Build an MCP server using the roll dice pattern to create a digital twin assistant that can answer questions about a person's professional profile using RAG (Retrieval-Augmented Generation).
Sign in to like and favorite skills
Build an MCP server using the roll dice pattern to create a digital twin assistant that can answer questions about a person's professional profile using RAG (Retrieval-Augmented Generation).
UPSTASH_VECTOR_REST_URL= UPSTASH_VECTOR_REST_TOKEN= GROQ_API_KEY=
import { Index } from "@upstash/vector" const index = new Index({ url: process.env.UPSTASH_VECTOR_REST_URL!, token: process.env.UPSTASH_VECTOR_REST_TOKEN!, }) // RAG search example await index.query({ data: "What is your experience with Python?", topK: 3, includeMetadata: true, })
import Groq from "groq-sdk" const groq = new Groq({ apiKey: process.env.GROQ_API_KEY!, }) const completion = await groq.chat.completions.create({ messages: [ { role: "system", content: "You are an AI digital twin. Answer in first person." }, { role: "user", content: prompt } ], model: "llama-3.1-8b-instant", temperature: 0.7, max_tokens: 500, })
The professional profile data is structured as content chunks with the following format:
interface ContentChunk { id: string; title: string; type: string; content: string; metadata: { category: string; tags: string[]; [key: string]: any; }; }
Content types include:
personalachievementskillprojecteducationcareer_goalsinterview_prepNote: This file provides context for GitHub Copilot to generate accurate, project-specific code suggestions. Keep it updated as requirements evolve.