RapidOCR depends on OpenCV which by default requires a bunch of GUI
paramters. This system package dependency set (like libgl1) is flaky
Making the RapidOCR dependency optional should allow khoj to be more
resilient to setup/dependency failures
Trade-off is that OCR for documents may not always be available and
it'll require looking at server logs to find out when this happens
* Add functions to chat with Google's gemini model series
* Gracefully close thread when there's an exception in the gemini llm thread
* Use enums for verifying the chat model option type
* Add a migration to add the gemini chat model type to the db model
* Fix chat model selection verification and math prompt tuning
* Fix extract questions method with gemini. Enforce json response in extract questions.
* Add standard stop sequence for Gemini chat response generation
---------
Co-authored-by: sabaimran <narmiabas@gmail.com>
Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>
This is a more robust way to extract json output requested from
gemma-2 (2B, 9B) models which tend to return json in md codeblocks.
Other models should remain unaffected by this change.
Also removed request to not wrap json in codeblocks from prompts. As
code is doing the unwrapping automatically now, when present
- Pass system message as the first user chat message as Gemma 2
doesn't support system messages
- Use gemma-2 chat format
- Pass chat model name to generic, extract questions chat actors
Used to figure out chat template to use for model
For generic chat actor argument was anyway available but not being
passed, which is confusing
- Deprecate khoj-assistant pypi package. Use more accurate and
succinct pypi project name, khoj
- Update references to sye khoj pypi package in docs and code instead
of the legacy khoj-assistant pypi package
- Update pypi workflow to publish to both khoj, khoj-assistant for now
- Update stale python 3.9 support mentioned in our pyproject. Can't
support python 3.9 as depend on latest django which support >=3.10
- Because we're using a FastAPI api framework with a Django ORM, we're running into some interesting conditions around connection pooling and clean-up. We're ending up with a large pile-up of open, stale connections to the DB recurringly when the server has been running for a while. To mitigate this problem, given starlette and django run in different python threads, add a middleware that will go and call the connection clean up method in each of the threads.
* Add support for chatting with Anthropic's suite of models
- Had to use a custom class because there was enough nuance with how the anthropic SDK works that it would be better to simply separate out the logic. The extract questions flow needed modification of the system prompt in order to work as intended with the haiku model
- Render crontime string in natural language in message & settings UI
- Show more fields in tasks web config UI
- Add link to the tasks settings page in task scheduled chat response
- Improve task variables names
Rename executing_query to query_to_run. scheduling_query to
scheduling_request
- Pass timezone string from ipapi to khoj via clients
- Pass this data from web, desktop and obsidian clients to server
- Use user tz to render next run time of scheduled task in user tz
- 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
- 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
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
### 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
* 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
- 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)
- RapidOCR for indexing image PDFs doesn't currently support python 3.12.
It's an optional dependency anyway, so only install it if python < 3.12
- Run unit tests with python version 3.12 as well
Resolves#522
- 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
### 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
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).
