@jarkkojs/readseek 0.4.21 → 0.4.23

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 +9 -7
  2. package/package.json +4 -4
package/README.md CHANGED
@@ -50,7 +50,7 @@ readseek identify src/main.rs:42 --column 8 | readseek def --from-identify src -
50
50
  ## Images
51
51
 
52
52
  `detect` reports format, dimensions, and animation status for images. Add a vision
53
- flag to analyze image contents with the embedded Florence-2 model:
53
+ flag to analyze image contents with the Qwen2.5-VL vision model:
54
54
 
55
55
  ```sh
56
56
  readseek detect screenshot.png --transcribe # text + per-region bounding quads
@@ -58,9 +58,11 @@ readseek detect photo.jpg --caption # detailed natural-language caption
58
58
  readseek detect photo.jpg --objects # object labels + bounding boxes
59
59
  ```
60
60
 
61
- The flags can be combined; the model loads once per invocation. The model is
62
- embedded in the binary, so no download or network access is required at runtime.
63
- Inference is CPU-only and takes a few seconds per image.
61
+ The flags can be combined; the model loads once per invocation. The model files
62
+ (~1.8 GB GGUF + ~1.3 GB multimodal projection) are downloaded lazily into the
63
+ user cache directory on first vision use and reused on subsequent runs; a
64
+ progress bar is shown while downloading when stdout is an interactive TTY.
65
+ Inference is CPU-only and takes a few to tens of seconds per image.
64
66
 
65
67
  ## Cache
66
68
 
@@ -86,6 +88,6 @@ native binaries are licensed under `LGPL-2.1-or-later`. Corresponding source for
86
88
  each published native binary is available from the GitHub repository tag that
87
89
  matches the package version.
88
90
 
89
- The binary embeds the Florence-2 model (`onnx-community/Florence-2-base-ft`, a
90
- re-export of `microsoft/Florence-2-base-ft`), which is licensed under `MIT`. See
91
- `LICENSE-Florence-2` for its license text.
91
+ readseek downloads the Qwen2.5-VL vision model (`unsloth/Qwen2.5-VL-3B-Instruct-GGUF`,
92
+ a re-export of `Qwen/Qwen2.5-VL-3B-Instruct`) into the user cache directory on
93
+ first use. It is licensed under `Apache-2.0`.
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@jarkkojs/readseek",
3
- "version": "0.4.21",
3
+ "version": "0.4.23",
4
4
  "description": "A structural read command",
5
5
  "license": "Apache-2.0 AND LGPL-2.1-or-later",
6
6
  "homepage": "https://github.com/jarkkojs/readseek#readme",
@@ -21,9 +21,9 @@
21
21
  "LICENSE-LGPL-2.1"
22
22
  ],
23
23
  "optionalDependencies": {
24
- "@jarkkojs/readseek-darwin-arm64": "0.4.21",
25
- "@jarkkojs/readseek-linux-x64": "0.4.21",
26
- "@jarkkojs/readseek-win32-x64": "0.4.21"
24
+ "@jarkkojs/readseek-darwin-arm64": "0.4.23",
25
+ "@jarkkojs/readseek-linux-x64": "0.4.23",
26
+ "@jarkkojs/readseek-win32-x64": "0.4.23"
27
27
  },
28
28
  "publishConfig": {
29
29
  "access": "public"