Build RAG Chatbot with LangChain, pgvector, Fireworks AI Llama 3.1 70B Instruct, 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:

LangChain: An open-source framework that helps you orchestrate the interaction between LLMs, vector stores, embedding models, etc, making it easier to integrate a RAG pipeline.
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.)
Fireworks AI Llama 3.1 70B Instruct: This advanced model is designed for instruction-following tasks, featuring a vast 70 billion parameters for enhanced comprehension and context. It excels in generating coherent, contextually relevant outputs for complex queries, making it ideal for interactive applications, educational tools, and customer support systems requiring detailed and precise information.
Cohere embed-multilingual-light-v3.0: This model is designed for efficient multilingual text embedding, enabling robust semantic search and similarity tasks across various languages. It excels in scenarios requiring rapid comprehension and matching of diverse linguistic datasets, making it ideal for global applications in content recommendation, categorization, and cross-language information retrieval.

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 LangChain

%pip install --quiet --upgrade langchain-text-splitters langchain-community langgraph

Step 2: Install and Set Up Fireworks AI Llama 3.1 70B Instruct

pip install -qU "langchain[fireworks]"

import getpass
import os

if not os.environ.get("FIREWORKS_API_KEY"):
  os.environ["FIREWORKS_API_KEY"] = getpass.getpass("Enter API key for Fireworks AI: ")

from langchain.chat_models import init_chat_model

llm = init_chat_model("accounts/fireworks/models/llama-v3p1-70b-instruct", model_provider="fireworks")

Step 3: Install and Set Up Cohere embed-multilingual-light-v3.0

pip install -qU langchain-cohere

import getpass
import os

if not os.environ.get("COHERE_API_KEY"):
  os.environ["COHERE_API_KEY"] = getpass.getpass("Enter API key for Cohere: ")

from langchain_cohere import CohereEmbeddings

embeddings = CohereEmbeddings(model="embed-multilingual-light-v3.0")

Step 4: Install and Set Up pgvector

pip install -qU langchain-postgres

from langchain_postgres import PGVector

vector_store = PGVector(
    embeddings=embeddings,
    collection_name="my_docs",
    connection="postgresql+psycopg://...",
)

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 bs4
from langchain import hub
from langchain_community.document_loaders import WebBaseLoader
from langchain_core.documents import Document
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langgraph.graph import START, StateGraph
from typing_extensions import List, TypedDict

# Load and chunk contents of the blog
loader = WebBaseLoader(
    web_paths=("https://milvus.io/docs/overview.md",),
    bs_kwargs=dict(
        parse_only=bs4.SoupStrainer(
            class_=("doc-style doc-post-content")
        )
    ),
)

docs = loader.load()

text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
all_splits = text_splitter.split_documents(docs)

# Index chunks
_ = vector_store.add_documents(documents=all_splits)

# Define prompt for question-answering
prompt = hub.pull("rlm/rag-prompt")


# Define state for application
class State(TypedDict):
    question: str
    context: List[Document]
    answer: str


# Define application steps
def retrieve(state: State):
    retrieved_docs = vector_store.similarity_search(state["question"])
    return {"context": retrieved_docs}


def generate(state: State):
    docs_content = "\n\n".join(doc.page_content for doc in state["context"])
    messages = prompt.invoke({"question": state["question"], "context": docs_content})
    response = llm.invoke(messages)
    return {"answer": response.content}


# Compile application and test
graph_builder = StateGraph(State).add_sequence([retrieve, generate])
graph_builder.add_edge(START, "retrieve")
graph = graph_builder.compile()

Test the Chatbot

Yeah! You've built your own chatbot. Let's ask the chatbot a question.

response = graph.invoke({"question": "What data types does Milvus support?"})
print(response["answer"])

Example Output

Milvus supports various data types including sparse vectors, binary vectors, JSON, and arrays. Additionally, it handles common numerical and character types, making it versatile for different data modeling needs. This allows users to manage unstructured or multi-modal data efficiently.

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.

LangChain optimization tips

To optimize LangChain, focus on minimizing redundant operations in your workflow by structuring your chains and agents efficiently. Use caching to avoid repeated computations, speeding up your system, and experiment with modular design to ensure that components like models or databases can be easily swapped out. This will provide both flexibility and efficiency, allowing you to quickly scale your system without unnecessary delays or complications.

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.

Fireworks AI Llama 3.1 70B Instruct optimization tips

Llama 3.1 70B Instruct is a powerful model with a balance of speed and reasoning capabilities. Enhance retrieval performance by using hybrid search methods that incorporate both semantic and keyword-based matching. Keep prompts structured with clear sections, ensuring optimal focus on key information. Set temperature between 0.1 and 0.3, fine-tuning top-k and top-p values to control output variability. Implement caching strategies for frequently used queries to optimize cost and efficiency. Fireworks AI's auto-scaling capabilities allow for dynamic resource allocation—use this to handle peak workloads effectively. Streaming responses can improve user experience for real-time applications. If deploying 70B alongside larger models, use it as an intermediate option for moderately complex queries while reserving the largest models for deep analytical reasoning.

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

Cohere embed-multilingual-light-v3.0 is optimized for faster and more efficient multilingual embeddings. Reduce input data size by filtering out non-essential elements and focusing on key phrases or terms that provide the most value in cross-lingual search scenarios. Implement approximate nearest neighbor search methods, such as FAISS, to ensure that retrieval remains fast and accurate even in large datasets. Use vector compression techniques to save on storage space while maintaining retrieval quality. Employ caching strategies to store commonly used embeddings and reduce unnecessary recomputation. Optimize search performance by organizing embeddings into a hierarchical structure based on languages or topics, enabling quicker retrieval from specific language groups.

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 build a functional, multilingual RAG system from the ground up! You learned how LangChain acts as the glue, seamlessly orchestrating the flow of data between components. With pgvector, you saw how to store and retrieve vector embeddings efficiently, turning PostgreSQL into a high-performance vector database. The magic happens when you pair Cohere’s embed-multilingual-light-v3.0—which handles text in over 100 languages—with Fireworks AI’s Llama 3.1 70B Instruct, a powerhouse LLM that generates insightful, context-aware responses. Together, they form a pipeline that ingests documents, retrieves relevant snippets, and synthesizes answers with remarkable accuracy. You also explored practical optimizations, like tuning chunk sizes for embeddings and balancing speed vs. quality in retrieval, ensuring your system is both efficient and effective. The free RAG cost calculator you experimented with adds a layer of financial mindfulness, helping you estimate expenses as you scale.

Now that you’ve seen how these pieces fit together, the world of RAG is yours to shape! Whether you’re building customer support bots, research assistants, or multilingual knowledge bases, you’re equipped to innovate. Remember, the best way to learn is by doing—start small, experiment with different models or databases, and iterate. Optimize for your unique use case, leverage the multilingual capabilities, and don’t shy away from tweaking parameters to see what sparks creativity. The tools are here, the foundation is laid, and your journey is just beginning. Go build something amazing—the future of intelligent applications is in your hands! 🚀

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! 💖