diff --git a/scripts/encoding.py b/scripts/encoding.py
index 1c0c7ff..3e7092c 100644
--- a/scripts/encoding.py
+++ b/scripts/encoding.py
@@ -25,6 +25,30 @@ DEFAULT_CHUNK_SIZE = 500
 DEFAULT_CHUNK_OVERLAP = 50
 
 
+def _docx_cell_paragraphs(cell):
+    yield from (p for p in cell.paragraphs if p.text.strip())
+    for nested in cell.tables:
+        for row in nested.rows:
+            for c in row.cells:
+                yield from _docx_cell_paragraphs(c)
+
+
+def _pptx_shape_text(shape):
+    from pptx.enum.shapes import MSO_SHAPE_TYPE
+    parts = []
+    if shape.shape_type == MSO_SHAPE_TYPE.GROUP:
+        for sub in shape.shapes:
+            parts.extend(_pptx_shape_text(sub))
+        return parts
+    if hasattr(shape, "text") and shape.text.strip():
+        parts.append(shape.text)
+    if getattr(shape, "has_table", False):
+        for cell in shape.table.iter_cells():
+            if cell.text.strip():
+                parts.append(cell.text)
+    return parts
+
+
 def extract_text(filepath: Path) -> str:
     """Return the text of a supported file. Returns "" on any failure or
     unsupported extension. Does not write to ingest_failures — caller decides."""
@@ -32,7 +56,21 @@ def extract_text(filepath: Path) -> str:
     try:
         if suffix == ".docx":
             doc = DocxDocument(filepath)
-            return "\n".join(p.text for p in doc.paragraphs if p.text.strip())
+            parts = [p.text for p in doc.paragraphs if p.text.strip()]
+            for tbl in doc.tables:
+                for row in tbl.rows:
+                    for cell in row.cells:
+                        parts.extend(p.text for p in _docx_cell_paragraphs(cell))
+            for section in doc.sections:
+                parts.extend(p.text for p in section.header.paragraphs if p.text.strip())
+                parts.extend(p.text for p in section.footer.paragraphs if p.text.strip())
+            from docx.oxml.ns import qn
+            for txbx in doc.element.body.findall(".//" + qn("w:txbxContent")):
+                for p in txbx.findall(".//" + qn("w:p")):
+                    text = "".join(t.text or "" for t in p.findall(".//" + qn("w:t")))
+                    if text.strip():
+                        parts.append(text)
+            return "\n".join(parts)
         elif suffix == ".pdf":
             reader = PdfReader(filepath)
             return "".join(
@@ -41,11 +79,15 @@ def extract_text(filepath: Path) -> str:
             )
         elif suffix == ".pptx":
             prs = Presentation(filepath)
-            return "\n".join(
-                shape.text for slide in prs.slides
-                for shape in slide.shapes
-                if hasattr(shape, "text") and shape.text.strip()
-            )
+            parts = []
+            for slide in prs.slides:
+                for shape in slide.shapes:
+                    parts.extend(_pptx_shape_text(shape))
+                if slide.has_notes_slide:
+                    notes = slide.notes_slide.notes_text_frame.text
+                    if notes.strip():
+                        parts.append(notes)
+            return "\n".join(parts)
         elif suffix in {".txt", ".md"}:
             return filepath.read_text(encoding="utf-8", errors="ignore")
     except Exception as e: