Skip to content

Create a chatbot that speaks to the Snowflake Cortex Analyst

Source: R/provider-cortex.R
chat_cortex.Rd

Chat with the LLM-powered Snowflake Cortex Analyst.

Unlike most comparable model APIs, Cortex does not take a system prompt. Instead, the caller must provide a "semantic model" describing available tables, their meaning, and verified queries that can be run against them as a starting point. The semantic model can be passed as a YAML string or via reference to an existing file in a Snowflake Stage.

Note that Cortex does not support multi-turn, so it will not remember previous messages. Nor does it support registering tools, and attempting to do so will result in an error.

Usage

chat_cortex(
  account = Sys.getenv("SNOWFLAKE_ACCOUNT"),
  credentials = cortex_credentials,
  model_spec = NULL,
  model_file = NULL,
  api_args = list(),
  echo = c("none", "text", "all")
)

cortex_credentials(account = Sys.getenv("SNOWFLAKE_ACCOUNT"))

Arguments

account

A Snowflake account identifier, e.g. "testorg-test_account".

credentials

A list of authentication headers to pass into httr2::req_headers() or a function that returns them when passed account as a parameter. The default cortex_credentials() function picks up ambient Snowflake OAuth and key-pair authentication credentials and handles refreshing them automatically.

model_spec

A semantic model specification, or NULL when using model_file instead.

model_file

Path to a semantic model file stored in a Snowflake Stage, or NULL when using model_spec instead.

api_args

Named list of arbitrary extra arguments appended to the body of every chat API call.

echo

One of the following options:

  • none: don't emit any output (default when running in a function).

  • text: echo text output as it streams in (default when running at the console).

  • all: echo all input and output.

Note this only affects the chat() method.

Value

A Chat object.

Details

cortex_credentials() picks up the following ambient Snowflake credentials:

  • A static OAuth token defined via the SNOWFLAKE_TOKEN environment variable.

  • Key-pair authentication credentials defined via the SNOWFLAKE_USER and SNOWFLAKE_PRIVATE_KEY (which can be a PEM-encoded private key or a path to one) environment variables.

  • Posit Workbench-managed Snowflake credentials for the corresponding account.

See also

Other chatbots: chat_bedrock(), chat_claude(), chat_databricks(), chat_gemini(), chat_github(), chat_groq(), chat_ollama(), chat_openai(), chat_perplexity()

Examples

if (FALSE) { # elmer:::cortex_credentials_exist()
chat <- chat_cortex(
  model_file = "@my_db.my_schema.my_stage/model.yaml"
)
chat$chat("What questions can I ask?")
}