Build a RAG Pipeline

User Query
    ↓
Embed query (Runcrate embedding model)
    ↓
Vector similarity search (your vector DB)
    ↓
Top-K relevant chunks
    ↓
Prompt = system instructions + chunks + user query
    ↓
Chat completion (Runcrate chat model)
    ↓
Grounded answer

import { runcrate } from '@runcrate/ai';
import { embedMany } from 'ai';
import { sql } from '@vercel/postgres';

const docs = [
  { id: '1', title: 'Pricing', content: 'GPU instances start at $0.35/hr for an RTX 4090...' },
  { id: '2', title: 'Storage', content: 'Persistent volumes cost $0.03/GB/month...' },
  { id: '3', title: 'Auto-recharge', content: 'Set a credit threshold and recharge amount...' },
];

// Embed all documents
const { embeddings } = await embedMany({
  model: runcrate.embeddingModel('BAAI/bge-large-en-v1.5'),
  values: docs.map(d => `${d.title}: ${d.content}`),
});

// Store in pgvector
for (let i = 0; i < docs.length; i++) {
  await sql`
    INSERT INTO documents (id, title, content, embedding)
    VALUES (${docs[i].id}, ${docs[i].title}, ${docs[i].content}, ${JSON.stringify(embeddings[i])})
  `;
}

import { runcrate } from '@runcrate/ai';
import { embed, generateText } from 'ai';
import { sql } from '@vercel/postgres';

async function askDocs(question: string) {
  // Embed the question
  const { embedding } = await embed({
    model: runcrate.embeddingModel('BAAI/bge-large-en-v1.5'),
    value: question,
  });

  // Find similar documents
  const { rows } = await sql`
    SELECT title, content, 1 - (embedding <=> ${JSON.stringify(embedding)}) AS similarity
    FROM documents
    ORDER BY embedding <=> ${JSON.stringify(embedding)}
    LIMIT 5
  `;

  // Generate answer with context
  const context = rows.map(r => `[${r.title}]: ${r.content}`).join('\n\n');

  const { text } = await generateText({
    model: runcrate('deepseek-ai/DeepSeek-V3'),
    messages: [
      {
        role: 'system',
        content: `Answer the user's question using ONLY the following context. If the context doesn't contain the answer, say so.\n\n${context}`,
      },
      { role: 'user', content: question },
    ],
  });

  return { answer: text, sources: rows.map(r => r.title) };
}

const result = await askDocs('How much does storage cost?');
console.log(result.answer);
console.log('Sources:', result.sources);

from runcrate import Runcrate
import numpy as np

client = Runcrate(api_key="rc_live_...")

# Your documents
docs = [
    "GPU instances are billed hourly. RTX 4090 starts at $0.35/hr, A100 at $1.20/hr, H100 at $2.50/hr.",
    "Storage volumes cost $0.03/GB/month, charged weekly. Volumes persist across instance termination.",
    "Auto-recharge tops up credits automatically when your balance drops below a threshold you set.",
    "API keys are scoped to a workspace. The full key is shown only once at creation.",
    "The Models API supports chat, image, video, TTS, and ASR across 140+ open-source models.",
]

# Embed all documents
doc_embeddings = []
for doc in docs:
    resp = client.models.embed(model="BAAI/bge-large-en-v1.5", input=doc)
    doc_embeddings.append(resp.data[0].embedding)

doc_embeddings = np.array(doc_embeddings)

def ask(question: str, top_k: int = 3) -> str:
    # Embed the question
    q_resp = client.models.embed(model="BAAI/bge-large-en-v1.5", input=question)
    q_vec = np.array(q_resp.data[0].embedding)

    # Cosine similarity
    sims = doc_embeddings @ q_vec / (
        np.linalg.norm(doc_embeddings, axis=1) * np.linalg.norm(q_vec)
    )
    top_indices = np.argsort(sims)[-top_k:][::-1]

    context = "\n\n".join(docs[i] for i in top_indices)

    # Generate answer
    response = client.models.chat_completion(
        model="deepseek-ai/DeepSeek-V3",
        messages=[
            {"role": "system", "content": f"Answer using ONLY this context:\n\n{context}"},
            {"role": "user", "content": question},
        ],
    )

    return response.choices[0].message.content

print(ask("How much does an A100 cost per hour?"))
print(ask("What happens when my credits run out?"))