mirror of
https://github.com/khoaliber/khoj.git
synced 2026-03-02 13:18:18 +00:00
Use url fragment schema for deep link URIs, borrowing from URL/PDF schemas. E.g file:///path/to/file.txt#line=<line_no>&#page=<page_no> Compute line number during (recursive) org-mode entry chunking. Thoroughly test line number in URI maps to line number of chunk in actual org mode file. This deeplink URI with line number is passed to llm as context to better combine with line range based view file tool. Grep tool already passed matching line number. This change passes line number in URIs of org entries matched by the semantic search tool
2.1 KiB
Vendored
2.1 KiB
Vendored
Khoj
Allow natural language search on user content like notes, images using transformer based models
All data is processed locally. User can interface with khoj app via Emacs, API or Commandline
Dependencies id:123-421-121-12 TAG1 @TAG1_1
- Python3
- Miniconda
Install
git clone https://github.com/khoj-ai/khoj && cd khoj
conda env create -f environment.yml
conda activate khoj
Run
Load ML model, generate embeddings and expose API to query specified org-mode files
python3 main.py --input-files ~/Notes/Schedule.org ~/Notes/Incoming.org --verbose
Use
Khoj via Emacs link to khoj website @EMACS CLIENT_1 KHOJ
Khoj via API
- Query:
GEThttp://localhost:42110/api/search?q="What is the meaning of life" - Update Index:
GEThttp://localhost:42110/api/update - Khoj API Docs
Call Khoj via Python Script Directly
python3 search_types/asymmetric.py \
--compressed-jsonl .notes.jsonl.gz \
--embeddings .notes_embeddings.pt \
--results-count 5 \
--verbose \
--interactive
Acknowledgments
- MiniLM Model for Asymmetric Text Search. See SBert Documentation
- OpenAI CLIP Model for Image Search. See SBert Documentation
- Charles Cave for OrgNode Parser