Phospho documentation

This guide will help you get started with the phospho platform.

Create your phospho account

Create an account on phospho.ai.

Import your data in a project

Import your data

From CSV/Excel
From LangSmith
From LangFuse
From API

Setup events, and get insights on your dashboard

Analyze user interactions, explore the analytics and improve your app.

Go to the phospho platform. Login or create an account if you don’t have one.

If this is your first time using phospho, a Default project has been created for you.

2. Import your data in a project

Import your data

In the header, to the right, look for the gears icon and click on it.

You can then click on import data.

Click on settings

You now have different options, the easiest options are to import from a CSV/Excel file, to synchronise with LangSmith or LangFuse if you have existing data there.

For other options, you can take a look at the technical documentation to import data directly from your system.

Import data

Import from file

You can import a CSV or a Excel file into phospho.

Head over to the phospho platform and click on the settings icon at the top right of the screen. Then select Import data.

Import data

Click on the Upload dataset button.

Import from CSV

You can now drag and drop your file or click on the box to select it.

You should have the following columns in your file:

input;output;task_id;session_id;created_at
"Hello! This is what the user asked to the system";"This is the response showed to the user by the app.";"task_1";"session_1";"2024-05-31 12:31:22"

Make sure that your CSV is a valid CSV file separated by a colon or a semicolon.
Make sure the created_at field is in the format YYYY-MM-DD HH:MM:SS.

Import from LangSmith

You can import existing data from LangSmith by providing the LangSmith API key and your LangSmith project name.

We will periodically fetch your data from LangSmith and import it into phospho.

This data is encrypted and stored securely. We need it to periodically fetch your data from LangSmith and import it into phospho.

Import from LangFuse

You can import existing data from LangFuse by providing your LangFuse Public and Secret keys.

We will periodically fetch your data from LangFuse and import it into phospho.

This data is encrypted and stored securely. We need it to periodically fetch your data from LangFuse and import it into phospho.

3. Define and run events in the past

Using events

Events are the key to getting insights from your data.

An event is a specific interaction between a user and the system you want to track.

To define an event, go to the Events tab in the phospho platform and click on the Add Event button.

Add Event

In this tab you can setup events in natural language, in this image, we have setup an event to detect when the system is unable to answer the user’s question.

Run events in the past

Once you’ve defined your events, you can run them on past data.

Click on the Detect events button in the Events tab to run an event on your data.

Detect events

4. That’s it, you’re all set !

You can now Leverage your data, analyze it, and get insights on your dashboard.

Next steps

Learn to use the phospho platform with our guides:

LLM as a judge

Setup LLM as a judge in your application. Detect events in your data.

User Intentions

Detect user intentions and get a global overview your LLM app.

Understand your data

Get insights on your data through vizualisation, clustering and more. Quick and easy

Guides

Run analytics on your LLM app data