Files
DocsGPT/docsgpt/vectorstore
arc53-machine 06de211e61 Download an embedding model whose cached snapshot lacks its graph
The chunker caches only a model's tokenizer.json in the embeddings cache.
FastEmbed counts any cached snapshot as the model, so it never downloaded
the ONNX graph and every load failed with NO_SUCHFILE. The loader now
checks the files FastEmbed needs and fetches them first when they are
missing; offline it leaves them for FastEmbed to report.
2026-09-29 12:12:28 +01:00
..
2026-09-28 18:40:49 +04:00
2026-09-28 17:35:16 +04:00
2026-09-28 17:35:16 +04:00
2026-09-28 17:35:16 +04:00
2026-09-28 17:35:16 +04:00