Build RAG Chatbot with Haystack, Haystack In-memory store, Cohere Command R+, and BAAI bge-large-en-v1.5

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.)
Cohere Command R+: A state-of-the-art enterprise-focused LLM optimized for high-efficiency Retrieval-Augmented Generation (RAG) and tool use, designed to automate complex workflows. Strengths include multilingual support, scalability, and robust accuracy for enterprise-grade applications. Ideal for automating customer support, data analysis, and knowledge-intensive tasks while ensuring secure, reliable collaboration between AI and human teams.
BAAI bge-large-en-v1.5: A dense embedding model optimized for semantic retrieval, excelling in capturing nuanced text semantics for tasks like retrieval-augmented generation (RAG), semantic search, and clustering. Its strengths include high accuracy across diverse domains, robust handling of complex queries, and efficient scalability. Ideal for enterprise search engines, recommendation systems, and knowledge-intensive NLP applications requiring precise contextual 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 Cohere Command R+

To use Cohere models with Haystack for a RAG pipeline, you need to get a Cohere API Key first. You can write this key in:

The api_key init parameter using Secret API
The COHERE_API_KEY environment variable (recommended)

Now, let's install and set up the Cohere model.

pip install cohere-haystack

from haystack_integrations.components.generators.cohere import CohereGenerator

generator = CohereGenerator(model="command-r-plus")

Step 3: Install and Set Up BAAI bge-large-en-v1.5

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

doc_embedder = SentenceTransformersDocumentEmbedder(model="BAAI/bge-large-en-v1.5")
doc_embedder.warm_up()
text_embedder = SentenceTransformersTextEmbedder(model="BAAI/bge-large-en-v1.5")
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-large-en-v1.5")
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

Cohere Command R+ optimization tips

To optimize Cohere Command R+ in a RAG setup, preprocess input queries by chunking large texts and filtering irrelevant context to reduce noise. Use retrieval-friendly parameters like temperature=0.3 for focused responses and max_tokens=512 to balance detail and conciseness. Fine-tune document retrieval with semantic reranking and metadata filtering to prioritize high-relevance sources. Enable confidence_score to validate output reliability, and cache frequent queries to reduce latency. Monitor token usage and response quality to iteratively adjust retrieval thresholds and generation settings for cost-performance balance.

BAAI bge-large-en-v1.5 optimization tips

To optimize BAAI bge-large-en-v1.5 in RAG, ensure input text is clean and preprocessed (remove noise, truncate to 512 tokens). Use the model’s instruction prefix ("Represent this sentence for retrieval: ") for query embeddings to align with its training. Batch embedding generation for efficiency, and normalize outputs before similarity comparisons. Fine-tune on domain-specific data if retrieval accuracy lags. Use FAISS or HNSW for fast vector search, and quantize embeddings to reduce memory. Regularly evaluate recall@k to balance speed and relevance. Leverage GPU acceleration and optimize temperature/sampling for generation coherence.

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 the magic of Haystack brings everything together to create a powerful RAG pipeline! You learned how this flexible framework acts as the backbone, seamlessly connecting your Haystack In-Memory Store (a lightweight but mighty vector database) with the BAAI bge-large-en-v1.5 embedding model to transform text into meaningful vectors. These embeddings become the secret sauce for lightning-fast retrieval, allowing your system to find the most relevant information in a snap. Then, Cohere Command R+ steps in as the genius storyteller, synthesizing those retrieved snippets into coherent, human-like answers. The tutorial walked you through every step—from ingesting data and tuning retrieval settings to crafting prompts that get the best out of your LLM. You even picked up pro tips for optimizing performance, like balancing chunk sizes and leveraging metadata filters, plus how to use the free RAG cost calculator to budget wisely without sacrificing quality.

But here’s the best part: you’re now equipped to build smarter, faster, and more efficient AI applications! Whether you’re creating a chatbot that feels eerily human or a research tool that digs through mountains of data in seconds, you’ve got the tools to make it happen. This isn’t just about following a tutorial—it’s about stepping into a world where you can experiment, tweak, and innovate. Imagine adding hybrid search, fine-tuning embeddings, or even swapping in different LLMs to see how they shine. The possibilities are endless, and every tweak you make will teach you something new. So go ahead—fire up your IDE, play with those parameters, and watch your ideas come to life. The future of intelligent applications is yours to build, and there’s no better time to start than right now. Let’s get coding! 🚀

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! 💖