Steps to Build a RAG Application with Real-Time Data Using PGVector and Llama 3

June 10, 2024

In a typical AI application trained on a vast corpus of data, the model may not have access to specific, customized data, leading to less accurate or relevant responses. However, with Retrieval-Augmented Generation (RAG), businesses can provide their own data to the AI application. RAG allows the AI to retrieve and utilize this custom data to generate more precise and contextually accurate responses.

Additionally, RAG enhances data security. In many situations, businesses may not want to share proprietary or sensitive data with AI companies due to privacy or security concerns. By using RAG, they can keep their data private and secure while still benefiting from the AI's capabilities. This approach ensures that the data is used solely within a controlled environment, mitigating the risks associated with data sharing.

To understand the process, let's go through the various steps involved in building a Retrieval Augmented Generation (RAG) application step by step.

The Tools We Shall Use


First, we’ll convert our data into embeddings, which are numerical representations of the data that capture its semantic meaning. To efficiently manage these embeddings, we’ll use a PGVector container to store them. This approach allows us to retrieve the embeddings whenever needed without having to convert the data each time. Converting data into embeddings repeatedly can be time-consuming and resource-intensive, requiring significant computational power and money. By storing our embeddings in a PGVector container, we avoid this repetitive and costly process, ensuring that our embedded data is readily available for quick and efficient retrieval.

The PGVector extension for PostgreSQL is a tool that helps you work with vectors right inside your database. Here's a breakdown of the key concepts in simpler terms:

What Does PGVector Do?

Storage: It allows you to store vectors in your PostgreSQL database.

Manipulation: You can change and work with these vectors easily.

Querying: It provides tools to search and analyze vector data efficiently.


LangChain is a framework designed to streamline the development of applications utilizing large language models (LLMs). As a language model integration framework, LangChain supports a wide range of use cases including document analysis and summarization, and chatbots.

Llama 3

Llama 3 is the next-generation open-source LLM developed by Meta that's been trained on internet-scale data. This allows it to understand and comprehensively respond to language, making it suitable for tasks like writing creative content, translating languages, and answering queries in an informative way.

Gradio UI

Gradio is an open-source Python package that allows you to quickly build a demo or web application for your machine learning model, API, or any Python function. You can then share a link to your demo or web application in just a few seconds using Gradio's built-in sharing features.

E2E Cloud

E2E’s AI development platform, TIR, allows you to host LLMs and fine-tune them easily. TIR has seamless integration with PGVector and Llama 3 – and we can use that as well as an alternative deployment option.


Ollama is a streamlined open-source tool used for running open-source LLMs locally, like Llama 2, Mistral, Falcon, etc. Ollama bundles all the necessary ingredients for the model to function locally including model core data (weights), instruction (configuration), and dataset into a neat package managed by a modelfile.

To use Ollama, one simply needs to download it from the website. It's available for macOS, Linux, and Windows.

Let's Code

Since we are working with a locally deployed LLM, we need an advanced GPU for our task. E2E Cloud provides a range of GPUs geared towards building AI applications. You can check out the offerings at

Go ahead and register, and then launch a GPU node. Alternatively, you can head to TIR and launch a Llama 3 endpoint and a PGVector endpoint.

Loading all the libraries: 

import gradio as gr
from langchain_community.document_loaders import TextLoader  
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import HuggingFaceEmbeddings
from langchain_postgres.vectorstores import PGVector
from langchain.chains import RetrievalQA
from langchain_community.llms import Ollama

Load the text and split it into manageable chunks.

To simulate real-time data updates, we are using the Faker library to generate dynamic data. Here, we’re creating log files and refreshing the data every 60 seconds. You can customize it with your own real-time data as needed.

# Initialize Faker for generating fake data
fake = Faker()

# Configure logging with direct file path
log_file_path = "Path_to_file"
logging.basicConfig(filename=log_file_path, level=logging.DEBUG, format='%(asctime)s - %(message)s')

# Function to generate fake log data with detailed text content
def generate_fake_logs():
    for _ in range(1):  # Generate 1 log entry each time
        # Generate a random timestamp
        timestamp = time.strftime('%Y-%m-%dT%H:%M:%S.') + str(random.randint(100000, 999999))

        ip_address = ".".join(str(random.randint(0, 255)) for _ in range(4))

        user_agent = fake.user_agent()
        details_text = fake.paragraph(nb_sentences=5)

        # Generate the log entry with detaile
        log_entry = f"{timestamp} - {ip_address} - {user_agent} - {details_text}"

        # Write the log entry to the log file

# Function to update the log file with new log data
def update_log_file():
    while True:
        generate_fake_logs()  # Generate new log data"Updating log file with new data")
        time.sleep(60)  # Wait for 1 minute before updating again

# Start a thread to update the log file in the background
log_thread = threading.Thread(target=update_log_file)
log_thread.daemon = True

# Function to load and reprocess the document
def load_and_reprocess_documents():
    loader = TextLoader(log_file_path)
    documents = loader.load()
    return documents
# Function to add documents to the vector store
def update_vector_store():
    my_logs = load_and_reprocess_documents()
    vectorstore.add_documents(my_logs, replace=True)

# Initially load and add documents to the vector store

Connecting to PGVector database and storing embedding:

You can run the following command to spin up a Postgres container with the PGVector extension:

docker run --name pgvector-container -e POSTGRES_USER=langchain -e POSTGRES_PASSWORD=langchain -e POSTGRES_DB=langchain -p 6024:5432 -d pgvector/pgvector:pg16

# Database connection string
connection ="postgresql+psycopg://langchain:langchain@localhost:6024/langchain"  

collection_name = "my_docs"  # Name of the collection in the database

vectorstore = PGVector(
    embeddings=embeddings,  # Use the initialized embeddings
    collection_name=collection_name,  # Specify the collection name
    connection=connection,  # Database connection
    use_jsonb=True, )

Once our connection to PGVector is established and we’ve created our container, we can start adding real-time data using the code below. Then we’ll use a retriever to access the stored embeddings when needed. 

Initialize the LLM model. Make sure you’ve installed Ollama on your system, launched an Ollama server, and pulled Llama 3. You can follow the instructions here.

Download Ollama - Link

After downloading, you can run the model locally by using simple code on your terminal. - 

>ollama run llama3

# Initialize the language model

llm = Ollama(model="llama3")  

# Initialize the RetrievalQA
qa_stuff = RetrievalQA.from_chain_type(
    llm=llm,  # Use the initialized language model

    chain_type="stuff",  # Specify the chain type

    retriever=retriever,  # Use the created retriever

    verbose=True,  # Enable verbose mode for debugging

Finally getting the query back and also creating the Gradio UI interface.

# Function to handle the query
def get_answer(query):
    update_vector_store()  # Update the vector store with the latest content
    response =  # Run the QA chain with the query
    return response  # Return the response

# Create a Gradio interface
iface = gr.Interface(
    fn=get_answer,  # Function to handle the query


    outputs="text",  # Output type for the interface

    title="llama 3 RAG",  # Title of the Gradio interface

    description="Ask a question and get an answer:",)

# Launch the interface

Below is the response I received:


By leveraging Retrieval Augmented Generation (RAG), you can create a customized chatbot that is both highly accurate and secure, tailored specifically to your data. Tools like Gradio UI and Streamlit facilitate the creation of visually appealing interfaces with ease, enhancing the user experience.In applications like customer support, knowledge management, and information retrieval, users often ask complex questions that require detailed and precise answers. Traditional natural language processing (NLP) systems, including both retrieval-based and generation-based models, face significant challenges in delivering high-quality responses.

Latest Blogs
This is a decorative image for: A Complete Guide To Customer Acquisition For Startups
October 18, 2022

A Complete Guide To Customer Acquisition For Startups

Any business is enlivened by its customers. Therefore, a strategy to constantly bring in new clients is an ongoing requirement. In this regard, having a proper customer acquisition strategy can be of great importance.

So, if you are just starting your business, or planning to expand it, read on to learn more about this concept.

The problem with customer acquisition

As an organization, when working in a diverse and competitive market like India, you need to have a well-defined customer acquisition strategy to attain success. However, this is where most startups struggle. Now, you may have a great product or service, but if you are not in the right place targeting the right demographic, you are not likely to get the results you want.

To resolve this, typically, companies invest, but if that is not channelized properly, it will be futile.

So, the best way out of this dilemma is to have a clear customer acquisition strategy in place.

How can you create the ideal customer acquisition strategy for your business?

  • Define what your goals are

You need to define your goals so that you can meet the revenue expectations you have for the current fiscal year. You need to find a value for the metrics –

  • MRR – Monthly recurring revenue, which tells you all the income that can be generated from all your income channels.
  • CLV – Customer lifetime value tells you how much a customer is willing to spend on your business during your mutual relationship duration.  
  • CAC – Customer acquisition costs, which tells how much your organization needs to spend to acquire customers constantly.
  • Churn rate – It tells you the rate at which customers stop doing business.

All these metrics tell you how well you will be able to grow your business and revenue.

  • Identify your ideal customers

You need to understand who your current customers are and who your target customers are. Once you are aware of your customer base, you can focus your energies in that direction and get the maximum sale of your products or services. You can also understand what your customers require through various analytics and markers and address them to leverage your products/services towards them.

  • Choose your channels for customer acquisition

How will you acquire customers who will eventually tell at what scale and at what rate you need to expand your business? You could market and sell your products on social media channels like Instagram, Facebook and YouTube, or invest in paid marketing like Google Ads. You need to develop a unique strategy for each of these channels. 

  • Communicate with your customers

If you know exactly what your customers have in mind, then you will be able to develop your customer strategy with a clear perspective in mind. You can do it through surveys or customer opinion forms, email contact forms, blog posts and social media posts. After that, you just need to measure the analytics, clearly understand the insights, and improve your strategy accordingly.

Combining these strategies with your long-term business plan will bring results. However, there will be challenges on the way, where you need to adapt as per the requirements to make the most of it. At the same time, introducing new technologies like AI and ML can also solve such issues easily. To learn more about the use of AI and ML and how they are transforming businesses, keep referring to the blog section of E2E Networks.

Reference Links

This is a decorative image for: Constructing 3D objects through Deep Learning
October 18, 2022

Image-based 3D Object Reconstruction State-of-the-Art and trends in the Deep Learning Era

3D reconstruction is one of the most complex issues of deep learning systems. There have been multiple types of research in this field, and almost everything has been tried on it — computer vision, computer graphics and machine learning, but to no avail. However, that has resulted in CNN or convolutional neural networks foraying into this field, which has yielded some success.

The Main Objective of the 3D Object Reconstruction

Developing this deep learning technology aims to infer the shape of 3D objects from 2D images. So, to conduct the experiment, you need the following:

  • Highly calibrated cameras that take a photograph of the image from various angles.
  • Large training datasets can predict the geometry of the object whose 3D image reconstruction needs to be done. These datasets can be collected from a database of images, or they can be collected and sampled from a video.

By using the apparatus and datasets, you will be able to proceed with the 3D reconstruction from 2D datasets.

State-of-the-art Technology Used by the Datasets for the Reconstruction of 3D Objects

The technology used for this purpose needs to stick to the following parameters:

  • Input

Training with the help of one or multiple RGB images, where the segmentation of the 3D ground truth needs to be done. It could be one image, multiple images or even a video stream.

The testing will also be done on the same parameters, which will also help to create a uniform, cluttered background, or both.

  • Output

The volumetric output will be done in both high and low resolution, and the surface output will be generated through parameterisation, template deformation and point cloud. Moreover, the direct and intermediate outputs will be calculated this way.

  • Network architecture used

The architecture used in training is 3D-VAE-GAN, which has an encoder and a decoder, with TL-Net and conditional GAN. At the same time, the testing architecture is 3D-VAE, which has an encoder and a decoder.

  • Training used

The degree of supervision used in 2D vs 3D supervision, weak supervision along with loss functions have to be included in this system. The training procedure is adversarial training with joint 2D and 3D embeddings. Also, the network architecture is extremely important for the speed and processing quality of the output images.

  • Practical applications and use cases

Volumetric representations and surface representations can do the reconstruction. Powerful computer systems need to be used for reconstruction.

Given below are some of the places where 3D Object Reconstruction Deep Learning Systems are used:

  • 3D reconstruction technology can be used in the Police Department for drawing the faces of criminals whose images have been procured from a crime site where their faces are not completely revealed.
  • It can be used for re-modelling ruins at ancient architectural sites. The rubble or the debris stubs of structures can be used to recreate the entire building structure and get an idea of how it looked in the past.
  • They can be used in plastic surgery where the organs, face, limbs or any other portion of the body has been damaged and needs to be rebuilt.
  • It can be used in airport security, where concealed shapes can be used for guessing whether a person is armed or is carrying explosives or not.
  • It can also help in completing DNA sequences.

So, if you are planning to implement this technology, then you can rent the required infrastructure from E2E Networks and avoid investing in it. And if you plan to learn more about such topics, then keep a tab on the blog section of the website

Reference Links

This is a decorative image for: Comprehensive Guide to Deep Q-Learning for Data Science Enthusiasts
October 18, 2022

A Comprehensive Guide To Deep Q-Learning For Data Science Enthusiasts

For all data science enthusiasts who would love to dig deep, we have composed a write-up about Q-Learning specifically for you all. Deep Q-Learning and Reinforcement learning (RL) are extremely popular these days. These two data science methodologies use Python libraries like TensorFlow 2 and openAI’s Gym environment.

So, read on to know more.

What is Deep Q-Learning?

Deep Q-Learning utilizes the principles of Q-learning, but instead of using the Q-table, it uses the neural network. The algorithm of deep Q-Learning uses the states as input and the optimal Q-value of every action possible as the output. The agent gathers and stores all the previous experiences in the memory of the trained tuple in the following order:

State> Next state> Action> Reward

The neural network training stability increases using a random batch of previous data by using the experience replay. Experience replay also means the previous experiences stocking, and the target network uses it for training and calculation of the Q-network and the predicted Q-Value. This neural network uses openAI Gym, which is provided by taxi-v3 environments.

Now, any understanding of Deep Q-Learning   is incomplete without talking about Reinforcement Learning.

What is Reinforcement Learning?

Reinforcement is a subsection of ML. This part of ML is related to the action in which an environmental agent participates in a reward-based system and uses Reinforcement Learning to maximize the rewards. Reinforcement Learning is a different technique from unsupervised learning or supervised learning because it does not require a supervised input/output pair. The number of corrections is also less, so it is a highly efficient technique.

Now, the understanding of reinforcement learning is incomplete without knowing about Markov Decision Process (MDP). MDP is involved with each state that has been presented in the results of the environment, derived from the state previously there. The information which composes both states is gathered and transferred to the decision process. The task of the chosen agent is to maximize the awards. The MDP optimizes the actions and helps construct the optimal policy.

For developing the MDP, you need to follow the Q-Learning Algorithm, which is an extremely important part of data science and machine learning.

What is Q-Learning Algorithm?

The process of Q-Learning is important for understanding the data from scratch. It involves defining the parameters, choosing the actions from the current state and also choosing the actions from the previous state and then developing a Q-table for maximizing the results or output rewards.

The 4 steps that are involved in Q-Learning:

  1. Initializing parameters – The RL (reinforcement learning) model learns the set of actions that the agent requires in the state, environment and time.
  2. Identifying current state – The model stores the prior records for optimal action definition for maximizing the results. For acting in the present state, the state needs to be identified and perform an action combination for it.
  3. Choosing the optimal action set and gaining the relevant experience – A Q-table is generated from the data with a set of specific states and actions, and the weight of this data is calculated for updating the Q-Table to the following step.
  4. Updating Q-table rewards and next state determination – After the relevant experience is gained and agents start getting environmental records. The reward amplitude helps to present the subsequent step.  

In case the Q-table size is huge, then the generation of the model is a time-consuming process. This situation requires Deep Q-learning.

Hopefully, this write-up has provided an outline of Deep Q-Learning and its related concepts. If you wish to learn more about such topics, then keep a tab on the blog section of the E2E Networks website.

Reference Links

This is a decorative image for: GAUDI: A Neural Architect for Immersive 3D Scene Generation
October 13, 2022

GAUDI: A Neural Architect for Immersive 3D Scene Generation

The evolution of artificial intelligence in the past decade has been staggering, and now the focus is shifting towards AI and ML systems to understand and generate 3D spaces. As a result, there has been extensive research on manipulating 3D generative models. In this regard, Apple’s AI and ML scientists have developed GAUDI, a method specifically for this job.

An introduction to GAUDI

The GAUDI 3D immersive technique founders named it after the famous architect Antoni Gaudi. This AI model takes the help of a camera pose decoder, which enables it to guess the possible camera angles of a scene. Hence, the decoder then makes it possible to predict the 3D canvas from almost every angle.

What does GAUDI do?

GAUDI can perform multiple functions –

  • The extensions of these generative models have a tremendous effect on ML and computer vision. Pragmatically, such models are highly useful. They are applied in model-based reinforcement learning and planning world models, SLAM is s, or 3D content creation.
  • Generative modelling for 3D objects has been used for generating scenes using graf, pigan, and gsn, which incorporate a GAN (Generative Adversarial Network). The generator codes radiance fields exclusively. Using the 3D space in the scene along with the camera pose generates the 3D image from that point. This point has a density scalar and RGB value for that specific point in 3D space. This can be done from a 2D camera view. It does this by imposing 3D datasets on those 2D shots. It isolates various objects and scenes and combines them to render a new scene altogether.
  • GAUDI also removes GANs pathologies like mode collapse and improved GAN.
  • GAUDI also uses this to train data on a canonical coordinate system. You can compare it by looking at the trajectory of the scenes.

How is GAUDI applied to the content?

The steps of application for GAUDI have been given below:

  • Each trajectory is created, which consists of a sequence of posed images (These images are from a 3D scene) encoded into a latent representation. This representation which has a radiance field or what we refer to as the 3D scene and the camera path is created in a disentangled way. The results are interpreted as free parameters. The problem is optimized by and formulation of a reconstruction objective.
  • This simple training process is then scaled to trajectories, thousands of them creating a large number of views. The model samples the radiance fields totally from the previous distribution that the model has learned.
  • The scenes are thus synthesized by interpolation within the hidden space.
  • The scaling of 3D scenes generates many scenes that contain thousands of images. During training, there is no issue related to canonical orientation or mode collapse.
  • A novel de-noising optimization technique is used to find hidden representations that collaborate in modelling the camera poses and the radiance field to create multiple datasets with state-of-the-art performance in generating 3D scenes by building a setup that uses images and text.

To conclude, GAUDI has more capabilities and can also be used for sampling various images and video datasets. Furthermore, this will make a foray into AR (augmented reality) and VR (virtual reality). With GAUDI in hand, the sky is only the limit in the field of media creation. So, if you enjoy reading about the latest development in the field of AI and ML, then keep a tab on the blog section of the E2E Networks website.

Reference Links

Build on the most powerful infrastructure cloud

A vector illustration of a tech city using latest cloud technologies & infrastructure