@gmickel/gno 0.39.0 → 0.39.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (2) hide show
  1. package/README.md +14 -1
  2. package/package.json +1 -1
package/README.md CHANGED
@@ -87,7 +87,7 @@ gno daemon
87
87
 
88
88
  ## What's New
89
89
 
90
- > Latest release: [v0.37.0](./CHANGELOG.md#0370---2026-04-06)
90
+ > Latest release: [v0.39.1](./CHANGELOG.md#0391---2026-04-06)
91
91
  > Full release history: [CHANGELOG.md](./CHANGELOG.md)
92
92
 
93
93
  - **Retrieval Quality Upgrade**: stronger BM25 lexical handling, code-aware chunking, terminal result hyperlinks, and per-collection model overrides
@@ -95,6 +95,19 @@ gno daemon
95
95
  - **Default Embed Model**: built-in presets now use `Qwen3-Embedding-0.6B-GGUF` after it beat `bge-m3` on both code and multilingual prose benchmark lanes
96
96
  - **Regression Fixes**: tightened phrase/negation/hyphen/underscore BM25 behavior, cleaned non-TTY hyperlink output, improved `gno doctor` chunking visibility, and fixed the embedding autoresearch harness
97
97
 
98
+ ### Upgrading Existing Collections
99
+
100
+ If you already had collections indexed before the default embed-model switch to
101
+ `Qwen3-Embedding-0.6B-GGUF`, run:
102
+
103
+ ```bash
104
+ gno models pull --embed
105
+ gno embed
106
+ ```
107
+
108
+ That regenerates embeddings for the new default model. Old vectors are kept
109
+ until you explicitly clear stale embeddings.
110
+
98
111
  ### Fine-Tuned Model Quick Use
99
112
 
100
113
  ```yaml
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@gmickel/gno",
3
- "version": "0.39.0",
3
+ "version": "0.39.1",
4
4
  "description": "Local semantic search for your documents. Index Markdown, PDF, and Office files with hybrid BM25 + vector search.",
5
5
  "keywords": [
6
6
  "embeddings",