BehaviorGPT

The foundation model for behavior.

BehaviorGPT is Unbox AI's Large Behavioral Model. It is trained on long sequences of things people actually did (viewed this, added that, bought the other) and predicts what comes next, so search, recommendations and personalization are the same call with different histories. BehaviorGPT-v4 is a single 12.5B-parameter model pretrained on 150 billion user actions across retail, engagement and payments, and it ranks catalogs it has never seen with no training.

Website · Live demo · Research · Notebook

This repository holds the Python SDK for the Unbox AI API and a notebook that walks through the model step by step.

Three apps built on this SDK: two that recommend, on a store's catalog and a museum's, and one that reads the same rankings as a fraud detector.

Storefront (live demo). Search results and recommendations change with what the shopper did before, and a panel shows the history the model read.	Curate my wall (live app, source). 19,000 public-domain artworks from the Art Institute of Chicago. Hang three Hokusai prints, and the "Fashion for you" tab suggests scarves and kimonos from those art clicks alone.	Anomaly detection (source). An account takeover: after the owner's headphone views, someone carts a phone and then a lawn mower, and the session is flagged at the mower. No fraud labels, rules or training.

Requirements

• An Unbox AI API key. Create and copy the key at unboxai.com/behaviorgpt; the key also arrives by email.
• Python 3.11 or newer.

Quick start

pip install behaviorgpt
export UNBOXAI_API_KEY=...   # or pass api_key= to UnboxAIClient

from behaviorgpt import Search, UnboxAIClient, View

client = UnboxAIClient(market="us")

# a history of one search
res = client.complete([Search("running shoes")], limit=5)
print(res.names)

# the same call, personalized: a viewed item (Nike pants), then a query
res = client.complete([View("paB08NYK61PJ"), Search("shoes")], limit=5)
print(res.names)

# items close to one another in the model's space
print(client.similar_items(res.items[0].id).names)

complete takes the history and returns the items most likely to come next. Each result in res.items has an id, a score and the catalog row in data; res.to_pandas() gives a DataFrame if pandas is installed.

How it works

• One call, many features. Every request asks the same question: given what this person did, which items are they most likely to act on next? The history picks the feature. End it with a Search for search results, with a View for "more like this", with an Order for what they want after buying; leave it empty for a cold start.
• The whole sequence counts. The model reads the history in order, so the same query means different things after different actions: "gloves" after "golf clubs" returns golf gloves. market on the client says where the user is, which helps most when the history is short.
• Items are read from their content, not their ids. Each item is embedded from its name, brand, categories, image and price. That is why the model can rank a catalog it has never seen as soon as it is uploaded, with no interaction data and no training, and why those columns decide how well it does (catalog format).
• One pass per request. Item vectors are computed once when the catalog is embedded, so ranking the whole catalog costs one forward pass over the history rather than one per item: the model itself takes under a millisecond per query, and most of an API call's time is the network.

Events

A history is a list of three kinds of event:

• Search("running shoes"): a query.
• View(item_id): the person looked at an item. Any sign of interest counts as a view: a click, a like, a save, an item added to a cart.
• Order([item_id, ...]): a finished purchase of those items. Only which items were bought matters; quantities do not change results.

The names come from a store, but they work for any catalog: map your users' actions by meaning. In Curate my wall, "look closer" is a view and "hang it on the wall" is an order, since hanging a work means choosing it. To leave something out, such as an item the person removed, leave it out of the list: taking a work down drops it from the history the app sends.

complete predicts what the person looks at next. With predict="purchase" it predicts what else goes in the same purchase as the current session's items instead; that needs a history that does not end in a search.

client.complete([View(shoe)])                      # others also viewed
client.complete([View(shoe)], predict="purchase")  # bought together
client.complete([View(shoe), Order([shoe])])       # what they want after buying it

Your own catalog

The model can only return items it knows about. Out of the box the client uses retail_catalog, a sample retail catalog. To use the model on your own data, upload your catalog as a parquet file. A catalog doesn't have to be products for sale: artworks, articles, listings or anything else people browse and pick from work the same way.

docs/catalog-format.md lists the columns the file needs. A CSV with those column names converts to parquet with catalog_from_csv; examples/sample_catalog.csv shows what each column holds.

from behaviorgpt import catalog_from_csv

path = catalog_from_csv("my_catalog.csv")  # writes my_catalog.parquet
job = client.embed(path, wait=True, timeout=1800.0)
client.complete([Search("...")], catalog_id=job.catalog_id)

A catalog holds up to 100,000 items, and each API key holds 2 catalogs. The file name is the catalog's name, so uploading the same name again refreshes that catalog.

Once it is embedded, you can add or replace items, list and delete catalogs, and generate the keywords that sections uses to group results under titles such as "black coats":

client.add_items("new_items.parquet", catalog_id=job.catalog_id, wait=True)
client.list_catalogs()
client.delete_catalog("cat_...")

client.add_keywords(job.catalog_id, wait=True)  # about 2 hours per 20,000 items
for section in client.sections([Search("coat")], catalog_id=job.catalog_id).sections:
    print(section.title, [item.data["name"] for item in section.items])

docs/catalogs.md has the details: catalog slots, what replacing an item keeps, how long keywords take and what happens when a job fails.

If mapping your data to the format is hard, open a coding agent in this directory and ask it to embed your catalog. The repo ships a skill at .claude/skills/embed-catalog/SKILL.md that walks the agent through mapping your columns, building and validating the parquet, checking image URLs, and uploading. Claude Code picks it up automatically; for other agents, point them at that file.

To try your catalog in the storefront demo, select the BehaviorGPT V4.0-12.5B model, choose Bring your own catalog and enter your API key. Images must be publicly reachable for the demo to display them.

The notebook

notebooks/showcase.ipynb covers the model in eight steps: setup, a first query, one call for many features, how context changes the answer, then embedding your own catalog, inspecting the embedding space, querying it, and trying it in the demo.

Needs uv. Clone, install, add your key, register the kernel, start JupyterLab:

git clone https://github.com/Unbox-AI/behaviorgpt.git
cd behaviorgpt
uv sync
cp .env.example .env   # paste your key as UNBOXAI_API_KEY
uv run ipython kernel install --user --env VIRTUAL_ENV $(pwd)/.venv --name=behaviorgpt-env
uv run jupyter lab

JupyterLab opens in your browser. Open the notebook and pick the behaviorgpt-env kernel.

Async

In asyncio code, such as a FastAPI or aiohttp server, use AsyncUnboxAIClient. It takes the same arguments and has the same methods, awaited, so a call never blocks the event loop and many calls can run at once:

import asyncio

from behaviorgpt import AsyncUnboxAIClient, Search

async def main():
    async with AsyncUnboxAIClient(market="us") as client:
        shoes, gloves = await asyncio.gather(
            client.complete([Search("running shoes")], limit=5),
            client.complete([Search("gloves")], limit=5),
        )
        print(shoes.names, gloves.names)

asyncio.run(main())

Create one client and reuse it, for example for the lifetime of your server: async with closes its connections at the end, or call await client.aclose(). embed(..., wait=True) waits for the job without blocking other requests.