Construir um pipeline RAG: Carregando dados do S3 para o Milvus

Este tutorial orienta-o no processo de construção de um pipeline RAG (Retrieval-Augmented Generation) utilizando o Milvus e o Amazon S3. Você aprenderá como carregar documentos de forma eficiente a partir de um bucket do S3, dividi-los em pedaços gerenciáveis e armazenar seus embeddings vetoriais no Milvus para uma recuperação rápida e escalável. Para simplificar esse processo, usaremos o LangChain como uma ferramenta para carregar dados do S3 e facilitar seu armazenamento no Milvus.

Preparação

Dependências e ambiente

$ pip install --upgrade --quiet pymilvus milvus-lite openai requests tqdm boto3 langchain langchain-core langchain-community langchain-text-splitters langchain-milvus langchain-openai bs4

Neste exemplo, vamos utilizar o OpenAI como LLM. Deve preparar a chave api OPENAI_API_KEY como uma variável de ambiente.

import os

os.environ["OPENAI_API_KEY"] = "your-openai-api-key"

Configuração do S3

Para carregar documentos do S3, é necessário o seguinte:

1. AWS Access Key e Secret Key: Armazene-as como variáveis de ambiente para acessar com segurança seu bucket do S3:

os.environ["AWS_ACCESS_KEY_ID"] = "your-aws-access-key-id"
os.environ["AWS_SECRET_ACCESS_KEY"] = "your-aws-secret-access-key"

2. Bucket e documento S3: Especifique o nome do bucket e o nome do documento como argumentos para a classe S3FileLoader.

from langchain_community.document_loaders import S3FileLoader

loader = S3FileLoader(
    bucket="milvus-s3-example",  # Replace with your S3 bucket name
    key="WhatIsMilvus.docx",  # Replace with your document file name
    aws_access_key_id=os.environ["AWS_ACCESS_KEY_ID"],
    aws_secret_access_key=os.environ["AWS_SECRET_ACCESS_KEY"],
)

3. Carregar documentos: Depois de configurado, você pode carregar o documento do S3 no seu pipeline:

documents = loader.load()

Esta etapa garante que seus documentos sejam carregados com êxito do S3 e estejam prontos para processamento no pipeline do RAG.

Dividir documentos em partes

Depois de carregar o documento, use o RecursiveCharacterTextSplitter do LangChain para dividir o conteúdo em partes gerenciáveis:

from langchain_text_splitters import RecursiveCharacterTextSplitter

# Initialize a RecursiveCharacterTextSplitter for splitting text into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=2000, chunk_overlap=200)

# Split the documents into chunks using the text_splitter
docs = text_splitter.split_documents(documents)

# Let's take a look at the first document
docs[1]

Document(metadata={'source': 's3://milvus-s3-example/WhatIsMilvus.docx'}, page_content='Milvus offers three deployment modes, covering a wide range of data scales—from local prototyping in Jupyter Notebooks to massive Kubernetes clusters managing tens of billions of vectors: \n\nMilvus Lite is a Python library that can be easily integrated into your applications. As a lightweight version of Milvus, it’s ideal for quick prototyping in Jupyter Notebooks or running on edge devices with limited resources. Learn more.\nMilvus Standalone is a single-machine server deployment, with all components bundled into a single Docker image for convenient deployment. Learn more.\nMilvus Distributed can be deployed on Kubernetes clusters, featuring a cloud-native architecture designed for billion-scale or even larger scenarios. This architecture ensures redundancy in critical components. Learn more. \n\nWhat Makes Milvus so Fast\U0010fc00 \n\nMilvus was designed from day one to be a highly efficient vector database system. In most cases, Milvus outperforms other vector databases by 2-5x (see the VectorDBBench results). This high performance is the result of several key design decisions: \n\nHardware-aware Optimization: To accommodate Milvus in various hardware environments, we have optimized its performance specifically for many hardware architectures and platforms, including AVX512, SIMD, GPUs, and NVMe SSD. \n\nAdvanced Search Algorithms: Milvus supports a wide range of in-memory and on-disk indexing/search algorithms, including IVF, HNSW, DiskANN, and more, all of which have been deeply optimized. Compared to popular implementations like FAISS and HNSWLib, Milvus delivers 30%-70% better performance.')

Nesta fase, os seus documentos são carregados a partir do S3, divididos em partes mais pequenas e prontos para serem processados no pipeline RAG (Retrieval-Augmented Generation).

Criar cadeia RAG com o Milvus Vetor Store

Iremos inicializar um armazenamento de vectores Milvus com os documentos, que carregam os documentos no armazenamento de vectores Milvus e constroem um índice sob o capô.

from langchain_milvus import Milvus
from langchain_openai import OpenAIEmbeddings

embeddings = OpenAIEmbeddings()

vectorstore = Milvus.from_documents(
    documents=docs,
    embedding=embeddings,
    connection_args={
        "uri": "./milvus_demo.db",
    },
    drop_old=False,  # Drop the old Milvus collection if it exists
)

Pesquise os documentos no armazenamento de vectores do Milvus utilizando uma pergunta de teste. Vejamos o documento 1 de topo.

query = "How can Milvus be deployed"
vectorstore.similarity_search(query, k=1)

[Document(metadata={'pk': 455631712233193487, 'source': 's3://milvus-s3-example/WhatIsMilvus.docx'}, page_content='Milvus offers three deployment modes, covering a wide range of data scales—from local prototyping in Jupyter Notebooks to massive Kubernetes clusters managing tens of billions of vectors: \n\nMilvus Lite is a Python library that can be easily integrated into your applications. As a lightweight version of Milvus, it’s ideal for quick prototyping in Jupyter Notebooks or running on edge devices with limited resources. Learn more.\nMilvus Standalone is a single-machine server deployment, with all components bundled into a single Docker image for convenient deployment. Learn more.\nMilvus Distributed can be deployed on Kubernetes clusters, featuring a cloud-native architecture designed for billion-scale or even larger scenarios. This architecture ensures redundancy in critical components. Learn more. \n\nWhat Makes Milvus so Fast\U0010fc00 \n\nMilvus was designed from day one to be a highly efficient vector database system. In most cases, Milvus outperforms other vector databases by 2-5x (see the VectorDBBench results). This high performance is the result of several key design decisions: \n\nHardware-aware Optimization: To accommodate Milvus in various hardware environments, we have optimized its performance specifically for many hardware architectures and platforms, including AVX512, SIMD, GPUs, and NVMe SSD. \n\nAdvanced Search Algorithms: Milvus supports a wide range of in-memory and on-disk indexing/search algorithms, including IVF, HNSW, DiskANN, and more, all of which have been deeply optimized. Compared to popular implementations like FAISS and HNSWLib, Milvus delivers 30%-70% better performance.')]

from langchain_core.runnables import RunnablePassthrough
from langchain_core.prompts import PromptTemplate
from langchain_core.output_parsers import StrOutputParser
from langchain_openai import ChatOpenAI

# Initialize the OpenAI language model for response generation
llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0)

# Define the prompt template for generating AI responses
PROMPT_TEMPLATE = """
Human: You are an AI assistant, and provides answers to questions by using fact based and statistical information when possible.
Use the following pieces of information to provide a concise answer to the question enclosed in <question> tags.
If you don't know the answer, just say that you don't know, don't try to make up an answer.
<context>
{context}
</context>

<question>
{question}
</question>

The response should be specific and use statistics or numbers when possible.

Assistant:"""

# Create a PromptTemplate instance with the defined template and input variables
prompt = PromptTemplate(
    template=PROMPT_TEMPLATE, input_variables=["context", "question"]
)
# Convert the vector store to a retriever
retriever = vectorstore.as_retriever()


# Define a function to format the retrieved documents
def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)

Utilize a LCEL (LangChain Expression Language) para criar uma cadeia RAG.

rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)


res = rag_chain.invoke(query)
res

'Milvus can be deployed in three different modes: Milvus Lite for local prototyping and edge devices, Milvus Standalone for single-machine server deployment, and Milvus Distributed for deployment on Kubernetes clusters. These deployment modes cover a wide range of data scales, from small-scale prototyping to massive clusters managing tens of billions of vectors.'