title: “Pinecone — Managed vector DB for production RAG and search” sidebar_label: “Pinecone” description: “Managed vector DB for production RAG and search”
{/* 本页面由 website/scripts/generate-skill-docs.py 根据技能对应的 SKILL.md 文件自动生成。请直接编辑源文件 SKILL.md,而非此页面。 */}
Pinecone
专为生产级 RAG 应用及搜索功能设计的托管向量数据库。
技能元数据
| 来源 | 可选 — 通过 hermes skills install official/mlops/pinecone 安装 |
| 路径 | optional-skills/mlops\pinecone |
| 版本 | 1.0.1 |
| 开发者 | Orchestra Research |
| 许可协议 | MIT |
| 依赖项 | pinecone |
| 支持平台 | linux、macos、windows |
| 标签 | RAG、Pinecone、向量数据库、托管服务、无服务器、混合搜索、生产环境、自动扩展、低延迟、推荐系统 |
参考:完整的 SKILL.md 文件
Pinecone — 托管向量数据库
专为生产级人工智能应用打造的向量数据库。
何时使用 Pinecone
适用场景:
- 需要托管型、无服务器架构的向量数据库
- 开发生产级 RAG 应用
- 需要自动扩展功能
- 对低延迟有严格要求(<100毫秒)
- 不希望自行管理基础设施
- 需要实现混合搜索(密集向量与稀疏向量混合处理)
核心优势:
- 完全托管的 SaaS 模式
- 可支持数十亿级向量数据的自动扩展
- p95 延迟低于 100毫秒
- 99.9% 的正常运行时间服务等级协议保障
可选替代方案:
- Chroma:开源、可自行部署
- FAISS:离线使用、纯相似度搜索工具
- Weaviate:功能更丰富、同样支持自行部署
快速入门指南
安装
pip install pinecone
注意:旧的
pinecone-client包已不再维护。请安装pinecone(版本 5 及以上,当前为 9.x 版)。导入语句仍需保持为from pinecone import Pinecone。
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
创建索引
# 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"
)
)
向量插入/更新操作
# 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)
查询向量
# 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": {"$eq": "tutorial"}}
)
# Namespace query
results = index.query(
vector=[0.1, 0.2, ...],
top_k=5,
namespace="production"
)
# Access results
for match in results["matches"]:
print(f"ID: {match['id']}")
print(f"Score: {match['score']}")
print(f"Metadata: {match['metadata']}")
元数据过滤
# Exact match
filter = {"category": "tutorial"}
# Comparison
filter = {"price": {"$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"]}}
命名空间
# 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(密集型 + 稀疏型)
# 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
# NOTE: index.query() does NOT accept an `alpha` kwarg. Pinecone stores a
# single sparse-dense vector, so weighting must be applied by pre-scaling the
# query vectors before sending them. Use the hybrid_score_norm helper below
# (alpha * dense + (1 - alpha) * sparse; alpha=1 → pure dense, 0 → pure sparse).
def hybrid_score_norm(dense, sparse, alpha: float):
"""Scale dense/sparse query vectors for weighted hybrid search."""
if not 0 <= alpha <= 1:
raise ValueError("alpha must be between 0 and 1")
scaled_sparse = {
"indices": sparse["indices"],
"values": [v * (1 - alpha) for v in sparse["values"]],
}
return [v * alpha for v in dense], scaled_sparse
hdense, hsparse = hybrid_score_norm(
dense=[0.1, 0.2, ...],
sparse={"indices": [10, 45], "values": [0.5, 0.3]},
alpha=0.5, # 0=sparse, 1=dense, 0.5=balanced
)
results = index.query(
vector=hdense,
sparse_vector=hsparse,
top_k=5,
)
与 LangChain 的集成
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})
与 LlamaIndex 的集成
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")
删除向量
# 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)
最佳实践
- 使用无服务器架构——具备自动扩展能力,更具成本效益
- 批量插入/更新数据——效率更高(每批处理100-200条记录)
- 添加元数据——便于后续数据筛选
- 使用命名空间——按用户或租户隔离数据
- 监控使用情况——查看Pinecone控制面板
- 优化筛选条件——对频繁被筛选的字段建立索引
- 利用免费套餐进行测试——可创建1个索引,存储10万条向量
- 采用混合搜索方式——提升搜索质量
- 设置合适的维度参数——与嵌入模型相匹配
- 定期备份数据——导出重要数据
性能表现
| 操作类型 | 延迟时间 | 备注 |
|---|---|---|
| 插入/更新数据 | 约50-100毫秒 | 每批处理量对应此延迟 |
| 查询(p50分位值) | 约50毫秒 | 取决于索引规模 |
| 查询(p95分位值) | 约100毫秒 | 符合服务等级协议要求 |
| 元数据筛选 | 约+10-20毫秒 | 额外的处理开销 |
定价方案(2025年数据)
无服务器架构:
- 每百万次读取操作费用:0.096美元
- 每百万次写入操作费用:0.06美元
- 每GB存储空间每月费用:0.06美元
免费套餐:
- 提供1个无服务器索引
- 支持存储10万条向量(1536个维度)
- 非常适合原型开发
相关资源
- 官网:https://www.pinecone.io
- 文档:https://docs.pinecone.io
- 控制台:https://app.pinecone.io
- 定价页面:https://www.pinecone.io/pricing