Vector Database API Key

Pinecone REST API

Serverless vector database for AI applications

Pinecone is a fully managed vector database built for AI and machine learning applications. It provides real-time vector similarity search and powers recommendation engines, semantic search, RAG applications, and other AI use cases. Developers use Pinecone to store and query high-dimensional vector embeddings at scale without managing infrastructure.

Base URL https://api.pinecone.io

API Endpoints

Method	Endpoint	Description
GET	`/indexes`	List all indexes in your Pinecone project
POST	`/indexes`	Create a new vector index with specified dimensions and configuration
GET	`/indexes/{indexName}`	Get details about a specific index including status and configuration
DELETE	`/indexes/{indexName}`	Delete an index and all its vectors permanently
POST	`/indexes/{indexName}/upsert`	Insert or update vectors in an index with metadata
POST	`/indexes/{indexName}/query`	Query an index with a vector to find similar vectors
POST	`/indexes/{indexName}/delete`	Delete vectors from an index by ID or metadata filter
GET	`/indexes/{indexName}/fetch`	Fetch vectors by ID from an index
POST	`/indexes/{indexName}/update`	Update vector values or metadata for existing vectors
GET	`/indexes/{indexName}/describe_index_stats`	Get statistics about an index including vector count and fullness
POST	`/collections`	Create a static copy of an index as a collection
GET	`/collections`	List all collections in your project
DELETE	`/collections/{collectionName}`	Delete a collection permanently

Code Examples

# Query vectors for similarity search
curl -X POST "https://index-name-project.svc.environment.pinecone.io/query" \
  -H "Api-Key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "vector": [0.1, 0.2, 0.3, 0.4],
    "topK": 10,
    "includeMetadata": true,
    "includeValues": true
  }'

// Query vectors using the Pinecone client
const { Pinecone } = require('@pinecone-database/pinecone');

const pinecone = new Pinecone({
  apiKey: 'YOUR_API_KEY'
});

const index = pinecone.index('index-name');

const queryResponse = await index.query({
  vector: [0.1, 0.2, 0.3, 0.4],
  topK: 10,
  includeMetadata: true,
  includeValues: true
});

console.log(queryResponse.matches);

# Query vectors using the Pinecone Python client
from pinecone import Pinecone

pc = Pinecone(api_key="YOUR_API_KEY")
index = pc.Index("index-name")

query_response = index.query(
    vector=[0.1, 0.2, 0.3, 0.4],
    top_k=10,
    include_metadata=True,
    include_values=True
)

for match in query_response['matches']:
    print(f"ID: {match['id']}, Score: {match['score']}")

Connect Pinecone to AI

Deploy a Pinecone MCP server on IOX Cloud and connect it to Claude, ChatGPT, Cursor, or any AI client. Your AI assistant gets direct access to Pinecone through these tools:

search_vectors Perform semantic similarity search across vector embeddings to find relevant documents or content based on natural language queries

upsert_embeddings Store vector embeddings with metadata for documents, images, or other content to enable AI-powered search and retrieval

manage_indexes Create, configure, and manage vector indexes with different dimensions and distance metrics for various AI applications

fetch_by_metadata Query and retrieve vectors based on metadata filters to find specific subsets of your vector data

get_index_stats Retrieve statistics and health metrics for vector indexes including vector counts, namespace distribution, and storage utilization

Deploy in 60 seconds

Describe what you need, AI generates the code, and IOX deploys it globally.

Deploy Pinecone MCP Server →

Pinecone REST API

API Endpoints

Code Examples

Connect Pinecone to AI

Deploy in 60 seconds

Related APIs