ApertureDB
ApertureDB 是一个数据库，用于存储、索引和管理多模态数据，例如文本、图像、视频、边界框和嵌入，以及它们相关的元数据。
本笔记本解释了如何使用 ApertureDB 的嵌入功能。
安装 ApertureDB Python SDK
这将安装用于编写 ApertureDB 客户端代码的 Python SDK。
%pip install --upgrade --quiet aperturedb
Note: you may need to restart the kernel to use updated packages.
运行 ApertureDB 实例
要继续操作，您应该已经 启动并运行 ApertureDB 实例，并配置您的环境以使用它。
有多种方法可以做到这一点，例如
docker run --publish 55555:55555 aperturedata/aperturedb-standalone
adb config create local --active --no-interactive
下载一些网页文档
我们将在这里进行一个小型爬取，只爬取一个网页。
# For loading documents from web
from langchain_community.document_loaders import WebBaseLoader
loader = WebBaseLoader("https://docs.aperturedata.io")
docs = loader.load()
API 参考：WebBaseLoader
USER_AGENT environment variable not set, consider setting it to identify your requests.
选择嵌入模型
我们想要使用 OllamaEmbeddings，因此我们需要导入必要的模块。
Ollama 可以像 文档 中所述的那样作为 Docker 容器进行设置，例如
# Run server
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
# Tell server to load a specific model
docker exec ollama ollama run llama2
from langchain_community.embeddings import OllamaEmbeddings
embeddings = OllamaEmbeddings()
API 参考：OllamaEmbeddings
将文档拆分为段落
我们想要将我们的单个文档分成多个段落。
from langchain_text_splitters import RecursiveCharacterTextSplitter
text_splitter = RecursiveCharacterTextSplitter()
documents = text_splitter.split_documents(docs)
从文档和嵌入创建向量存储
此代码在 ApertureDB 实例中创建了一个向量存储。在实例中，此向量存储表示为“描述符集”。默认情况下，描述符集名为 langchain。以下代码将为每个文档生成嵌入，并将它们存储在 ApertureDB 中作为描述符。这将需要几秒钟，因为嵌入正在生成。
from langchain_community.vectorstores import ApertureDB
vector_db = ApertureDB.from_documents(documents, embeddings)
API 参考：ApertureDB
选择大型语言模型
同样，我们使用为本地处理设置的 Ollama 服务器。
from langchain_community.llms import Ollama
llm = Ollama(model="llama2")
API 参考：Ollama
构建 RAG 链
现在，我们拥有创建 RAG（检索增强生成）链所需的所有组件。此链执行以下操作
- 为用户查询生成嵌入描述符
- 使用向量存储查找与用户查询相似的文本段落
- 使用提示模板将用户查询和上下文文档传递给 LLM
- 返回 LLM 的答案
# Create prompt
from langchain_core.prompts import ChatPromptTemplate
prompt = ChatPromptTemplate.from_template("""Answer the following question based only on the provided context:
<context>
{context}
</context>
Question: {input}""")
# Create a chain that passes documents to an LLM
from langchain.chains.combine_documents import create_stuff_documents_chain
document_chain = create_stuff_documents_chain(llm, prompt)
# Treat the vectorstore as a document retriever
retriever = vector_db.as_retriever()
# Create a RAG chain that connects the retriever to the LLM
from langchain.chains import create_retrieval_chain
retrieval_chain = create_retrieval_chain(retriever, document_chain)
Based on the provided context, ApertureDB can store images. In fact, it is specifically designed to manage multimodal data such as images, videos, documents, embeddings, and associated metadata including annotations. So, ApertureDB has the capability to store and manage images.
运行 RAG 链
最后，我们将问题传递给链并获得答案。这将需要几秒钟才能运行，因为 LLM 从查询和上下文文档中生成答案。
user_query = "How can ApertureDB store images?"
response = retrieval_chain.invoke({"input": user_query})
print(response["answer"])
Based on the provided context, ApertureDB can store images in several ways:
1. Multimodal data management: ApertureDB offers a unified interface to manage multimodal data such as images, videos, documents, embeddings, and associated metadata including annotations. This means that images can be stored along with other types of data in a single database instance.
2. Image storage: ApertureDB provides image storage capabilities through its integration with the public cloud providers or on-premise installations. This allows customers to host their own ApertureDB instances and store images on their preferred cloud provider or on-premise infrastructure.
3. Vector database: ApertureDB also offers a vector database that enables efficient similarity search and classification of images based on their semantic meaning. This can be useful for applications where image search and classification are important, such as in computer vision or machine learning workflows.
Overall, ApertureDB provides flexible and scalable storage options for images, allowing customers to choose the deployment model that best suits their needs.