Enhancement(beta): move filename/storage path/ASN to node metadata

Same treatment as title/tags/correspondent in #12944: excluded from
the embedded text, visible to the LLM via metadata prepend. Changes
embedded text for every document, so it ships inside the sqlite-vec
transition, whose forced rebuild re-embeds everything anyway.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/paperless_ai/embedding.py

@@ -112,15 +112,11 @@ def _normalize_llm_index_text(text: str) -> str:
 
 
 def build_llm_index_text(doc: Document) -> str:
-    # TODO: Filename, Storage Path, and Archive Serial Number are short structured
-    # values that could move to node.metadata (excluded from embeddings, visible to
-    # LLM via metadata prepend) — same pattern as title/tags/correspondent. Notes
-    # and Custom Fields should stay here: Notes can be long free text, Custom Fields
-    # are dynamic in count and best kept in the embedding.
+    # Short structured fields (filename, storage path, ASN, title, tags, ...) live
+    # in node.metadata: excluded from embeddings, shown to the LLM via metadata
+    # prepend. Notes and Custom Fields stay in the body: Notes can be long free
+    # text, Custom Fields are dynamic in count and best kept in the embedding.
     lines = [
-        f"Filename: {doc.filename}",
-        f"Storage Path: {doc.storage_path.name if doc.storage_path else ''}",
-        f"Archive Serial Number: {doc.archive_serial_number or ''}",
         f"Notes: {','.join([str(c.note) for c in Note.objects.filter(document=doc)])}",
     ]
 

src/paperless_ai/indexing.py

@@ -130,6 +130,9 @@ def build_document_node(
         "document_type": document.document_type.name
         if document.document_type
         else None,
+        "filename": document.filename,
+        "storage_path": document.storage_path.name if document.storage_path else None,
+        "archive_serial_number": document.archive_serial_number,
         "created": document.created.isoformat() if document.created else None,
         "added": document.added.isoformat() if document.added else None,
         "modified": document.modified.isoformat(),

src/paperless_ai/tests/test_ai_indexing.py

@@ -33,6 +33,16 @@ def test_build_document_node(real_document: Document) -> None:
     nodes = indexing.build_document_node(real_document)
     assert len(nodes) > 0
     assert nodes[0].metadata["document_id"] == str(real_document.id)
+    assert nodes[0].metadata["filename"] == real_document.filename
+    assert nodes[0].metadata["storage_path"] == (
+        real_document.storage_path.name if real_document.storage_path else None
+    )
+    assert (
+        nodes[0].metadata["archive_serial_number"]
+        == real_document.archive_serial_number
+    )
+    assert "filename" in nodes[0].excluded_embed_metadata_keys
+    assert "filename" not in nodes[0].excluded_llm_metadata_keys
 
 
 @pytest.mark.django_db

src/paperless_ai/tests/test_embedding.py

@@ -224,15 +224,17 @@ def test_build_llm_index_text(mock_document):
 
         result = build_llm_index_text(mock_document)
 
-        # Structured fields live in node.metadata for LLM context — not body text
+        # Structured fields live in node.metadata for LLM context -- not body text
         assert "Title: Test Title" not in result
         assert "Created: 2023-01-01" not in result
         assert "Tags: Tag1, Tag2" not in result
         assert "Document Type: Invoice" not in result
         assert "Correspondent: Test Correspondent" not in result
+        assert "Filename:" not in result
+        assert "Storage Path:" not in result
+        assert "Archive Serial Number:" not in result
 
         # Fields without a metadata equivalent stay in body text
-        assert "Filename: test_file.pdf" in result
         assert "Notes: Note1,Note2" in result
         assert "Content:\n\nThis is the document content." in result
         assert "Custom Field - Field1: Value1\nCustom Field - Field2: Value2" in result