Build RAG Chatbot with Haystack, Haystack In-memory store, STACKIT Mistral-Nemo-Instruct-2407-FP8, and Cohere embed-english-light-v2.0

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 Mistral-Nemo-Instruct-2407-FP8: An instruction-tuned AI model optimized for efficient, real-time natural language processing. Combining Mistral’s robust language capabilities with Nemo’s scalability, it excels in low-latency text generation, query resolution, and task automation using FP8 precision. Ideal for resource-constrained environments, customer support automation, and edge-computing applications requiring rapid, accurate responses.
Cohere embed-english-light-v2.0: A lightweight embedding model optimized to convert English text into dense vector representations efficiently. It excels in semantic search, clustering, and similarity tasks, balancing speed and accuracy. Ideal for real-time applications, cost-sensitive deployments, and resource-constrained environments requiring scalable, rapid text analysis without compromising performance.

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 Mistral-Nemo-Instruct-2407-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/Mistral-Nemo-Instruct-2407-FP8")

Step 3: Install and Set Up Cohere embed-english-light-v2.0

To start using this integration with Haystack, install it with:

pip install cohere-haystack

from haystack import Document
from haystack_integrations.components.embedders.cohere.document_embedder import CohereDocumentEmbedder
from haystack_integrations.components.embedders.cohere.text_embedder import CohereTextEmbedder

text_embedder = CohereTextEmbedder(model="embed-english-light-v2.0")
document_embedder = CohereDocumentEmbedder(model="embed-english-light-v2.0")

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 = CohereTextEmbedder(model="embed-english-light-v2.0")

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 Mistral-Nemo-Instruct-2407-FP8 optimization tips

To optimize STACKIT Mistral-Nemo-Instruct-2407-FP8 in a RAG setup, ensure input prompts are concise and contextually enriched with retrieved documents, truncating irrelevant sections to stay within the 4k token limit. Leverage FP8 precision for faster inference by enabling compatible hardware acceleration (e.g., NVIDIA Tensor Cores). Batch process queries when possible, and fine-tune retrieval thresholds to balance relevance and noise. Use caching for frequent queries, and monitor latency to adjust chunk sizes or parallelize document processing. Regularly validate outputs against ground truth to refine retrieval-model alignment.

Cohere embed-english-light-v2.0 optimization tips

To optimize Cohere embed-english-light-v2.0 in RAG, preprocess input text by truncating or chunking documents to the model’s 512-token limit for efficiency. Use batch processing to encode multiple texts simultaneously, reducing API overhead. Normalize embeddings to improve cosine similarity accuracy. Pair with a fast vector database (e.g., FAISS) for low-latency retrieval. Cache frequent queries to minimize redundant computations. Monitor embedding quality via retrieval hit rates and adjust text chunking strategies for domain-specific contexts. Fine-tune batch sizes to balance speed and memory usage.

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?

Wow, what an awesome journey you’ve been on! By diving into this tutorial, you’ve learned how to piece together the building blocks of a powerful RAG system, turning abstract concepts into a functional pipeline that breathes life into your applications. You discovered how Haystack acts as the glue, seamlessly orchestrating the flow of data between components. The Haystack In-Memory Store became your trusty sidekick, handling lightning-fast vector searches without the fuss of external databases. You saw how the Cohere embed-english-light-v2.0 model transformed raw text into rich embeddings, capturing meaning in ways that make retrieval intuitive and precise. Then, STACKIT Mistral-Nemo-Instruct-2407-FP8 stepped in as the brains of the operation, synthesizing retrieved information into coherent, context-aware responses. Together, these tools showed you how to fetch, understand, and generate answers dynamically—like giving your app a supercharged memory and a knack for conversation!

But wait—there’s more! You also picked up pro tips for optimizing your RAG pipeline, like balancing speed and accuracy with chunk sizing or tweaking embedding dimensions. And let’s not forget the free RAG cost calculator you explored, a game-changer for budgeting resources without surprises. Now that you’ve seen how these pieces fit together, imagine the possibilities: chatbots that truly understand context, research tools that dig deeper, or creative apps that remix knowledge in real-time. The tools are in your hands, and the best part? You’re ready to iterate, experiment, and innovate. So what’s next? Start building! Tweak that pipeline, test new models, or share your creation with the world. Every line of code you write is a step toward something groundbreaking. Go ahead—your RAG adventure is just beginning, and the future is wide open. Let’s make it amazing! 🚀

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! 💖