Populate content_hash with embed_multi, refs #217

simonw · Sep 3, 2023 · 156bed7 · 156bed7
1 parent 53fc9cb
commit 156bed7
Show file tree

Hide file tree

Showing 2 changed files with 3 additions and 0 deletions.
diff --git a/llm/embeddings.py b/llm/embeddings.py
@@ -187,6 +187,7 @@ def embed_multi_with_metadata(
                             "id": id,
                             "embedding": llm.encode(embedding),
                             "content": text if store else None,
+                            "content_hash": self.content_hash(text),
                             "metadata": json.dumps(metadata) if metadata else None,
                             "updated": int(time.time()),
                         }

diff --git a/tests/test_embed.py b/tests/test_embed.py
@@ -110,6 +110,8 @@ def test_embed_multi(with_metadata):
     else:
         assert len(rows_with_metadata) == 0
         assert len(rows_with_content) == 1000
+    # Every row should have content_hash set
+    assert all(row["content_hash"] is not None for row in rows)
 
 
 def test_collection_delete(collection):