💡 Learn more
This guide shows the steps needed to install the app via the user interface. If you prefer to install it using SQL scripts, please follow this guide.
1. Installing the app from the Snowflake Marketplace
The first step is to request access to our Native App. Once done, our team will review your request and you will be able to start the installation.
The application will show up in Data Products > Apps > Recently Shared with You. After installing the app, a modal window will show up. Click on Configure to go to the next step.
2. Granting Permissions
🤚 Heads up
Note that the following steps can only be done using the ACCOUNTADMIN role or by an user/role with the appropriate privileges
The app requires certain account privileges to function properly. These are listed below:
The next step would be to allow the connection to external services.
Our app needs access to an LLM and Slack. The Slack connection is required to send the AI Agent insights to your selected Slack room.
Choosing your LLM
A) Open AI
If you want to use Open AI, you must provide an API token from your organization. Learn how to get an API token.
B) Llama
If you want to use Llama (via Snowflake's Cortex), you will need to click on Review when setting up the Open AI connection and include an invalid token (e.g. NOT_VALID). This step is required due to how the Native Apps currently work.
3. Give access to a Snowflake View
Lastly, we need to give the Native App the data that will be used by the agents. Go to Data Products > Apps and click on the app.
To generate insights, the AI Agents need read access to a Snowflake view containing the unstructured text data generated by your users, such as support tickets, call transcripts, or survey responses.
The view must have AT LEAST the following columns in order to work:
id: The id of the document (ticket, survey, etc.)
text: The unstructured text to be analyzed
creation_date: The date of creation of the unstructured text
user_id: The id of the user that generated the unstructured text
You may include additional columns that may be used by the AI agent to aggregate the insights generated.
Here is an example of a view created in Snowflake with the required format:
create or replace view APP_DATABASE.PUBLIC.LANGAI_APP_VIEW(
ID,
TEXT,
CREATION_DATE,
USER_ID,
PLAN
) as SELECT id, text as text, creation_date, user_id, plan FROM APP_DATABASE.PUBLIC.OPSWD_REVIEWS;
The last column "plan" is not mandatory, but we included so the agent is able to group the insights by the user's subscription plan.
This is a preview of the view we created:
Once the view is ready, you can now add it in the app configuration:
You are now ready to launch and start using the application.
If you want to test the application with sample data, follow our Quickstart guide.
4. Launching the App
After completing the above steps, click Activate to begin the onboarding process and create your first agent.
Additional resources: