From c20f357697b4495d23b155723eaa45aa39df018d Mon Sep 17 00:00:00 2001
From: stumpylog <797416+stumpylog@users.noreply.github.com>
Date: Tue, 8 Sep 2026 11:39:34 -0700
Subject: [PATCH] Deletes _node_document_ids

---
 src/paperless_ai/indexing.py               | 17 -----------------
 src/paperless_ai/tests/test_ai_indexing.py |  8 +++-----
 2 files changed, 3 insertions(+), 22 deletions(-)

diff --git a/src/paperless_ai/indexing.py b/src/paperless_ai/indexing.py
index af20669e5..07c20b526 100644
--- a/src/paperless_ai/indexing.py
+++ b/src/paperless_ai/indexing.py
@@ -721,20 +721,3 @@ def retrieve_similar_nodes(
             continue
         filtered.append(node)
     return filtered
-
-
-def _node_document_ids(nodes: list["NodeWithScore"]) -> list[int]:
-    document_ids: list[int] = []
-    for node in nodes:
-        document_id = node.metadata.get("document_id")
-        if document_id is None:  # pragma: no cover
-            # See the matching guard in retrieve_similar_nodes() above.
-            continue
-        try:
-            document_ids.append(int(document_id))
-        except ValueError:  # pragma: no cover
-            logger.warning(
-                "Skipping LLM index result with invalid document_id %r.",
-                document_id,
-            )
-    return document_ids
diff --git a/src/paperless_ai/tests/test_ai_indexing.py b/src/paperless_ai/tests/test_ai_indexing.py
index 659eaa2f5..3866e6345 100644
--- a/src/paperless_ai/tests/test_ai_indexing.py
+++ b/src/paperless_ai/tests/test_ai_indexing.py
@@ -1188,9 +1188,7 @@ class TestRetrieveSimilarNodesAgainstRealIndex:
 
         nodes = indexing.retrieve_similar_nodes(a, document_ids=[b.id])
 
-        assert all(
-            document_id == b.id for document_id in indexing._node_document_ids(nodes)
-        )
+        assert all(int(node.metadata["document_id"]) == b.id for node in nodes)
 
     def test_excludes_self(
         self,
@@ -1212,7 +1210,7 @@ class TestRetrieveSimilarNodesAgainstRealIndex:
 
         nodes = indexing.retrieve_similar_nodes(a, top_k=5)
 
-        assert set(indexing._node_document_ids(nodes)) == {b.id}
+        assert {int(node.metadata["document_id"]) for node in nodes} == {b.id}
 
     def test_excludes_self_with_multiple_chunks(
         self,
@@ -1235,4 +1233,4 @@ class TestRetrieveSimilarNodesAgainstRealIndex:
 
         nodes = indexing.retrieve_similar_nodes(a, top_k=3)
 
-        assert set(indexing._node_document_ids(nodes)) == {b.id}
+        assert {int(node.metadata["document_id"]) for node in nodes} == {b.id}