This page covers how to run models on Replicate within LangChain.

Installation and Setup​

• Create aReplicate account. Get your API key and set it as an environment variable (REPLICATE_API_TOKEN)
• Install theReplicate python client withpip install replicate

Calling a model​

Find a model on theReplicate explore page, and then paste in the model name and version in this format:owner-name/model-name:version

For example, for thisdolly model, click on the API tab. The model name/version would be:"replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899f0f7e001ec445893500e5"

Only themodel param is required, but any other model parameters can also be passed in with the formatinput={model_param: value, ...}

For example, if we were running stable diffusion and wanted to change the image dimensions:

Replicate(model="stability-ai/stable-diffusion:db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf", input={'image_dimensions': '512x512'})

Note that only the first output of a model will be returned.From here, we can initialize our model:

llm= Replicate(model="replicate/dolly-v2-12b:ef0e1aefc61f8e096ebe4db6b2bacc297daf2ef6899f0f7e001ec445893500e5")

And run it:

prompt="""
Answer the following yes/no question by reasoning step by step.
Can a dog drive a car?
"""
llm(prompt)

We can call any Replicate model (not just LLMs) using this syntax. For example, we can callStable Diffusion:

text2image= Replicate(model="stability-ai/stable-diffusion:db21e45d3f7023abc2a46ee38a23973f6dce16bb082a930b0c49861f96d1e5bf",input={'image_dimensions':'512x512'})

image_output= text2image("A cat riding a motorcycle by Picasso")