Build RAG Chatbot with Haystack, Haystack In-memory store, STACKIT Meta-Llama-3.1-70B-Instruct-FP8, and Cohere embed-english-light-v3.0

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 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.
Cohere embed-english-light-v3.0: A lightweight, efficient embedding model designed to convert English text into high-dimensional vector representations. Excelling in speed and scalability, it balances accuracy with low computational demands, making it ideal for semantic search, text clustering, and retrieval-augmented applications in resource-constrained environments.

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 Cohere embed-english-light-v3.0

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-v3.0")
document_embedder = CohereDocumentEmbedder(model="embed-english-light-v3.0")

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-v3.0")

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 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.

Cohere embed-english-light-v3.0 optimization tips

To optimize Cohere embed-english-light-v3.0 in RAG, ensure input text is clean and concise by removing redundant whitespace, special characters, or irrelevant metadata. Use batch processing for embeddings to reduce API calls and latency. Align chunk sizes with the model’s 512-token limit, splitting longer texts into coherent segments. Cache frequent or static embeddings to save costs. Fine-tune retrieval scoring (e.g., cosine similarity) to match your data distribution, and pre-filter low-relevance documents using metadata to reduce computational overhead. Regularly validate embedding quality against domain-specific benchmarks.

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 now, you’ve seen how seamlessly a RAG system comes to life when you combine the right tools! You learned to use Haystack as the backbone framework, orchestrating the entire pipeline with its intuitive design—perfect for connecting components without getting lost in complexity. The Haystack In-Memory Store stepped in as your lightning-fast vector database, handling embeddings and retrieval with ease, ensuring your system stays snappy even when juggling large datasets. Then came Cohere’s embed-english-light-v3.0, transforming raw text into rich, meaningful embeddings that capture context like a pro, making your documents searchable and your answers precise. And let’s not forget the star of the show: STACKIT’s Meta-Llama-3.1-70B-Instruct-FP8, the powerhouse LLM that turns retrieved data into fluent, human-like responses, proving that cutting-edge AI can be both accessible and scalable. Together, these tools created a RAG pipeline that’s not just functional but efficient—a game-changer for anyone building intelligent applications.

But wait, there’s more! The tutorial didn’t stop at the basics. You picked up optimization gems like tweaking chunk sizes for better retrieval and balancing speed vs. accuracy, plus that nifty free RAG cost calculator to keep your projects budget-friendly. Imagine the possibilities now: chatbots that truly understand context, research tools that dig deeper, or customer support that feels magical. You’ve unlocked the power to turn raw data into actionable insights—and that’s just the beginning. So what’s next? Start experimenting! Tweak parameters, test new datasets, or integrate these tools into your own projects. The world of RAG is yours to explore, optimize, and innovate. Ready to build something amazing? Let’s go—your next breakthrough is waiting! 🚀

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! 💖