How to Use LLMs To Interact With Your SQL Data

August 22, 2023

The recent advancements in natural language processing have led to the emergence of Large Language Models (LLMs), which have shown impressive performance in tasks like text generation, translation, and several other tasks. These advancements have also extended to database interactions, which enable users to interact with SQL databases using simple, everyday language. Significant attention has been drawn to these language models across different fields due to their capability to produce text like humans. The emergence of transformer-based structures, as showcased by the GPT-3.5 model, has paved the way for a new age in language understanding, exceeding previous constraints and enabling a deeper understanding of context.

Large Language Models (LLMs) are a revolutionary advancement that links human language and SQL, and may, in the future, form the interface to SQL databases for humans. Through the interpretation of queries in natural language, LLM can create SQL commands. This makes it a great choice for users with minimal database knowledge.

Advantages of LLMs in SQL Data Interactions

  • LLMs make database interactions accessible for users with non-technical skills by simplifying SQL data tasks.
  • LLMs let users communicate with databases in their language, removing the need for exact command syntax.
  • By leveraging their superior understanding of language abilities, LLMs can extract contextual data from user queries, which results in the generation of more precise SQL queries.
  • Mastering SQL requires heavy training, and LLMs provide a more intuitive alternative by eliminating the learning process and accelerating data access and updates.

As we progress through the sections, we will examine the practical elements of establishing the environment, performing queries, updates, inserts, and deleting SQL data with LLMs. We will also analyze optimal methods and factors to consider while using LLMs for SQL database interaction. Upon completion of this article, readers will be able to comprehend and efficiently use LLMs in their database dealings, which can transform their interaction with SQL data.

Setting Up the Environment

There needs to be a conducive environment to begin interacting with the SQL database using LLMs. This section outlines a step-by-step process for setting up the environment to enable interaction between your PostgreSQL database and DB-GPT pre-trained LLM model. 

  • Head over to MyAccount portal on E2E Cloud.
  • Install a GPU node. It comes pre-installed with the right drivers. 
  • Make sure Python is installed (preferably a 3.6 version or higher) on your machine.
  • Install the transformer-based library with `pip install transformers`.
  • Install the ‘psycopg2’ library that allows communication with the PostgreSQL database using `pip install psycopg2`.
  • You need to retrieve the necessary credentials for your system, like hostname, port, database name, username, and password. 
  • To establish a connection to your PostgreSQL database, use the psycopg2 library as shown below:

import psycopg2 
host = 'your_postgresql_host' 
port = 'your_postgresql_port' 
database = 'your_postgresql_database' 
username = 'your_postgresql_username' 
password = 'your_postgresql_password' 
connection_string = f'host={host} port={port} dbname={database} user={username} password={password}' 
connection = psycopg2.connect(connection_string)
  • Load the DB-GBT pre-trained model using the transformers library

from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model_name = 'eosphoros/db-gpt'
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)

The environment is now prepared to mediate interactions with the PostgreSQL database using the ‘DB-GPT’ pre-trained LLM model. The following sections will show how to use this setup for natural language querying, updating, inserting, and deleting data within the PostgreSQL database using LLMs.

Generating and Executing SQL Queries

The use of Language Models and the 'DB-GPT' pre-trained Language Model for Databases for engaging with SQL data provides an easy-to-use method for database queries. In this part, we'll show you how to use an LLM to perform SQL queries from natural language inputs. An  LLM is engineered to understand and interpret natural language queries, enabling users to articulate their data retrieval requirements in a simple language instead of depending on intricate SQL syntax. The model's advanced language comprehension abilities allow it to formulate equivalent SQL queries that accurately extract the necessary information from the database. For creating SQL queries utilizing LLM, follow these instructions below: 

  • Request the user to formulate their query in a natural language format. 
  • Use the LLM's tokenizer to tokenize the input provided by the user, making it ready for model input. 
  • Channel the tokenized input through the LLM model to produce the SQL query.
  • Convert the SQL query generated by the model from its tokenized form into a SQL syntax that is understandable to humans.

The SQL query obtained from an LLM needs to be run against the linked PostgreSQL database to fetch the results. The following code snippet provides an example of the process:

def execute_sql_query(connection, query):
        cursor = connection.cursor()
        result = cursor.fetchall()
        return result
    except (Exception, psycopg2.Error) as error:
        print('Error executing the query:', error)
        return None

user_query = 'Insert query here.'

# Tokenize and generate SQL query
encoded_input = tokenizer(user_query, return_tensors='pt')
with torch.no_grad():
    output = model.generate(**encoded_input)
decoded_query = tokenizer.decode(output[0], skip_special_tokens=True)

result_set = execute_sql_query(connection, decoded_query)

# Display the results
if result_set:
    for row in result_set:
    print('No results found.')

Utilizing LLM for SQL data queries allows users to effectively retrieve information from the database without mastering complex SQL syntax. This makes the data retrieval procedure more user-friendly and intuitive.

Executing Updated SQL Statements on the Database

To update your database, follow these steps:

  • Request the user to provide the details they wish to implement and the criteria that pinpoint the records for updating.
  • Utilize LLM's tokenizer to break down the user's input and ready it for model input.
  • Feed the tokenized input into the LLM model to create the SQL update statement.
  • Convert the SQL update statement borne by the model from its tokenized form into an understandable SQL syntax.

After successfully getting the updated statement, refer to the following code snippet to apply the modifications:

def execute_sql_update(connection, update_statement):
        cursor = connection.cursor()
        print('Update successful!')
    except (Exception, psycopg2.Error) as error:
        print('Error executing the update:', error)

# Updated instructions
user_update_instruction = 'Write your updated instruction here.'

encoded_input = tokenizer(user_update_instruction, return_tensors='pt')
with torch.no_grad():
    output = model.generate(**encoded_input)
decoded_update_statement = tokenizer.decode(output[0], skip_special_tokens=True)

execute_sql_update(connection, decoded_update_statement)

This helps in conveniently altering the database records without needing to craft complex update queries. This strategy simplifies the data management process, allowing users to engage with the database through straightforward and intuitive language instructions.

Inserting and Deleting the SQL Data

Users can use natural language instructions to detail the data they wish to include when adding new records to the database. Since any LLM has language skills, it can translate these descriptions and produce the corresponding results to the inserted SQL statements. Follow these steps to insert the data by using LLM:

  • Ask the user for a description in the natural language of the data they wish to input.
  • Use the LLM's tokenizer to break down the user's input into tokens for model processing.
  • Feed the tokenized input into the LLM model to create the SQL insert statement.
  • Convert the SQL insert statement generated by the model from its tokenized form to a human-friendly SQL syntax.

After obtaining the insert statement, execute the following:

def execute_sql_insert(connection, insert_statement):
        cursor = connection.cursor()
        print('Insertion successful!')
    except (Exception, psycopg2.Error) as error:
        print('Error executing the insert:', error)

# User's natural language description of data to insert
user_insert_description = 'Insert new natural language description for updating here.'

encoded_input = tokenizer(user_insert_description, return_tensors='pt')
with torch.no_grad():
    output = model.generate(**encoded_input)
decoded_insert_statement = tokenizer.decode(output[0], skip_special_tokens=True)

execute_sql_insert(connection, decoded_insert_statement)

Similarly, use natural language instructions to detail the data that needs to be deleted and the LLM can convert these descriptions to produce the required results. Follow the site steps as before and obtain the delete statement.

After getting the delete statement, implement the following code:

def execute_sql_delete(connection, delete_statement):
        cursor = connection.cursor()
        print('Deletion successful!')
    except (Exception, psycopg2.Error) as error:
        print('Error executing the delete:', error)

# Natural language instruction for data deletion
user_delete_instruction = 'Insert new natural language description for deleting here.'

encoded_input = tokenizer(user_delete_instruction, return_tensors='pt')
with torch.no_grad():
    output = model.generate(**encoded_input)
decoded_delete_statement = tokenizer.decode(output[0], skip_special_tokens=True)

execute_sql_delete(connection, decoded_delete_statement)

The effortless implementation of operations like data querying, updating, inserting, and deleting within the SQL database is made possible for users of various skill levels through LLM's seamless integration of natural language instructions. This article has displayed the practical use of LLMs, by making use of an open-source tech stack to maintain transparency and reproducibility. By following the instructions in this article, one can create an optimal environment for an LLM, link to their PostgreSQL database, and interact with it efficiently. 

You can try this today on a node on E2E Cloud. Simply head over to MyAccount, login or register, spin up a node, and test the above in a Jupyter Notebook.

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