Getting started with AI on enterprise data can seem overwhelming, between getting familiar with LLMs, how to perform custom prompt engineering, and how to get a wide range of LLMs deployed/integrated to run multiple tests all while keeping that valuable enterprise data secure. Well, a lot of these complexities are being abstracted away for you in Snowflake Cortex AI.
In this guide, we will go through various flows and show you the fastest and easiest way to get started with Snowflake Cortex AI.
Snowflake offers two broad categories of powerful, intelligent features based on Artificial Intelligence (AI) and Machine Learning (ML). These features can help you do more with your data in less time than ever before.
Snowflake Cortex is a suite of AI features that use large language models (LLMs) to understand unstructured data, answer freeform questions, and provide intelligent assistance.
Learn more about Snowflake Cortex AI.
Prior to GenAI, a lot of the information was buried in text format and therefore going underutilized for root cause analysis due to complexities in implementing natural language processing. But with Snowflake Cortex AI it's as easy as writing a SQL statement!
In this guide, we'll utilize synthetic call transcripts data, mimicking text sources commonly overlooked by organizations, including customer calls/chats, surveys, interviews, and other text data generated in marketing and sales teams.
In a new SQL worksheet, run the following statements to set up your environment. This will:
USE ROLE ACCOUNTADMIN;
CREATE DATABASE IF NOT EXISTS DASH_DB;
CREATE SCHEMA IF NOT EXISTS DASH_SCHEMA;
CREATE WAREHOUSE IF NOT EXISTS DASH_XS_WH WAREHOUSE_SIZE=XSMALL;
USE DASH_DB.DASH_SCHEMA;
USE WAREHOUSE DASH_XS_WH;
CREATE or REPLACE file format csvformat
SKIP_HEADER = 1
FIELD_OPTIONALLY_ENCLOSED_BY = '"'
type = 'CSV';
CREATE or REPLACE stage call_transcripts_data_stage
file_format = csvformat
url = 's3://sfquickstarts/misc/call_transcripts/';
CREATE or REPLACE table CALL_TRANSCRIPTS (
date_created date,
language varchar(60),
country varchar(60),
product varchar(60),
category varchar(60),
damage_type varchar(90),
transcript varchar
) COMMENT = '{"origin":"sf_sit-is", "name":"aiml_notebooks_cortex_ai", "version":{"major":1, "minor":0}, "attributes":{"is_quickstart":1, "source":"sql"}}';
COPY into CALL_TRANSCRIPTS
from @call_transcripts_data_stage;
Given the data in CALL_TRANSCRIPTS table, let's see how we can use task specific LLMs functions in Snowflake Cortex. It offers access to industry-leading AI models, without requiring any knowledge of how the AI models work, how to deploy LLMs, or how to manage GPU infrastructure.
Run the following statements in the same or a new SQL worksheet.
Using Snowflake Cortex function snowflake.cortex.translate we can easily translate any text from one language to another. Let's see how easy it is to use this function.
select snowflake.cortex.translate('wie geht es dir heute?','de_DE','en_XX');
Executing the above SQL should generate "How are you today?"
Now let's see how you can translate call transcripts from German to English in batch mode using just SQL.
select transcript,snowflake.cortex.translate(transcript,'de_DE','en_XX') from call_transcripts where language = 'German';
See the list of supported languages.
Now let's see how we can use snowflake.cortex.sentiment function to generate sentiment scores on call transcripts.
Note: Score is between -1 and 1; -1 = most negative, 1 = positive, 0 = neutral
select transcript, snowflake.cortex.sentiment(transcript) from call_transcripts where language = 'English';
Now that we know how to translate call transcripts in English, it would be great to have the model pull out the most important details from each transcript so we don't have to read the whole thing. Let's see how snowflake.cortex.summarize function can do this and try it on one record.
select transcript,snowflake.cortex.summarize(transcript) as summary from call_transcripts where language = 'English' limit 1;
select transcript,snowflake.cortex.summarize(transcript) as summary,snowflake.cortex.count_tokens('summarize',transcript) as number_of_tokens from call_transcripts where language = 'English' limit 1;
Being able to pull out the summary is good, but it would be great if we specifically pull out the product name, what part of the product was defective, and limit the summary to 200 words.
Let's see how we can accomplish this using the snowflake.cortex.complete function.
ALTER ACCOUNT SET CORTEX_ENABLED_CROSS_REGION = 'ANY_REGION';
SET prompt =
'###
Summarize this transcript in less than 200 words.
Put the product name, defect and summary in JSON format.
###';
select snowflake.cortex.complete('claude-4-sonnet',concat('[INST]',$prompt,transcript,'[/INST]')) as summary
from call_transcripts where language = 'English' limit 1;
Here we're selecting the Claude 4 model and giving it a prompt telling it how to customize the output. Sample response:
{
"product": "XtremeX helmets",
"defect": "Broken buckles that won't secure the helmet properly",
"summary": "Jessica Turner from Mountain Ski Adventures contacted customer service regarding a recent order (order #68910) of XtremeX helmets. Upon inspection, they discovered that 10 helmets had broken buckles that wouldn't secure properly. The customer service agent apologized for the inconvenience and offered either a refund or replacement. Jessica requested replacements since they still needed the helmets for their customers. The agent processed a replacement order for 10 new XtremeX helmets with functioning buckles, which will be expedited and should arrive within 3-5 business days. The issue was resolved satisfactorily with the customer expressing appreciation for the assistance."
}
To put it all together, let's create a Streamlit application in Snowflake.
Step 1. Click on Streamlit on the left navigation menu
Step 2. Click on + Streamlit App on the top right
Step 3. Enter App name
Step 4. Select App location (DASH_DB and DASH_SCHEMA) and App warehouse (DASH_XS_WH)
Step 5. Select Run on warehouse for Runtime.
Step 6. Click on Create
Step 7. Replace the entire sample application code on the left with the following code snippet.
import streamlit as st
from snowflake.snowpark.context import get_active_session
st.set_page_config(layout='wide')
session = get_active_session()
def summarize():
with st.container():
st.header("JSON Summary With Snowflake Cortex AI")
entered_text = st.text_area("Enter text",label_visibility="hidden",height=400,placeholder='Enter text. For example, a call transcript.')
btn_summarize = st.button("Summarize",type="primary")
if entered_text and btn_summarize:
entered_text = entered_text.replace("'", "\\'")
prompt = f"Summarize this transcript in less than 200 words. Put the product name, defect if any, and summary in JSON format: {entered_text}"
cortex_prompt = "'[INST] " + prompt + " [/INST]'"
cortex_response = session.sql(f"select snowflake.cortex.complete('claude-4-sonnet', {cortex_prompt}) as response").to_pandas().iloc[0]['RESPONSE']
st.write(cortex_response)
def translate():
supported_languages = {'German':'de','French':'fr','Korean':'ko','Portuguese':'pt','English':'en','Italian':'it','Russian':'ru','Swedish':'sv','Spanish':'es','Japanese':'ja','Polish':'pl'}
with st.container():
st.header("Translate With Snowflake Cortex AI")
col1,col2 = st.columns(2)
with col1:
from_language = st.selectbox('From',dict(sorted(supported_languages.items())))
with col2:
to_language = st.selectbox('To',dict(sorted(supported_languages.items())))
entered_text = st.text_area("Enter text",label_visibility="hidden",height=300,placeholder='Enter text. For example, a call transcript.')
btn_translate = st.button("Translate",type="primary")
if entered_text and btn_translate:
entered_text = entered_text.replace("'", "\\'")
cortex_response = session.sql(f"select snowflake.cortex.translate('{entered_text}','{supported_languages[from_language]}','{supported_languages[to_language]}') as response").to_pandas().iloc[0]['RESPONSE']
st.write(cortex_response)
def sentiment_analysis():
with st.container():
st.header("Sentiment Analysis With Snowflake Cortex AI")
entered_text = st.text_area("Enter text",label_visibility="hidden",height=400,placeholder='Enter text. For example, a call transcript.')
btn_sentiment = st.button("Sentiment Score",type="primary")
if entered_text and btn_sentiment:
entered_text = entered_text.replace("'", "\\'")
cortex_response = session.sql(f"select snowflake.cortex.sentiment('{entered_text}') as sentiment").to_pandas().iloc[0]['SENTIMENT']
st.text(f"Sentiment score: {cortex_response}")
st.caption("Note: Score is between -1 and 1; -1 = Most negative, 1 = Positive, 0 = Neutral")
page_names_to_funcs = {
"JSON Summary": summarize,
"Translate": translate,
"Sentiment Analysis": sentiment_analysis,
}
selected_page = st.sidebar.selectbox("Select", page_names_to_funcs.keys())
page_names_to_funcs[selected_page]()
To run the application, click on Run located at the top right corner. If all goes well, you should see the application running as shown below.
Copy and paste the following sample transcript for JSON Summary, Translate, and Sentiment Analysis:
Customer: Hello!
Agent: Hello! I hope you're having a great day. To best assist you, can you please share your first and last name and the company you're calling from?
Customer: Sure, I'm Michael Green from SnowSolutions.
Agent: Thanks, Michael! What can I help you with today?
Customer: We recently ordered several DryProof670 jackets for our store, but when we opened the package, we noticed that half of the jackets have broken zippers. We need to replace them quickly to ensure we have sufficient stock for our customers. Our order number is 60877.
Agent: I apologize for the inconvenience, Michael. Let me look into your order. It might take me a moment.
Customer: Thank you.
Let's try using one of the other supported LLMs in Snowflake with snowflake.cortex.complete function and see how it might perform given the same prompt/instructions.
claude-4-sonnet in the Streamlit app code and repalce it with llama3.1-70b. Note: If that model is not available in your region, pick another one that you can use.This is also a good way to quickly and easily compare how different LLMs might perform given the same prompt/instructions.
For an end-to-end application experience with Snowflake Cortex AI using SQL and Python APIs, download this .ipynb and import it in your Snowflake account.
snowflake, snowflake-ml-python, streamlit. Learn how to install packages.Congratulations! You've successfully completed the Getting Started with Snowflake Cortex AI quickstart guide.