Build RAG Chatbot with Haystack, Milvus, STACKIT Meta-Llama-3.1-70B-Instruct-FP8, and AmazonBedrock cohere embed-multilingual-v3

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.
STACKIT Meta-Llama-3.1-70B-Instruct-FP8: A 70-billion-parameter instruction-tuned AI model optimized for complex NLP tasks. Leveraging FP8 quantization, it balances high performance with efficient resource usage, excelling in understanding nuanced instructions and generating context-aware responses. Ideal for enterprise applications requiring precise, scalable solutions in chatbots, virtual assistants, data analysis, and automated content generation.
AmazonBedrock Cohere Embed-Multilingual-v3: A multilingual text embedding model hosted on Amazon Bedrock designed to generate high-dimensional vector representations (1024 dimensions) for text in over 100 languages. It excels at semantic understanding, cross-lingual retrieval, and scalability, making it ideal for multilingual search, content recommendation, clustering, and retrieval-augmented generation (RAG) systems requiring broad language support and semantic accuracy.

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 STACKIT Meta-Llama-3.1-70B-Instruct-FP8

STACKIT is the cloud and colocation provider of the Schwarz Group. We can use different models on its cloud services with ease through its API.

pip install stackit-haystack

from haystack_integrations.components.generators.stackit import STACKITChatGenerator
from haystack.dataclasses import ChatMessage

generator = STACKITChatGenerator(model="neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8")

Step 3: Install and Set Up AmazonBedrock cohere embed-multilingual-v3

Amazon Bedrock is a fully managed service that makes high-performing foundation models from leading AI startups and Amazon available through a unified API.

To use embedding models on Amazon Bedrock for text and document embedding together with Haystack, you need to initialize an AmazonBedrockTextEmbedder and AmazonBedrockDocumentEmbedderwith the model name, the AWS credentials (aws_access_key_id, aws_secret_access_key, and aws_region_name) should be set as environment variables, be configured as described above or passed as Secret arguments. Note, make sure the region you set supports Amazon Bedrock.

Now, let's start installing and setting up models with Amazon Bedrock.

pip install amazon-bedrock-haystack

import os
from haystack_integrations.components.embedders.amazon_bedrock import AmazonBedrockTextEmbedder
from haystack_integrations.components.embedders.amazon_bedrock import AmazonBedrockDocumentEmbedder
from haystack.dataclasses import Document

os.environ["AWS_ACCESS_KEY_ID"] = "..."
os.environ["AWS_SECRET_ACCESS_KEY"] = "..."
os.environ["AWS_DEFAULT_REGION"] = "us-east-1" # just an example

text_embedder = AmazonBedrockTextEmbedder(model="cohere.embed-multilingual-v3",
                                                                                                                                                                        input_type="search_query"

document_embedder = AmazonBedrockDocumentEmbedder(model="cohere.embed-multilingual-v3",
                                                                                                                                                                        input_type="search_document"

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 = AmazonBedrockTextEmbedder(model="cohere.embed-multilingual-v3",
                                                                                                                                                                        input_type="search_query"

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.

STACKIT Meta-Llama-3.1-70B-Instruct-FP8 optimization tips

To optimize STACKIT Meta-Llama-3.1-70B-Instruct-FP8 in RAG, prioritize reducing input token length by truncating or summarizing retrieved documents to fit the model’s context window. Use FP8 precision to accelerate inference while maintaining accuracy. Batch processing for parallel queries improves throughput. Cache frequent or repetitive queries to avoid redundant computations. Fine-tune retrieval thresholds to balance relevance and noise. Leverage hardware-specific optimizations (e.g., Tensor Cores on GPUs) and enable model parallelism for distributed workloads. Monitor memory usage to prevent bottlenecks, and prune low-confidence outputs early to save resources.

AmazonBedrock cohere embed-multilingual-v3 optimization tips

Optimize input preprocessing by normalizing text (lowercasing, removing special characters) and splitting documents into chunks aligned with the model’s 512-token limit. Use batch processing for bulk embeddings to reduce latency and costs. Filter irrelevant content before embedding to improve retrieval quality. For multilingual queries, ensure language-specific stopword removal and consider hybrid retrieval combining semantic and keyword search. Regularly validate embedding quality via cosine similarity checks and align vector dimensions with your database (e.g., PCA for dimensionality reduction). Cache frequent queries and update embeddings periodically to reflect data changes.

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 flexible framework that stitches everything together, orchestrating data flow and interactions seamlessly. Milvus, your high-performance vector database, steps in to store and retrieve embeddings at lightning speed, ensuring your system handles complex queries effortlessly. The STACKIT Meta-Llama-3.1-70B-Instruct-FP8 model, accessed via Amazon Bedrock, became your powerhouse LLM, generating human-like responses with precision and depth. And let’s not forget the Cohere Embed-Multilingual-v3 model, which transformed text into rich, multilingual embeddings, making your RAG system globally accessible and context-aware. Together, these tools form a dynamic pipeline where data is ingested, encoded, stored, and synthesized into actionable insights—proving that integrating specialized components is the key to unlocking next-level AI applications!

But that’s not all! You also picked up pro tips for optimizing performance, like tuning chunking strategies and refining indexing parameters, ensuring your system runs efficiently at scale. The tutorial even introduced a free RAG cost calculator to help you estimate expenses and plan deployments smartly. Now, armed with this knowledge, you’re ready to innovate! Whether you’re building chatbots, research tools, or enterprise-grade solutions, the possibilities are endless. So go ahead—experiment, iterate, and push boundaries. Your journey with RAG has just begun, and the future is yours to shape. Start building today, and watch your ideas come alive with the magic of integrated AI! 🚀

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! 💖