SnowflakeCortexAnalyst

Setup:

Install langchain-snowflake and configure Snowflake connection.

.. code-block:: bash

pip install -U langchain-snowflake

Key init args:

session: Optional[Session] Active Snowflake session account: str Snowflake account identifier user: str Snowflake username database: str Database to query schema: str Schema to query warehouse: Optional[str] Warehouse to use for queries use_rest_api: bool Whether to use REST API (default: True) or SQL function fallback semantic_model_file: Optional[str] Path to semantic model file on Snowflake stage

Instantiate:

.. code-block:: python

from . import SnowflakeCortexAnalyst

analyst = SnowflakeCortexAnalyst( session=session, semantic_model_file="@my_stage/semantic_model.yaml" )

Use within an agent:

.. code-block:: python

from langchain.agents import AgentExecutor, create_tool_calling_agent from langchain_core.prompts import ChatPromptTemplate from .. import ChatSnowflake

llm = ChatSnowflake(model="claude-3-5-sonnet", session=session) tools = [analyst]

prompt = ChatPromptTemplate.from_messages([ ("system", "You are a helpful data analyst assistant."), ("human", "{input}"), ("placeholder", "{agent_scratchpad}"), ])

agent = create_tool_calling_agent(llm, tools, prompt) agent_executor = AgentExecutor(agent=agent, tools=tools)

response = agent_executor.invoke({ "input": "What were our top 5 products by revenue last quarter?" })