Build RAG Chatbot with Haystack, Pgvector, Mixtral 8x7B, and Cohere embed-multilingual-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.
Pgvector: an open-source extension for PostgreSQL that enables efficient storage and querying of high-dimensional vector data, essential for machine learning and AI applications. Designed to handle embeddings, it supports fast approximate nearest neighbor (ANN) searches using algorithms like HNSW and IVFFlat. Since it is just a vector search add-on to traditional search 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.)
Mixtral 8x7B: A sparse mixture-of-experts (MoE) model with eight 7B parameter networks, designed for efficient, high-performance NLP tasks. Excels in text generation, reasoning, and multilingual support while minimizing computational costs. Ideal for scalable enterprise applications, real-time chatbots, and multi-task environments requiring optimized resource utilization and versatile AI capabilities.
Cohere embed-multilingual-light-v3.0: A compact multilingual embedding model designed to generate high-quality text representations across 100+ languages. It excels in efficient semantic understanding and retrieval, optimized for low-resource environments. Ideal for multilingual search, content moderation, and customer support applications requiring fast, accurate cross-lingual text analysis.

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 Mixtral 8x7B

To use Mistral models, you need first to get a Mistral API key. You can write this key in:

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

Now, after you get the API key, let's install the Install the mistral-haystack package.

pip install mistral-haystack

from haystack_integrations.components.generators.mistral import MistralChatGenerator
from haystack.components.generators.utils import print_streaming_chunk
from haystack.dataclasses import ChatMessage
from haystack.utils import Secret

generator = MistralChatGenerator(api_key=Secret.from_env_var("MISTRAL_API_KEY"), streaming_callback=print_streaming_chunk, model='open-mixtral-8x7b')

Step 3: Install and Set Up Cohere embed-multilingual-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-multilingual-light-v3.0")
document_embedder = CohereDocumentEmbedder(model="embed-multilingual-light-v3.0")

Step 4: Install and Set Up Pgvector

To quickly set up a PostgreSQL database with pgvector, you can use Docker:

docker run -d -p 5432:5432 -e POSTGRES_USER=postgres -e POSTGRES_PASSWORD=postgres -e POSTGRES_DB=postgres ankane/pgvector

To use pgvector with Haystack, install the pgvector-haystack integration:

pip install pgvector-haystack

import os
from haystack_integrations.document_stores.pgvector import PgvectorDocumentStore
from haystack_integrations.components.retrievers.pgvector import PgvectorEmbeddingRetriever

os.environ["PG_CONN_STR"] = "postgresql://postgres:postgres@localhost:5432/postgres"

document_store = PgvectorDocumentStore()
retriever = PgvectorEmbeddingRetriever(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 = PgvectorEmbeddingRetriever(document_store=document_store) 
 text_embedder = CohereTextEmbedder(model="embed-multilingual-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.

pgvector optimization tips

To optimize pgvector in a Retrieval-Augmented Generation (RAG) setup, consider indexing your vectors using GiST or IVFFlat to significantly speed up search queries and improve retrieval performance. Make sure to leverage parallelization for query execution, allowing multiple queries to be processed simultaneously, especially for large datasets. Optimize memory usage by tuning the vector storage size and using compressed embeddings where possible. To further enhance query speed, implement pre-filtering techniques to narrow down search space before querying. Regularly rebuild indexes to ensure they are up to date with any new data. Fine-tune vectorization models to reduce dimensionality without sacrificing accuracy, thus improving both storage efficiency and retrieval times. Finally, manage resource allocation carefully, utilizing horizontal scaling for larger datasets and offloading intensive operations to dedicated processing units to maintain responsiveness during high-traffic periods.

Mixtral 8x7B optimization tips

To optimize Mixtral 8x7B in RAG, prioritize efficient context retrieval by fine-tuning chunk size and overlap for balanced relevance and latency. Use sparse attention configurations to reduce computational overhead, and enable tensor parallelism to leverage its mixture-of-experts architecture. Quantize the model to 4-bit precision (e.g., via GPTQ) for faster inference with minimal accuracy loss. Pre-filter retrieved documents to remove noise, and cache frequent query embeddings. Adjust temperature (0.2-0.5) and max tokens to balance creativity and focus. Profile expert routing to ensure balanced workload distribution across GPU resources.

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

To optimize Cohere’s embed-multilingual-light-v3.0 in RAG, preprocess text by truncating or chunking inputs to 512 tokens for efficiency. Use batch inference to parallelize embedding generation, balancing batch size with latency and memory constraints. Normalize embeddings post-generation to improve cosine similarity accuracy. Leverage multilingual capabilities by ensuring consistent language tagging and avoiding mixed-language batches. Cache frequently accessed embeddings to reduce redundant computations. Fine-tune retrieval thresholds to balance precision and recall. Monitor model performance using metrics like retrieval hit rate and latency, and update document embeddings periodically to reflect data changes.

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 diving into this tutorial, you’ve unlocked the power of combining cutting-edge tools to create a RAG system that’s both intelligent and efficient! You’ve seen how Haystack acts as the backbone, seamlessly stitching together every component into a cohesive pipeline. With Pgvector, you’ve harnessed a vector database that’s not just fast and scalable but also deeply integrated with PostgreSQL, making it perfect for storing and retrieving embeddings. Speaking of embeddings, Cohere’s embed-multilingual-light-v3.0 showed off its magic by converting text into rich, multilingual vectors, ensuring your system understands context across languages. And let’s not forget Mixtral 8x7B, the LLM powerhouse that balances speed and quality, generating responses that feel human while staying resource-efficient. Along the way, you picked up optimization tricks—like tuning chunk sizes and balancing latency with accuracy—to squeeze every drop of performance from your setup. Plus, the free RAG cost calculator gave you a practical way to estimate expenses, so you can build smarter without breaking the bank!

Now, imagine what’s next: You’ve got the blueprint to build systems that answer questions, summarize content, or even chat with users in multiple languages—all while keeping costs in check. The tools are in your hands, and the possibilities are endless. Whether you’re refining your pipeline, experimenting with new datasets, or scaling to serve millions, you’re ready to innovate. So go ahead—tweak those parameters, test new embeddings, or integrate this RAG magic into your next big project. The future of AI-powered applications is yours to shape. Start building, keep optimizing, and let your creativity run wild. The world’s waiting for what you’ll create next! 🚀

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! 💖