Build RAG Chatbot with Haystack, Haystack In-memory store, STACKIT Meta-Llama-3.1-70B-Instruct-FP8, and BAAI bge-m3

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.
Haystack in-memory store: a very simple, in-memory document store with no extra services or dependencies. It is great for experimenting with Haystack, and we do not recommend using it for production. If you want a much more scalable solution for your apps or even enterprise projects, we recommend using Zilliz Cloud, which is a fully managed vector database service built on the open-source Milvusand 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.
BAAI bge-m3: A multilingual embedding model optimized for dense retrieval and semantic representation across 100+ languages. It excels in handling long texts, multi-task learning, and cross-lingual applications, offering high accuracy and scalability. Ideal for multilingual search engines, content recommendation systems, and enterprise-grade text analysis requiring robust semantic understanding.

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 BAAI bge-m3

from haystack import Document
from haystack.components.embedders import SentenceTransformersDocumentEmbedder
from haystack.components.embedders import SentenceTransformersTextEmbedder

doc_embedder = SentenceTransformersDocumentEmbedder(model="BAAI/bge-m3")
doc_embedder.warm_up()
text_embedder = SentenceTransformersTextEmbedder(model="BAAI/bge-m3")
text_embedder.warm_up()

Step 4: Install and Set Up Haystack In-memory store

from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack.components.retrievers import InMemoryEmbeddingRetriever

document_store = InMemoryDocumentStore()
retriever=InMemoryEmbeddingRetriever(document_store=document_store))

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=InMemoryEmbeddingRetriever(document_store=document_store) 
 text_embedder = SentenceTransformersTextEmbedder(model="BAAI/bge-m3")
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.

Haystack in-memory store optimization tips

Haystack in-memory store is just a very simple, in-memory document store with no extra services or dependencies. We recommend that you just experiment it with RAG pipeline within your Haystack framework, and we do not recommend using it for production. If you want a much more scalable solution for your apps or even enterprise projects, we recommend using Zilliz Cloud, which is a fully managed vector database service built on the open-source Milvusand offers a free tier supporting up to 1 million vectors

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.

BAAI bge-m3 optimization tips

To optimize BAAI bge-m3 in a RAG setup, fine-tune the model on domain-specific data to enhance retrieval relevance. Use dynamic chunking (e.g., 256-512 tokens) for balanced context capture and computational efficiency. Normalize embeddings before similarity scoring to reduce bias. Enable mixed-precision inference for faster processing without significant accuracy loss. Experiment with pooling strategies like CLS or mean-pooling for dense vectors. Regularly update the retrieval corpus to reflect new data, and apply batch processing during inference to maximize GPU utilization. Monitor embedding quality via recall@k metrics to refine parameters iteratively.

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 taken a huge leap into the world of RAG systems—and you’ve seen firsthand how powerful components like Haystack, the Haystack In-Memory Store, STACKIT Meta-Llama-3.1-70B-Instruct-FP8, and the BAAI bge-m3 embedding model work together to create something truly transformative! You learned how Haystack acts as the backbone, seamlessly connecting your data pipeline, retrieval system, and language model. The Haystack In-Memory Store showed you how lightweight yet efficient vector databases can supercharge retrieval speeds, while the BAAI bge-m3 model revealed the magic of turning text into rich, context-aware embeddings. And let’s not forget the star of the show—Meta-Llama-3.1-70B-Instruct-FP8, which demonstrated how cutting-edge LLMs can generate human-like responses by synthesizing retrieved knowledge with creativity. You even picked up pro tips for optimizing your RAG pipeline, like balancing chunk sizes and leveraging metadata for precision, plus how to use the free RAG cost calculator to estimate expenses and scale smartly.

Now, imagine what you can build next! Whether it’s a chatbot that feels eerily human, a research assistant that digs through mountains of data, or a creative tool that blends facts with flair, you’ve got the skills to make it happen. This tutorial was just the beginning—your playground for innovation is wide open. So go ahead: experiment with different models, tweak your retrieval strategies, and push the boundaries of what RAG can do. The future of intelligent applications is in your hands, and every line of code you write brings it closer. Let’s build something amazing—start today, and watch your ideas come to life! 🚀

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! 💖