Chroma

此笔记本涵盖了如何开始使用Chroma向量数据库。

Chroma 是一个面向开发人员生产力和幸福感的 AI 原生开源向量数据库。Chroma 采用 Apache 2.0 许可。在此页面查看Chroma的完整文档，并在此页面找到 LangChain 集成的 API 参考。

设置

要访问Chroma向量数据库，您需要安装langchain-chroma集成包。

pip install -qU "langchain-chroma>=0.1.2"

凭据

您可以无需任何凭据即可使用Chroma向量数据库，只需安装上面的包即可！

如果您希望获得一流的模型调用自动跟踪，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_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
# os.environ["LANGSMITH_TRACING"] = "true"

初始化

基本初始化

下面是一个基本初始化，包括使用目录在本地保存数据。

OpenAI

pip install -qU langchain-openai

import getpass

    os.environ["OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import OpenAIEmbeddings

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

HuggingFace

pip install -qU langchain-huggingface

from langchain_huggingface import HuggingFaceEmbeddings

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

伪嵌入

pip install -qU langchain-core

from langchain_core.embeddings import FakeEmbeddings

embeddings = FakeEmbeddings(size=4096)

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 neccesary
)

从客户端初始化

您也可以从Chroma客户端初始化，如果您希望更轻松地访问底层数据库，这尤其有用。

import chromadb

persistent_client = chromadb.PersistentClient()
collection = persistent_client.get_or_create_collection("collection_name")
collection.add(ids=["1", "2", "3"], documents=["a", "b", "c"])

vector_store_from_client = Chroma(
    client=persistent_client,
    collection_name="collection_name",
    embedding_function=embeddings,
)

管理向量数据库

创建向量数据库后，我们可以通过添加和删除不同的项目与之交互。

将项目添加到向量数据库

我们可以使用add_documents函数将项目添加到向量数据库中。

from uuid import uuid4

from langchain_core.documents import Document

document_1 = Document(
    page_content="I had chocalate chip pancakes and scrambled eggs for breakfast this morning.",
    metadata={"source": "tweet"},
    id=1,
)

document_2 = Document(
    page_content="The weather forecast for tomorrow is cloudy and overcast, with a high of 62 degrees.",
    metadata={"source": "news"},
    id=2,
)

document_3 = Document(
    page_content="Building an exciting new project with LangChain - come check it out!",
    metadata={"source": "tweet"},
    id=3,
)

document_4 = Document(
    page_content="Robbers broke into the city bank and stole $1 million in cash.",
    metadata={"source": "news"},
    id=4,
)

document_5 = Document(
    page_content="Wow! That was an amazing movie. I can't wait to see it again.",
    metadata={"source": "tweet"},
    id=5,
)

document_6 = Document(
    page_content="Is the new iPhone worth the price? Read this review to find out.",
    metadata={"source": "website"},
    id=6,
)

document_7 = Document(
    page_content="The top 10 soccer players in the world right now.",
    metadata={"source": "website"},
    id=7,
)

document_8 = Document(
    page_content="LangGraph is the best framework for building stateful, agentic applications!",
    metadata={"source": "tweet"},
    id=8,
)

document_9 = Document(
    page_content="The stock market is down 500 points today due to fears of a recession.",
    metadata={"source": "news"},
    id=9,
)

document_10 = Document(
    page_content="I have a bad feeling I am going to get deleted :(",
    metadata={"source": "tweet"},
    id=10,
)

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 参考：文档

['f22ed484-6db3-4b76-adb1-18a777426cd6',
 'e0d5bab4-6453-4511-9a37-023d9d288faa',
 '877d76b8-3580-4d9e-a13f-eed0fa3d134a',
 '26eaccab-81ce-4c0a-8e76-bf542647df18',
 'bcaa8239-7986-4050-bf40-e14fb7dab997',
 'cdc44b38-a83f-4e49-b249-7765b334e09d',
 'a7a35354-2687-4bc2-8242-3849a4d18d34',
 '8780caf1-d946-4f27-a707-67d037e9e1d8',
 'dec6af2a-7326-408f-893d-7d7d717dfda9',
 '3b18e210-bb59-47a0-8e17-c8e51176ea5e']

更新向量数据库中的项目

现在我们已将文档添加到向量数据库中，我们可以使用update_documents函数更新现有文档。

updated_document_1 = Document(
    page_content="I had chocalate chip pancakes and fried eggs for breakfast this morning.",
    metadata={"source": "tweet"},
    id=1,
)

updated_document_2 = Document(
    page_content="The weather forecast for tomorrow is sunny and warm, with a high of 82 degrees.",
    metadata={"source": "news"},
    id=2,
)

vector_store.update_document(document_id=uuids[0], document=updated_document_1)
# You can also update multiple documents at once
vector_store.update_documents(
    ids=uuids[:2], documents=[updated_document_1, updated_document_1]
)

从向量数据库中删除项目

我们还可以按如下方式从向量数据库中删除项目

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

查询向量数据库

创建向量数据库并添加相关文档后，您很可能希望在链或代理运行期间查询它。

直接查询

相似性搜索

可以按如下方式执行简单的相似性搜索

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'}]

带分数的相似性搜索

如果您想执行相似性搜索并接收相应的得分，您可以运行

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=1.726390] The stock market is down 500 points today due to fears of a recession. [{'source': 'news'}]

按向量搜索

您也可以按向量搜索

results = vector_store.similarity_search_by_vector(
    embedding=embeddings.embed_query("I love green eggs and ham!"), k=1
)
for doc in results:
    print(f"* {doc.page_content} [{doc.metadata}]")

* I had chocalate chip pancakes and fried eggs for breakfast this morning. [{'source': 'tweet'}]

其他搜索方法

此笔记本中未涵盖各种其他搜索方法，例如 MMR 搜索或按向量搜索。有关AstraDBVectorStore可用的所有搜索功能的完整列表，请查看API 参考。

通过转换为检索器进行查询

您还可以将向量数据库转换为检索器，以便在链中更轻松地使用。有关您可以传递的不同搜索类型和关键字参数的更多信息，请访问此处的 API 参考。

retriever = vector_store.as_retriever(
    search_type="mmr", search_kwargs={"k": 1, "fetch_k": 5}
)
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.')]

检索增强生成的使用

有关如何将此向量数据库用于检索增强生成 (RAG) 的指南，请参阅以下部分

• 教程：使用外部知识
• 操作方法：使用 RAG 进行问答
• 检索概念文档

API 参考

有关所有Chroma向量数据库功能和配置的详细文档，请访问 API 参考：https://python.langchain.ac.cn/v0.2/api_reference/chroma/vectorstores/langchain_chroma.vectorstores.Chroma.html

相关

• 向量数据库概念指南
• 向量数据库操作指南