跳到主要內容

Pinecone

用於生產級 AI 應用的託管向量數據庫。完全託管、自動擴縮，支持混合搜索（稠密 + 稀疏）、元數據過濾和命名空間。低延遲（p95 <100ms）。適用於生產級 RAG、推薦系統或大規模語義搜索。最適合無服務器、託管基礎設施。

技能元數據​

來源可選 — 使用 hermes skills install official/mlops/pinecone 安裝
路徑optional-skills/mlops/pinecone
版本1.0.0
作者Orchestra Research
許可證MIT
依賴項pinecone-client
標籤RAG, Pinecone, Vector Database, Managed Service, Serverless, Hybrid Search, Production, Auto-Scaling, Low Latency, Recommendations

參考：完整 SKILL.md​

信息

以下是 Hermes 在觸發此技能時加載的完整技能定義。這是技能激活時代理看到的指令。

Pinecone - 託管向量數據庫

用於生產級 AI 應用的向量數據庫。

何時使用 Pinecone​

使用時機：

  • 需要託管的無服務器向量數據庫
  • 生產級 RAG 應用
  • 需要自動擴縮
  • 對低延遲有關鍵要求（<100ms）
  • 不想管理基礎設施
  • 需要混合搜索（稠密 + 稀疏向量）

指標：

  • 完全託管的 SaaS
  • 自動擴縮至數十億向量
  • p95 延遲 <100ms
  • 99.9% 可用性 SLA

改用替代方案：

  • Chroma：自託管，開源
  • FAISS：離線，純相似度搜索
  • Weaviate：自託管，功能更豐富

快速開始​

安裝​

pip install pinecone-client

基本用法​

from pinecone import Pinecone, ServerlessSpec

# Initialize
pc = Pinecone(api_key="your-api-key")

# Create index
pc.create_index(
    name="my-index",
    dimension=1536,  # Must match embedding dimension
    metric="cosine",  # or "euclidean", "dotproduct"
    spec=ServerlessSpec(cloud="aws", region="us-east-1")
)

# Connect to index
index = pc.Index("my-index")

# Upsert vectors
index.upsert(vectors=[
    {"id": "vec1", "values": [0.1, 0.2, ...], "metadata": {"category": "A"}},
    {"id": "vec2", "values": [0.3, 0.4, ...], "metadata": {"category": "B"}}
])

# Query
results = index.query(
    vector=[0.1, 0.2, ...],
    top_k=5,
    include_metadata=True
)

print(results["matches"])

核心操作​

創建索引​

# Serverless (recommended)
pc.create_index(
    name="my-index",
    dimension=1536,
    metric="cosine",
    spec=ServerlessSpec(
        cloud="aws",         # or "gcp", "azure"
        region="us-east-1"
    )
)

# Pod-based (for consistent performance)
from pinecone import PodSpec

pc.create_index(
    name="my-index",
    dimension=1536,
    metric="cosine",
    spec=PodSpec(
        environment="us-east1-gcp",
        pod_type="p1.x1"
    )
)

Upsert 向量​

# Single upsert
index.upsert(vectors=[
    {
        "id": "doc1",
        "values": [0.1, 0.2, ...],  # 1536 dimensions
        "metadata": {
            "text": "Document content",
            "category": "tutorial",
            "timestamp": "2025-01-01"
        }
    }
])

# Batch upsert (recommended)
vectors = [
    {"id": f"vec{i}", "values": embedding, "metadata": metadata}
    for i, (embedding, metadata) in enumerate(zip(embeddings, metadatas))
]

index.upsert(vectors=vectors, batch_size=100)

查詢向量​

# Basic query
results = index.query(
    vector=[0.1, 0.2, ...],
    top_k=10,
    include_metadata=True,
    include_values=False
)

# With metadata filtering
results = index.query(
    vector=[0.1, 0.2, ...],
    top_k=5,
    filter={"category": {"$eq": "tutorial"}}
)

# Namespace query
results = index.query(
    vector=[0.1, 0.2, ...],
    top_k=5,
    namespace="production"
)

# Access results
for match in results["matches"]:
    print(f"ID: {match['id']}")
    print(f"Score: {match['score']}")
    print(f"Metadata: {match['metadata']}")

元數據過濾​

# Exact match
filter = {"category": "tutorial"}

# Comparison
filter = {"price": {"$gte": 100}}  # $gt, $gte, $lt, $lte, $ne

# Logical operators
filter = {
    "$and": [
        {"category": "tutorial"},
        {"difficulty": {"$lte": 3}}
    ]
}  # Also: $or

# In operator
filter = {"tags": {"$in": ["python", "ml"]}}

命名空間​

# Partition data by namespace
index.upsert(
    vectors=[{"id": "vec1", "values": [...]}],
    namespace="user-123"
)

# Query specific namespace
results = index.query(
    vector=[...],
    namespace="user-123",
    top_k=5
)

# List namespaces
stats = index.describe_index_stats()
print(stats['namespaces'])

混合搜索（稠密 + 稀疏）​

# Upsert with sparse vectors
index.upsert(vectors=[
    {
        "id": "doc1",
        "values": [0.1, 0.2, ...],  # Dense vector
        "sparse_values": {
            "indices": [10, 45, 123],  # Token IDs
            "values": [0.5, 0.3, 0.8]   # TF-IDF scores
        },
        "metadata": {"text": "..."}
    }
])

# Hybrid query
results = index.query(
    vector=[0.1, 0.2, ...],
    sparse_vector={
        "indices": [10, 45],
        "values": [0.5, 0.3]
    },
    top_k=5,
    alpha=0.5  # 0=sparse, 1=dense, 0.5=hybrid
)

LangChain 集成​

from langchain_pinecone import PineconeVectorStore
from langchain_openai import OpenAIEmbeddings

# Create vector store
vectorstore = PineconeVectorStore.from_documents(
    documents=docs,
    embedding=OpenAIEmbeddings(),
    index_name="my-index"
)

# Query
results = vectorstore.similarity_search("query", k=5)

# With metadata filter
results = vectorstore.similarity_search(
    "query",
    k=5,
    filter={"category": "tutorial"}
)

# As retriever
retriever = vectorstore.as_retriever(search_kwargs={"k": 10})

LlamaIndex 集成​

from llama_index.vector_stores.pinecone import PineconeVectorStore

# Connect to Pinecone
pc = Pinecone(api_key="your-key")
pinecone_index = pc.Index("my-index")

# Create vector store
vector_store = PineconeVectorStore(pinecone_index=pinecone_index)

# Use in LlamaIndex
from llama_index.core import StorageContext, VectorStoreIndex

storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(documents, storage_context=storage_context)

索引管理​

# List indices
indexes = pc.list_indexes()

# Describe index
index_info = pc.describe_index("my-index")
print(index_info)

# Get index stats
stats = index.describe_index_stats()
print(f"Total vectors: {stats['total_vector_count']}")
print(f"Namespaces: {stats['namespaces']}")

# Delete index
pc.delete_index("my-index")

刪除向量​

# Delete by ID
index.delete(ids=["vec1", "vec2"])

# Delete by filter
index.delete(filter={"category": "old"})

# Delete all in namespace
index.delete(delete_all=True, namespace="test")

# Delete entire index
index.delete(delete_all=True)

最佳實踐​

  1. 使用無服務器 - 自動擴縮，具有成本效益
  2. 批量 upsert - 更高效（每批 100-200 條）
  3. 添加元數據 - 啟用過濾
  4. 使用命名空間 - 按用戶/租戶隔離數據
  5. 監控使用情況 - 檢查 Pinecone 儀表板
  6. 優化過濾器 - 為經常過濾的字段建立索引
  7. 使用免費層測試 - 1 個索引，10 萬向量免費
  8. 使用混合搜索 - 質量更高
  9. 設置適當的維度 - 與嵌入模型匹配
  10. 定期備份 - 導出重要數據

性能​

操作延遲說明
Upsert~50-100ms每批次
查詢 (p50)~50ms取決於索引大小
查詢 (p95)~100msSLA 目標
元數據過濾~+10-20ms額外開銷

定價（截至 2025 年）​

無服務器：

  • 每百萬讀取單元 $0.096
  • 每百萬寫入單元 $0.06
  • 每 GB 存儲/月 $0.06

免費層：

  • 1 個無服務器索引
  • 10 萬向量（1536 維）
  • 非常適合原型設計

資源​