Build RAG Chatbot with Llamaindex, Pgvector, Mistral Ministral 3B, and AmazonBedrock cohere embed-multilingual-v3

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:

Llamaindex: a data framework that connects large language models (LLMs) with various data sources, enabling efficient retrieval-augmented generation (RAG). It helps structure, index, and query private or external data, optimizing LLM applications for search, chatbots, and analytics.
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.)
Mistral Ministral 3B: A compact, high-efficiency language model optimized for fast inference and low-resource environments. With 3 billion parameters, it balances performance and scalability, excelling in text generation, summarization, and question-answering tasks. Ideal for edge computing, real-time applications, and cost-sensitive deployments requiring reliable NLP capabilities without heavy computational demands.
AmazonBedrock Cohere Embed-Multilingual-v3: A multilingual text embedding model hosted on Amazon Bedrock designed to generate high-dimensional vector representations (1024 dimensions) for text in over 100 languages. It excels at semantic understanding, cross-lingual retrieval, and scalability, making it ideal for multilingual search, content recommendation, clustering, and retrieval-augmented generation (RAG) systems requiring broad language support and semantic accuracy.

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 Llamaindex

pip install llama-index

Step 2: Install and Set Up Mistral Ministral 3B

%pip install llama-index-llms-mistralai

from llama_index.llms.mistralai import MistralAI

llm = MistralAI(model="ministral-3b-latest")

Step 3: Install and Set Up AmazonBedrock cohere embed-multilingual-v3

%pip install llama-index-embeddings-bedrock

from llama_index.embeddings.bedrock import BedrockEmbedding

ebed_model = BedrockEmbedding(model_name="cohere.embed-multilingual-v3")

Step 4: Install and Set Up Pgvector

%pip install llama-index-vector-stores-postgres

from llama_index.core import VectorStoreIndex
from llama_index.vector_stores.postgres import PGVectorStore

vector_store = PGVectorStore.from_params(
    database=db_name,
    host=url.host,
    password=url.password,
    port=url.port,
    user=url.username,
    table_name="your_table_name",
    embed_dim=1536,  # openai embedding dimension
    hnsw_kwargs={
        "hnsw_m": 16,
        "hnsw_ef_construction": 64,
        "hnsw_ef_search": 40,
        "hnsw_dist_method": "vector_cosine_ops",
    },
)

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 with your own dataset to customize your RAG chatbot.

import requests

from llama_index.core import SimpleDirectoryReader

# load documents
url = 'https://raw.githubusercontent.com/milvus-io/milvus-docs/refs/heads/v2.5.x/site/en/about/overview.md'
example_file = 'example_file.md'  # You can replace it with your own file paths.
response = requests.get(url)
with open(example_file, 'wb') as f:
    f.write(response.content)
documents = SimpleDirectoryReader(
    input_files=[example_file]
).load_data()

print("Document ID:", documents[0].doc_id)

storage_context = StorageContext.from_defaults(vector_store=vector_store)
index = VectorStoreIndex.from_documents(
    documents, storage_context=storage_context, embed_model=embed_model
)

query_engine = index.as_query_engine(llm=llm)
res = query_engine.query("What is Milvus?")  # You can replace it with your own question.
print(res)

Example output

Milvus is a high-performance, highly scalable vector database designed to operate efficiently across various environments, from personal laptops to large-scale distributed systems. It is available as both open-source software and a cloud service. Milvus excels in managing unstructured data by converting it into numerical vectors through embeddings, which facilitates fast and scalable searches and analytics. The database supports a wide range of data types and offers robust data modeling capabilities, allowing users to organize their data effectively. Additionally, Milvus provides multiple deployment options, including a lightweight version for quick prototyping and a distributed version for handling massive data scales.

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.

LlamaIndex optimization tips

To optimize LlamaIndex for a Retrieval-Augmented Generation (RAG) setup, structure your data efficiently using hierarchical indices like tree-based or keyword-table indices for faster retrieval. Use embeddings that align with your use case to improve search relevance. Fine-tune chunk sizes to balance context length and retrieval precision. Enable caching for frequently accessed queries to enhance performance. Optimize metadata filtering to reduce unnecessary search space and improve speed. If using vector databases, ensure indexing strategies align with your query patterns. Implement async processing to handle large-scale document ingestion efficiently. Regularly monitor query performance and adjust indexing parameters as needed for optimal results.

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.

Mistral Ministral 3B optimization tips

To optimize Mistral Ministral 3B in RAG, fine-tune it on domain-specific data to improve retrieval relevance and response accuracy. Use 4-bit or 8-bit quantization to reduce memory usage while maintaining performance. Implement dynamic batching during inference to handle multiple queries efficiently. Prune redundant layers or apply LoRA for lightweight adaptation. Cache frequent retrieval outputs to minimize recomputation. Optimize prompt engineering to reduce input token length, and leverage FlashAttention for faster processing. Monitor latency and adjust context window sizes based on use-case requirements to balance speed and coherence.

AmazonBedrock cohere embed-multilingual-v3 optimization tips

Optimize input preprocessing by normalizing text (lowercasing, removing special characters) and splitting documents into chunks aligned with the model’s 512-token limit. Use batch processing for bulk embeddings to reduce latency and costs. Filter irrelevant content before embedding to improve retrieval quality. For multilingual queries, ensure language-specific stopword removal and consider hybrid retrieval combining semantic and keyword search. Regularly validate embedding quality via cosine similarity checks and align vector dimensions with your database (e.g., PCA for dimensionality reduction). Cache frequent queries and update 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?

Congratulations on completing this tutorial! You've taken a significant step towards mastering the integration of a powerful framework, vector database, LLM, and embedding model to build a Retrieval-Augmented Generation (RAG) system. By leveraging LlamaIndex for a robust structure, Pgvector to efficiently manage and search through vectors, the Mistral Ministral 3B for dynamic text generation, and Cohere's embed-multilingual-v3 for embedding diverse data, you've equipped yourself with an incredible toolkit to elevate your projects. Each of these components plays a unique role: the framework helps organize your pipeline, the vector database accelerates data retrieval, the LLM enhances content generation, and the embedding model enables multilingual capabilities. Isn’t that exciting?

What’s even better is that you’ve not only learned how these pieces fit together, but you’ve also discovered optimization tips to streamline your RAG systems for maximum efficiency. With resources like the free RAG cost calculator, you can keep track of your setup’s performance and costs, allowing you to optimize further as you grow. Now, as you stand at the cusp of innovation, it’s time to unleash your creativity! Dive in, start building your own RAG applications, and experiment with unique use cases. The possibilities are endless, and your journey of discovery has just begun. Embrace the challenge, and see how far you can take your ideas!

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! 💖