Notebooks
M
Milvus Build RAG From S3 With Milvus

Build RAG From S3 With Milvus

image-searchvector-databasesemantic-searchIntegrationmilvusembeddingsunstructured-dataquestion-answeringLLMmilvus-bootcampdeep-learningimage-recognitionimage-classificationaudio-searchPythonragNLP
alph-notebooks/milvus-bootcamp / build_RAG_from_s3_with_milvus.ipynb

Building a RAG Pipeline: Loading Data from S3 into Milvus

This tutorial walks you through the process of building a Retrieval-Augmented Generation (RAG) pipeline using Milvus and Amazon S3. You will learn how to efficiently load documents from a S3 bucket, split them into manageable chunks, and store their vector embeddings in Milvus for fast and scalable retrieval. To streamline this process, we will use LangChain as a tool to load data from S3 and facilitate its storage in Milvus.

Preparation

Dependencies and Environment

[ ]

If you are using Google Colab, to enable dependencies just installed, you may need to restart the runtime (click on the "Runtime" menu at the top of the screen, and select "Restart session" from the dropdown menu).

We will use OpenAI as the LLM in this example. You should prepare the api key OPENAI_API_KEY as an environment variable.

[44]

S3 Configuration

For loading documents from S3, you need the following:

  1. AWS Access Key and Secret Key: Store these as environment variables to securely access your S3 bucket:
[45]
  1. S3 Bucket and Document: Specify the bucket name and document name as arguments to the S3FileLoader class.
[46]
  1. Load Documents: Once configured, you can load the document from S3 into your pipeline:
[47]

This step ensures that your documents are successfully loaded from S3 and ready for processing in the RAG pipeline.

Split Documents into Chunks

After loading the document, use LangChain's RecursiveCharacterTextSplitter to break the content into manageable chunks:

[49]
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.')

At this stage, your documents are loaded from S3, split into smaller chunks, and ready for further processing in the Retrieval-Augmented Generation (RAG) pipeline.

Build RAG chain with Milvus Vector Store

We will initialize a Milvus vector store with the documents, which load the documents into the Milvus vector store and build an index under the hood.

[50]

For the connection_args:

  • Setting the uri as a local file, e.g../milvus.db, is the most convenient method, as it automatically utilizes Milvus Lite to store all data in this file.
  • If you have large scale of data, you can set up a more performant Milvus server on docker or kubernetes. In this setup, please use the server uri, e.g.http://localhost:19530, as your uri.
  • If you want to use Zilliz Cloud, the fully managed cloud service for Milvus, please adjust the uri and token, which correspond to the Public Endpoint and Api key in Zilliz Cloud.

Search the documents in the Milvus vector store using a test query question. Let’s take a look at the top 1 document.

[51]
[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.')]
[52]

Use the LCEL(LangChain Expression Language) to build a RAG chain.

[53]
'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.'
[ ]