Search

- **Supabase** with PGVector for vector search
- **OpenAI/Mistral** for AI responses
- **Hugging Face** for embeddings
### Database Schema
```sql
-- Medical content chunks with embeddings
CREATE TABLE medical_content (
  id SERIAL PRIMARY KEY,
- Supabase project with PGVector extension
- OpenAI or Mistral API key
- Hugging Face API key (optional for server-side embeddings)
### Environment Variables
│   ├── routes/
│   │   ├── chat.ts         # Chat API endpoints
│   │   ├── embeddings.ts   # Embedding generation
│   │   └── static.ts       # Static file serving
│   └── index.ts            # Main API entry point

  try {
    // Get embedding
    const embResponse = await fetch("https://api.openai.com/v1/embeddings", {
      method: "POST",
      headers: {

  async getEmbedding(text: string, apiKey: string) {
    const response = await fetch("https://api.openai.com/v1/embeddings", {
      method: "POST",
      headers: {
      },
      body: JSON.stringify({
        model: "text-embedding-3-small", // IMPORTANT: Match your Pinecone embeddings
        input: text,
      }),

  try {
    // Get embedding
    const embResponse = await fetch("https://api.openai.com/v1/embeddings", {
      method: "POST",
      headers: {

import { Pinecone } from "https://esm.sh/@pinecone-database/pinecone@2.0.0";
// Use OpenAI client only for embeddings
const openai = new OpenAI({
  apiKey: Deno.env.get("OPENAI_API_KEY"),
  // Get embedding for query
  const embeddingResponse = await openai.embeddings.create({
    model: "text-embedding-3-small",
    input: query,

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

  // Get embedding for query
  const embeddingResponse = await openai.embeddings.create({
    model: "text-embedding-3-small",
    input: query,

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",

    "slug": "val-vibes",
    "link": "/blog/val-vibes",
    "description": "How to build semantic search with embeddings for Val Town within Val Town itself",
    "pubDate": "Tue, 18 Jun 2024 00:00:00 GMT",
    "author": "JP Posma",