向量存储 - Docs by LangChain

概述

向量存储存储嵌入数据并执行相似性搜索。

接口

LangChain 为向量存储提供了统一接口，允许您：

add_documents - 将文档添加到存储中。
delete - 根据 ID 移除已存储的文档。
similarity_search - 查询语义相似的文档。

该抽象允许您在不同的实现之间切换，而无需修改应用程序逻辑。

初始化

要初始化向量存储，需要为其提供一个嵌入模型：

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

添加文档

添加 Document 对象（包含 page_content 和可选的元数据），如下：

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

删除文档

通过指定 ID 删除：

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

相似性搜索

使用 similarity_search 发出语义查询，该查询会返回最接近的嵌入文档：

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

许多向量存储支持如下参数：

k — 返回的结果数量
filter — 基于元数据的条件过滤

相似度指标与索引

嵌入相似度可以使用以下方法计算：

余弦相似度
欧几里得距离
点积

高效搜索通常采用 HNSW (Hierarchical Navigable Small World) 等索引方法，但具体实现取决于向量存储。

元数据过滤

按元数据（例如，来源、日期）过滤可以优化搜索结果：

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

热门集成

选择嵌入模型：

OpenAI

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]"

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")

Google Vertex

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="llama3")

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")

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[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[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[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 install -qU langchain-core

from langchain_core.vectorstores import InMemoryVectorStore

vector_store = InMemoryVectorStore(embeddings)

AstraDB

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 install -qU langchain-azure-ai azure-cosmos

from langchain_azure_ai.vectorstores.azure_cosmos_db_no_sql 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 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 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
)

FAISS

pip install -qU langchain-community

import faiss
from langchain_community.docstore.in_memory import InMemoryDocstore
from langchain_community.vectorstores import FAISS

embedding_dim = len(embeddings.embed_query("hello world"))
index = faiss.IndexFlatL2(embedding_dim)

vector_store = FAISS(
    embedding_function=embeddings,
    index=index,
    docstore=InMemoryDocstore(),
    index_to_docstore_id={},
)

Milvus

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",
)

PGVector

pip install -qU langchain-postgres

from langchain_postgres import PGVector

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

PGVectorStore

pip install -qU langchain-postgres

from langchain_postgres import PGEngine, PGVectorStore

$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 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 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,
)

向量存储	按 ID 删除	过滤	按向量搜索	带分数搜索	异步	通过标准测试	多租户	添加文档中的 ID
`AstraDBVectorStore`	✅	✅	✅	✅	✅	❌	❌	✅
`AzureCosmosDBNoSqlVectorStore`	✅	✅	✅	✅	❌	✅	✅	✅
`AzureCosmosDBMongoVCoreVectorStore`	✅	✅	✅	✅	❌	✅	✅	✅
`Chroma`	✅	✅	✅	✅	✅	✅	✅	✅
`Clickhouse`	✅	✅	❌	✅	❌	❌	❌	✅
`CouchbaseSearchVectorStore`	✅	✅	✅	✅	✅	❌	✅	✅
`DatabricksVectorSearch`	✅	✅	✅	✅	✅	❌	❌	✅
`ElasticsearchStore`	✅	✅	✅	✅	✅	❌	❌	✅
`FAISS`	✅	✅	✅	✅	✅	❌	❌	✅
`InMemoryVectorStore`	✅	✅	❌	✅	✅	❌	❌	✅
`Milvus`	✅	✅	✅	✅	✅	✅	✅	✅
`Moorcheh`	✅	✅	✅	✅	✅	✅	✅	✅
`MongoDBAtlasVectorSearch`	✅	✅	✅	✅	✅	✅	✅	✅
`openGauss`	✅	✅	✅	✅	❌	✅	❌	✅
`PGVector`	✅	✅	✅	✅	✅	❌	❌	✅
`PGVectorStore`	✅	✅	✅	✅	✅	✅	❌	✅
`PineconeVectorStore`	✅	✅	✅	✅	❌	❌	❌	✅
`QdrantVectorStore`	✅	✅	✅	✅	✅	❌	✅	✅
`Weaviate`	✅	✅	✅	✅	✅	❌	✅	✅
`SQLServer`	✅	✅	✅	✅	❌	❌	❌	✅
`ZeusDB`	✅	✅	✅	✅	✅	✅	❌	✅

所有向量存储

Activeloop Deep Lake

Alibaba Cloud OpenSearch

AnalyticDB

Annoy

Apache Doris

ApertureDB

Astra DB Vector Store

Atlas

AwaDB

Azure Cosmos DB Mongo vCore

Azure Cosmos DB No SQL

Azure AI Search

Bagel

BagelDB

Baidu Cloud ElasticSearch VectorSearch

Baidu VectorDB

Apache Cassandra

Chroma

Clarifai

ClickHouse

Couchbase

DashVector

Databricks

IBM Db2

DingoDB

DocArray HnswSearch

DocArray InMemorySearch

Amazon Document DB

DuckDB

China Mobile ECloud ElasticSearch

Elasticsearch

Epsilla

Faiss

Faiss (Async)

FalkorDB

Gel

Google AlloyDB

Google BigQuery Vector Search

Google Cloud SQL for MySQL

Google Cloud SQL for PostgreSQL

Firestore

Google Memorystore for Redis

Google Spanner

Google Vertex AI Feature Store

Google Vertex AI Vector Search

Hippo

Hologres

Jaguar Vector Database

Kinetica

LanceDB

Lantern

Lindorm

LLMRails

ManticoreSearch

MariaDB

Marqo

Meilisearch

Amazon MemoryDB

Milvus

Momento Vector Index

Moorcheh

MongoDB Atlas

MyScale

Neo4j Vector Index

NucliaDB

Oceanbase

openGauss

OpenSearch

Oracle AI Vector Search

Pathway

Postgres Embedding

PGVecto.rs

PGVector

PGVectorStore

Pinecone

Pinecone (sparse)

Qdrant

Relyt

Rockset

SAP HANA Cloud Vector Engine

ScaNN

SemaDB

SingleStore

scikit-learn

SQLiteVec

SQLite-VSS

SQLServer

StarRocks

Supabase

SurrealDB

Tablestore

Tair

Tencent Cloud VectorDB

ThirdAI NeuralDB

TiDB Vector

Tigris

TileDB

Timescale Vector

Typesense

Upstash Vector

USearch

Vald

VDMS

Vearch

Vectara

Vespa

viking DB

vlite

Weaviate

Xata

YDB

Yellowbrick

Zep

Zep Cloud

ZeusDB

Zilliz

在 GitHub 上编辑此页面的源代码。

通过 MCP 以编程方式将这些文档连接到 Claude、VSCode 等，以获取实时答案。

热门提供商

按组件分类的集成

​概述

​接口

​初始化

​添加文档

​删除文档

​相似性搜索

​相似度指标与索引

​元数据过滤

​热门集成

​所有向量存储

Activeloop Deep Lake

Alibaba Cloud OpenSearch

AnalyticDB

Annoy

Apache Doris

ApertureDB

Astra DB Vector Store

Atlas

AwaDB

Azure Cosmos DB Mongo vCore

Azure Cosmos DB No SQL

Azure AI Search

Bagel

BagelDB

Baidu Cloud ElasticSearch VectorSearch

Baidu VectorDB

Apache Cassandra

Chroma

Clarifai

ClickHouse

Couchbase

DashVector

Databricks

IBM Db2

DingoDB

DocArray HnswSearch

DocArray InMemorySearch

Amazon Document DB

DuckDB

China Mobile ECloud ElasticSearch

Elasticsearch

Epsilla

Faiss

Faiss (Async)

FalkorDB

Gel

Google AlloyDB

Google BigQuery Vector Search

Google Cloud SQL for MySQL

Google Cloud SQL for PostgreSQL

Firestore

Google Memorystore for Redis

Google Spanner

Google Vertex AI Feature Store

Google Vertex AI Vector Search

Hippo

Hologres

Jaguar Vector Database

Kinetica

LanceDB

Lantern

Lindorm

LLMRails

ManticoreSearch

MariaDB

Marqo

Meilisearch

Amazon MemoryDB

Milvus

Momento Vector Index

Moorcheh

MongoDB Atlas

MyScale

Neo4j Vector Index

NucliaDB

Oceanbase

openGauss

OpenSearch

概述

接口

初始化

添加文档

删除文档

相似性搜索

相似度指标与索引

元数据过滤

热门集成

所有向量存储