A simple interface for querying and managing your Pinecone vector database. Search through your documents using natural language queries.

To use PineconeIndex in your own Val Town project:

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

const pineconeKey = Deno.env.get("PINECONE_KEY");
const modelToken = Deno.env.get("OPENAI_KEY");

const index = new PineconeIndex({
  name: "2025-all-docs",
  model: "text-embedding-ada-002",
  dimensions: 1536,
  pineconeKey,
  modelToken,
});

// Use the methods directly
const results = await index.query("machine learning applications");
await index.upsertRecords(["Document 1", "Document 2"]);
await index.empty();

Find the most relevant documents for your query.

const results = await index.query("your search text");

Returns:

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

Upload new documents to your index.

await index.upsertRecords([
  "First document content",
  "Second document content"
]);

Remove all documents from your index.

await index.empty();

Create a new Pinecone index (if it doesn't exist).

await index.create();

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

const index = new PineconeIndex({
  name: "my-documents",
  model: "text-embedding-ada-002", 
  dimensions: 1536,
  pineconeKey: Deno.env.get("PINECONE_KEY"),
  modelToken: Deno.env.get("OPENAI_KEY"),
});

// Add some documents
await index.upsertRecords([
  "AI is revolutionizing healthcare",
  "Machine learning enables automation",
  "Solar energy is becoming more efficient"
]);

// Search for relevant documents
const results = await index.query("renewable energy technologies");
console.log(results.matches);

Create an HTTP endpoint that uses your index:

// query index with string for nearest neighbors
export default async function (req: Request): Promise<Response> {
  return await index.handleRequest(req);
}

When using the HTTP server, operations are determined by the URL path. The first segment after the domain specifies the operation to perform.

https://your-val-url.web.val.run/{operation}/

Where {operation} can be:

• query - Search for documents
• upsert - Add new documents
• empty - Clear the index
• health - Check server status

POST /query/
Content-Type: application/json

"your search query here"

Response:

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

POST /upsert/
Content-Type: application/json

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

Response:

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

POST /empty/

Response:

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

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
const searchResponse = await fetch(`${API_URL}/query/`, {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify("artificial intelligence trends")
});
const results = await searchResponse.json();

// Add documents
await fetch(`${API_URL}/upsert/`, {
  method: "POST",
  headers: { "Content-Type": "application/json" },
  body: JSON.stringify({
    texts: ["AI is revolutionizing healthcare", "Machine learning in finance"]
  })
});

// Clear index
await fetch(`${API_URL}/empty/`, { method: "POST" });

// Health check
const healthResponse = await fetch(`${API_URL}/health/`);
const health = await healthResponse.json();

# 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/

import requests

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

# Search documents
response = requests.post(f'{API_URL}/query/', json="climate change solutions")
results = response.json()

# Add documents
requests.post(f'{API_URL}/upsert/', json={
    'texts': ['Solar energy is efficient', 'Wind power costs decreasing']
})

# Health check
health = requests.get(f'{API_URL}/health/').json()

The HTTP API returns standard 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"
}