82 lines
2.4 KiB
JavaScript
82 lines
2.4 KiB
JavaScript
require ('dotenv').config();
|
|
const express = require('express');
|
|
const {getEnv, OLLAMA, PORTS, logger} = require('@nexusai/shared');
|
|
|
|
const app = express();
|
|
app.use(express.json());
|
|
|
|
const PORT = getEnv('PORT', PORTS.EMBEDDING);
|
|
const OLLAMA_URL = getEnv('OLLAMA_URL', OLLAMA.DEFAULT_URL);
|
|
const EMBED_MODEL = getEnv('EMBEDDING_MODEL', OLLAMA.EMBED_MODEL);
|
|
|
|
//OLLAMA embedding helper function
|
|
async function embedText(text) {
|
|
const res = await fetch(`${OLLAMA_URL}/api/embed`, {
|
|
method: 'POST',
|
|
headers: { 'Content-Type': 'application/json' },
|
|
body: JSON.stringify({ model: EMBED_MODEL, input: text })
|
|
});
|
|
|
|
if (!res.ok) {
|
|
throw new Error(`Ollama error: ${res.status} ${res.statusText}`);
|
|
}
|
|
|
|
const data = await res.json();
|
|
return data.embeddings[0];
|
|
}
|
|
|
|
|
|
/**** ROUTES ***** */
|
|
|
|
// Health check endpoint
|
|
app.get('/health', (req,res) => {
|
|
res.json({ service: 'Embedding Service', status: 'healthy' });
|
|
})
|
|
|
|
// Single text embedding
|
|
app.post('/embed', async (req, res) => {
|
|
const { text } = req.body;
|
|
if (!text || typeof text !== 'string' || text.trim() === '') {
|
|
return res.status(400).json({ error: 'text is required and must be empty' });
|
|
}
|
|
|
|
try {
|
|
const embedding = await embedText(text.trim());
|
|
res.json({
|
|
embedding,
|
|
model: EMBED_MODEL,
|
|
dimensions: embedding.length
|
|
});
|
|
} catch (err) {
|
|
res.status(502).json({ error: 'Embedding failed', detail: err.message });
|
|
}
|
|
});
|
|
|
|
// Batch embedding endpoint
|
|
app.post('/embed/batch', async (req, res) => {
|
|
const { texts } = req.body;
|
|
if (!Array.isArray(texts) || texts.length ===0 ) {
|
|
return res.status(400).json({ error: 'texts array must not be empty' });
|
|
}
|
|
|
|
try {
|
|
//sequential embedding for now, Ollama doesn't natively parallize embeddings
|
|
const embeddings = [];
|
|
for (const text of texts) {
|
|
embeddings.push(await embedText(text.trim()));
|
|
}
|
|
res.json ({
|
|
embeddings,
|
|
model: EMBED_MODEL,
|
|
dimensions: embeddings[0].length,
|
|
count: embeddings.length
|
|
})
|
|
} catch (err) {
|
|
res.status(502).json({ error: 'Batch embedding failed', detail: err.message });
|
|
}
|
|
})
|
|
|
|
/******* Start Server ********/
|
|
app.listen(PORT, () => {
|
|
logger.info(`Embedding Service listening on port ${PORT}`);
|
|
}); |