lowers the chance of
breakage
We need the index file paths to make sense on the khoj backend server
Having path of index on backend relative to current vault directory
on frontend ignores the fact that the frontend maybe on a different
machine than the khoj backend server
Using unique index name per vault allows switching vaults without
overwriting indices of other vaults created on khoj backend when khoj
obsidian plugin is loaded on opening a different vault
- Overview
Limits using Khoj with a single vault at a time. This is
automatically configured to the most recently opened vault.
Once directory filters are supported on backend, the plugin will be
updated to index multiple vault but search only current vault from
current vaults khoj obsidian plugin
- Code Details
- Remove setting to configure Vault directory from Khoj Obsidian plugin
- Automatically configure Khoj to index only current Vault.
- Overwrites any previous vaults that were intended to be indexed by
Khoj backend
- Force update of index after configuring vault
- Why
It's not helpful for now and can lead to more problems, confusion.
Once directory filters
- Previously the backend was just throwing backend error.
The frontend calling the /update API wasn't getting notified
- Now the frontend can react appropriately and make the issue
visible to the user
- Only show notification on plugin load and failure.
- In settings page, set current backend status at top of pane instead
of showing notification
Notices bubbles cluttered the UI while typing updates to settings
- Show notification once index updated via settings pane button click
There was no notification on index updated, which usually takes time
on the backend
### Search Modal Enhancements
- b52cd85 Allow Reranking results using Keybinding from Khoj Search Modal
- 580f4ac Add hints to Modal for available Keybindings
- da49ea2 Add placeholder text to modal in Khoj Obsidian plugin
### Handle Failure to Connect to Khoj Backend
Load plugin but warn on failure to connect to Khoj backend
- f046a95 Track connectedToBackend as a setting. Use it across obsidian plugin to:
- Disable command if not connected to backend
- Trigger warning notice on clicking Khoj ribbon if not connected to backend
- Show warning at top of Khoj Obsidian plugin settings pane
- 768e874 Load obsidian plugin even if fail to connect to backend but show warning
- Allows user to see reason for failure to try resolve it
- Allows user to update Khoj URL settings to point to URL of Khoj server
### Miscellaneous
- 7991ab7 Add button in Obsidian plugin settings to force re-indexing your vault
- Useful if index gets corrupted
- Display warning at top of khoj obsidian plugin settings
- Make search command available only if connected to backend
- Show warning notice on clicking khoj search ribbon button
- Call saveData after configureKhojBackend to ensure
connnectedToBackend setting saved after being (potentially) updated
in configureKhojBackend function
- Previously the plugin would not load if cannot connect to Khoj backend
- Silently failing to load with no reason provided is not helpful
- Load plugin to allow user to fix the Khoj URL in their plugin setting
- Show reason for khoj plugin not working. More helpful than failing silently
Use the timer context manager in all places where code was being timed
- Benefits
- Deduplicate timing code scattered across codebase.
- Provides single place to manage perf timing code
- Use consistent timing log patterns
The query method had become too big.
Extract out filter, score, sort and deduplicate logic used by
text_search.query into separate methods.
This should improve readabilty of code.
- Changes
- Fix method signatures of BaseFilter subclasses.
Else typing information isn't translating to them
- Explicitly pass `entries: list[Entry]' as arg to `load' method
- Fix type of `raw_entries' arg to `apply' method
to list[Entry] from list[str]
- Rename `raw_entries' arg to `apply' method to `entries'
- Fix `raw_query' arg used in `apply' method of subclasses to `query'
- Set type of entries, corpus_embeddings in TextSearchModel
- Verification
Ran `mypy --config-file .mypy.ini src' to verify typing
- `torch.Tensor' is apparently a legacy tensor constructor
- Using that to create tensor on MPS devices throws error:
RuntimeError: legacy constructor expects device type: cpu but device type: mps was passed
- `torch.tensor' can handle creating tensors on Mac GPU (MPS) fine
This is unlike the more general chat API that combines summarization
of top search result and conversing with the OpenAI model
This should give faster summary results. As no intent categorization
API call required
- Use latest davinci model for tests
- Wrap prompt in triple quotes to improve legibilty
- `understand' method returns dictionary instead of string. Fix its test
- Fix prompt for new model to pass `chat_with_history' test
- Default to using `text-davinci-003' if conversation model not
explicitly configured by user. Stop using the older `davinci' and
`davinci-instruct' models
- Use `model' instead of `engine' as parameter.
Usage of `engine' parameter in OpenAI API is deprecated
- 2fe37a0 Make type of encoder to use for embeddings configurable via `khoj.yml'
- Previously `encoder_type' was set in the setup code of search_type
- All *encoders* were of type `SentenceTransformer'
- All *cross_encoders* were of type `CrossEncoder'
- Now the `encoder_type' can be configured via the new `encoder_type' field
in `TextSearchConfig' under `search_type` in `khoj.yml'
- All the specified `encoder-type' class needs is an `encode' method
that takes entries and returns embedding vectors
- 826f9dc Drop long words from compiled entries to be within max token limit of models
Long words (>500 characters) provide less useful context to models.
Dropping very long words allow models to create better embeddings by
passing more of the useful context from the entry to the model
- c0ae8ee Allow using OpenAI models for search in Khoj
To use OpenAI models for search in Khoj, in `~/.khoj/khoj.yml'
1. Set `encoder' to name of an OpenAI model. E.g *text-embedding-ada-002*
2. Set `encoder-type' to *src.utils.models.OpenAI*
3. Set `model-directory` to *null*, as this is an online model and
cannot be stored on the file system
- Init processor before search to instantiate `openai_api_key'
from `khoj.yml'. The key is used to configure search with openai models
- To use OpenAI models for search in Khoj
- Set `encoder' to name of an OpenAI model. E.g text-embedding-ada-002
- Set `encoder-type' in `khoj.yml' to `src.utils.models.OpenAI'
- Set `model-directory' to `null', as online model cannot be stored on disk
Long words (>500 characters) provide less useful context to models.
Dropping very long words allow models to create better embeddings by
passing more of the useful context from the entry to the model
- Previously `model_type' was set in the setup of each `search_type'
- All encoders were of type `SentenceTransformer'
- All cross_encoders were of type `CrossEncoder'
- Now `encoder-type' can be configured via the new `encoder_type' field
in `TextSearchConfig' under `search-type` in `khoj.yml`.
- All the specified `encoder-type' class needs is an `encode' method
that takes entries and returns embedding vectors
- Ensure all tensors are on MPS device before doing operations across them
- Background
- GPU is used by default for Khoj on MacOS now
- Needed PyTorch > 1.13.0 on Macs to use GPU, which we do now
- MPS should speed up search and indexing on MacOS
