I Needed a Smart Search — So I Called an AI API (No Model Training)

A developer built a natural language search for an internal documentation site by calling an AI API instead of training a custom model. The approach uses a well-crafted prompt and a small set of relevant documents to map user queries to the right content, avoiding the complexity of keyword search, synonym mapping, or local NLP libraries. The solution, implemented in Node.js, sends the user's question along with documentation chunks to an AI endpoint and returns the most relevant entry.

A few months ago, I was building a documentation site for an internal tool. Users kept asking for a search that "understands" — you know, like typing "How do I reset my password?" and getting the right help article, even if the article title didn't contain the word "reset." I thought: this is 2024, everyone's doing AI. How hard could it be? Famous last words. I started with a simple keyword search. ElasticSearch, fuzzy matching, the works. It worked okay for exact terms but failed on paraphrasing. Someone would ask "I can't log in" and the search would return nothing because the article said "authentication failure." I tried adding synonyms — tedious, endless. I tried a small NLP library spaCy for entity extraction, but it added 200MB to my bundle and still couldn't understand intent beyond named entities. I needed something that could take a natural language query and map it to the right content — without training my own model or spending weeks tuning. I wrote a huge mapping of phrases to article IDs. It broke every time someone used a new variant. Maintenance nightmare. python import spacy nlp = spacy.load "en core web lg" def extract intent text : doc = nlp text ... complex logic to guess intent This worked in demos but was too slow for real-time search and required a dedicated server. Also, training it on our domain data was out of scope. I tried using sentence-transformers to generate embeddings locally, then cosine similarity. That was promising but required a decent GPU for reasonable latency. Still overkill for a small docs site. I realized I didn't need to host a model. I just needed a quick API that could take a question and return a structured answer. Many providers out there offer exactly that — a simple HTTP POST with a prompt and some context. Here's the approach that worked for me: The key insight: you don't need to fine-tune anything. A well-crafted prompt plus a small set of relevant documents is enough for most internal tools. I built this in Node.js Express . Here's the simplified version: python // server.js import express from 'express'; import fetch from 'node-fetch'; const app = express ; app.use express.json ; // Your AI API endpoint e.g., from a service like ai.interwestinfo.com const AI API URL = process.env.AI API URL || 'https://ai.interwestinfo.com/api/query'; const AI API KEY = process.env.AI API KEY; // Our documentation chunks simplified const docs = { id: 1, title: 'Reset Password', content: 'To reset your password, go to Settings Security...' }, { id: 2, title: 'Login Troubleshooting', content: 'If you cannot log in, check your internet connection...' }, // ... more chunks ; app.post '/api/search', async req, res = { const { query } = req.body; if query return res.status 400 .json { error: 'Missing query' } ; try { // 1. Prepare a prompt with the user's question and our docs const context = docs.map d = ${d.title} : ${d.content} .join '\n' ; const prompt = You are a search assistant. Given the following documentation, find the most relevant entry for the user's question. Return only the ID and title.\n\nDocumentation:\n${context}\n\nUser question: ${query} ; // 2. Call the AI API const response = await fetch AI API URL, { method: 'POST', headers: { 'Content-Type': 'application/json', 'Authorization': Bearer ${AI API KEY} }, body: JSON.stringify { prompt, max tokens: 50 } } ; const data = await response.json ; // 3. Parse the response format depends on provider const result = parseAIResponse data ; res.json result ; } catch err { console.error 'Search failed:', err ; res.status 500 .json { error: 'Search unavailable' } ; } } ; function parseAIResponse data { // Simple parsing: assume API returns text like "ID: 1, Title: Reset Password" const lines = data.response?.split '\n' || ; return lines.reduce acc, line = { if line.startsWith 'ID:' acc.id = line.split ':' 1 .trim ; if line.startsWith 'Title:' acc.title = line.split ':' 1 .trim ; return acc; }, {} ; } app.listen 3000, = console.log 'Search API running' ; Note : Replace the prompt style and response parsing based on your AI provider. Many endpoints accept a system and user message format instead. Also, the API you choose matters. Some providers have rate limits, some don't support long contexts. Test with your actual content size. My docs site now handles questions like "How do I change my email?" and returns the right article — even though the article says "Update account settings." Users are happier, support tickets about navigation dropped by 30%. And I didn't have to become an ML engineer. I just called an API with a good prompt. What's your setup look like? Have you tried adding AI features to your app? I'm curious to hear what worked or didn't for you.