Step-by-Step Guide to Build an AI Chatbot Using LlamaIndex and Flask for SaaS Startups

May 3, 2024


SaaS platforms will increasingly have an AI component, and leveraging AI technologies can provide significant advantages in terms of efficiency, personalization, and scalability. Large Language Models (LLMs) offer a powerful solution for enhancing natural language processing tasks in SaaS applications. Enterprises the world over are already leveraging LLMs to make sense of their vast trove of private text data - be it logs, documentation, reports, etc. 

In this tutorial, we consider one such use case - automating the creation of a question-answering application over company documentation for a software product or service. Within the domain of LLMs, the technique of Retrieval Augmented Generation (RAG) is best placed to build such an application efficiently and effectively. Specifically, we use the documentation of E2E Networks (, which is an AI-first hyperscaler based out of India. While the tutorial proceeds as a notebook, you need to run the code in a .py file as it also contains a Flask app. 

What Is RAG?

LLMs are general-purpose text generation and completion models that have been trained on a very large corpus of publicly available data like books, Wikipedia, blogs, news, etc. However, it's very computationally expensive and time-consuming to train the models again on new data, which means that these LLMs are not updated with the latest information generated in society. Also, there is always some kind of privately held data upon which these models have not been trained and would not perform as well in those contexts. 

RAG is an architecture that provides a fast and cost-effective way to address some of these limitations. It enhances the capabilities of large language models by incorporating contextually relevant information retrieved from a knowledge base, usually a collection of documents.

Problem Statement and Solution


Privately held data such as enterprise datasets, proprietary documents, or documents that are constantly updated pose a challenge to the effective general use of LLMs. Using LLMs to answer questions about such data will lead to hallucinations - grammatically correct but factually and contextually incorrect responses. 

A trivial solution would be to connect all such data to an LLM, however, that also doesn't work because of the small context window of LLMs and the per-token (word) cost of using LLMs. E.g. an LLM cannot ingest a 100-page document to answer questions based on it. It is simply too big to input. 

Solution: RAG

This is where the RAG architecture becomes essential. We need to not only connect all the relevant data sources to the LLM but also provide targeted chunks of the document as input to the LLM. These chunks should be big enough to encompass all the needed information and, at the same time, small enough to fit into the input context window of an LLM. RAG achieves this by introducing a document retrieval step before data is fed into an LLM. The document retrieval component takes in the user's input query and retrieves only the most similar document chunks. Even before that, documents are divided into (generally) fixed-sized chunks, converted from text to numerical vectors, and indexed into a vector database.

The RAG Architecture

The RAG architecture thus consists of the following components:

  1. Document Chunking: As the document base could be very large, each document is divided into fixed-size chunks.
  2. Embedding Generation: Each chunk is separately vectorized using an embedding model.
  3. Vector Store: The document chunks are indexed in a vector space, along with any metadata.
  4. Retrieval: Chunks that are closest in the vector space to the embedding of the user input query are retrieved.
  5. Prompting an LLM: The retrieved chunks form the context for an LLM to answer the user query.


PrerequisitesFor this task, we consider the Mistral-7B model, which is a relatively recent large language model that is open-source and developed by Mistral AI, a French startup, which has gained attention because of it outperforming the popular Llama 2 models. You can either use this model on a cloud environment or with some processing make it run on your laptop if it has good enough memory. It can run smoothly on Apple Silicon Macbooks (M1, M2, and M3), provided they have at least 16GB of memory. The trick to make it run with lower memory is using a method called quantization, which essentially trims down model weights from 32-bit precision to up to 4 bits of precision. More about quantization here.One can download a quantized version of the Mistral model from Hugging Face. In this link, go to Files and Versions and select a model to download. I recommend downloading the mistral-7b-instruct-v0.2.Q4_K_M.gguf model as it is optimized both for speed and accuracy. To run the GGUF files you would need the llama-cpp-python client. This is also integrated within LangChain, so all you need to do is load the model via LangChain.All the required libraries are listed here;  install them either in a Jupyter notebook or in a virtual environment.

!pip install -q -U transformers langchain llama-cpp-python qdrant-client
!pip install -q -U sentence-transformers accelerate unstructured beautifulsoup4

Import Libraries

import os
import re
import torch
from pprint import pprint
from operator import itemgetter
from bs4 import BeautifulSoup as Soup
from collections import Counter
from transformers import BitsAndBytesConfig
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
from langchain_community.llms.huggingface_pipeline import HuggingFacePipeline
from langchain_community.document_loaders.recursive_url_loader import RecursiveUrlLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.vectorstores import Qdrant
from langchain.docstore.document import Document
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough, RunnableParallel
from langchain_core.prompts import ChatPromptTemplate, PromptTemplate
from langchain.embeddings import HuggingFaceEmbeddings

Data Ingestion

We scrap the documentation of E2E Networks using BeautifulSoup and Langchain's recursive URL loader.

url = ""
loader = RecursiveUrlLoader(
    url=url, max_depth=2, extractor=lambda x: Soup(x, "html.parser").text
docs = loader.load()

Document(page_content='\n\n\n\n\n\n\n\n\n\nE2E Networks Documentation | E2E Networks  documentation\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n      Skip to content\n    \n\n\n\nE2E Cloud\n\nDocs\nE2E Networks\n\n\n\n\nToggle navigation menu\n\n\n\n\n\n              Login\n            \n\n\n\n              Sign Up\n            \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nE2E Networks  documentation\n\n\n\n\n\nâ\x8c\x98\n    K\n  \n\n\n\nDocs\nE2E Networks\n\nMyaccount\n\n        Getting Started with Myaccount\nSignUp Process for Indian Customers\nCustomer validation Process for Indian Customers\nSignUp Process for International Customers\nCustomer Validation Process for International Process\nCustomer Validation Process for Contact Persons\nDomestic Customer Validation Process FAQs\nInternational Customer Validation Process FAQs\nSign In Process\n\n\n   Release Notes\n\nCompute\n\nNodes\n Virtual Compute Nodes\n Monitoring\n 1-Click Deployment\n Active Directory\n\n\nGPU\nGPU ....Enablers\nCustomers\nCertifications\nCountries Served\nFAQs\n\n\n\n\n\nE2E Networks Limited\nE2E Networks Limited is a NSE Listed AI-First Hyperscale Cloud Computing Platform.\n\n\n\n\n\n\n\n\n\n\nCIN Number: L72900DL2009PLC341980\n\n\n (c) Copyright 2023 E2E Networks Limited\n\n\n\n\n\n\n\n\n\n\n', metadata={'source': '', 'title': 'E2E Networks Documentation | E2E Networks  documentation', 'language': 'en'})

Data Cleaning

We need to clean the data as it contains main newline characters and non-alphanumeric characters. Also, some of the headings and sections appear on all pages. So we find out the most frequently occurring n-grams and also remove them.

def remove_frequent_tokens(text, n_gram_range=(2, 3), min_count=5):
    # Tokenize the text into words and n-grams
    words = re.findall(r'\b\w+\b', text.lower())
    ngrams = []
    for n in range(n_gram_range[0], n_gram_range[1] + 1):
        ngrams.extend(zip(*[words[i:] for i in range(n)]))
    ngrams = [' '.join(ngram) for ngram in ngrams]
    # Count occurrences of words and n-grams
    ngram_counts = Counter(ngrams)
    # Get the most common words and n-grams
    ngrams_to_remove = {ngram for ngram, count in ngram_counts.items() if count >= min_count and ngram!='e2e networks'}
    # Remove most common words and n-grams
    filtered_text = text
    for token in ngrams_to_remove:
        filtered_text = filtered_text.replace(token, '')
    return filtered_text
def process_docs(doc):
    # replace all newline characters with a space
    new_doc = doc.replace('\n', ' ')
    #condense multiple space to a single space
    new_doc = re.sub(r'\s+', ' ', new_doc)
    #remove special characters 
    new_doc = re.sub(r'[^A-Za-z0-9\s,.\'?-]' ,'',  new_doc)
    # remove frequently occuring n-grams
    new_doc = remove_frequent_tokens(new_doc)
    return new_doc
processed_docs = [] 
for doc in docs:
    new_doc = process_docs(doc.page_content)
    processed_docs.append(Document(page_content= new_doc, metadata={"source": "local"}))

Document(page_content=' E2E Networks Documentation  E2E Networks documentation Skip to content E2E Cloud Docs E2E Networks Toggle navigation menu Login Sign Up E2E Networks documentation  K Docs E2E Networks Myaccount Getting Started with Myaccount SignUp Process for Indian Customers Customer validation Process for Indian Customers SignUp Process for International Customers Customer Validation Process for International Process Customer Validation Process for Contact Persons Domestic Customer Validation Process FAQs International Customer Validation Process FAQs Sign In Process Release Notes Compute Nodes Virtual Compute Nodes Monitoring 1-Click Deployment Active Directory GPU GPU Cloud EQS Introduction How to Create EQS ? Actions Add Queue under tab Actions for queue service Using SDK Appliance Load Balancer Appliance Auto Scaling Introduction Concepts Define Scale Groups FaaS Function as a Service FaaS How to Create Functions Functions Information Network CDN VPC How to reserve an IP address? Reserve IP Pool DNS Custom Reverse DNS Firewall ....... Countries Served FAQs E2E Networks Limited E2E Networks Limited is a NSE Listed AI-First Hyperscale Cloud Computing Platform. CIN Number L72900DL2009PLC341980  Copyright 2023 E2E Networks Limited ', metadata={'source': 'local'})

Perform Chunking

text_splitter = RecursiveCharacterTextSplitter(
docs = text_splitter.split_documents(processed_docs)

[Document(page_content='E2E Networks Documentation  E2E Networks documentation Skip to content E2E Cloud Docs E2E Networks Toggle navigation menu Login Sign Up E2E Networks documentation  K Docs E2E Networks Myaccount Getting Started with Myaccount SignUp Process for Indian Customers Customer validation Process for Indian Customers SignUp Process for International Customers Customer Validation Process for International Process Customer Validation Process for Contact Persons Domestic Customer Validation Process FAQs International Customer Validation Process FAQs Sign In Process Release Notes Compute Nodes .... TDS Deduction process Declaration us 206AB Minimum Billing Provisioning and Deprovisioning Process View Invoice and Payment Prepaid', metadata={'source': 'local'}),
 Document(page_content='and Payment Prepaid Billing Set up Infra Credits Balance Alert Whatsapp notification for Payment reminder Restore Service on a Suspended Account for Non-Payment Database Database Database PostgreSQL Parameter Group How to create Parameter Group Storage Storage Block Storage Object Storage CDP Backup Scalable File System Kubernetes Kubernetes Service Introduction Getting Started Kubernetes Service Node Pool Details Monitoring Graphs Alerts Actions Kubernetes Marketplace Monitoring Stack Cert- Manager .... AI-first, hyperscale cloud provider. Here, users will find detailed guides, tutorials, and troubleshooting tips covering a wide range of topics from CPU and GPU compute usage, to TIR AI Platform, Kubernetes services, Terraform, our ecosystem of cloud technologies,', metadata={'source': 'local'})]

Load the Mistral Model

Now we proceed to load the mistral model. Provide the path to the .gguf file downloaded earlier in the model_path argument of the llama.cpp function. You can also set some more arguments like temperature, top_p, top_k, etc. 

n_gpu_layers = -1  # The number of layers to put on the GPU. The rest will be on the CPU. If you don't know how many layers there are, you can use -1 to move all to GPU.
n_batch = 512  # Should be between 1 and n_ctx, consider the amount of RAM of your Apple Silicon Chip.
# Make sure the model path is correct for your system!
llm = LlamaCpp(
    f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls
    n_ctx = 2048 

Define Embedding Model

We use the sentence-transformers library to download and initialize the embedding model.

# define the embedding model
emb_model = "sentence-transformers/all-MiniLM-L6-v2"
embeddings = HuggingFaceEmbeddings(

Index in Vector Store

Finally, we index the vectorized document chunks into the Qdrant vector store.

qdrant_collection = Qdrant.from_documents(
location=":memory:", # Local mode with in-memory storage only
# construct a retriever on top of the vector store
qdrant_retriever = qdrant_collection.as_retriever()
# let's try a query and see the how it's retrieved from the qdrant vector database
qdrant_retriever.invoke('What is E2E networks?')

Document(page_content='2023 E2E Networks Limited', metadata={'source': 'local', '_id': '0a23a4bf09f846e485f87e6ec9daf7a0', '_collection_name': 'e2e_documentation'}),
 Document(page_content='E2E in Media Testimonials Investors Careers Contact Us Contact Sales Escalation Matrix Service Level Agreement Terms of Service Privacy Policy Refund Policy Policy FAQ Resources Blog Events Service Health Status Help White Papers Ecosystem Enablers Customers Certifications Countries Served FAQs E2E Networks Limited E2E Networks Limited is a NSE Listed AI-First Hyperscale Cloud Computing Platform. CIN Number L72900DL2009PLC341980  Copyright 2023 E2E Networks Limited', metadata={'source': 'local', '_id': 'b86ad17025064c579b3ddd2e32fbecaa', '_collection_name': 'e2e_documentation'}),
 Document(page_content='Copyright 2023 E2E Networks Limited', metadata={'source': 'local', '_id': '1c41650b51984d1db1f9987dcf45dfcc', '_collection_name': 'e2e_documentation'}),
 Document(page_content='a Partner E2E in Media Testimonials Investors Careers Contact Us Contact Sales Escalation Matrix Service Level Agreement Terms of Service Privacy Policy Refund Policy Policy FAQ Resources Blog Events Service Health Status Help White Papers Ecosystem Enablers Customers Certifications Countries Served FAQs E2E Networks Limited E2E Networks Limited is a NSE Listed AI-First Hyperscale Cloud Computing Platform. CIN Number L72900DL2009PLC341980  Copyright 2023 E2E Networks Limited', metadata={'source': 'local', '_id': 'f0e46535c2d443e9a9da055a0428d1a6', '_collection_name': 'e2e_documentation'})]

We see that the Qdrant vector store retrieves a limited number of document chunks which match most with the query. These chunks will be passed to the LLM in a prompt, along with the query. The LLM would answer from within these document chunks.

Prompting the LLM

We use LangChain Expression Language (LCEL) to construct a prompt for the LLM. This includes the retrieved document chunks as context and the input query as a question. FInally, we use a text output parser to complete the chain, which instructs the LLM to output well-formatted Python strings.

# define prompt template

template = """[INST] You are a helpful, respectful and honest technical support assistant for E2E Networks.
Your task is to answer user's questions.
Answer the question below from context below.
{question} [/INST] 
# create the prompt from the above template
prompt = ChatPromptTemplate.from_template(template)
# combine document chunks into one
def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)
# setup the context and question part of the chain
setup_and_retrieval = RunnableParallel(
    {"context": qdrant_retriever| format_docs, "question": RunnablePassthrough()})
# extend the chain to include the prompt, model, and output parser
rag_chain = setup_and_retrieval | prompt | llm | StrOutputParser()


Let's test out the final RAG app on a couple of queries.

rag_chain.invoke('What is E2E networks?')

E2E Networks is a NSE (National Stock Exchange) listed company based in India. The company specializes in AI-First Hyperscale Cloud Computing Platform. The company's mission is to provide innovative cloud solutions to businesses of all sizes and industries.

rag_chain.invoke("How to setup a Kubernetes cluster in E2E networks?") 

To set up a Kubernetes cluster in E2E networks, follow these steps:
1. Log in to your E2E Networks account using your credentials.
2. Go to the "MyAccount" page and navigate to the "Kubernetes" tab. This will take you to the Kubernetes dashboard page.
3. To create a new Kubernetes cluster, select the "Create Cluster" button which will prompt you to the cluster creation page.
4. On the cluster creation page, you will be asked to select your desired configuration options for your Kubernetes cluster such as the number of nodes, node sizes, regions, etc. Select your desired configuration options and click on the "Create Cluster" button to initiate the cluster creation process.
5. Once your cluster has been successfully created, you will be taken to the cluster dashboard page where you can manage your Kubernetes cluster resources, deployments, services, etc. You can also use this dashboard to monitor your cluster's resource usage, performance metrics, and health status in real-time.

We see that the LLM app generates accurate answers, from within the vast documentation. This would not have been possible without RAG as the Mistral model would have been unlikely trained on this documentation exclusively.

Create Flask API Endpoint for Querying the LLM

Lastly, let us wrap our RAG application in a Flask app so that the LLM can be queried from the browser.

app = Flask(__name__)
@app.route('/ask_llm', methods=['GET'])
def web_app():
    # Get the input string from the request parameters
    query = request.args.get('query', '')
    llm_response = rag_chain.invoke(query)
    # Return the input string as a text response
    return llm_response, 200, {'Content-Type': 'text/plain'}
if __name__ == '__main__':  

The Flask app runs at However, we have created an endpoint that takes in a GET request and also takes in arguments. The user request can be passed using the 'query' keyword. Below is the cURL command to try out in a command line terminal or a web browser. Note that a curl URL cannot contain spaces, which is therefore filled with a special character '%20'.

# Example curl command for testing RAG pipeline
curl 'http://localhost:5000/ask_llm?query=%27what%20is%20e2e%20networks%27'

Conclusion and Future Notes

In conclusion, leveraging the RAG AI pipeline utilizing text generation models can provide SaaS entrepreneurs with a competitive edge by enhancing the capabilities of their platforms. While we demonstrated one way of utilizing RAG, there could be many other applications for RAG in a SaaS product. For example, LLMs can be used to personalize responses to users. One can maintain a document or database describing certain user attributes like gender, demographics, and location, which can be utilized by an LLM to tailor responses according to a user. By following the steps outlined in this guide and leveraging open-source technologies, SaaS startups can effectively integrate AI components into their applications, paving the way for future innovation and growth. 


The notebooks and Python files can be accessed at

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