Lars e86e9f2313 Implement backward propagation of section_type in chunking parser
- Added a new function `_propagate_section_type_backwards` to ensure that the section_type is correctly assigned to all blocks within a heading section, even if the [!section] callout appears later in the text.
- Updated the `parse_blocks` function to call this new method, enhancing the accuracy of section-type assignments.
- Modified chunking strategies to reflect the changes in section-type handling, simplifying logic related to section-type transitions.
- Expanded unit tests to validate the backward propagation of section_type, ensuring comprehensive coverage of the new functionality.
2026-01-25 18:21:17 +01:00
2025-12-07 15:49:44 +01:00
2025-12-13 06:48:13 +01:00
2025-12-23 15:57:50 +01:00

mindnet API (bundle)

This bundle provides a minimal FastAPI app for embeddings and Qdrant upserts/queries plus a Markdown importer.

Quick start

python3 -m venv .venv && source .venv/bin/activate
pip install -r requirements.txt

# Environment (adjust as needed)
export QDRANT_URL=http://127.0.0.1:6333
export MINDNET_PREFIX=mindnet
export MINDNET_MODEL=sentence-transformers/all-MiniLM-L6-v2

# Run API
uvicorn app.main:app --host 0.0.0.0 --port 8001 --workers 1

# (optional) Ensure collections exist (or use setup_mindnet_collections.py you already have)
# python3 scripts/setup_mindnet_collections.py --qdrant-url $QDRANT_URL --prefix $MINDNET_PREFIX --dim 384 --distance Cosine

# Import some notes
python3 scripts/import_markdown.py --vault /path/to/Obsidian

Endpoints

  • POST /embed → { "texts": [...] } → 384-d vectors
  • POST /qdrant/upsert_note
  • POST /qdrant/upsert_chunk
  • POST /qdrant/upsert_edge
  • POST /qdrant/query → semantic search over chunks with optional filters

See scripts/quick_test.sh for a runnable example.

Anmerkung: Diese Datei ist veraltet und muss auf Stand 2.6.0 gebracht werden

S
Description
No description provided
Readme
7.8 MiB
0 Stars 1 Watchers 0 Forks
Languages
Python 98.9%
Shell 0.9%
Dockerfile 0.2%