refactor: Update vectorstore search to support inline embedding (#201)

refactor: Update vectorstore search to support inline embedding

While using inline embedding functions in the current select sql query,
due to parameterization, sql throws an error( The parameter has to
already be in vector datatype).
This change is to support inline embedding functions.

Author: dishaprakash

langchain_postgres/v2/async_vectorstore.py

@@ -561,10 +561,12 @@ async def __query_collection(
         inline_embed_func = getattr(self.embedding_service, "embed_query_inline", None)
         if not embedding and callable(inline_embed_func) and "query" in kwargs:
             query_embedding = self.embedding_service.embed_query_inline(kwargs["query"])  # type: ignore
+            embedding_data_string = f"{query_embedding}"
         else:
             query_embedding = f"{[float(dimension) for dimension in embedding]}"
-        stmt = f"""SELECT {column_names}, {search_function}("{self.embedding_column}", :query_embedding) as distance
-        FROM "{self.schema_name}"."{self.table_name}" {param_filter} ORDER BY "{self.embedding_column}" {operator} :query_embedding LIMIT :k;
+            embedding_data_string = ":query_embedding"
+        stmt = f"""SELECT {column_names}, {search_function}("{self.embedding_column}", {embedding_data_string}) as distance
+        FROM "{self.schema_name}"."{self.table_name}" {param_filter} ORDER BY "{self.embedding_column}" {operator} {embedding_data_string} LIMIT :k;
         """
         param_dict = {"query_embedding": query_embedding, "k": k}
         if filter_dict: