added scaffold struct for the prj

kg_ocr/__init__.py

@@ -0,0 +1,4 @@
+from .ocr import get_screenshots, extract_text
+from .embeddings import create_and_index, query_embedding
+
+__all__ = ["get_screenshots", "extract_text", "create_and_index", "query_embedding"]

kg_ocr/cli/build_graph.py

@@ -0,0 +1,3 @@
+# to do
+
+# add entrypoint to setuppy

kg_ocr/cli/export_graph.py

@@ -0,0 +1 @@
+# to do

kg_ocr/cli/process_screenshots.py

@@ -0,0 +1 @@
+# to do

kg_ocr/embeddings/__init__.py

@@ -0,0 +1,3 @@
+from .indexer import create_and_index, query_embedding
+
+__all__ = ["create_and_index", "query_embedding"]

kg_ocr/embeddings/config_loader.py

@@ -0,0 +1 @@
+# in future prefer a config, especially for graph traversal

kg_ocr/embeddings/indexer.py

@@ -0,0 +1,23 @@
+from txtai.embeddings import Embeddings
+
+
+def create_and_index(
+    data: list[str], model: str = "sentence-transformers/all-MiniLM-L6-v2"
+) -> Embeddings:
+    """Create and index embeddings from text."""
+    embeddings = Embeddings({
+        "path": model,
+        "content": True,
+        "hybrid": True,
+        "scoring": "bm25",
+    })
+    embeddings.index(data)
+    return embeddings
+
+
+def query_embedding(
+    embeddings: Embeddings, query: str, limit: int = 100
+) -> list[str]:
+    """Search embeddings and return matching texts."""
+    results = embeddings.search(query, limit)
+    return [r["text"] for r in results]

kg_ocr/graph/analyzer.py

@@ -0,0 +1 @@
+# also anomaly detection here

kg_ocr/ocr/__init__.py

@@ -0,0 +1,4 @@
+from .extractor import get_screenshots
+from .batch_processor import extract_text
+
+__all__ = ["get_screenshots", "extract_text"]

kg_ocr/ocr/batch_processor.py

@@ -0,0 +1,7 @@
+from PIL import Image
+import pytesseract
+
+
+def extract_text(images: list[str]) -> list[str]:
+    """OCR a list of image paths into text."""
+    return [pytesseract.image_to_string(Image.open(img)) for img in images]

kg_ocr/ocr/constants.py

@@ -0,0 +1,15 @@
+from pathlib import Path
+
+import platform
+
+def_paths = {
+    "Darwin": Path.home() / "Desktop",
+    "Windows": Path.home() / "Pictures" / "Screenshots",
+    "Linux": Path.home() / "Pictures",
+}
+
+sc_pathpatterns = {
+    "Darwin": ["SCR*.png", "Screenshot*.png"],
+    "Windows": ["Screenshot*.png"],
+    "Linux": ["Screenshot*.png", "scrot*.png", "screenshot*.png"],
+}

kg_ocr/ocr/extractor.py

@@ -0,0 +1,17 @@
+import platform
+from pathlib import Path
+from typing import Optional
+
+from .constants import def_paths, sc_pathpatterns
+
+
+def get_screenshots(path: Optional[str | Path] = None) -> list[str]:
+    """Find screenshot files for the current OS."""
+    if path is None:
+        path = def_paths.get(platform.system(), Path.home())
+    path = Path(path)
+    patterns = sc_pathpatterns.get(platform.system(), ["SCR*.png"])
+    results = []
+    for pattern in patterns:
+        results.extend(str(f.absolute()) for f in path.glob(pattern))
+    return sorted(set(results))