clean: format custom pgvector

custom_pgvector.py

@@ -283,9 +283,7 @@ class CustomPGVector(VectorStore):
             List of Documents most similar to the query and score for each.
         """
         embedding = self.embedding_function.embed_query(query)
-        docs = self.similarity_search_with_score_by_vector(
-            embedding=embedding, k=k
-        )
+        docs = self.similarity_search_with_score_by_vector(embedding=embedding, k=k)
         return docs
 
     @property
@@ -316,16 +314,18 @@ class CustomPGVector(VectorStore):
         docs = [
             (
                 Document(
-                    page_content=json.dumps({
-                        "abstract": result["abstract"],
-                        "id": result["id"],
-                        "title": result["title"],
-                        "authors": result["authors"],
-                        "doi": result["doi"],
-                        # "halID": result["halID"],
-                        "keywords": result["keywords"],
-                        "distance": result["distance"],
-                    }),
+                    page_content=json.dumps(
+                        {
+                            "abstract": result["abstract"],
+                            "id": result["id"],
+                            "title": result["title"],
+                            "authors": result["authors"],
+                            "doi": result["doi"],
+                            # "halID": result["halID"],
+                            "keywords": result["keywords"],
+                            "distance": result["distance"],
+                        }
+                    ),
                 ),
                 result["distance"] if self.embedding_function is not None else None,
             )