Faiss

Facebook AI Similarity Search (FAISS) 是一个用于高效相似性搜索和密集向量聚类的库。它包含在任何大小的向量集中进行搜索的算法，甚至可以处理可能不适合放入内存的向量。它还包括用于评估和参数调整的支持代码。

请参阅 FAISS 库 论文。

您可以在此页面上找到 FAISS 文档。

本笔记本展示了如何使用与 FAISS 向量数据库相关的功​​能。它将展示此集成特有的功​​能。在学习之后，可以浏览相关用例页面以了解如何将此向量存储作为更大链的一部分来使用。

设置

集成位于 langchain-community 包中。我们还需要安装 faiss 包本身。我们可以通过以下命令安装它们：

请注意，如果您想使用支持 GPU 的版本，也可以安装 faiss-gpu

pip install -qU langchain-community faiss-cpu

如果您想获得一流的自动化模型调用跟踪，还可以通过取消注释以下内容来设置您的 LangSmith API 密钥：

# os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

初始化

Select embeddings model:

OpenAI

Azure

Google Gemini

Google Vertex

AWS

HuggingFace

Ollama

Cohere

MistralAI

Nomic

NVIDIA

Voyage AI

IBM watsonx

Fake

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")

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

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

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

API Reference:InMemoryDocstore | FAISS

管理向量存储

向向量存储添加项目

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocolate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
)

documents = [
    document_1,
    document_2,
    document_3,
    document_4,
    document_5,
    document_6,
    document_7,
    document_8,
    document_9,
    document_10,
]
uuids = [str(uuid4()) for _ in range(len(documents))]

vector_store.add_documents(documents=documents, ids=uuids)

API Reference:Document

['22f5ce99-cd6f-4e0c-8dab-664128307c72',
 'dc3f061b-5f88-4fa1-a966-413550c51891',
 'd33d890b-baad-47f7-b7c1-175f5f7b4e59',
 '6e6c01d2-6020-4a7b-95da-ef43d43f01b5',
 'e677223d-ad75-4c1a-bef6-b5912bd1de03',
 '47e2a168-6462-4ed2-b1d9-d9edfd7391d6',
 '1e4d66d6-e155-4891-9212-f7be97f36c6a',
 'c0663096-e1a5-4665-b245-1c2e6c4fb653',
 '8297474a-7f7c-4006-9865-398c1781b1bc',
 '44e4be03-0a8d-4316-b3c4-f35f4bb2b532']

从矢量存储中删除项目

vector_store.delete(ids=[uuids[-1]])

True

查询向量数据库

一旦你创建了向量数据库并添加了相关文档，你很可能希望在运行链或代理时查询它。

直接查询

相似性搜索

可以通过以下方式进行带有元数据过滤的简单相似性搜索：

results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy",
    k=2,
    filter={"source": "tweet"},
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

可以使用一些 MongoDB 查询和投影运算符 来进行更高级的元数据过滤。当前支持的运算符列表如下：

• $eq (等于)
• $neq (不等于)
• $gt (大于)
• $lt (小于)
• $gte (大于或等于)
• $lte (小于或等于)
• $in (在列表中)
• $nin (不在列表中)
• $and (所有条件必须匹配)
• $or (任何条件必须匹配)
• $not (条件取反)

使用以下方法可以执行上面相同的带高级元数据过滤的相似性搜索：

results = vector_store.similarity_search(
    "LangChain provides abstractions to make working with LLMs easy",
    k=2,
    filter={"source": {"$eq": "tweet"}},
)
for res in results:
    print(f"* {res.page_content} [{res.metadata}]")

* Building an exciting new project with LangChain - come check it out! [{'source': 'tweet'}]
* LangGraph is the best framework for building stateful, agentic applications! [{'source': 'tweet'}]

含分数的相似性搜索

您也可以使用分数进行搜索：

results = vector_store.similarity_search_with_score(
    "Will it be hot tomorrow?", k=1, filter={"source": "news"}
)
for res, score in results:
    print(f"* [SIM={score:3f}] {res.page_content} [{res.metadata}]")

* [SIM=0.893688] The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees. [{'source': 'news'}]

其他搜索方法

您还可以通过多种其他方式搜索 FAISS 向量存储。有关这些方法的完整列表，请参阅 API 参考。

通过转换为检索器进行查询

您还可以将向量存储转换为检索器，以便在链中更轻松地使用。

retriever = vector_store.as_retriever(search_type="mmr", search_kwargs={"k": 1})
retriever.invoke("Stealing from the bank is a crime", filter={"source": "news"})

[Document(metadata={'source': 'news'}, page_content='Robbers broke into the city bank and stole $1 million in cash.')]

用于检索增强生成的使用方法

有关如何将此向量存储用于检索增强生成 (RAG) 的指南，请参阅以下部分：

• 教程
• 操作指南：使用 RAG 进行问答
• 检索概念文档

保存与加载

您还可以保存和加载 FAISS 索引。这非常有用，因为您不必每次使用它时都重新创建它。

vector_store.save_local("faiss_index")

new_vector_store = FAISS.load_local(
    "faiss_index", embeddings, allow_dangerous_deserialization=True
)

docs = new_vector_store.similarity_search("qux")

docs[0]

Document(metadata={'source': 'tweet'}, page_content='Building an exciting new project with LangChain - come check it out!')

合并

你也可以合并两个 FAISS 向量存储

db1 = FAISS.from_texts(["foo"], embeddings)
db2 = FAISS.from_texts(["bar"], embeddings)

db1.docstore._dict

{'b752e805-350e-4cf5-ba54-0883d46a3a44': Document(page_content='foo')}

db2.docstore._dict

{'08192d92-746d-4cd1-b681-bdfba411f459': Document(page_content='bar')}

db1.merge_from(db2)

db1.docstore._dict

{'b752e805-350e-4cf5-ba54-0883d46a3a44': Document(page_content='foo'),
 '08192d92-746d-4cd1-b681-bdfba411f459': Document(page_content='bar')}

API 参考

如需了解 FAISS 向量存储的所有功能和配置的详细文档，请访问 API 参考：https://python.langchain.com/api_reference/community/vectorstores/langchain_community.vectorstores.faiss.FAISS.html

Related

• Vector store conceptual guide
• Vector store how-to guides