classifyre-cli 0.4.16__tar.gz → 0.4.18__tar.gz

{classifyre_cli-0.4.16 → classifyre_cli-0.4.18}/.turbo/turbo-build.log

@@ -1,3 +1,3 @@
 $ uv sync
-Resolved 255 packages in 216ms
+Resolved 256 packages in 167ms
 Checked 50 packages in 1ms

{classifyre_cli-0.4.16 → classifyre_cli-0.4.18}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: classifyre-cli
-Version: 0.4.16
+Version: 0.4.18
 Summary: Classifyre CLI — scan and classify unstructured data sources
 License: MIT
 Keywords: data,ingestion,metadata,pii,secrets,unstructured

{classifyre_cli-0.4.16 → classifyre_cli-0.4.18}/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@classifyre/cli",
-  "version": "0.4.16",
+  "version": "0.4.18",
   "private": true,
   "scripts": {
     "build": "uv sync",

{classifyre_cli-0.4.16 → classifyre_cli-0.4.18}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "classifyre-cli"
-version = "0.4.16"
+version = "0.4.18"
 description = "Classifyre CLI — scan and classify unstructured data sources"
 readme = "README.md"
 requires-python = ">=3.12"
@@ -100,6 +100,9 @@ custom = [
     "scikit-learn>=1.7.2",
     "gliner2>=1.3.1",
     "sentence-transformers>=5.5.0",
+    # Direct declaration so the [tool.uv.sources] cpu-index pin applies (timm
+    # pulls torchvision transitively; see the ocr group note).
+    "torchvision>=0.27.0",
 ]
 regex = [
     "google-re2>=1.1",
@@ -135,6 +138,12 @@ ocr = [
     { include-group = "file-processing" },
     "docling>=2.94.0",
     "rapidocr-onnxruntime>=1.4.0",
+    # torchvision is a transitive dep of docling-ibm-models, but [tool.uv.sources]
+    # index pins only apply to dependencies declared directly in this project.
+    # Without this entry uv resolves the CUDA-built PyPI wheel, which fails to
+    # import against torch+cpu (surfaces as transformers "Could not import
+    # module 'AutoProcessor'").
+    "torchvision>=0.27.0",
 ]
 postgresql = [
     "psycopg2-binary>=2.9.12,<3.0.0",

{classifyre_cli-0.4.16 → classifyre_cli-0.4.18}/src/main.py

@@ -379,9 +379,13 @@ async def run_command_async(args: argparse.Namespace, recipe: dict[str, Any]) ->
                             edges = await source.collect_relationships()
                             if edges:
                                 await sink.emit_edges(edges)
-                                logger.info("Emitted %d source-derived relationship edges", len(edges))
+                                logger.info(
+                                    "Emitted %d source-derived relationship edges", len(edges)
+                                )
                         except Exception as rel_error:
-                            logger.warning("Relationship emission failed (non-fatal): %s", rel_error)
+                            logger.warning(
+                                "Relationship emission failed (non-fatal): %s", rel_error
+                            )
                 except Exception as extraction_error:
                     if _is_timeout_error(extraction_error):
                         logger.warning(

{classifyre_cli-0.4.16 → classifyre_cli-0.4.18}/src/sources/base.py

@@ -317,7 +317,6 @@ class BaseSource(ABC):
         """
         return normalize_http_url(link)
 
-
     async def collect_relationships(self) -> list[IngestEdge]:
         """Return source-derived relationship edges for the investigation graph.