chentianrui
108 lines
3.3 KiB
Python
108 lines
3.3 KiB
Python
import logging
|
|
from typing import Any, List, Optional
|
|
|
|
from llama_index.core import Document
|
|
from pydantic import BaseModel
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
class CustomDatabaseReader:
|
|
"""Simple Database reader.
|
|
|
|
Concatenates each row into Document used by LlamaIndex.
|
|
|
|
Args:
|
|
sql_database (Optional[SQLDatabase]): SQL database to use,
|
|
including table names to specify.
|
|
See :ref:`Ref-Struct-Store` for more details.
|
|
|
|
OR
|
|
|
|
engine (Optional[Engine]): SQLAlchemy Engine object of the database connection.
|
|
|
|
OR
|
|
|
|
uri (Optional[str]): uri of the database connection.
|
|
|
|
OR
|
|
|
|
scheme (Optional[str]): scheme of the database connection.
|
|
host (Optional[str]): host of the database connection.
|
|
port (Optional[int]): port of the database connection.
|
|
user (Optional[str]): user of the database connection.
|
|
password (Optional[str]): password of the database connection.
|
|
dbname (Optional[str]): dbname of the database connection.
|
|
|
|
Returns:
|
|
DatabaseReader: A DatabaseReader object.
|
|
"""
|
|
|
|
def __init__(
|
|
self,
|
|
sql_database: Optional[Any] = None,
|
|
engine: Optional[Any] = None,
|
|
uri: Optional[str] = None,
|
|
scheme: Optional[str] = None,
|
|
host: Optional[str] = None,
|
|
port: Optional[str] = None,
|
|
user: Optional[str] = None,
|
|
password: Optional[str] = None,
|
|
dbname: Optional[str] = None,
|
|
*args: Any,
|
|
**kwargs: Any,
|
|
) -> None:
|
|
"""Initialize with parameters."""
|
|
# Setting the database-related properties to None
|
|
self.sql_database = None
|
|
self.uri = None
|
|
|
|
def load_data(self, query: str, explanation: str) -> List[Document]:
|
|
"""Simulate loading data without a database connection.
|
|
|
|
Args:
|
|
query (str): Query parameter (not used).
|
|
explanation (str): Explanation to be included in the document.
|
|
|
|
Returns:
|
|
List[Document]: A list of Document objects.
|
|
"""
|
|
dco_str = explanation + "\n"
|
|
# Simulate data without querying a real database
|
|
dco_str += "Simulated column1, Simulated column2\n"
|
|
dco_str += "Simulated data1, Simulated data2\n"
|
|
|
|
doc = Document(text=dco_str)
|
|
doc.metadata["name"] = query
|
|
doc.metadata["context"] = query
|
|
doc.metadata["file_type"] = "application/vnd.ms-excel"
|
|
return [doc]
|
|
|
|
class DBLoaderConfig(BaseModel):
|
|
uri: str
|
|
queries: List[dict]
|
|
|
|
def get_db_documents(configs: list[DBLoaderConfig]):
|
|
docs = []
|
|
|
|
if len(configs) == 0 or configs[0].uri == "":
|
|
logger.warning(
|
|
f"Failed to load database, error message: uri is empty. Return as empty document list."
|
|
)
|
|
return docs
|
|
|
|
metadata = {
|
|
'file_type': 'application/booway.document.zj',
|
|
}
|
|
|
|
for entry in configs:
|
|
# Skipping the database connection part
|
|
loader = CustomDatabaseReader()
|
|
for query_dict in entry.queries:
|
|
query = query_dict.get("sql", "")
|
|
explanation = query_dict.get("explanation", "")
|
|
logger.info(f"Loading data from database with query: {query}")
|
|
documents = loader.load_data(query=query, explanation=explanation)
|
|
|
|
docs.extend(documents)
|
|
return docs
|