Update app/data_indexing.py

app/data_indexing.py

@@ -58,22 +58,13 @@ class DataIndexer:
         return vectorstore
 
     def index_data(self, docs, batch_size=32):
-
-        with open(self.source_file, 'a') as file:
-            for doc in docs:
-                file.writelines(doc.metadata['source'] + '\n')
-
         for i in range(0, len(docs), batch_size):
             batch = docs[i: i + batch_size]
             values = self.embedding_client.embed_documents([
                 doc.page_content for doc in batch
             ])
 
-            # values = self.embedding_client.feature_extraction([
-            #     doc.page_content for doc in batch
-            # ])
             vector_ids = [str(uuid.uuid4()) for _ in batch]
- 
             metadatas = [{
                 'text': doc.page_content,
                 **doc.metadata
@@ -83,7 +74,8 @@ class DataIndexer:
                 'id': vector_id,
                 'values': value,
                 'metadata': metadata
-            } for vector_id, value, metadata in zip(vector_ids, values, metadatas)]
+            } for vector_id, value, metadata in zip(vector_ids, values, metadatas
+            )]
 
             try: 
                 upsert_response = self.index.upsert(vectors=vectors)
@@ -91,7 +83,7 @@ class DataIndexer:
             except Exception as e:
                 print(e)
 
-    def search(text_query, top_k=5):
+    def search(self,text_query, top_k=5):
         vector = self.embedding_client.embed_query(text_query)
         result = self.index.query(
             vector=vector,