Build RAG Chatbot with Haystack, OpenSearch, STACKIT Meta-Llama-3.1-70B-Instruct-FP8, 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.
- 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.)
- 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.
- 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 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 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 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 = 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.
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.
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.
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
What Have You Learned?
By diving into this tutorial, you’ve unlocked the magic of building a powerful RAG system from the ground up! You learned how Haystack, the flexible framework, acts as the backbone, seamlessly stitching together components like a pro. OpenSearch stepped in as your trusty vector database, storing and retrieving dense embeddings at lightning speed, while BAAI’s bge-large-en-v1.5 embedding model transformed text into rich numerical representations, making your data “searchable” in ways plain keywords never could. Then came STACKIT Meta-Llama-3.1-70B-Instruct-FP8, the powerhouse LLM that took those retrieved snippets and crafted human-like responses, blending accuracy with creativity. Along the way, you discovered optimization hacks like tuning chunk sizes and balancing latency with quality, plus how to use the free RAG cost calculator to budget your projects smartly. Every piece—framework, database, model—played a vital role, proving that RAG isn’t just theory but a practical toolkit for real-world AI magic.
Now, imagine what’s next! You’ve got the blueprint to build, tweak, and scale RAG systems that answer questions, summarize content, or even chat with users in your own apps. Whether you’re refining retrieval accuracy, experimenting with hybrid search, or optimizing costs, the skills you’ve gained are your launchpad. Don’t just stop here—start tinkering, deploy a prototype, or push the boundaries with custom enhancements. The world of generative AI is evolving fast, and you’re now equipped to ride the wave. So fire up your IDE, embrace the trial-and-error joy, and let your creativity flow. Your next breakthrough RAG application is waiting to be built—go make it happen! 🚀
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! 💖
- Introduction to RAG
- Key Components We'll Use for This RAG Chatbot
- Step 1: Install and Set Up Haystack
- Step 2: Install and Set Up STACKIT Meta-Llama-3.1-70B-Instruct-FP8
- Step 3: Install and Set Up BAAI bge-large-en-v1.5
- Step 4: Install and Set Up OpenSearch
- Step 5: Build a RAG Chatbot
- Optimization Tips
- RAG Cost Calculator: A Free Tool to Calculate Your Cost in Seconds
- What Have You Learned?
- Further Resources
- We'd Love to Hear What You Think!
Content
Vector Database at Scale
Zilliz Cloud is a fully-managed vector database built for scale, perfect for your RAG apps.
Try Zilliz Cloud for Free