exa-core-workflow-a

# Exa Core Workflow A — Neural Search ## Overview Primary workflow for Exa: semantic web search using `search()` and `searchAndContents()`. Exa's neural search understands query meaning rather than matching keywords, making it ideal for research, RAG pipelines, and content discovery. This skill covers search types, content extraction, filtering, and categories. ## Prerequisites - `exa-js` installed and `EXA_API_KEY` configured - Understanding of neural vs keyword search tradeoffs ## Search Types | Type | Latency | Best For | |------|---------|----------| | `auto` (default) | 300-1500ms | General queries; Exa picks best approach | | `neural` | 500-2000ms | Conceptual/semantic queries | | `keyword` | 200-500ms | Exact terms, names, URLs | | `fast` | p50 < 425ms | Speed-critical applications | | `instant` | < 150ms | Real-time autocomplete | | `deep` | 2-5s | Maximum quality, light deep search | | `deep-reasoning` | 5-15s | Complex research questions | ## Instructions ### Step 1: Basic Neural Search ```typescript import Exa from "exa-js"; const exa = new Exa(process.env.EXA_API_KEY); // Neural search: phrase your query as a statement, not a question const results = await exa.search( "comprehensive guide to building production RAG systems", { type: "neural", numResults: 10, // max 100 for neural/deep } ); for (const r of results.results) { console.log(`[${r.score.toFixed(2)}] ${r.title} — ${r.url}`); console.log(` Published: ${r.publishedDate || "unk...