How to Launch LLM Chatbot Powered by Enterprise Data on E2E Cloud


Large language models (LLMs) have revolutionized the field of natural language processing, enabling new capabilities such as text generation, translation, and question answering. 

However, LLMs can be prone to hallucination, generating responses that are factually incorrect or irrelevant to the user query. This can be a problem when Enterprise Chatbots are built using LLM technology. 

This tutorial will show you how to build a chatbot augmented by enterprise data to address this challenge. By connecting an LLM to a vector database containing your enterprise knowledge base, and harnessing the power of RAG, you can generate more factual and informative responses.

This tutorial is intended for developers with experience in Python and machine learning. No prior experience with LLMs or vector databases is required.


When a user sends a direct query to the open-source Large Language Model (LLM), there is an increased likelihood of receiving responses that may contain inaccuracies or information not directly related to the query. 

However, by enriching the user's input with context extracted from a knowledge database, the LLM can more effectively craft a response that is grounded in factual information. This process can be described as Retrieval Augmented Generation.

For a more comprehensive understanding of architectures like this and their potential to enhance Natural Language Processing (NLP) tasks, you can refer to the following paper: "Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks."

Retrieval Augmented Generation (RAG) Architecture:

  • Knowledge Base Integration into a Vector Database
  • Start with a local directory containing proprietary data files – we will use a user-policy document from E2E Networks for this.
  • Generate embeddings for each of these files using a pretrained open-source model.
  • Store these embeddings, along with document IDs, in a Vector Database, facilitating semantic search.
  • Enriching User Queries with Additional Context from the Knowledge Base
  • When a user submits a question, search the Vector Database to identify documents that are semantically closest based on their embeddings.
  • Retrieve context information based on document IDs and embeddings obtained from the search results.
  • Generating Enhanced Prompts for the LLM
  • Construct a prompt that incorporates the retrieved context and the user's question.
  • Obtaining Factual Responses from the LLM
  • Send the enhanced prompt to the LLM to generate a response grounded in factual content.
  • Presentation in a Web Application
  • Display the LLM response within a web application for the user.

Essentially, this approach leverages a knowledge base and semantic search to provide users with more accurate and contextually relevant responses from the LLM.

In this tutorial, we will walk you through the process of implementing a proof of concept LLM chatbot that can be trained on enterprise data, using V100 GPU nodes on E2E Cloud. 


E2E Cloud is one of the most affordable and a highly performant advanced GPU cloud provider, and will be our platform of choice for this tutorial. 

As a first step, head over to MyAccount portal on E2E Cloud, and create an account / register if you already haven’t. 

Once you have registered, click on the ‘Compute’ section in the left sidebar. 

Select V100 GPU and the flavor of Linux you are comfortable with. We will select Ubuntu or Debian for this tutorial. Then click on Create. 

The node should be up in a minute or two. You can choose hourly billed, or committed (which offers extra savings). 

Once the node is up and running, you should assign it a Reserved IP address as well, and upload your SSH Key. These are to be found in the tabs ‘Network’ and ‘Node Security’. 

For the rest of the tutorial, let’s assume the IP address assigned is 

Once you ssh into the machine using root username, create a user for development, say ‘aidev’, and allow it sudo and ssh access. Assuming you have completed these steps, let’s move to actual steps to implement the chatbot.

Step 1: Create Python Virtual Environment

For this project, we will need a vector database, for storing and retrieving the embeddings data. We will use Milvus. 

We will also need Gradio, in order to quickly spin up an interface where you can test and play with the LLM. 

Let’s proceed.

As is the recommended practice, you should first create a virtual environment for your project. 

aidev@e2e-81-9:~$ mkdir envs
aidev@e2e-81-9:~$ cd envs/
aidev@e2e-81-9:~/envs$ python3 -m venv aienv
aidev@e2e-81-9:~/envs$ source aienv/bin/activate

Next, let’s create a directory for our project and install requirements. 

(aienv) aidev@e2e-81-9:~$ mkdir e2e_llm_chatbot
(aienv) aidev@e2e-81-9:~$ cd e2e_llm_chatbot

Let’s now install the required python packages.

(aienv) aidev@e2e-81-9:~/e2e_llm_chatbot$ vim requirements.txt

…and add the following lines: 


(aienv) aidev@e2e-81-9:~/e2e_llm_chatbot$ pip install -r requirements.txt

Once this is done, you should have everything you need for the next steps. 

Step 2: Check GPU Capabilities (optional)

We will be using a GPU instance type that supports CUDA 5.0 or higher. The torch libraries used in this AMP necessitate a GPU with a CUDA compute capability of 5.0 or greater, such as V100, A100, or T4 GPUs.

While not strictly necessary, it’s always a good practice to test GPU capabilities, and ensure CUDA support. 

You can create a python script for that. 

(aienv) aidev@e2e-81-9:~/e2e_llm_chatbot$ vi‍

import torch
import sys

# Check that the CUDA capability of the GPUs in this workspace meet minimum requirements for this experiment
version = torch.cuda.get_device_capability()
if version[0] < = 5:
   device = torch.cuda.get_device_name()
   msg = "CUDA Capability (%d.%d) of the GPU device (%s) " \
       "is less than the required (5.0), please use a newer" \
       "GPU instance type" % (version[0], version[1], device)

   print("GPU instance meets requirements")

Since we selected V100, the test should easily pass. 

(aienv) aidev@e2e-81-9:~/e2e_llm_chatbot$ python 

GPU instance meets requirements

Step 3: Download Models

We will now download the LLM models required for this experiment. For this, create the following shell script. 

(aienv) aidev@e2e-81-9:~/e2e_llm_chatbot$ vi 

# This script is used to pre=download files stored with git-lfs in CML Runtimes which do not have git-lfs support
# You can use any models that can be loaded with the huggingface transformers library.


download_lfs_files () {
   echo "These files must be downloaded manually since there is no git-lfs here:"
   git ls-files | git check-attr --stdin filter | awk -F': ' '$3 ~ /lfs/ { print $1}' | while read line; do
       echo "Downloading ${line}"
       echo $(git remote get-url $(git remote))/resolve/$COMMIT/${line}
       curl -O -L $(git remote get-url $(git remote))/resolve/$COMMIT/${line}
       echo "Downloading ${line} completed"

# Clear out any existing checked out models
rm -rf ./models
mkdir models
cd models

# Downloading model for generating vector embeddings
GIT_LFS_SKIP_SMUDGE=1 git clone ${EMBEDDING_MODEL_REPO} --branch main embedding-model
cd embedding-model
download_lfs_files $EMBDEDDING_MODEL_COMMIT
cd ..
 # Downloading LLM model that has been fine tuned to handle instructions/q&a
GIT_LFS_SKIP_SMUDGE=1 git clone ${LLM_MODEL_REPO} --branch main llm-model
cd llm-model
git checkout ${LLM_MODEL_COMMIT}
download_lfs_files $LLM_MODEL_COMMIT
cd ..

You can trigger the download using the following: 

(aienv) aidev@e2e-81-9:~/e2e_llm_chatbot$ sh ./

That will take some time. Once completed, you will see a folder called ‘models’ that would contain the downloaded models. 

Remember that if you execute this again, it will delete the directory and restart. You can modify the above script to whatever suits your automation workflow. 

Step 4: Embedding Utils

Now let’s create some helper modules that would assist in creating and inserting the embeddings into the vector db. 

First, create a file called ‘’ and add the following: 

Next, create another file that would help loading the LLM model, tokenizer and create a pipeline. 

Let’s call this file - ‘’. 

from transformers import pipeline, AutoModelForCausalLM, AutoTokenizer, StoppingCriteria, StoppingCriteriaList
import torch

class KeywordsStoppingCriteria(StoppingCriteria):
   def __init__(self, keywords_ids:list):
       self.keywords = keywords_ids

   def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor, **kwargs) -> bool:
       if input_ids[0][-1] in self.keywords:
           return True
       return False

# Load the model stored in models/llm-model
print(f"Starting to load the LLM model")
model = AutoModelForCausalLM.from_pretrained('models/llm-model', local_files_only=True, torch_dtype=torch.bfloat16, device_map="auto")

print(f"Starting to load the LLM tokenizer")
tokenizer = AutoTokenizer.from_pretrained('models/llm-model', local_files_only=True, padding_side="left")

print(f"Finished loading the model and tokenizer")

# Now create a generator and a prompting function to ask a question to the LLM where the prompt sets context and attempts to massage some instructions to answer the question
generator = pipeline('text-generation', model=model, tokenizer=tokenizer)

# Generate text using loaded LLM model
# Total prompt size is limited to 2048 tokens with the included model
# the prompt includes (prompt template, user input, retrieved context)
def get_llm_generation(prompt, stop_words, temperature=0.7, max_new_tokens=256, top_p=0.85, top_k=70, repetition_penalty=1.07, do_sample=False):
   stop_ids = [tokenizer.encode(w)[0] for w in stop_words]
   stop_criteria = KeywordsStoppingCriteria(stop_ids)

   generated_text = generator(prompt, max_new_tokens=max_new_tokens, do_sample=do_sample, temperature=temperature, top_p=top_p, top_k=top_k, repetition_penalty=repetition_penalty, pad_token_id=tokenizer.eos_token_id, stopping_criteria=StoppingCriteriaList([stop_criteria]),)[0]

   #return a response that cuts out the prompt
   return generated_text['generated_text'][len(prompt):]

You should now have two files, which will be used below: 


Next we will save context data. 

Step 5: Context Data

To reduce hallucinations in the chatbot, we will need to augment with enterprise data. You will see in the following steps that the output that the LLM would give with and without this context will vastly vary. 

Create a ‘data’ directory, and save the LLM context data as .txt files. 

The python module that would insert the embeddings into the vector db, would look for the context data in the ‘data’ folder. 

In this experiment, we have saved two .txt files in the data directory. 

(aienv) aidev@e2e-81-9:~/workspace/llm_chatbots/e2e_llm_chatbot$ tree data/
|-- about_e2e_2.txt
`-- about_e2e.txt

Step 6: Insert Embeddings into Vector DB

Create a python script ‘’ and copy paste the following: 

from milvus import default_server
from pymilvus import connections, FieldSchema, CollectionSchema, DataType, Collection, utility
import subprocess

import model_embedding_utils as model_embedding

import os
from pathlib import Path

def create_milvus_collection(collection_name, dim):
     if utility.has_collection(collection_name):

     fields = [
     FieldSchema(name='relativefilepath', dtype=DataType.VARCHAR, description='file path relative to root directory ', max_length=1000, is_primary=True, auto_id=False),
     FieldSchema(name='embedding', dtype=DataType.FLOAT_VECTOR, description='embedding vectors', dim=dim)
     schema = CollectionSchema(fields=fields, description='reverse image search')
     collection = Collection(name=collection_name, schema=schema)

     # create IVF_FLAT index for collection.
     index_params = {
     collection.create_index(field_name="embedding", index_params=index_params)
     return collection
# Create an embedding for given text/doc and insert it into Milvus Vector DB
def insert_embedding(collection, id_path, text):
   embedding =  model_embedding.get_embeddings(text)
   data = [[id_path], [embedding]]
def main():
 # Reset the vector database files
 print(["rm -rf milvus-data"], shell=True))


   connections.connect(alias='default', host='localhost', port=default_server.listen_port)  

   # Create/Recreate the Milvus collection
   collection_name = 'e2e_docs'
   collection = create_milvus_collection(collection_name, 384)

   print("Milvus database is up and collection is created")

   # Read KB documents in ./data directory and insert embeddings into Vector DB for each doc
   # The default embeddings generation model specified in this AMP only generates embeddings for the first 256 tokens of text.
   doc_dir = './data'
   for file in Path(doc_dir).glob(f'**/*.txt'):
       with open(file, "r") as f: # Open file in read mode
           print("Generating embeddings for: %s" %
           text =
           insert_embedding(collection, os.path.abspath(file), text)

   print('Total number of inserted embeddings is {}.'.format(collection.num_entities))
   print('Finished loading Knowledge Base embeddings into Milvus')

 except Exception as e:
   raise (e)

if __name__ == "__main__":

If you execute this, you will see that milvus-data directory has now been created, and output along the following lines: 

Milvus database is up and collection is created
Generating embeddings for: about_e2e_2.txt
Generating embeddings for: about_e2e.txt
Total number of inserted embeddings is 2.
Finished loading Knowledge Base embeddings into Milvus

Also, let’s create a module that allows for our LLM chatbot to start the vector db. 

Create the file ‘’ with following content: 

from milvus import default_server
from pymilvus import connections, Collection, utility

# Start Milvus Vector DB

   connections.connect(alias='default', host='localhost', port=default_server.listen_port)  
except Exception as e:
   raise e

So, now that you have the embeddings loaded from your context data into the milvus-data folder, you are ready to spin up the LLM and augment it with context. 

Step 7: LLM Chatbot augmented with Data

We are now ready to set up the main chatbot function, which would be augmented with the embeddings data that has been loaded into the vector db. 

Create a file - and insert the following code into it: 

import os
import gradio

from milvus import default_server
from pymilvus import connections, Collection
import model_llm_utils as model_llm
import vector_db_utils as vector_db
import model_embedding_utils as model_embedding

def main():
   # Configure gradio QA app
   print("Configuring gradio app")
   demo = gradio.Interface(fn=get_responses,
                           inputs=gradio.Textbox(label="Question", placeholder=""),
                           outputs=[gradio.Textbox(label="Asking LLM with No Context"),
                                    gradio.Textbox(label="Asking LLM with Context (RAG)")],
                           examples=["What is E2E Networks?",
                                     "What kind of work does E2E Networks do?",
                                     "What solutions does E2E Networks offer?"],

   # Launch gradio app
   print("Launching gradio app")
   print("Gradio app ready")
# Helper function for generating responses for the QA app
def get_responses(question):
   # Load Milvus Vector DB collection
   vector_db_collection = Collection('e2e_docs')
   # Phase 1: Get nearest knowledge base chunk for a user question from a vector db
   context_chunk = get_nearest_chunk_from_vectordb(vector_db_collection, question)
   # Phase 2: Create enhanced instruction prompts for use with the LLM
   prompt_with_context = create_enhanced_prompt(context_chunk, question)
   prompt_without_context = create_enhanced_prompt("none", question)
   # Phase 3a: Perform text generation with LLM model using found kb context chunk
   contextResponse = get_llm_response(prompt_with_context)
   rag_response = contextResponse
   # Phase 3b: For comparison, also perform text generation with LLM model without providing context
   plainResponse = get_llm_response(prompt_without_context)
   plain_response = plainResponse

   return plain_response, rag_response

# Get embeddings for a user question and query Milvus vector DB for nearest knowledge base chunk
def get_nearest_chunk_from_vectordb(vector_db_collection, question):
   # Generate embedding for user question
   question_embedding =  model_embedding.get_embeddings(question)
   # Define search attributes for Milvus vector DB
   vector_db_search_params = {"metric_type": "IP", "params": {"nprobe": 10}}
   # Execute search and get nearest vector, outputting the relativefilepath
   nearest_vectors =
       data=[question_embedding], # The data you are querying on
       anns_field="embedding", # Column in collection to search on
       limit=1, # limit results to 1
       output_fields=['relativefilepath'], # The fields you want to retrieve from the search result.
   # Print the file path of the kb chunk
   # Return text of the nearest knowledgebase chunk
   return load_context_chunk_from_data(nearest_vectors[0].ids[0])
 # Return the Knowledge Base doc based on Knowledge Base ID (relative file path)
def load_context_chunk_from_data(id_path):
   with open(id_path, "r") as f: # Open file in read mode
def create_enhanced_prompt(context, question):
   prompt_template = """:%s. Answer this question based on given context %s
   prompt = prompt_template % (context, question)
   return prompt
 # Pass through user input to LLM model with enhanced prompt and stop tokens
def get_llm_response(prompt):
   stop_words = [':', '\n:']

   generated_text = model_llm.get_llm_generation(prompt,
   return generated_text 

if __name__ == "__main__":

In this script, we are also spinning up Gradio instance, which will allow us to interact with the LLM, and compare results that we get with and without context. 

In the get_responses() function, we are querying the LLM with context, and without context. 

To load data from vector db, the function get_nearest_chunk_from_vectordb() acts as a helper. 

The function ‘create_enhanced_prompt()’ loads up the context and creates the prompt that would be fed into the LLM. 

Finally, the display is handled by passing the responses back to the Gradio instance that we have spun up in the start. 

Step 8: Execute and View Results!

In the previous step, we created the python script - 

Now we are ready to test our LLM chatbot. 

(aienv) aidev@e2e-81-9:~/e2e_llm_chatbot$ python

You would eventually see a line which says: 

Running on public URL:

This link will be unique in each instance, and will be live only for 72 hours. Good enough for us to test and play around with. 

Once you open this on the browser, you would see the following: 

You can now ask a question, and view the results with and without augmentation. In our case, as in the screenshot below, the response ‘without context’ is completely hallucinatory. 

This is the response without context, for the question ‘What is E2E Networks’: 

This is almost fully inaccurate. 

Now, let’s compare it with the response generated with context (RAG): 

Success! The results are much more accurate, and almost without hallucination. By refining the context data, you can achieve stellar results in many cases. 

Let’s ask another question: 


As we had mentioned in the beginning of this tutorial, LLMs have a tendency to hallucinate when it doesn’t have context data around knowledge-intensive questions. 

RAG offers a powerful way to remove these hallucinations, thereby making it possible to create enterprise-grade chatbots that are far more accurate and provide a way to mitigate the risks from hallucinations. 

Furthermore, one additional advantage of the approach of using open source LLMs which you deploy, train and build yourself, is that you don’t leak sensitive enterprise context data to proprietary LLMs, avoid vendor lock-in, and reduce your total cost of ownership in the long run. 

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