Build RAG Chatbot with Haystack, Haystack In-memory store, Amazon Bedrock Claude 3.5 Haiku, and Ollama granite-embedding

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.)
AmazonBedrock Claude 3.5 Haiku: A high-efficiency AI model designed for fast, scalable processing of diverse tasks. Strengths include low-latency responses, cost-effectiveness, and seamless AWS integration. Ideal for real-time applications, high-volume data analysis, and enterprise solutions requiring reliable performance with minimal operational overhead.
Ollama Granite-Embedding: A high-performance embedding model designed for semantic understanding and retrieval tasks. It excels at generating dense vector representations for text, enabling robust similarity search, clustering, and retrieval-augmented generation (RAG). Ideal for enterprise applications requiring scalable, privacy-preserving semantic analysis in on-premises or edge 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 Amazon Bedrock Claude 3.5 Haiku

Amazon Bedrock is a fully managed service that makes high-performing foundation models from leading AI startups and Amazon available through a unified API. You can choose from various foundation models to find the one best suited for your use case.

To use LLMs on Amazon Bedrock for text generation together with Haystack, you need to initialize an AmazonBedrockGenerator with the model name, the AWS credentials (AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION) 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

from haystack_integrations.components.generators.amazon_bedrock import AmazonBedrockGenerator

aws_access_key_id="..."
aws_secret_access_key="..."
aws_region_name="eu-central-1"

generator = AmazonBedrockGenerator(model="anthropic.claude-3-5-haiku-20241022-v1:0")

Step 3: Install and Set Up Ollama granite-embedding

pip install ollama-haystack

Make sure that you have a running Ollama model (either through a docker container, or locally hosted). No other configuration is necessary as Ollama has the embedding API built in.

from haystack import Document
from haystack_integrations.components.embedders.ollama import OllamaDocumentEmbedder
from haystack_integrations.components.embedders.ollama import OllamaTextEmbedder

text_embedder = OllamaTextEmbedder(model="granite-embedding")
document_embedder = OllamaDocumentEmbedder(model="granite-embedding")

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 = OllamaTextEmbedder(model="granite-embedding")

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

AmazonBedrock Claude 3.5 Haiku optimization tips

Optimize chunk size for retrieved context to balance relevance and processing efficiency, aiming for 500-800 tokens. Structure inputs with clear separators between user queries and retrieved documents, and use system prompts like "Base responses on the provided context" to reduce hallucinations. Fine-tune parameters: lower temperature (0.2-0.4) for factual accuracy, adjust max_tokens to trim verbose outputs, and enable caching for repeated queries. Preprocess retrieved data to remove noise, validate outputs against source relevance, and implement batch processing for cost-effective scaling. Monitor latency and error rates via Amazon CloudWatch to refine performance.

Ollama Granite-Embedding optimization tips

To optimize Ollama Granite-Embedding in RAG, ensure input text is cleanly chunked (avoid truncation by splitting documents into 512-token segments). Fine-tune embedding parameters like temperature and batch size for speed-quality balance. Use hardware acceleration (e.g., CUDA) and quantize the model for faster inference. Normalize embeddings to improve similarity calculations. Regularly evaluate retrieval accuracy with benchmarks like NDCG or recall@k. Cache frequent queries to reduce redundant computations, and pre-filter low-relevance documents using metadata to lighten embedding workloads.

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, you’ve just unlocked the power to build a RAG system from scratch! By diving into this tutorial, you’ve learned how to seamlessly weave together four critical components: the Haystack framework as your orchestration backbone, the Haystack In-memory Document Store for lightning-fast vector storage, Amazon Bedrock’s Claude 3.5 Haiku as your clever LLM for generating human-like responses, and Ollama’s granite-embedding model to transform text into rich, searchable vectors. You saw firsthand how Haystack acts as the glue, connecting your data pipeline—ingesting documents, chunking them, and embedding them into the in-memory store. Claude 3.5 Haiku then steps in to synthesize answers by retrieving and contextualizing the most relevant information, all while balancing speed and accuracy. The tutorial also highlighted how Ollama’s embedding model ensures your queries and documents “speak the same language,” making retrieval precise and efficient.

But this tutorial didn’t stop at the basics! You picked up pro tips for optimizing your RAG pipeline, like tweaking chunk sizes for better context retention and using metadata to filter results. Plus, the free RAG cost calculator you explored helps you estimate expenses and scale smarter. Now that you’ve seen how these pieces fit together—and how to fine-tune them—you’re ready to create your own AI-powered applications. Imagine building chatbots that answer like experts, search tools that feel magical, or knowledge bases that evolve with your needs. The tools are in your hands, and the possibilities are endless. So go ahead—experiment, iterate, and innovate. Your next breakthrough RAG project is just a few lines of code away. Let’s build something 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! 💖