Pineconeを始める

Pineconeとは

Pinecone SDKのインストール

# pip install pinecone-client
import os
from pinecone import Pinecone

pc = Pinecone(api_key=os.environ['PINECONE_API_KEY'])

# List existing indexes to verify connection
existing = pc.list_indexes().names()
print('Existing indexes:', existing)

Pineconeインデックスの作成

from pinecone import Pinecone, ServerlessSpec
import os

pc = Pinecone(api_key=os.environ['PINECONE_API_KEY'])

index_name = 'my-rag-index'

if index_name not in pc.list_indexes().names():
    pc.create_index(
        name=index_name,
        dimension=1536,         # text-embedding-3-small dimension
        metric='cosine',
        spec=ServerlessSpec(
            cloud='aws',
            region='us-east-1'
        )
    )
    print(f'Created index: {index_name}')
else:
    print(f'Index already exists: {index_name}')

index = pc.Index(index_name)

メタデータ付きベクトルのアップサート

from openai import OpenAI

oai = OpenAI()

documents = [
    {'id': 'doc-001', 'text': 'What is RAG and how does it work?', 'category': 'faq'},
    {'id': 'doc-002', 'text': 'Pinecone is a managed vector database.', 'category': 'docs'},
    {'id': 'doc-003', 'text': 'OpenAI embeddings have 1536 dimensions.', 'category': 'docs'}
]

texts = [d['text'] for d in documents]
resp = oai.embeddings.create(model='text-embedding-3-small', input=texts)

vectors = [
    {
        'id': doc['id'],
        'values': resp.data[i].embedding,
        'metadata': {'text': doc['text'], 'category': doc['category']}
    }
    for i, doc in enumerate(documents)
]

index.upsert(vectors=vectors)
print(f'Upserted {len(vectors)} vectors')

Pineconeインデックスへのクエリ

from openai import OpenAI

oai = OpenAI()

query = 'How many dimensions do OpenAI embeddings have?'
q_resp = oai.embeddings.create(model='text-embedding-3-small', input=query)
q_vec = q_resp.data[0].embedding

results = index.query(
    vector=q_vec,
    top_k=3,
    include_metadata=True
)

for match in results['matches']:
    score = match['score']
    text = match['metadata']['text']
    print(f'{score:.4f}: {text}')

メタデータによるフィルタリング

# Filter to only 'docs' category results
results = index.query(
    vector=q_vec,
    top_k=5,
    filter={
        'category': {'$eq': 'docs'}
    },
    include_metadata=True
)

print(f'Filtered results: {len(results["matches"])}')
for m in results['matches']:
    print(f'  [{m["metadata"]["category"]}] {m["metadata"]["text"][:60]}')

データ分離のための名前空間

# Upsert into a specific namespace
index.upsert(
    vectors=[{'id': 'doc-001', 'values': q_vec, 'metadata': {'text': 'Tenant A doc'}}],
    namespace='tenant-a'
)

# Query only tenant-a's documents
results = index.query(
    vector=q_vec,
    top_k=5,
    namespace='tenant-a',
    include_metadata=True
)
print(f'Tenant-A results: {len(results["matches"])}')

大規模コーパスのためのバッチアップサート

def batch_upsert(index, vectors, batch_size=100):
    total = len(vectors)
    for start in range(0, total, batch_size):
        batch = vectors[start:start + batch_size]
        index.upsert(vectors=batch)
        print(f'Upserted {min(start + batch_size, total)}/{total}')

# Usage:
# batch_upsert(index, all_vectors, batch_size=100)

インデックス統計の確認

stats = index.describe_index_stats()

print(f'Total vectors: {stats["total_vector_count"]}')
print(f'Namespaces:')
for ns, info in stats.get('namespaces', {}).items():
    print(f'  {ns!r}: {info["vector_count"]} vectors')

ベクトルの削除と更新

# Delete specific vectors by id
index.delete(ids=['doc-001', 'doc-002'])

# Update a vector (upsert overwrites by id)
index.upsert(vectors=[{
    'id': 'doc-003',
    'values': q_vec,            # new embedding
    'metadata': {'text': 'Updated content.'}
}])

# Delete all vectors in a namespace
# index.delete(delete_all=True, namespace='tenant-a')

Pineconeの料金と無料プラン

クイックチェック

レッスンのまとめ