Skip to main content


Predibase allows you to train, finetune, and deploy any ML model—from linear regression to large language model.

This example demonstrates using Langchain with models deployed on Predibase


To run this notebook, you'll need a Predibase account and an API key.

You'll also need to install the Predibase Python package:

pip install predibase
import os


Initial Call

from langchain.llms import Predibase

model = Predibase(
model="vicuna-13b", predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN")

API Reference:

response = model("Can you recommend me a nice dry wine?")

Chain Call Setup

llm = Predibase(
model="vicuna-13b", predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN")


from langchain.chains import LLMChain
from langchain.prompts import PromptTemplate
# This is an LLMChain to write a synopsis given a title of a play.
template = """You are a playwright. Given the title of play, it is your job to write a synopsis for that title.

Title: {title}
Playwright: This is a synopsis for the above play:"""
prompt_template = PromptTemplate(input_variables=["title"], template=template)
synopsis_chain = LLMChain(llm=llm, prompt=prompt_template)
# This is an LLMChain to write a review of a play given a synopsis.
template = """You are a play critic from the New York Times. Given the synopsis of play, it is your job to write a review for that play.

Play Synopsis:
Review from a New York Times play critic of the above play:"""
prompt_template = PromptTemplate(input_variables=["synopsis"], template=template)
review_chain = LLMChain(llm=llm, prompt=prompt_template)
# This is the overall chain where we run these two chains in sequence.
from langchain.chains import SimpleSequentialChain

overall_chain = SimpleSequentialChain(
chains=[synopsis_chain, review_chain], verbose=True

API Reference:

review ="Tragedy at sunset on the beach")

Fine-tuned LLM (Use your own fine-tuned LLM from Predibase)

from langchain.llms import Predibase

model = Predibase(
model="my-finetuned-LLM", predibase_api_key=os.environ.get("PREDIBASE_API_TOKEN")
# replace my-finetuned-LLM with the name of your model in Predibase

API Reference:

# response = model("Can you help categorize the following emails into positive, negative, and neutral?")