Added embedding service
This commit is contained in:
@@ -5,13 +5,81 @@ const {getEnv} = require('@nexusai/shared');
|
||||
const app = express();
|
||||
app.use(express.json());
|
||||
|
||||
const PORT = getEnv('PORT', '3003'); // Default to 3003 if PORT is not set
|
||||
const PORT = getEnv('PORT', '3003'); // Default to 3003 if PORT is not set
|
||||
const OLLAMA_URL = getEnv('OLLAMA_URL', 'http://localhost:11434'); // URL for Ollama API
|
||||
const EMBED_MODEL = getEnv('EMBED_MODEL', 'nomic-embed-text'); // Ollama model for embeddings
|
||||
|
||||
console.log('OLLAMA_URL:', OLLAMA_URL);
|
||||
console.log('EMBED_MODEL:', EMBED_MODEL);
|
||||
|
||||
//OLLAMA embedding helper function
|
||||
async function embedText(text) {
|
||||
const res = await fetch(`${OLLAMA_URL}/api/v1/embeddings`, {
|
||||
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.embedding;
|
||||
}
|
||||
|
||||
|
||||
/**** 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, () => {
|
||||
console.log(`Embedding Service listening on port ${PORT}`);
|
||||
});
|
||||
Reference in New Issue
Block a user