向量存储集成

使用 LangChain Python 集成向量存储。

概述

向量存储 嵌入 数据并执行相似性搜索。

接口

LangChain 提供了统一的向量存储接口，允许您：

• add_documents - 添加文档到存储中
• delete - 通过 ID 删除存储的文档
• similarity_search - 查询语义相似文档

这种抽象层使您能够无缝切换不同实现而不影响应用逻辑。

初始化

初始化向量存储时需提供嵌入模型：

from langchain_core.vectorstores import InMemoryVectorStore
vector_store = InMemoryVectorStore(embedding=SomeEmbeddingModel())

添加文档

添加 @[Document] 对象（包含 page_content 和可选元数据）的示例如下：

vector_store.add_documents(documents=[doc1, doc2], ids=["id1", "id2"])

删除文档

通过指定 ID 进行删除：

vector_store.delete(ids=["id1"])

相似性搜索

使用 similarity_search 发起语义查询，返回最接近的嵌入文档：

similar_docs = vector_store.similarity_search("your query here")

许多向量存储支持以下参数：

• k — 返回结果的数量
• filter — 基于元数据的条件过滤

相似度指标与索引

嵌入相似度可通过以下方式计算：

• 余弦相似度
• 欧氏距离
• 点积

高效搜索常采用索引算法如 HNSW（Hierarchical Navigable Small World），但具体实现取决于向量存储。

元数据过滤

通过元数据（如来源、日期）可优化搜索结果：

vector_store.similarity_search(
  "query",
  k=3,
  filter={"source": "tweets"}
)

顶集成

选择嵌入模型：

OpenAI

pip

pip install -qU langchain-openai

import getpass
import os

if not os.environ.get("OPENAI_API_KEY"):
  os.environ["OPENAI_API_KEY"] = getpass.getpass("Enter API key for OpenAI: ")

from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings(model="text-embedding-3-large")

Azure

pip install -qU langchain-azure-ai

import getpass
import os

if not os.environ.get("AZURE_OPENAI_API_KEY"):
  os.environ["AZURE_OPENAI_API_KEY"] = getpass.getpass("Enter API key for Azure: ")

from langchain_openai import AzureOpenAIEmbeddings

embeddings = AzureOpenAIEmbeddings(
    azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
    azure_deployment=os.environ["AZURE_OPENAI_DEPLOYMENT_NAME"],
    openai_api_version=os.environ["AZURE_OPENAI_API_VERSION"],
)

Google Gemini

pip install -qU langchain-google-genai

import getpass
import os

if not os.environ.get("GOOGLE_API_KEY"):
  os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter API key for Google Gemini: ")

from langchain_google_genai import GoogleGenerativeAIEmbeddings

embeddings = GoogleGenerativeAIEmbeddings(model="models/gemini-embedding-001")

Gemini Enterprise Agent Platform

pip install -qU langchain-google-vertexai

from langchain_google_vertexai import VertexAIEmbeddings

embeddings = VertexAIEmbeddings(model="text-embedding-005")

AWS

pip install -qU langchain-aws

from langchain_aws import BedrockEmbeddings

embeddings = BedrockEmbeddings(model_id="amazon.titan-embed-text-v2:0")

HuggingFace

pip install -qU langchain-huggingface

from langchain_huggingface import HuggingFaceEmbeddings

embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")

Ollama

pip install -qU langchain-ollama

from langchain_ollama import OllamaEmbeddings

embeddings = OllamaEmbeddings(model="nomic-embed-text")

Cohere

pip install -qU langchain-cohere

import getpass
import os

if not os.environ.get("COHERE_API_KEY"):
  os.environ["COHERE_API_KEY"] = getpass.getpass("Enter API key for Cohere: ")

from langchain_cohere import CohereEmbeddings

embeddings = CohereEmbeddings(model="embed-english-v3.0")

Mistral AI

pip install -qU langchain-mistralai

import getpass
import os

if not os.environ.get("MISTRALAI_API_KEY"):
  os.environ["MISTRALAI_API_KEY"] = getpass.getpass("Enter API key for MistralAI: ")

from langchain_mistralai import MistralAIEmbeddings

embeddings = MistralAIEmbeddings(model="mistral-embed")

Nomic

pip install -qU langchain-nomic

import getpass
import os

if not os.environ.get("NOMIC_API_KEY"):
  os.environ["NOMIC_API_KEY"] = getpass.getpass("Enter API key for Nomic: ")

from langchain_nomic import NomicEmbeddings

embeddings = NomicEmbeddings(model="nomic-embed-text-v1.5")

NVIDIA

pip install -qU langchain-nvidia-ai-endpoints

import getpass
import os

if not os.environ.get("NVIDIA_API_KEY"):
  os.environ["NVIDIA_API_KEY"] = getpass.getpass("Enter API key for NVIDIA: ")

from langchain_nvidia_ai_endpoints import NVIDIAEmbeddings

embeddings = NVIDIAEmbeddings(model="NV-Embed-QA")

Voyage AI

pip install -qU langchain-voyageai

import getpass
import os

if not os.environ.get("VOYAGE_API_KEY"):
  os.environ["VOYAGE_API_KEY"] = getpass.getpass("Enter API key for Voyage AI: ")

from langchain_voyageai import VoyageAIEmbeddings

embeddings = VoyageAIEmbeddings(model="voyage-3")

对于更多详情，请参考 Voyage AI 文档。

IBM watsonx

pip install -qU langchain-ibm

import getpass
import os

if not os.environ.get("WATSONX_APIKEY"):
  os.environ["WATSONX_APIKEY"] = getpass.getpass("Enter API key for IBM watsonx: ")

from langchain_ibm import WatsonxEmbeddings

embeddings = WatsonxEmbeddings(
    model_id="ibm/slate-125m-english-rtrvr",
    url="https://us-south.ml.cloud.ibm.com",
    project_id="<WATSONX PROJECT_ID>",
)

Fake

pip install -qU langchain-core

from langchain_core.embeddings import DeterministicFakeEmbedding

embeddings = DeterministicFakeEmbedding(size=4096)

xAI

pip install -qU langchain-xai

import getpass
import os

if not os.environ.get("XAI_API_KEY"):
  os.environ["XAI_API_KEY"] = getpass.getpass("Enter API key for xAI: ")

from langchain.chat_models import init_chat_model

model = init_chat_model("grok-2", model_provider="xai")

Perplexity

pip install -qU langchain-perplexity

import getpass
import os

if not os.environ.get("PPLX_API_KEY"):
  os.environ["PPLX_API_KEY"] = getpass.getpass("Enter API key for Perplexity: ")

from langchain.chat_models import init_chat_model

model = init_chat_model("llama-3.1-sonar-small-128k-online", model_provider="perplexity")

DeepSeek

pip install -qU langchain-deepseek

import getpass
import os

if not os.environ.get("DEEPSEEK_API_KEY"):
  os.environ["DEEPSEEK_API_KEY"] = getpass.getpass("Enter API key for DeepSeek: ")

from langchain.chat_models import init_chat_model

model = init_chat_model("deepseek-chat", model_provider="deepseek")

选择向量存储：

In-memory

pip

pip install -qU langchain-core

from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)

Amazon OpenSearch

pip

pip install -qU boto3

from opensearchpy import RequestsHttpConnection

service = "es"  # must set the service as 'es'
region = "us-east-2"
credentials = boto3.Session(
    aws_access_key_id="xxxxxx", aws_secret_access_key="xxxxx"
).get_credentials()
awsauth = AWS4Auth("xxxxx", "xxxxxx", region, service, session_token=credentials.token)

vector_store = OpenSearchVectorSearch.from_documents(
    docs,
    embeddings,
    opensearch_url="host url",
    http_auth=awsauth,
    timeout=300,
    use_ssl=True,
    verify_certs=True,
    connection_class=RequestsHttpConnection,
    index_name="test-index",
)

Astra DB

pip

pip install -qU langchain-astradb

from langchain_astradb import AstraDBVectorStore

vector_store = AstraDBVectorStore(
    embedding=embeddings,
    api_endpoint=ASTRA_DB_API_ENDPOINT,
    collection_name="astra_vector_langchain",
    token=ASTRA_DB_APPLICATION_TOKEN,
    namespace=ASTRA_DB_NAMESPACE,
)

Azure Cosmos DB NoSQL

pip

pip install -qU langchain-azure-cosmosdb azure-cosmos

from langchain_azure_cosmosdb import AzureCosmosDBNoSqlVectorSearch

vector_search = AzureCosmosDBNoSqlVectorSearch.from_documents(
    documents=docs,
    embedding=openai_embeddings,
    cosmos_client=cosmos_client,
    database_name=database_name,
    container_name=container_name,
    vector_embedding_policy=vector_embedding_policy,
    full_text_policy=full_text_policy,
    indexing_policy=indexing_policy,
    cosmos_container_properties=cosmos_container_properties,
    cosmos_database_properties={},
    full_text_search_enabled=True,
)

Azure Cosmos DB Mongo vCore

pip

pip install -qU langchain-azure-ai pymongo

from langchain_azure_ai.vectorstores.azure_cosmos_db_mongo_vcore import (
    AzureCosmosDBMongoVCoreVectorSearch,
)

vectorstore = AzureCosmosDBMongoVCoreVectorSearch.from_documents(
    docs,
    openai_embeddings,
    collection=collection,
    index_name=INDEX_NAME,
)

Chroma

pip

pip install -qU langchain-chroma

from langchain_chroma import Chroma

vector_store = Chroma(
    collection_name="example_collection",
    embedding_function=embeddings,
    persist_directory="./chroma_langchain_db",  # Where to save data locally, remove if not necessary
)

CockroachDB

pip

pip install -qU langchain-cockroachdb

from langchain_cockroachdb import AsyncCockroachDBVectorStore, CockroachDBEngine

CONNECTION_STRING = "cockroachdb://user:pass@host:26257/db?sslmode=verify-full"

engine = CockroachDBEngine.from_connection_string(CONNECTION_STRING)
await engine.ainit_vectorstore_table(
    table_name="vectors",
    vector_dimension=1536,
)

vector_store = AsyncCockroachDBVectorStore(
    engine=engine,
    embeddings=embeddings,
    collection_name="vectors",
)

Elasticsearch

安装包并使用 start-local 脚本启动本地 Elasticsearch：

pip install -qU langchain-elasticsearch
curl -fsSL https://elastic.co/start-local | sh

这将创建一个 elastic-start-local 文件夹。启动 Elasticsearch 的命令如下：

cd elastic-start-local
./start.sh

Elasticsearch 将在 http://localhost:9200 可用。 elastic 用户和 API 密钥存储在 .env 文件夹的 elastic-start-local 文件中。

from langchain_elasticsearch import ElasticsearchStore

vector_store = ElasticsearchStore(
    index_name="langchain-demo",
    embedding=embeddings,
    es_url="http://localhost:9200",
)

Google AlloyDB

pip

pip install -qU langchain-google-alloydb-pg

from langchain_google_alloydb_pg import AlloyDBEngine, AlloyDBVectorStore

engine = AlloyDBEngine.from_instance(
    project_id="my-project",
    region="us-central1",
    cluster="my-cluster",
    instance="my-instance",
    database="my-database",
)

vector_store = AlloyDBVectorStore.create_sync(
    engine=engine,
    table_name="my_vectors",
    embedding_service=embeddings
)

Milvus

pip

pip install -qU langchain-milvus

from langchain_milvus import Milvus

URI = "./milvus_example.db"

vector_store = Milvus(
    embedding_function=embeddings,
    connection_args={"uri": URI},
    index_params={"index_type": "FLAT", "metric_type": "L2"},
)

MongoDB

pip install -qU langchain-mongodb

from langchain_mongodb import MongoDBAtlasVectorSearch

vector_store = MongoDBAtlasVectorSearch(
    embedding=embeddings,
    collection=MONGODB_COLLECTION,
    index_name=ATLAS_VECTOR_SEARCH_INDEX_NAME,
    relevance_score_fn="cosine",
)

对于更多详情，请查阅 MongoDB LangChain 集成文档。

PGVector

pip

pip install -qU langchain-postgres

from langchain_postgres import PGVector

vector_store = PGVector(
    embeddings=embeddings,
    collection_name="my_docs",
    connection="postgresql+psycopg://..."
)

PGVectorStore

pip

pip install -qU langchain-postgres

from langchain_postgres import PGEngine, PGVectorStore

pg_engine = PGEngine.from_connection_string(
    url="postgresql+psycopg://..."
)

vector_store = PGVectorStore.create_sync(
    engine=pg_engine,
    table_name='test_table',
    embedding_service=embedding
)

Pinecone

pip

pip install -qU langchain-pinecone

from langchain_pinecone import PineconeVectorStore
from pinecone import Pinecone

pc = Pinecone(api_key=...)
index = pc.Index(index_name)

vector_store = PineconeVectorStore(embedding=embeddings, index=index)

Qdrant

pip

pip install -qU langchain-qdrant

from qdrant_client.models import Distance, VectorParams
from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient

client = QdrantClient(":memory:")

vector_size = len(embeddings.embed_query("sample text"))

if not client.collection_exists("test"):
    client.create_collection(
        collection_name="test",
        vectors_config=VectorParams(size=vector_size, distance=Distance.COSINE)
    )
vector_store = QdrantVectorStore(
    client=client,
    collection_name="test",
    embedding=embeddings,
)

Redis

pip

pip install -qU langchain-redis

import os
from langchain_redis import RedisConfig, RedisVectorStore

config = RedisConfig(
    index_name="my_vectors",
    redis_url=os.getenv("REDIS_URL", "redis://localhost:6379"),
    distance_metric="COSINE"
)

vector_store = RedisVectorStore(embeddings=embeddings, config=config)

Oracle AI Database

pip

pip install -qU langchain-oracledb

import oracledb
from langchain_oracledb.vectorstores import OracleVS
from langchain_oracledb.vectorstores.oraclevs import create_index
from langchain_community.vectorstores.utils import DistanceStrategy

username = "<username>"
password = "<password>"
dsn = "<hostname>:<port>/<service_name>"

connection = oracledb.connect(user=username, password=password, dsn=dsn)

vector_store = OracleVS(
    client=connection,
    embedding_function=embedding_model,
    table_name="VECTOR_SEARCH_DEMO",
    distance_strategy=DistanceStrategy.EUCLIDEAN_DISTANCE
)

turbopuffer

pip

pip install -qU langchain-turbopuffer

from langchain_turbopuffer import TurbopufferVectorStore
from turbopuffer import Turbopuffer

tpuf = Turbopuffer(region="gcp-us-central1")
ns = tpuf.namespace("langchain-test")

vector_store = TurbopufferVectorStore(embedding=embeddings, namespace=ns)

Valkey

pip

pip install -qU "langchain-aws[valkey]"

from langchain_aws.vectorstores import ValkeyVectorStore

vector_store = ValkeyVectorStore(
    embedding=embeddings,
    valkey_url="valkey://localhost:6379",
    index_name="my_index"
)

Weaviate

pip

pip install -qU langchain-weaviate

import weaviate
from langchain_weaviate import WeaviateVectorStore

# Assumes a local Weaviate instance on http://localhost:8080 with gRPC on 50051.
# See the Weaviate guide for other deployment options (Weaviate Cloud, Docker, etc.).
weaviate_client = weaviate.connect_to_local()

vector_store = WeaviateVectorStore(
    client=weaviate_client,
    index_name="langchain_example",
    text_key="text",
    embedding=embeddings,
)

向量存储	通过 ID 删除	过滤	向量搜索	带分数搜索	异步	通过标准测试	多租户	添加文档中的 ID	下载
ValkeyVectorStore	✅	✅	✅	✅	❌	❌	❌	✅
MongoDBAtlasVectorSearch	✅	✅	✅	✅	✅	✅	✅	✅
QdrantVectorStore	✅	✅	✅	✅	✅	❌	✅	✅
AzureCosmosDBMongoVCoreVectorStore	✅	✅	✅	✅	❌	✅	✅	✅
DatabricksVectorSearch	✅	✅	✅	✅	✅	❌	❌	✅
PineconeVectorStore	✅	✅	✅	❌	✅	❌	❌	✅
Milvus	✅	✅	✅	✅	✅	✅	✅	✅
Weaviate	✅	✅	✅	✅	✅	❌	✅	✅
Oracle AI Database	✅	✅	✅	✅	✅	✅	❌	✅
AstraDBVectorStore	✅	✅	✅	✅	✅	✅	✅	✅
ElasticsearchStore	✅	✅	✅	✅	✅	❌	❌	✅
RedisVectorStore	✅	✅	✅	✅	❌	❌	❌	✅
Google AlloyDB	✅	✅	✅	✅	✅	❌	❌	✅
AzureCosmosDBNoSqlVectorStore	✅	✅	✅	✅	❌	✅	✅	✅
InMemoryVectorStore	✅	✅	❌	✅	✅	❌	❌	✅	N/A

所有向量存储

向量存储	ID删除	过滤	向量搜索	带分数搜索	异步	通过标准测试	多租户	添加文档的ID	下载
Feature Store on Gemini Enterprise Agent Platform
Google bigquery vector search
Vector Search on Gemini Enterprise Agent Platform
Amazon MemoryDB
ValkeyVectorStore	✅	✅	✅	✅	❌	❌	❌	✅
PGVector
PGVectorStore	✅	✅	✅	✅	✅			✅
MongoDBAtlasVectorSearch	✅	✅	✅	✅	✅	✅	✅	✅
Chroma
QdrantVectorStore	✅	✅	✅	✅	✅	❌	✅	✅
AzureCosmosDBMongoVCoreVectorStore	✅	✅	✅	✅	❌	✅	✅	✅
DatabricksVectorSearch	✅	✅	✅	✅	✅	❌	❌	✅
Pinecone (Sparse)
PineconeVectorStore	✅	✅	✅	❌	✅	❌	❌	✅
Milvus	✅	✅	✅	✅	✅	✅	✅	✅
Weaviate	✅	✅	✅	✅	✅	❌	✅	✅
Oracle AI Database	✅	✅	✅	✅	✅	✅	❌	✅
AstraDBVectorStore	✅	✅	✅	✅	✅	✅	✅	✅
Neo4j vector index
ElasticsearchStore	✅	✅	✅	✅	✅	❌	❌	✅
RedisVectorStore	✅	✅	✅	✅	❌	❌	❌	✅
Google AlloyDB	✅	✅	✅	✅	✅	❌	❌	✅
AzureCosmosDBNoSqlVectorStore	✅	✅	✅	✅	❌	✅	✅	✅
Google cloud SQL for postgresql
Sap hana cloud vector engine
Google firestore
SemanticaVectorStore	❌
Google spanner
AsyncCockroachDBVectorStore
OceanbaseVectorStore
IBM db2 vector store and vector search
InfinoVectorStore	✅	✅	✅	✅	❌	✅	✅	✅
OpensolrVectorStore
TeradataVectorStore
CyborgVectorStore	✅	✅	✅	✅	✅		✅
SingleStoreVectorStore	✅	✅	✅	✅	❌	✅	❌	✅
YDB
CouchbaseSearchVectorStore
Azure database for postgresql - flexible server
Intel's visual data management system (VDMS)
SQLServer
FalkorDBVector		✅	✅
VastDBVectorStore	✅	✅	✅	✅	❌	✅	✅	✅
Mariadb
AMUVectorStore	✅
MixpeekVectorStore	✅	✅	✅	✅	✅	❌	❌	✅
SurrealDBVectorStore
PolarDBXVectorStore	✅	✅	✅	✅	✅	✅	❌	✅
InfinispanVectorStore	✅	✅	✅	✅	❌	✅	❌	✅
BigtableVectorStore
ShannonBaseVectorStore
openGauss
Google memorystore for Redis
ChronoVecVectorStore
turbopuffer
TypesenseVectorStore	✅	✅	✅	✅	✅	✅	❌	✅
LambdaDB
ZeusDB
PixeltableVectorStore
Gel
VectorPandaStore	✅	✅	✅	✅	✅	✅	❌	✅
Google cloud SQL for mysql
Kinetica vectorstore
Moorcheh
PolarDBPGVector	✅	✅	✅	✅	✅	✅	❌	✅
Vectara
HouyiVectorStore	✅	✅
Actian VectorAI DB	✅	✅	✅	✅	✅			✅
PolignVectorStore	✅	✅	✅	✅	✅	✅	❌	✅
Firebolt
SereneDB	✅	✅	✅	✅	✅	✅	✅	✅
DeweyVectorStore
Activeloop Deep lake
Vedb for mysql
Volcengine rds for mysql
RostamVectorStore
Alibaba cloud mysql
LindormVectorStore
ChDBVectorStore	✅	✅	✅	✅	✅	✅	❌	✅
YantrikDBVectorStore	✅		✅	✅	❌	✅	✅	✅
FAISS									N/A
InMemoryVectorStore	✅	✅	❌	✅	✅	❌	❌	✅	N/A

---

官方原文：src/oss/python/integrations/vectorstores/index.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。