Skip to content

refactor: parse embedding dimensions as float[] for numpyV2 #277

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
vishwarajanand merged 1 commit into from
Mar 4, 2025
Merged

refactor: parse embedding dimensions as float[] for numpyV2 #277

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 7 additions & 3 deletions src/langchain_google_cloud_sql_pg/async_vectorstore.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -246,7 +246,11 @@ async def __aadd_embeddings(
else ""
)
insert_stmt = f'INSERT INTO "{self.schema_name}"."{self.table_name}"("{self.id_column}", "{self.content_column}", "{self.embedding_column}"{metadata_col_names}'
values = {"id": id, "content": content, "embedding": str(embedding)}
values = {
"id": id,
"content": content,
"embedding": str([float(dimension) for dimension in embedding]),
}
values_stmt = "VALUES (:id, :content, :embedding"

# Add metadata
Expand Down Expand Up @@ -496,9 +500,9 @@ async def __query_collection(
columns.append(self.metadata_json_column)

column_names = ", ".join(f'"{col}"' for col in columns)

filter = f"WHERE {filter}" if filter else ""
stmt = f"SELECT {column_names}, {search_function}({self.embedding_column}, '{embedding}') as distance FROM \"{self.schema_name}\".\"{self.table_name}\" {filter} ORDER BY {self.embedding_column} {operator} '{embedding}' LIMIT {k};"
embedding_string = f"'{[float(dimension) for dimension in embedding]}'"
stmt = f'SELECT {column_names}, {search_function}({self.embedding_column}, {embedding_string}) as distance FROM "{self.schema_name}"."{self.table_name}" {filter} ORDER BY {self.embedding_column} {operator} {embedding_string} LIMIT {k};'
if self.index_query_options:
async with self.pool.connect() as conn:
await conn.execute(
Expand Down
8 changes: 6 additions & 2 deletions tests/test_engine.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -130,7 +130,9 @@ async def test_init_table(self, engine):
id = str(uuid.uuid4())
content = "coffee"
embedding = await embeddings_service.aembed_query(content)
stmt = f"INSERT INTO {DEFAULT_TABLE} (langchain_id, content, embedding) VALUES ('{id}', '{content}','{embedding}');"
# Note: DeterministicFakeEmbedding generates a numpy array, converting to list a list of float values
embedding_string = [float(dimension) for dimension in embedding]
stmt = f"INSERT INTO {DEFAULT_TABLE} (langchain_id, content, embedding) VALUES ('{id}', '{content}','{embedding_string}');"
await aexecute(engine, stmt)

async def test_init_table_custom(self, engine):
Expand Down Expand Up @@ -350,7 +352,9 @@ async def test_init_table(self, engine):
id = str(uuid.uuid4())
content = "coffee"
embedding = await embeddings_service.aembed_query(content)
stmt = f"INSERT INTO {DEFAULT_TABLE_SYNC} (langchain_id, content, embedding) VALUES ('{id}', '{content}','{embedding}');"
# Note: DeterministicFakeEmbedding generates a numpy array, converting to list a list of float values
embedding_string = [float(dimension) for dimension in embedding]
stmt = f"INSERT INTO {DEFAULT_TABLE_SYNC} (langchain_id, content, embedding) VALUES ('{id}', '{content}','{embedding_string}');"
await aexecute(engine, stmt)

async def test_init_table_custom(self, engine):
Expand Down