exa-architecture-variants

name	exa-architecture-variants
description	Choose and implement Exa architecture patterns at different scales: direct search, cached search, and RAG pipeline. Use when designing Exa integrations, choosing between simple search and full RAG, or planning architecture for different traffic volumes. Trigger with phrases like "exa architecture", "exa blueprint", "how to structure exa", "exa RAG design", "exa at scale".
allowed-tools	Read, Grep
version	1.0.0
license	MIT
author	Jeremy Longshore <[e-mail]>
compatible-with	claude-code, codex, openclaw
tags	["saas","exa","architecture","rag","scaling"]

Exa Architecture Variants

Overview

Three deployment architectures for Exa neural search at different scales. Each uses real Exa SDK methods: search, searchAndContents, findSimilar, getContents, and answer.

Decision Matrix

Factor	Direct Search	Cached Search	RAG Pipeline
Volume	< 1K/day	1K-50K/day	Any volume
Latency	500-2000ms	~50ms (cached)	3-8s total
Use Case	Simple search UI	Content aggregation	AI answers with citations
Complexity	Low	Medium	High
Cache Required	No	Yes (Redis/LRU)	Yes
Exa Methods	searchAndContents	searchAndContents + cache	All methods

Instructions

Variant 1: Direct Search Integration

Best for: Adding search to an existing app, < 1K queries/day.

import Exa from "exa-js";
import express from "express";

const app = express();
const exa = new Exa(process.env.EXA_API_KEY);

// Simple search endpoint
app.get("/api/search", async (req, res) => {
  const query = req.query.q as ;
   (!query)  res.().({ :  });

   {
     results =  exa.(query, {
      : ,
      : ,
      : { :  },
      : { : , query },
    });

    res.(results..( ({
      : r.,
      : r.,
      : r.?.() || r.?.(, ),
      : r.,
    })));
  }  (: ) {
    res.(err. || ).({ : err. });
  }
});