Build RAG Chatbot with Haystack, OpenSearch, NVIDIA Llama 3 70B Instruct, and OpenAI text-embedding-3-large

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.
OpenSearch: An open-source search and analytics suite derived from Elasticsearch. It offers robust full-text search and real-time analytics, with vector search available as an add-on for similarity-based queries, extending its capabilities to handle high-dimensional data. Since it is just a vector search add-on rather than a purpose-built vector database, it lacks scalability and availability and many other advanced features required by enterprise-level applications. Therefore, if you prefer a much more scalable solution or hate to manage your own infrastructure, we recommend using Zilliz Cloud, which is a fully managed vector database service built on the open-source Milvus and offers a free tier supporting up to 1 million vectors.)
NVIDIA Llama 3 70B Instruct: A high-performance AI model optimized by NVIDIA for complex instruction-following tasks, combining Meta's Llama 3 70B architecture with NVIDIA’s hardware-accelerated efficiency. Strengths include rapid inference, scalability on GPUs, and nuanced context understanding. Ideal for enterprise-grade chatbots, technical support automation, and data-driven decision-making in resource-intensive environments.
OpenAI text-embedding-3-large: A state-of-the-art embedding model designed to convert text into high-dimensional vectors, capturing deep semantic relationships. Renowned for its accuracy, scalability, and ability to handle long contexts (up to 8192 tokens), it excels in semantic search, retrieval-augmented generation (RAG), recommendation systems, and multilingual NLP tasks requiring nuanced language 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 NVIDIA Llama 3 70B Instruct

To start using models self-hosted with NVIDIA, we need to install the nvidia-haystack package first.

pip install nvidia-haystack

To use LLMs with NVIDIA, you need to specify the correct api_url and your API key. You can get your API key directly from the catalog website. You also need to get an NVIDIA API key to build this pipeline. Here, we will use the NVIDIA_API_KEY environment variable by default. Otherwise, you can pass an API key at initialization with api_key, as in the following example.

from haystack.utils.auth import Secret
from haystack_integrations.components.generators.nvidia import NvidiaGenerator

generator = NvidiaGenerator(
    model="meta/llama3-70b-instruct",
    api_url="https://integrate.api.nvidia.com/v1",
    api_key=Secret.from_token("<your-api-key>"),
    model_arguments={
        "temperature": 0.2,
        "top_p": 0.7,
        "max_tokens": 1024,
    },
)
generator.warm_up()

Step 3: Install and Set Up OpenAI text-embedding-3-large

Text documents often come with a set of metadata. If they are distinctive and semantically meaningful, you can embed them along with the text of the document to improve retrieval.

from haystack import Document
from haystack.components.embedders import OpenAIDocumentEmbedder

doc = Document(content="some text",meta={"title": "relevant title", "page number": 18})

document_embedder = OpenAIDocumentEmbedder(meta_fields_to_embed=["title"])

docs_w_embeddings = embedder.run(documents=[doc])["documents"]

Now let's install and set up the model.

from haystack import Document
from haystack.components.embedders import OpenAIDocumentEmbedder
from haystack.components.embedders import OpenAITextEmbedder

text_embedder = OpenAITextEmbedder(api_key=Secret.from_token("<your-api-key>"), model="text-embedding-3-large")
document_embedder = OpenAIDocumentEmbedder(api_key=Secret.from_token("<your-api-key>"), model="text-embedding-3-large")

Step 4: Install and Set Up OpenSearch

If you have Docker set up, we recommend pulling the Docker image and running it.

docker pull opensearchproject/opensearch:2.11.0
docker run -p 9200:9200 -p 9600:9600 -e "discovery.type=single-node" -e "ES_JAVA_OPTS=-Xms1024m -Xmx1024m" opensearchproject/opensearch:2.11.0

Once you have a running OpenSearch instance, install the opensearch-haystack integration:

pip install opensearch-haystack

from haystack_integrations.components.retrievers.opensearch  import OpenSearchEmbeddingRetriever
from haystack_integrations.document_stores.opensearch import OpenSearchDocumentStore

document_store = OpenSearchDocumentStore(hosts="http://localhost:9200", use_ssl=True,
verify_certs=False, http_auth=("admin", "admin"))
retriever = OpenSearchEmbeddingRetriever(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 = OpenSearchEmbeddingRetriever(document_store=document_store) 
 text_embedder = OpenAITextEmbedder(api_key=Secret.from_token("<your-api-key>"), model="text-embedding-3-large")

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.

OpenSearch optimization tips

To optimize OpenSearch in a Retrieval-Augmented Generation (RAG) setup, fine-tune indexing by enabling efficient mappings and reducing unnecessary stored fields. Use HNSW for vector search to speed up similarity queries while balancing recall and latency with appropriate ef_search and ef_construction values. Leverage shard and replica settings to distribute load effectively, and enable caching for frequent queries. Optimize text-based retrieval with BM25 tuning and custom analyzers for better relevance. Regularly monitor cluster health, index size, and query performance using OpenSearch Dashboards and adjust configurations accordingly.

NVIDIA Llama 3 70B Instruct optimization tips

Optimize inference speed by leveraging model quantization (e.g., 16-bit or 8-bit) to reduce memory usage without significant accuracy loss. Use NVIDIA’s TensorRT-LLM for kernel fusion and efficient GPU utilization, and enable dynamic batching to process multiple queries concurrently. Fine-tune retrieval relevance thresholds to balance precision and recall, minimizing unnecessary context. Cache frequent retrieval results and precompute embeddings. Profile memory usage to avoid bottlenecks, and employ mixed-precision training if fine-tuning. Regularly update drivers and libraries (e.g., CUDA, PyTorch) to leverage hardware acceleration and software optimizations.

OpenAI text-embedding-3-large optimization tips

Optimize OpenAI text-embedding-3-large in RAG by adjusting the dimensions parameter to balance accuracy and efficiency—lower values reduce latency and cost while retaining semantic relevance. Batch embedding requests to maximize throughput, preprocess text to remove noise (e.g., truncate to 8191 tokens, normalize whitespace), and cache frequent queries. Use cosine similarity for retrieval alignment, validate embeddings with domain-specific benchmarks, and fine-tune hybrid search strategies (e.g., combining sparse/dense vectors) to improve recall. Monitor API rate limits and leverage asynchronous calls for scalability.

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, look how far you’ve come! By diving into this tutorial, you’ve unlocked the magic of building a RAG system from the ground up. You learned how Haystack acts as the backbone, orchestrating every step of the pipeline with its flexible framework, letting you connect components like a pro. OpenSearch stepped in as your powerhouse vector database, storing and retrieving embeddings at lightning speed to ensure your system serves up the most relevant context. Then came NVIDIA’s Llama 3 70B Instruct, the brains of the operation, generating human-like responses that feel natural and insightful. And let’s not forget the star of the show—OpenAI’s text-embedding-3-large—which transformed your raw data into rich, semantic embeddings, making sense of even the trickiest queries. Together, these tools showed you how to ingest data, index it efficiently, retrieve context, and generate answers that wow users. Plus, you picked up optimization gems like tweaking chunk sizes and balancing latency with accuracy, alongside a nifty free RAG cost calculator to keep your projects budget-friendly!

But this is just the beginning! You’ve now got the toolkit to build smarter, faster, and more intuitive RAG applications. Imagine creating chatbots that understand nuance, search engines that feel psychic, or research tools that surface insights in seconds. The tutorial didn’t just teach you steps—it handed you a launchpad. So why wait? Start experimenting! Tweak parameters, test new datasets, and see how far you can push your system’s performance. Every iteration is a step toward innovation. Remember, the best RAG systems aren’t just built—they’re evolved through curiosity and iteration. You’ve got the knowledge, the tools, and the edge. Now go build something amazing, optimize it like a pro, and let your creativity reshape what’s possible. The future of AI-powered apps is in your hands—crush it! 🚀

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! 💖