Enhance Code Consistency Across Repository with .editorconfig (#19023)

api/core/rag/datasource/vdb/analyticdb/analyticdb_vector_sql.py

@@ -156,8 +156,8 @@ class AnalyticdbVectorBySql:
         values = []
         id_prefix = str(uuid.uuid4()) + "_"
         sql = f"""
-                INSERT INTO {self.table_name} 
-                (id, ref_doc_id, vector, page_content, metadata_, to_tsvector) 
+                INSERT INTO {self.table_name}
+                (id, ref_doc_id, vector, page_content, metadata_, to_tsvector)
                 VALUES (%s, %s, %s, %s, %s, to_tsvector('zh_cn',  %s));
             """
         for i, doc in enumerate(documents):
@@ -242,7 +242,7 @@ class AnalyticdbVectorBySql:
             where_clause += f"AND metadata_->>'document_id' IN ({document_ids})"
         with self._get_cursor() as cur:
             cur.execute(
-                f"""SELECT id, vector, page_content, metadata_, 
+                f"""SELECT id, vector, page_content, metadata_,
                 ts_rank(to_tsvector, to_tsquery_from_text(%s, 'zh_cn'), 32) AS score
                 FROM {self.table_name}
                 WHERE to_tsvector@@to_tsquery_from_text(%s, 'zh_cn') {where_clause}

api/core/rag/datasource/vdb/oceanbase/oceanbase_vector.py

@@ -203,7 +203,7 @@ class OceanBaseVector(BaseVector):
 
             full_sql = f"""SELECT metadata, text, MATCH (text) AGAINST (:query) AS score
             FROM {self._collection_name}
-            WHERE MATCH (text) AGAINST (:query) > 0 
+            WHERE MATCH (text) AGAINST (:query) > 0
             {where_clause}
             ORDER BY score DESC
             LIMIT {top_k}"""

api/core/rag/datasource/vdb/opengauss/opengauss.py

@@ -59,12 +59,12 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 """
 
 SQL_CREATE_INDEX_PQ = """
-CREATE INDEX IF NOT EXISTS embedding_{table_name}_pq_idx ON {table_name} 
+CREATE INDEX IF NOT EXISTS embedding_{table_name}_pq_idx ON {table_name}
 USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64, enable_pq=on, pq_m={pq_m});
 """
 
 SQL_CREATE_INDEX = """
-CREATE INDEX IF NOT EXISTS embedding_cosine_{table_name}_idx ON {table_name} 
+CREATE INDEX IF NOT EXISTS embedding_cosine_{table_name}_idx ON {table_name}
 USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
 """
 

api/core/rag/datasource/vdb/oracle/oraclevector.py

@@ -59,8 +59,8 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 )
 """
 SQL_CREATE_INDEX = """
-CREATE INDEX IF NOT EXISTS idx_docs_{table_name} ON {table_name}(text) 
-INDEXTYPE IS CTXSYS.CONTEXT PARAMETERS 
+CREATE INDEX IF NOT EXISTS idx_docs_{table_name} ON {table_name}(text)
+INDEXTYPE IS CTXSYS.CONTEXT PARAMETERS
 ('FILTER CTXSYS.NULL_FILTER SECTION GROUP CTXSYS.HTML_SECTION_GROUP LEXER world_lexer')
 """
 
@@ -164,7 +164,7 @@ class OracleVector(BaseVector):
                 with conn.cursor() as cur:
                     try:
                         cur.execute(
-                            f"""INSERT INTO {self.table_name} (id, text, meta, embedding) 
+                            f"""INSERT INTO {self.table_name} (id, text, meta, embedding)
                         VALUES (:1, :2, :3, :4)""",
                             value,
                         )
@@ -227,8 +227,8 @@ class OracleVector(BaseVector):
             conn.outputtypehandler = self.output_type_handler
             with conn.cursor() as cur:
                 cur.execute(
-                    f"""SELECT meta, text, vector_distance(embedding,(select to_vector(:1) from dual),cosine) 
-                    AS distance FROM {self.table_name} 
+                    f"""SELECT meta, text, vector_distance(embedding,(select to_vector(:1) from dual),cosine)
+                    AS distance FROM {self.table_name}
                     {where_clause} ORDER BY distance fetch first {top_k} rows only""",
                     [numpy.array(query_vector)],
                 )
@@ -290,7 +290,7 @@ class OracleVector(BaseVector):
                         document_ids = ", ".join(f"'{id}'" for id in document_ids_filter)
                         where_clause = f" AND metadata->>'document_id' in ({document_ids}) "
                     cur.execute(
-                        f"""select meta, text, embedding FROM {self.table_name} 
+                        f"""select meta, text, embedding FROM {self.table_name}
                     WHERE CONTAINS(text, :kk, 1) > 0  {where_clause}
                     order by score(1) desc fetch first {top_k} rows only""",
                         kk=" ACCUM ".join(entities),

api/core/rag/datasource/vdb/pgvector/pgvector.py

@@ -61,7 +61,7 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 """
 
 SQL_CREATE_INDEX = """
-CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name} 
+CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name}
 USING hnsw (embedding vector_cosine_ops) WITH (m = 16, ef_construction = 64);
 """
 

api/core/rag/datasource/vdb/pyvastbase/vastbase_vector.py

@@ -58,7 +58,7 @@ CREATE TABLE IF NOT EXISTS {table_name} (
 """
 
 SQL_CREATE_INDEX = """
-CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name} 
+CREATE INDEX IF NOT EXISTS embedding_cosine_v1_idx ON {table_name}
 USING hnsw (embedding floatvector_cosine_ops) WITH (m = 16, ef_construction = 64);
 """
 

api/core/rag/datasource/vdb/tidb_vector/tidb_vector.py

@@ -205,9 +205,9 @@ class TiDBVector(BaseVector):
 
         with Session(self._engine) as session:
             select_statement = sql_text(f"""
-                SELECT meta, text, distance 
+                SELECT meta, text, distance
                 FROM (
-                  SELECT 
+                  SELECT
                     meta,
                     text,
                     {tidb_dist_func}(vector, :query_vector_str) AS distance

api/core/rag/retrieval/template_prompts.py

@@ -50,7 +50,7 @@ You are a text metadata extract engine that extract text's metadata based on use
 # Your task is to ONLY extract the metadatas that exist in the input text from the provided metadata list and Use the following operators ["=", "!=", ">", "<", ">=", "<="] to express logical relationships, then return result in JSON format with the key "metadata_fields" and value "metadata_field_value" and comparison operator "comparison_operator".
 ### Format
 The input text is in the variable input_text. Metadata are specified as a list in the variable metadata_fields.
-### Constraint 
+### Constraint
 DO NOT include anything other than the JSON array in your response.
 ### Example
 Here is the chat example between human and assistant, inside <example></example> XML tags.
@@ -59,7 +59,7 @@ User:{{"input_text": ["I want to know which company’s email address test@examp
 Assistant:{{"metadata_map": [{{"metadata_field_name": "email", "metadata_field_value": "test@example.com", "comparison_operator": "="}}]}}
 User:{{"input_text": "What are the movies with a score of more than 9 in 2024?", "metadata_fields": ["name", "year", "rating", "country"]}}
 Assistant:{{"metadata_map": [{{"metadata_field_name": "year", "metadata_field_value": "2024", "comparison_operator": "="}, {{"metadata_field_name": "rating", "metadata_field_value": "9", "comparison_operator": ">"}}]}}
-</example> 
+</example>
 ### User Input
 {{"input_text" : "{input_text}", "metadata_fields" : {metadata_fields}}}
 ### Assistant Output