Pinecone Tutorial

14. 10. 2024 1 min read intermediate

Fully managed, zero ops, serverless.

Setup¶

pip install pinecone-client

import pinecone
pc = pinecone.Pinecone(api_key='key')
pc.create_index(
    name='docs', 
    dimension=1536, 
    metric='cosine',
    spec=pinecone.ServerlessSpec(cloud='aws', region='us-east-1')
)

Operations¶

index = pc.Index('docs')
index.upsert(vectors=[('d1',[0.1,0.2,...],{'text':'PG guide'})])
results = index.query(vector=[0.1,...], top_k=5, include_metadata=True)

Zero ops
Serverless
Metadata filtering
LangChain integration

Pinecone for Production¶

Simplest managed solution.

pineconevector dbmanaged

CORE SYSTEMS tým

Stavíme core systémy a AI agenty, které drží provoz. 15 let zkušeností s enterprise IT.

Všechny články

Další know-how

Vector Databases and Embeddings — The Foundation of a Modern AI Stack

Why vector databases are critical for AI applications. A comparison of Pinecone, Weaviate, and ChromaDB.

ChromaDB vs Pinecone

Open-source embedded vs managed serverless vector DB.

RAG — Retrieval Augmented Generation in Practice

How RAG (Retrieval Augmented Generation) works and why it's critical for enterprise AI. Architecture, embeddings,...