feat: US-013 - Self-host ONNX embedding model

Browse Source

Download all-MiniLM-L6-v2 model files to public/models/ and configure
@xenova/transformers to load from local path instead of Hugging Face CDN.
Eliminates external dependency for semantic search embedding model.

...

This commit is contained in:

Andy Charlwood

2026-02-15 20:59:03 +00:00

parent 9e9dd1ae4b

commit 667e5b249c

8 changed files with 30785 additions and 4 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

public/models/Xenova/all-MiniLM-L6-v2/tokenizer.json

+30686

File diff suppressed because it is too large Load Diff