Skip to main content


Banana is focused on building the machine learning infrastructure.

This example goes over how to use LangChain to interact with Banana models

##Installing the langchain packages needed to use the integration
%pip install -qU langchain-community
# Install the package
%pip install --upgrade --quiet banana-dev
# get new tokens:
# We need three parameters to make a API call:
# * a team api key
# * the model's unique key
# * the model's url slug

import os

# You can get this from the main dashboard
# at
os.environ["BANANA_API_KEY"] = "YOUR_API_KEY"
# OR
# BANANA_API_KEY = getpass()
from langchain.chains import LLMChain
from langchain_community.llms import Banana
from langchain_core.prompts import PromptTemplate
API Reference:LLMChain | Banana | PromptTemplate
template = """Question: {question}

Answer: Let's think step by step."""

prompt = PromptTemplate.from_template(template)
# Both of these are found in your model's
# detail page in
llm = Banana(model_key="YOUR_MODEL_KEY", model_url_slug="YOUR_MODEL_URL_SLUG")
llm_chain = LLMChain(prompt=prompt, llm=llm)
question = "What NFL team won the Super Bowl in the year Justin Beiber was born?"

Was this page helpful?

You can also leave detailed feedback on GitHub.