From 24b86770df6bac33cc416747ccb590937cbb365c Mon Sep 17 00:00:00 2001
From: stumpylog <797416+stumpylog@users.noreply.github.com>
Date: Tue, 28 Jul 2026 09:39:02 -0700
Subject: [PATCH] Perf: store document_chunks.document_id as INTEGER

document_chunks is a plain SQLite table, not a vec0 virtual table, so
(unlike vec0's own TEXT metadata column) it gets normal type-affinity
coercion between the TEXT document ids used elsewhere in this module and
an INTEGER column -- verified empirically. INTEGER keys make the
per-document delete lookup this table exists for cheaper: smaller index
entries and integer rather than text B-tree comparisons.
---
 src/paperless_ai/tests/test_vector_store.py | 2 +-
 src/paperless_ai/vector_store.py            | 8 +++++++-
 2 files changed, 8 insertions(+), 2 deletions(-)

diff --git a/src/paperless_ai/tests/test_vector_store.py b/src/paperless_ai/tests/test_vector_store.py
index e11dde1ea..6509a56d3 100644
--- a/src/paperless_ai/tests/test_vector_store.py
+++ b/src/paperless_ai/tests/test_vector_store.py
@@ -103,7 +103,7 @@ def _chunk_index_rows(
         sql += " WHERE document_id = ?"
         params.append(document_id)
     rows = store.client.execute(sql + " ORDER BY chunk_id", params).fetchall()
-    return [(r["chunk_id"], r["document_id"]) for r in rows]
+    return [(r["chunk_id"], str(r["document_id"])) for r in rows]
 
 
 @contextmanager
diff --git a/src/paperless_ai/vector_store.py b/src/paperless_ai/vector_store.py
index fc94fe6f2..27b320d2e 100644
--- a/src/paperless_ai/vector_store.py
+++ b/src/paperless_ai/vector_store.py
@@ -241,9 +241,15 @@ class PaperlessSqliteVecVectorStore(BasePydanticVectorStore):
         # (MATCH) query; a plain `WHERE document_id = ?` is a full table scan
         # regardless of index size. This plain, indexed table is how delete()/
         # upsert_document() find a document's chunk ids without that scan.
+        # document_id is INTEGER here (unlike vec0's own TEXT metadata
+        # column): this is a normal SQLite table, so standard type affinity
+        # correctly coerces the TEXT document ids written/looked-up
+        # elsewhere in this module -- it does not share vec0's own
+        # metadata-column comparison code, which silently mismatches
+        # non-TEXT bound values instead of coercing them.
         conn.execute(
             "CREATE TABLE IF NOT EXISTS document_chunks "
-            "(chunk_id TEXT PRIMARY KEY, document_id TEXT NOT NULL)",
+            "(chunk_id TEXT PRIMARY KEY, document_id INTEGER NOT NULL)",
         )
         conn.execute(
             "CREATE INDEX IF NOT EXISTS idx_document_chunks_document_id "