Llamhub SnowflakeReader: A Loader to query and chat Snowflake Data in your LLM Applications

 

Snowflake Loader for LLM

Recently my second contribution to Llamaindex "SnowflakeReader" was merged to Lllamahub repository. This loader connects to Snowflake (using SQLAlchemy under the hood). The user specifies a query and extracts Document objects corresponding to the results. This loader is designed to be used as a way to load data into LlamaIndex and/or subsequently used as a Tool in a LangChain Agent. 

Usage

Option 1: Pass your own SQLAlchemy Engine object of the database connection

Here's an example usage of the SnowflakeReader.

from llama_index import download_loader

SnowflakeReader = download_loader('SnowflakeReader')

reader = SnowflakeReader(
    engine= your_sqlalchemy_engine,
)

query = "SELECT * FROM your_table"

documents = reader.load_data(query=query)

Option 2: Pass the required parameters to esstablish Snowflake connection

Here's an example usage of the SnowflakeReader.

from llama_index import download_loader

SnowflakeReader = download_loader('SnowflakeReader')

reader = SnowflakeReader(
    account='your_account',
    user='your_user',
    password='your_password',
    database='your_database',
    schema='your_schema',
    warehouse='your_warehouse',
    role='your_role',  # Optional role setting
    proxy='http://proxusername:proxypassword@myproxy:port'  # Optional proxy setting
)

query = "SELECT * FROM your_table"

documents = reader.load_data(query=query)

Langchain compatibility

documents = [
  doc.to_langhchain_format()
  for doc in documents
]

Semantic Kernel compatibility

Convert documents to MemoryRecord objects

documents = [
  doc.to_semantic_kernel_format()
  for doc in documents
]

Llamahub.ai:  https://llamahub.ai/l/snowflake?from=all

Github:  https://github.com/run-llama/llama-hub/tree/main/llama_hub/snowflake

Author

Godwin Paul Vincent