Build RAG Chatbot with Haystack, Milvus, Google Vertex AI Gemini 2.0 Flash-Lite, and Optimum mpnet-base-v2

Introduction to RAG

Retrieval-Augmented Generation (RAG) is a game-changer for GenAI applications, especially in conversational AI. It combines the power of pre-trained large language models (LLMs) like OpenAI’s GPT with external knowledge sources stored in vector databases such as Milvus and Zilliz Cloud, allowing for more accurate, contextually relevant, and up-to-date response generation. A RAG pipeline usually consists of four basic components: a vector database, an embedding model, an LLM, and a framework.

Key Components We'll Use for This RAG Chatbot

This tutorial shows you how to build a simple RAG chatbot in Python using the following components:

Haystack: An open-source Python framework designed for building production-ready NLP applications, particularly question answering and semantic search systems. Haystack excels at retrieving information from large document collections through its modular architecture that combines retrieval and reader components. Ideal for developers creating search applications, chatbots, and knowledge management systems that require efficient document processing and accurate information extraction from unstructured text.
Milvus: An open-source vector database optimized to store, index, and search large-scale vector embeddings efficiently, perfect for use cases like RAG, semantic search, and recommender systems. If you hate to manage your own infrastructure, we recommend using Zilliz Cloud, which is a fully managed vector database service built on Milvus and offers a free tier supporting up to 1 million vectors.
Google Vertex AI Gemini 2.0 Flash-Lite: A lightweight, high-speed AI model optimized for rapid inference and low-latency applications. Designed for scalability and cost-efficiency, it excels in real-time processing, large-scale deployments, and scenarios requiring quick decision-making, such as chatbots, dynamic content generation, and real-time analytics. Ideal for enterprises prioritizing performance and resource optimization.
Optimum mpnet-base-v2: A high-performance model designed for sentence-level tasks, Optimum mpnet-base-v2 is optimized for semantic textual similarity, classification, and retrieval applications. Its efficient architecture excels in both speed and accuracy, making it ideal for use cases in natural language understanding, search, and recommendation systems.

By the end of this tutorial, you’ll have a functional chatbot capable of answering questions based on a custom knowledge base.

Note: Since we may use proprietary models in our tutorials, make sure you have the required API key beforehand.

Step 1: Install and Set Up Haystack

import os
import requests

from haystack import Pipeline
from haystack.components.converters import MarkdownToDocument

from haystack.components.preprocessors import DocumentSplitter
from haystack.components.writers import DocumentWriter

Step 2: Install and Set Up Google Vertex AI Gemini 2.0 Flash-Lite

Using theVertexAIGeminiGenerator with Haystack requires authentication using Google Cloud Application Default Credentials (ADCs). This means your application must be set up with credentials that allow it to access Google Cloud services. If you're not sure how to configure ADCs, check the official Google documentation for setup instructions.

It's important to use a Google Cloud account that has the right permissions to access a project with Google Vertex AI endpoints. Without proper access, the generator won’t work as expected.

To find your project ID, you can either look it up in the Google Cloud Console under the resource manager or run the following command in your terminal.

Now let's install and set up this model.

pip install google-vertex-haystack

from haystack_integrations.components.generators.google_vertex import VertexAIGeminiGenerator

generator = VertexAIGeminiGenerator(model="gemini-1.5-flash")

Step 3: Install and Set Up Optimum mpnet-base-v2

Haystack's OptimumTextEmbedder embeds text strings using models loaded with the HuggingFace Optimum library. It uses the ONNX runtime for high-speed inference. Similarly to other Embedders, this component allows adding prefixes (and suffixes) to include instructions. For more details, refer to the Optimum API Reference.

pip install optimum-haystack

from haystack_integrations.components.embedders.optimum import OptimumTextEmbedder
from haystack.dataclasses import Document
from haystack_integrations.components.embedders.optimum import OptimumDocumentEmbedder

text_embedder = OptimumTextEmbedder(model="sentence-transformers")
text_embedder.warm_up()

document_embedder = OptimumDocumentEmbedder(model="sentence-transformers/mpnet-base-v2")
document_embedder.warm_up()

Step 4: Install and Set Up Milvus

pip install --upgrade pymilvus milvus-haystack

from milvus_haystack import MilvusDocumentStore
from milvus_haystack.milvus_embedding_retriever import MilvusEmbeddingRetriever

document_store = MilvusDocumentStore(connection_args={"uri": "./milvus.db"}, drop_old=True,)
retriever = MilvusEmbeddingRetriever(document_store=document_store, top_k=3)

Step 5: Build a RAG Chatbot

Now that you’ve set up all components, let’s start to build a simple chatbot. We’ll use the Milvus introduction doc as a private knowledge base. You can replace it your own dataset to customize your RAG chatbot.

url = 'https://raw.githubusercontent.com/milvus-io/milvus-docs/refs/heads/v2.5.x/site/en/about/overview.md'
example_file = 'example_file.md'
response = requests.get(url)
with open(example_file, 'wb') as f:
    f.write(response.content)
file_paths = [example_file]  # You can replace it with your own file paths.

indexing_pipeline = Pipeline()
indexing_pipeline.add_component("converter", MarkdownToDocument())
indexing_pipeline.add_component("splitter", DocumentSplitter(split_by="sentence", split_length=2))
indexing_pipeline.add_component("embedder", document_embedder)
indexing_pipeline.add_component("writer", DocumentWriter(document_store))
indexing_pipeline.connect("converter", "splitter")
indexing_pipeline.connect("splitter", "embedder")
indexing_pipeline.connect("embedder", "writer")
indexing_pipeline.run({"converter": {"sources": file_paths}})

# print("Number of documents:", document_store.count_documents())
  
question = "What is Milvus?"  # You can replace it with your own question.

retrieval_pipeline = Pipeline()
retrieval_pipeline.add_component("embedder", text_embedder)
retrieval_pipeline.add_component("retriever", retriever)
retrieval_pipeline.connect("embedder", "retriever")

retrieval_results = retrieval_pipeline.run({"embedder": {"text": question}})

# for doc in retrieval_results["retriever"]["documents"]:
#     print(doc.content)
#     print("-" * 10)

from haystack.utils import Secret
from haystack.components.builders import PromptBuilder

retriever = MilvusEmbeddingRetriever(document_store=document_store, top_k=3) 
 text_embedder = OptimumTextEmbedder(model="sentence-transformers")
text_embedder.warm_up()

prompt_template = """Answer the following query based on the provided context. If the context does
                     not include an answer, reply with 'I don't know'.\n
                     Query: {{query}}
                     Documents:
                     {% for doc in documents %}
                        {{ doc.content }}
                     {% endfor %}
                     Answer: 
                  """

rag_pipeline = Pipeline()
rag_pipeline.add_component("text_embedder", text_embedder)
rag_pipeline.add_component("retriever", retriever)
rag_pipeline.add_component("prompt_builder", PromptBuilder(template=prompt_template))
rag_pipeline.add_component("generator", generator)
rag_pipeline.connect("text_embedder.embedding", "retriever.query_embedding")
rag_pipeline.connect("retriever.documents", "prompt_builder.documents")
rag_pipeline.connect("prompt_builder", "generator")

results = rag_pipeline.run({"text_embedder": {"text": question}, "prompt_builder": {"query": question},})
print('RAG answer:\n', results["generator"]["replies"][0])

Optimization Tips

As you build your RAG system, optimization is key to ensuring peak performance and efficiency. While setting up the components is an essential first step, fine-tuning each one will help you create a solution that works even better and scales seamlessly. In this section, we’ll share some practical tips for optimizing all these components, giving you the edge to build smarter, faster, and more responsive RAG applications.

Haystack optimization tips

To optimize Haystack in a RAG setup, ensure you use an efficient retriever like FAISS or Milvus for scalable and fast similarity searches. Fine-tune your document store settings, such as indexing strategies and storage backends, to balance speed and accuracy. Use batch processing for embedding generation to reduce latency and optimize API calls. Leverage Haystack's pipeline caching to avoid redundant computations, especially for frequently queried documents. Tune your reader model by selecting a lightweight yet accurate transformer-based model like DistilBERT to speed up response times. Implement query rewriting or filtering techniques to enhance retrieval quality, ensuring the most relevant documents are retrieved for generation. Finally, monitor system performance with Haystack’s built-in evaluation tools to iteratively refine your setup based on real-world query performance.

Milvus optimization tips

Milvus serves as a highly efficient vector database, critical for retrieval tasks in a RAG system. To optimize its performance, ensure that indexes are properly built to balance speed and accuracy; consider utilizing HNSW (Hierarchical Navigable Small World) for efficient nearest neighbor search where response time is crucial. Partitioning data based on usage patterns can enhance query performance and reduce load times, enabling better scalability. Regularly monitor and adjust cache settings based on query frequency to avoid latency during data retrieval. Employ batch processing for vector insertions, which can minimize database lock contention and enhance overall throughput. Additionally, fine-tune the model parameters by experimenting with the dimensionality of the vectors; higher dimensions can improve retrieval accuracy but may increase search time, necessitating a balance tailored to your specific use case and hardware infrastructure.

Google Vertex AI Gemini 2.0 Flash-Lite optimization tips

Optimize Gemini 2.0 Flash-Lite in RAG by preprocessing inputs to remove noise and standardize formats, ensuring cleaner context for retrieval. Adjust temperature and top-k values to balance creativity and relevance in outputs. Use smaller document chunks (e.g., 512 tokens) during retrieval to reduce latency and improve alignment with the model’s token limits. Cache frequent queries and responses to lower API costs and latency. Enable streaming for real-time applications and batch requests where feasible. Regularly validate outputs for accuracy and trim redundant content. Fine-tune with domain-specific data if available, and monitor usage metrics to adjust scaling dynamically.

Optimum mpnet-base-v2 optimization tips

To optimize the performance of Optimum mpnet-base-v2 in a Retrieval-Augmented Generation (RAG) setup, consider fine-tuning the model on domain-specific data to improve its understanding of specialized queries. Leverage batch processing for efficient inference and experiment with reduced precision (e.g., mixed-precision or FP16) to speed up computation without sacrificing much accuracy. For better retrieval performance, optimize your vector store by choosing an appropriate indexing strategy, such as HNSW or IVF, and ensuring the embeddings are well-aligned with the query space. Additionally, consider using a smaller version of the model for less complex tasks to balance speed and resource usage. Regularly monitor the retrieval quality and adjust hyperparameters, such as the number of nearest neighbors, for the best results.

By implementing these tips across your components, you'll be able to enhance the performance and functionality of your RAG system, ensuring it’s optimized for both speed and accuracy. Keep testing, iterating, and refining your setup to stay ahead in the ever-evolving world of AI development.

RAG Cost Calculator: A Free Tool to Calculate Your Cost in Seconds

Estimating the cost of a Retrieval-Augmented Generation (RAG) pipeline involves analyzing expenses across vector storage, compute resources, and API usage. Key cost drivers include vector database queries, embedding generation, and LLM inference.

RAG Cost Calculator is a free tool that quickly estimates the cost of building a RAG pipeline, including chunking, embedding, vector storage/search, and LLM generation. It also helps you identify cost-saving opportunities and achieve up to 10x cost reduction on vector databases with the serverless option.

Calculate your RAG cost now.

Calculate your RAG cost

What Have You Learned?

By diving into this tutorial, you’ve unlocked the power of combining cutting-edge tools to build a robust RAG system! You learned how Haystack acts as the glue, orchestrating the entire pipeline—from ingesting documents to generating answers—while Milvus steps in as your high-performance vector database, efficiently storing and retrieving embeddings at scale. The magic of Optimum’s mpnet-base-v2 embedding model transformed your raw text into rich, semantic vectors, capturing meaning in ways that make search results feel almost intuitive. And let’s not forget Google’s Gemini 2.0 Flash-Lite, the speed-optimized LLM that delivered lightning-fast, cost-effective responses without sacrificing quality. Together, these tools showed you how to create a system that doesn’t just answer questions but understands context, bridging the gap between data and insight. You even picked up pro tips like optimizing chunking strategies for better retrieval and balancing latency with accuracy—skills that’ll make your applications leaner and smarter. Plus, the free RAG cost calculator gave you a crystal-clear view of expenses, empowering you to experiment fearlessly without blowing your budget.

Now, armed with this knowledge, you’re ready to build, tweak, and scale RAG systems that solve real-world problems. Imagine the applications: chatbots that feel human, search engines that read minds, or tools that democratize access to complex data. The tutorial didn’t just teach you steps—it handed you a toolbox for innovation. So, what’s next? Start experimenting! Tweak those parameters, explore new datasets, and let your creativity run wild. The future of intelligent applications is yours to shape, and every line of code you write brings us closer to a world where information isn’t just accessible—it’s alive. Let’s build something amazing, together! 🚀

Further Resources

🌟 In addition to this RAG tutorial, unleash your full potential with these incredible resources to level up your RAG skills.

How to Build a Multimodal RAG | Documentation
How to Enhance the Performance of Your RAG Pipeline
Graph RAG with Milvus | Documentation
How to Evaluate RAG Applications - Zilliz Learn
Generative AI Resource Hub | Zilliz

We'd Love to Hear What You Think!

We’d love to hear your thoughts! 🌟 Leave your questions or comments below or join our vibrant Milvus Discord community to share your experiences, ask questions, or connect with thousands of AI enthusiasts. Your journey matters to us!

If you like this tutorial, show your support by giving our Milvus GitHub repo a star ⭐—it means the world to us and inspires us to keep creating! 💖