60 Commits

Author SHA1 Message Date
Marius Ailinca 0bfc53763e fix: clean up embedder imports and add memo key test coverage
- Replace `import typing` + `typing.TYPE_CHECKING` with direct `from typing import TYPE_CHECKING`
- Add `# type: ignore[assignment]` on model.encode() call with a per-file mypy override to suppress warn_unused_ignores (SentenceTransformer stubs not available)
- Add two missing TestLocalEmbedderMemoKey tests: trust_remote_code and normalize_embeddings variants

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-25 00:38:10 +02:00
Marius Ailinca 56a048d4c9 feat: add LocalEmbedder with device and trust_remote_code support
Implements a custom LocalEmbedder class wrapping sentence_transformers.SentenceTransformer
with explicit device= and trust_remote_code= args, required for Jina GPU models that
the built-in SentenceTransformerEmbedder does not support. Includes thread-safe lazy
loading, pickle-safe __getstate__/__setstate__, and CocoIndex memo key support.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-25 00:31:04 +02:00
Marius Ailinca f74bce8909 fix: restore .cocoindex_code discovery priority and clean up test isolation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-25 00:23:03 +02:00
Marius Ailinca 6459fc6136 feat: add device auto-detection and trust_remote_code to Config
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-25 00:05:21 +02:00
Jiangzhou He d5a3a86717 fix: use session level loop for e2e tests 2026-02-07 13:34:26 -08:00
Jiangzhou He 9156a9e95e upgrade: to latest cocoindex 2026-02-06 23:27:14 -08:00
Jiangzhou He 1767c32b15 feat: make chunk processing parallel 2026-01-31 22:51:07 -08:00
Jiangzhou He 5b792cc8fa feat: simplify tests 2026-01-31 22:35:11 -08:00
Jiangzhou He 007dd4ad45 feat: trigger index refresh more automatically 2026-01-31 21:10:45 -08:00
Jiangzhou He 7c1afca7b1 feat: initial version 2026-01-31 13:35:34 -08:00