Vercel Anyscale IntegrationMarketplace
Learn how to integrate Anyscale with Vercel.Anyscale Endpoints offers scalable computing solutions for handling complex, large-scale data processing tasks. It is particularly suited for distributed computing environments. The Vercel Anyscale integration enables you to leverage these capabilities in your applications, enhancing their scalability and computational efficiency.
You can use the Vercel and Anyscale integration to power a variety of AI applications, including:
- Distributed data processing: Use Anyscale for handling large-scale, distributed data processing tasks efficiently
- Machine learning workflows: Use Anyscale for training and deploying complex machine learning models that require high computational power
- Real-time analytics: Use Anyscale for real-time data analytics, ideal for applications needing quick data processing and insight extraction
Anyscale models provide scalable solutions for complex computational tasks, emphasizing efficiency in distributed computing and large-scale data processing across various industries.
CodeLlama-34b-Instruct
Type: Code
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 34B parameter version, fine tuned for instructions. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
CodeLlama-70b-Instruct
Type: Code
Code Llama is a collection of pretrained and fine-tuned generative text models ranging in scale from 7 billion to 70 billion parameters. This is the 70B parameter version, fine tuned for instructions. This model is designed for general code synthesis and understanding. Links to other models can be found in the index at the bottom.
Llama-2-13b-Chat
Type: Chat
Meta's Llama 2 13 billion paramater model
Llama-2-70b-Chat
Type: Chat
Meta's Llama 2 70 billion paramater model
Llama-2-7b-Chat
Type: Chat
Meta's Llama 2 7 billion paramater model
Llama-Guard-7b
Type: Chat
Llama Guard is a high-performance model designed to enhance your existing API-based safeguards. This model is adept at identifying various common types of potentially risky or violating content, catering to a range of developer use cases. It is crucial, however, to regard this tool as a flexible starting point rather than a universal solution.
Mistral-7b-Instruct-v0.1
Type: Chat
The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets. This model supports function calling and JSON mode.
Mistral-7b-OpenOrca
Type: Chat
This is a Mistral-7B finetune model.
Mixtral-8x7B-Instruct-v0.1
Type: Chat
The Mixtral-8x7B Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts.
NeuralHermes-2.5-Mistral-7B
Type: Chat
The mlabonne/NeuralHermes-2.5-Mistral-7B Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-Instruct-v0.1 generative text model using a variety of publicly available conversation datasets.
zephyr-7b-beta
Type: Chat
Zephyr-7B-β is the second model in the series, and is a fine-tuned version of mistralai/Mistral-7B-v0.1 that was trained on on a mix of publicly available, synthetic datasets using Direct Preference Optimization (DPO).
The Vercel Anyscale Endpoints integration can be accessed through the AI tab on your Vercel dashboard.
To follow this guide, you'll need the following:
- An existing Vercel project
- The latest version of Vercel CLI
pnpm i -g vercel@latest
- Navigate to the AI tab in your Vercel dashboard
- Select Anyscale Endpoints from the list of providers, and press Add
- Review the provider information, and press Add Provider
- You can now select which projects the provider will have access to. You can choose from All Projects or Specific Projects
- If you select Specific Projects, you'll be prompted to select the projects you want to connect to the provider. The list will display projects associated with your scoped team
- Multiple projects can be selected during this step
- Select the Connect to Project button
- You'll be redirected to the provider's website to complete the connection process
- Once the connection is complete, you'll be redirected back to the Vercel dashboard, and the provider integration dashboard page. From here you can manage your provider settings, view usage, and more
- Pull the environment variables into your project using Vercel CLI
terminal
vercel env pull .env.development.local - Install the providers package
pnpm i openai ai - Connect your project using the code below:
app/api/chat/route.ts// app/api/chat/route.tsimport { OpenAIStream, StreamingTextResponse } from 'ai';import OpenAI from 'openai';const anyscale = new OpenAI({apiKey: process.env.OPENAI_API_KEY || '',baseURL: 'https://api.endpoints.anyscale.com/v1',});export async function POST(req: Request) {// Extract the `messages` from the body of the requestconst { messages } = await req.json();// Request the OpenAI-compatible API for the response based on the promptconst response = await anyscale.chat.completions.create({model: 'meta-llama/Llama-2-70b-chat-hf',stream: true,messages: messages,});// Convert the response into a friendly text-streamconst stream = OpenAIStream(response);// Respond with the streamreturn new StreamingTextResponse(stream);}
- Add the provider to your page using the code below:
app/chat/page.tsx// app/chat/page.tsx'use client';import { useChat } from 'ai/react';export default function Chat() {const { messages, input, handleInputChange, handleSubmit } = useChat();return (<div>{messages.map((m) => (<div key={m.id}>{m.role === 'user' ? 'User: ' : 'AI: '}{m.content}</div>))}<form onSubmit={handleSubmit}><inputvalue={input}placeholder="Say something..."onChange={handleInputChange}/></form></div>);}
Was this helpful?