A simple HTTP interface for querying and managing your Pinecone vector database. Search through your documents using natural language queries via REST API endpoints.

To use PineconeIndex in your own Val Town project:

import PineconeIndex from "https://esm.town/v/peterqliu/PineconeIndex/PineconeIndex";

const index = new PineconeIndex({
  name: "my-index-name",              // Your Pinecone index name
  model: "text-embedding-ada-002",    // OpenAI embedding model
  dimensions: 1536,                   // Vector dimensions (1536 for ada-002)
  pineconeKey: Deno.env.get("PINECONE_KEY"),
  modelToken: Deno.env.get("OPENAI_KEY"),
  namespace: "optional-namespace"     // Optional: isolate data within index
});

// Use directly in code
const results = await index.query("search text");
await index.upsertRecords(["doc 1", "doc 2"]);

// Or create HTTP endpoints
export default async function(req: Request) {
  return await index.handleRequest(req);
}

1. Set Environment Variables

   • PINECONE_KEY: Your Pinecone API key
   • OPENAI_KEY: Your OpenAI API key

2. Use the API

   # Search your documents
   curl -X POST https://your-val-url.web.val.run/query/ \
     -H "Content-Type: application/json" \
     -d '"machine learning applications"'

Find the most relevant documents for your query.

POST /query/

Request Body:

"your search query here"

or

{
  "query": "your search query here"
}

Response:

{
  "matches": [
    {
      "id": "doc-123",
      "score": 0.95,
      "metadata": {
        "text": "Machine learning is transforming..."
      }
    }
  ]
}

Upload new documents to your index.

POST /upsert/

Request Body:

{
  "texts": [
    "First document content",
    "Second document content"
  ]
}

Response:

{
  "success": true,
  "count": 2
}

Remove all documents from your index.

POST /empty/

Response:

{
  "success": true,
  "message": "Index cleared"
}

Check if the service is running and configured properly.

GET /health/

Response:

{
  "status": "healthy",
  "timestamp": "2025-12-20T19:21:17.737Z",
  "config": {
    "pineconeKey": "✓ Set",
    "openaiKey": "✓ Set"
  }
}

const API_URL = 'https://your-val-url.web.val.run';

// Search for documents
async function search(query) {
  const response = await fetch(`${API_URL}/query/`, {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify(query)
  });
  return response.json();
}

// Add new documents
async function addDocuments(texts) {
  const response = await fetch(`${API_URL}/upsert/`, {
    method: 'POST',
    headers: { 'Content-Type': 'application/json' },
    body: JSON.stringify({ texts })
  });
  return response.json();
}

// Example usage
const results = await search('artificial intelligence trends');
await addDocuments(['AI is revolutionizing healthcare', 'Machine learning in finance']);

import requests

API_URL = 'https://your-val-url.web.val.run'

# Search documents
def search(query):
    response = requests.post(f'{API_URL}/query/', json=query)
    return response.json()

# Add documents
def add_documents(texts):
    response = requests.post(f'{API_URL}/upsert/', json={'texts': texts})
    return response.json()

# Example usage
results = search('climate change solutions')
add_documents(['Solar energy is becoming more efficient', 'Wind power costs are decreasing'])

# Search
curl -X POST https://your-val-url.web.val.run/query/ \
  -H "Content-Type: application/json" \
  -d '"renewable energy technologies"'

# Add documents
curl -X POST https://your-val-url.web.val.run/upsert/ \
  -H "Content-Type: application/json" \
  -d '{"texts": ["Document 1", "Document 2"]}'

# Clear index
curl -X POST https://your-val-url.web.val.run/empty/

# Health check
curl https://your-val-url.web.val.run/health/

The API returns standard HTTP status codes:

• 200 - Success
• 400 - Bad Request (missing required fields)
• 405 - Method Not Allowed (wrong HTTP method)
• 500 - Server Error (API key issues, service problems)

Error responses include helpful messages:

{
  "error": "Query text is required",
  "hint": "Make sure PINECONE_KEY and OPENAI_KEY environment variables are set"
}

The service uses these default settings:

• Index: wikipedia-simple-text-embedding-ada-002-250k
• Model: text-embedding-ada-002
• Dimensions: 1536
• Results: Top 10 matches per query

To customize these settings, modify the PineconeIndex configuration in the code.