From 2f5d199fefd573a8c8cd49ff9a8d84c9e609584d Mon Sep 17 00:00:00 2001
From: stumpylog <797416+stumpylog@users.noreply.github.com>
Date: Tue, 2 Jun 2026 15:11:21 -0700
Subject: [PATCH] feat(ai): tie LlamaDocument id to the paperless document id

Set id_=str(document.id) on the LlamaDocument constructor in
build_document_node so that every chunk node's ref_doc_id equals the
paperless document pk, enabling the LanceDB adapter's delete(str(doc.id))
and doc_id column to work correctly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 src/paperless_ai/indexing.py               |  1 +
 src/paperless_ai/tests/test_ai_indexing.py | 12 ++++++++++++
 2 files changed, 13 insertions(+)

diff --git a/src/paperless_ai/indexing.py b/src/paperless_ai/indexing.py
index 7ec1fdba3..cf68ebc53 100644
--- a/src/paperless_ai/indexing.py
+++ b/src/paperless_ai/indexing.py
@@ -142,6 +142,7 @@ def build_document_node(
     # the token count and exceed embedding models with small context windows
     # (e.g. nomic-embed-text via Ollama defaults to num_ctx=2048).
     doc = LlamaDocument(
+        id_=str(document.id),
         text=text,
         metadata=metadata,
         excluded_embed_metadata_keys=list(metadata.keys()),
diff --git a/src/paperless_ai/tests/test_ai_indexing.py b/src/paperless_ai/tests/test_ai_indexing.py
index 339d75ead..c1ddbb7d2 100644
--- a/src/paperless_ai/tests/test_ai_indexing.py
+++ b/src/paperless_ai/tests/test_ai_indexing.py
@@ -66,6 +66,18 @@ def test_build_document_node(real_document) -> None:
     assert nodes[0].metadata["document_id"] == str(real_document.id)
 
 
+@pytest.mark.django_db
+def test_build_document_node_sets_ref_doc_id(real_document: Document) -> None:
+    """Every node produced by build_document_node must carry the paperless document id
+    as its ref_doc_id so that the LanceDB adapter's delete(str(doc.id)) works correctly."""
+    nodes = indexing.build_document_node(real_document)
+    assert len(nodes) > 0, "Expected at least one node"
+    for node in nodes:
+        assert node.ref_doc_id == str(real_document.id), (
+            f"Expected ref_doc_id={real_document.id!r}, got {node.ref_doc_id!r}"
+        )
+
+
 @pytest.mark.django_db
 def test_build_document_node_excludes_metadata_from_embedding(real_document) -> None:
     """Metadata keys must not be prepended to the embedding text.