Skip to main content

Bedrock JCVD πŸ•ΊπŸ₯‹


LangChain template that uses Anthropic's Claude on Amazon Bedrock to behave like JCVD.

I am the Fred Astaire of Chatbots! πŸ•Ί


Environment Setup​

AWS Credentials​

This template uses Boto3, the AWS SDK for Python, to call Amazon Bedrock. You must configure both AWS credentials and an AWS Region in order to make requests.

For information on how to do this, see AWS Boto3 documentation (Developer Guide > Credentials).

Foundation Models​

By default, this template uses Anthropic's Claude v2 (anthropic.claude-v2).

To request access to a specific model, check out the Amazon Bedrock User Guide (Model access)

To use a different model, set the environment variable BEDROCK_JCVD_MODEL_ID. A list of base models is available in the Amazon Bedrock User Guide (Use the API > API operations > Run inference > Base Model IDs).

The full list of available models (including base and custom models) is available in the Amazon Bedrock Console under Foundation Models or by calling aws bedrock list-foundation-models.


To use this package, you should first have the LangChain CLI installed:

pip install -U langchain-cli

To create a new LangChain project and install this as the only package, you can do:

langchain app new my-app --package bedrock-jcvd

If you want to add this to an existing project, you can just run:

langchain app add bedrock-jcvd

And add the following code to your file:

from bedrock_jcvd import chain as bedrock_jcvd_chain

add_routes(app, bedrock_jcvd_chain, path="/bedrock-jcvd")

(Optional) Let's now configure LangSmith. LangSmith will help us trace, monitor and debug LangChain applications. You can sign up for LangSmith here. If you don't have access, you can skip this section

export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project> # if not specified, defaults to "default"

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

This will start the FastAPI app with a server is running locally at http://localhost:8000

We can see all templates at

We can also access the playground at

Help us out by providing feedback on this documentation page: