Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/acdeveloper-sci/fortriage/llms.txt

Use this file to discover all available pages before exploring further.

AI Insights is an optional feature that generates an executive summary and enables a conversational chat assistant after each analysis run. It requires a free Google AI Studio API key. The full dashboard — Overview, Drill-down, Executive Summary, and Report Explorer — works completely without it; no functionality is degraded if you skip this step.

​
Get an API key

1

Open Google AI Studio

Go to https://ai.google.dev/ in your browser.
2

Sign in

Sign in with a Google account. No billing setup is required for the free tier.
3

Create a new API key

In the Google AI Studio console, create a new API key. The free tier supports up to 1,500 requests per day at no cost.
4

Copy the key

Copy the generated key to your clipboard — you will paste it into your secrets configuration in the next section.

​
Local setup

Create the file .streamlit/secrets.toml in the root of your ForTriage project directory:
.streamlit/secrets.toml
GEMINI_API_KEY = "your-api-key-here"
Never commit .streamlit/secrets.toml to version control. Add it to your .gitignore immediately after creating it. Exposing an API key in a public repository can result in unauthorized use and quota exhaustion.
After creating the file, restart the Streamlit app if it is already running — secrets are read at startup and are not reloaded on hot-reload.

​
Streamlit Community Cloud deployment

If you are deploying ForTriage on Streamlit Community Cloud, configure the secret through the dashboard instead of a local file:
1

Open your app settings

Navigate to your app in the Streamlit Community Cloud dashboard and click Settings.
2

Open the Secrets panel

Select the Secrets tab within the Settings panel.
3

Add the secret

Paste the following into the secrets editor:
GEMINI_API_KEY = "your-api-key-here"
4

Save and reload

Click Save. The app will reload automatically and pick up the new key.

​
Model used

ForTriage uses the gemini-3.5-flash-lite model for both structured insights generation and the follow-up chat assistant. This is the current free-tier Flash-Lite GA model available on ai.google.dev at the time of this writing.
SettingValue
Modelgemini-3.5-flash-lite
Timeout30 seconds per request
Requests used per analysis run1 (structured insights generation)
Requests used per chat message1
Any failure during AI Insights generation — including an authentication error from a missing or invalid key, a rate limit response, a timeout, or a transport error — results in a generic “AI Insights could not be generated” error message with a Retry button. No technical details or provider information are surfaced to the user. The rest of the dashboard remains fully functional.
The free Gemini tier allows 1,500 requests per day. Each analysis run uses 1 request for structured insights generation. Each follow-up chat message uses 1 additional request. For most use cases, the free tier is more than sufficient.
If no secrets.toml exists or the GEMINI_API_KEY key is absent, AI Insights will display a generic error message and a Retry button — the rest of the dashboard (Overview, Drill-down, Executive Summary, Report Explorer) is completely unaffected.
For information about what data is sent to Google when AI Insights runs, see the Privacy and Data Handling page.

Build docs developers (and LLMs) love

Get started for freeTalk to us