How to Use Vultr Serverless Inference in Python with Langchain

Vultr Serverless Inference allows you to run inference workloads for large language models such as Mixtral 8x7B, Mistral 7B, Meta Llama 2 70B, and more. Using Vultr Serverless Inference, you can run inference workloads without having to worry about the infrastructure, and you only pay for the input and output tokens.

This guide demonstrates step-by-step process to start using Vultr Serverless Inference in Python with Langchain.

Prerequisites

Before you begin, you must:

• Create a Vultr Serverless Inference Subscription
• Fetch the API key for Vultr Serverless Inference
• Python 3.10 or later

Set Up the Environment

1. Create a new project directory and navigate to the project directory.

   console Copy

   $ mkdir vultr-serverless-inference-python-langchain
   $ cd vultr-serverless-inference-python-langchain
   

2. Create a new Python virtual environment.

   console Copy

   $ python3 -m venv venv
   $ source venv/bin/activate
   

3. Install the required Python packages.

   console Copy

   (venv) $ pip install langchain-openai
   

Inference via Langchain

Langchain provides a Python SDK to run inference workloads for Vultr Serverless Inference. You can use the langchain-openai package to make the API calls.

1. Create a new Python file name inference_langchain.py.

   console Copy

   (venv) $ nano inference_langchain.py
   

2. Add the following code to inference_langchain.py.

   python Copy

   import os
   from langchain_openai import ChatOpenAI
   from langchain_core.messages import HumanMessage, SystemMessage
   
   api_key = os.environ.get('VULTR_SERVERLESS_INFERENCE_API_KEY')
   
   # Set the model
   # List of available models: https://api.vultrinference.com/v1/chat/models
   model = ''
   messages = [
       HumanMessage(content="What is the capital of India?"),
   ]
   
   client = ChatOpenAI(openai_api_key=api_key, openai_api_base='https://api.vultrinference.com/v1' model=model)
   llm_response = chat.invoke(messages)
   
   print(llm_response.content)
   

3. Run the inference-langchain.py file.

   console Copy

   (venv) $ export VULTR_SERVERLESS_INFERENCE_API_KEY=<your_api_key>
   (venv) $ python inference-langchain.py
   

   Here, the inference_langchain.py file uses the langchain-openai package to run inference workloads for Vultr Serverless Inference. Langchain uses Langchain Expression Language (LCEL) for defining different types of messages such as HumanMessage and SystemMessage. For more information, refer to the Langchain documentation.

Conclusion

In this guide, you learned how to use Vultr Serverless Inference in Python with Langchain. You can now integrate Vultr Serverless Inference into your Python applications that uses Langchain to generate completions for large language models.