Category: Polars

AGENTIC AI IN THE ENTERPRISE: STRATEGY, ARCHITECTURE, AND IMPLEMENTATION – PART 3

Posted on by SatyakiDe in agents, ai, anthropic, api, audio, Azure, bharatgpt, BOT, call, circuitbreaker, clob, cloud, Computer-Vision, computing, CPU, Crossplatform, Data Science, deepseek, design, exposure, Fabric, faiss, features, function, gpt3, GPU, grok, gui, Haystack, HuggingFace, ibm, IoT, json, Keras, LangChain, Langflow, Linear-Regression, Listagg, llm, Logistic-regression, loop, machine-learning, mcpprotocol, Microsoft, mobile, Model, mulesoft, natural-language, neural prophet, ngrok, objects, Open-CV, openai, oracle-cloud, Performance, pl sql, Polars, prophet-api, React, Real-time, sarvam, Silicon, StabilityAI, StableDefussion, Technology, Tensorflow, Torch, video, voice, watson

This is a continuation of my previous post, which can be found here.

Let us recap the key takaways from our previous post –

Enterprise AI, utilizing the Model Context Protocol (MCP), leverages an open standard that enables AI systems to securely and consistently access enterprise data and tools. MCP replaces brittle “N×M” integrations between models and systems with a standardized client–server pattern: an MCP host (e.g., IDE or chatbot) runs an MCP client that communicates with lightweight MCP servers, which wrap external systems via JSON-RPC. Servers expose three assets—Resources (data), Tools (actions), and Prompts (templates)—behind permissions, access control, and auditability. This design enables real-time context, reduces hallucinations, supports model- and cloud-agnostic interoperability, and accelerates “build once, integrate everywhere” deployment. A typical flow (e.g., retrieving a customer’s latest order) encompasses intent parsing, authorized tool invocation, query translation/execution, and the return of a normalized JSON result to the model for natural-language delivery. Performance introduces modest overhead (RPC hops, JSON (de)serialization, network transit) and scale considerations (request volume, significant results, context-window pressure). Mitigations include in-memory/semantic caching, optimized SQL with indexing, pagination, and filtering, connection pooling, and horizontal scaling with load balancing. In practice, small latency costs are often outweighed by the benefits of higher accuracy, stronger governance, and a decoupled, scalable architecture.

How does MCP compare with other AI integration approaches?

Compared to other approaches, the Model Context Protocol (MCP) offers a uniquely standardized and secure framework for AI-tool integration, shifting from brittle, custom-coded connections to a universal plug-and-play model. It is not a replacement for underlying systems, such as APIs or databases, but instead acts as an intelligent, secure abstraction layer designed explicitly for AI agents.

MCP vs. Custom API integrations:

This approach was the traditional method for AI integration before standards like MCP emerged.

  • Custom API integrations (traditional): Each AI application requires a custom-built connector for every external system it needs to access, leading to an N x M integration problem (the number of connectors grows exponentially with the number of models and systems). This approach is resource-intensive, challenging to maintain, and prone to breaking when underlying APIs change.
  • MCP: The standardized protocol eliminates the N x M problem by creating a universal interface. Tool creators build a single MCP server for their system, and any MCP-compatible AI agent can instantly access it. This process decouples the AI model from the underlying implementation details, drastically reducing integration and maintenance costs.

For more detailed information, please refer to the following link.

MCP vs. Retrieval-Augmented Generation (RAG):

RAG is a technique that retrieves static documents to augment an LLM’s knowledge, while MCP focuses on live interactions. They are complementary, not competing. 

  • RAG:
    • Focus: Retrieving and summarizing static, unstructured data, such as documents, manuals, or knowledge bases.
    • Best for: Providing background knowledge and general information, as in a policy lookup tool or customer service bot.
    • Data type: Unstructured, static knowledge.
  • MCP:
    • Focus: Accessing and acting on real-time, structured, and dynamic data from databases, APIs, and business systems.
    • Best for: Agentic use cases involving real-world actions, like pulling live sales reports from a CRM or creating a ticket in a project management tool.
    • Data type: Structured, real-time, and dynamic data.

MCP vs. LLM plugins and extensions:

Before MCP, platforms like OpenAI offered proprietary plugin systems to extend LLM capabilities.

  • LLM plugins:
    • Proprietary: Tied to a specific AI vendor (e.g., OpenAI).
    • Limited: Rely on the vendor’s API function-calling mechanism, which focuses on call formatting but not standardized execution.
    • Centralized: Managed by the AI vendor, creating a risk of vendor lock-in.
  • MCP:
    • Open standard: Based on a public, interoperable protocol (JSON-RPC 2.0), making it model-agnostic and usable across different platforms.
    • Infrastructure layer: Provides a standardized infrastructure for agents to discover and use any compliant tool, regardless of the underlying LLM.
    • Decentralized: Promotes a flexible ecosystem and reduces the risk of vendor lock-in. 

How enterprise AI with MCP has opened up a specific Architecture pattern for Azure, AWS & GCP?

Microsoft Azure: 

The “agent factory” pattern: Azure focuses on providing managed services for building and orchestrating AI agents, tightly integrated with its enterprise security and governance features. The MCP architecture is a core component of the Azure AI Foundry, serving as a secure, managed “agent factory.” 

Azure architecture pattern with MCP:

  • AI orchestration layer: The Azure AI Agent Service, within Azure AI Foundry, acts as the central host and orchestrator. It provides the control plane for creating, deploying, and managing multiple specialized agents, and it natively supports the MCP standard.
  • AI model layer: Agents in the Foundry can be powered by various models, including those from Azure OpenAI Service, commercial models from partners, or open-source models.
  • MCP server and tool layer: MCP servers are deployed using serverless functions, such as Azure Functions or Azure Logic Apps, to wrap existing enterprise systems. These servers expose tools for interacting with enterprise data sources like SharePoint, Azure AI Search, and Azure Blob Storage.
  • Data and security layer: Data is secured using Microsoft Entra ID (formerly Azure AD) for authentication and access control, with robust security policies enforced via Azure API Management. Access to data sources, such as databases and storage, is managed securely through private networks and Managed Identity. 

Amazon Web Services (AWS): 

The “composable serverless agent” pattern: AWS emphasizes a modular, composable, and serverless approach, leveraging its extensive portfolio of services to build sophisticated, flexible, and scalable AI solutions. The MCP architecture here aligns with the principle of creating lightweight, event-driven services that AI agents can orchestrate. 

AWS architecture pattern with MCP:

  • The AI orchestration layer, which includes Amazon Bedrock Agents or custom agent frameworks deployed via AWS Fargate or Lambda, acts as the MCP hosts. Bedrock Agents provide built-in orchestration, while custom agents offer greater flexibility and customization options.
  • AI model layer: The models are sourced from Amazon Bedrock, which provides a wide selection of foundation models.
  • MCP server and tool layer: MCP servers are deployed as serverless AWS Lambda functions. AWS offers pre-built MCP servers for many of its services, including the AWS Serverless MCP Server for managing serverless applications and the AWS Lambda Tool MCP Server for invoking existing Lambda functions as tools.
  • Data and security layer: Access is tightly controlled using AWS Identity and Access Management (IAM) roles and policies, with fine-grained permissions for each MCP server. Private data sources like databases (Amazon DynamoDB) and storage (Amazon S3) are accessed securely within a Virtual Private Cloud (VPC). 

Google Cloud Platform (GCP): 

The “unified workbench” pattern: GCP focuses on providing a unified, open, and data-centric platform for AI development. The MCP architecture on GCP integrates natively with the Vertex AI platform, treating MCP servers as first-class tools that can be dynamically discovered and used within a single workbench. 

GCP architecture pattern with MCP:

  • AI orchestration layer: The Vertex AI Agent Builder serves as the central environment for building and managing conversational AI and other agents. It orchestrates workflows and manages tool invocation for agents.
  • AI model layer: Agents use foundation models available through the Vertex AI Model Garden or the Gemini API.
  • MCP server and tool layer: MCP servers are deployed as containerized microservices on Cloud Run or managed by services like App Engine. These servers contain tools that interact with GCP services, such as BigQuery, Cloud Storage, and Cloud SQL. GCP offers pre-built MCP server implementations, such as the GCP MCP Toolbox, for integration with its databases.
  • Data and security layer: Vertex AI Vector Search and other data sources are encapsulated within the MCP server tools to provide contextual information. Access to these services is managed by Identity and Access Management (IAM) and secured through virtual private clouds. The MCP server can leverage Vertex AI Context Caching for improved performance.

Note that all the native technology is referred to in each respective cloud. Hence, some of the better technologies can be used in place of the tool mentioned here. This is more of a concept-level comparison rather than industry-wise implementation approaches.

We’ll go ahead and conclude this post here & continue discussing on a further deep dive in the next post.

Till then, Happy Avenging! 🙂

Note: All the data & scenarios posted here are representational data & scenarios & available over the internet & for educational purposes only. There is always room for improvement in this kind of model & the solution associated with it. I’ve shown the basic ways to achieve the same for educational purposes only.

Exploring the new Polars library in Python

Posted on by SatyakiDe in analytic function, api, cast, cloud, code, computing, Crossplatform, Data Science, function, objects, Pandas, Polars, Python, snippet, Technology

Today, I will present some valid Python packages where you can explore most of the complex SQLs by using this new package named “Polars,” which can be extremely handy on many occasions.

This post will be short posts where I’ll prepare something new on LLMs for the upcoming posts for the next month.

Why not view the demo before going through it?

Demo

Python Packages:

pip install polars
pip install pandas

Code:

Let us understand the key class & snippets.

  • clsConfigClient.py (Key entries that will be discussed later)
################################################
#### Written By: SATYAKI DE                 ####
#### Written On:  15-May-2020               ####
#### Modified On: 28-Oct-2023               ####
####                                        ####
#### Objective: This script is a config     ####
#### file, contains all the keys for        ####
#### personal OpenAI-based MAC-shortcuts    ####
#### enable bot.                            ####
####                                        ####
################################################

import os
import platform as pl

class clsConfigClient(object):
    Curr_Path = os.path.dirname(os.path.realpath(__file__))

    os_det = pl.system()
    if os_det == "Windows":
        sep = '\\'
    else:
        sep = '/'

    conf = {
        'APP_ID': 1,
        'ARCH_DIR': Curr_Path + sep + 'arch' + sep,
        'LOG_PATH': Curr_Path + sep + 'log' + sep,
        'DATA_PATH': Curr_Path + sep + 'data' + sep,
        'TEMP_PATH': Curr_Path + sep + 'temp' + sep,
        'OUTPUT_DIR': 'model',
        'APP_DESC_1': 'Polars Demo!',
        'DEBUG_IND': 'Y',
        'INIT_PATH': Curr_Path,
        'TITLE': "Polars Demo!",
        'PATH' : Curr_Path,
        'OUT_DIR': 'data',
        'MERGED_FILE': 'mergedFile.csv',
        'ACCT_FILE': 'AccountAddress.csv',
        'ORDER_FILE': 'Orders.csv',
        'CUSTOMER_FILE': 'CustomerDetails.csv',
        'STATE_CITY_WISE_REPORT_FILE': 'StateCityWiseReport.csv'
    }
  • clsSQL.py (Main class file that contains how to use the SQL)
#####################################################
#### Written By: SATYAKI DE                      ####
#### Written On: 27-May-2023                     ####
#### Modified On 28-Oct-2023                     ####
####                                             ####
#### Objective: This is the main calling         ####
#### python class that will invoke the           ####
#### Polar class, which will enable SQL          ####
#### capabilitites.                              ####
####                                             ####
#####################################################

import polars as pl
import os
from clsConfigClient import clsConfigClient as cf
import pandas as p

###############################################
###           Global Section                ###
###############################################

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

###############################################
###    End of Global Section                ###
###############################################

class clsSQL:
    def __init__(self):
        self.acctFile = cf.conf['ACCT_FILE']
        self.orderFile = cf.conf['ORDER_FILE']
        self.stateWiseReport = cf.conf['STATE_CITY_WISE_REPORT_FILE']
        self.custFile = cf.conf['CUSTOMER_FILE']
        self.dataPath = cf.conf['DATA_PATH']

    def execSQL(self):
        try:
            dataPath = self.dataPath
            acctFile = self.acctFile
            orderFile = self.orderFile
            stateWiseReport = self.stateWiseReport
            custFile = self.custFile

            fullAcctFile = dataPath + acctFile
            fullOrderFile = dataPath + orderFile
            fullStateWiseReportFile = dataPath + stateWiseReport
            fullCustomerFile = dataPath + custFile

            ctx = pl.SQLContext(accountMaster = pl.scan_csv(fullAcctFile),
            orderMaster = pl.scan_csv(fullOrderFile),
            stateMaster = pl.scan_csv(fullStateWiseReportFile))

            querySQL = """
            SELECT orderMaster.order_id,
            orderMaster.total,
            stateMaster.state,
            accountMaster.Acct_Nbr,
            accountMaster.Name,
            accountMaster.Email,
            accountMaster.user_id,
            COUNT(*) TotalCount
            FROM orderMaster
            JOIN stateMaster USING (city)
            JOIN accountMaster USING (user_id)
            ORDER BY stateMaster.state
            """

            res = ctx.execute(querySQL, eager=True)
            res_Pandas = res.to_pandas()

            print('Result:')
            print(res_Pandas)
            print(type(res_Pandas))

            ctx_1 = pl.SQLContext(customerMaster = pl.scan_csv(fullCustomerFile),
            tempMaster=pl.from_pandas(res_Pandas))

            querySQL_1 = """
            SELECT tempMaster.order_id,
            tempMaster.total,
            tempMaster.state,
            tempMaster.Acct_Nbr,
            tempMaster.Name,
            tempMaster.Email,
            tempMaster.TotalCount,
            tempMaster.user_id,
            COUNT(*) OVER(PARTITION BY tempMaster.state ORDER BY tempMaster.state, tempMaster.Acct_Nbr) StateWiseCount,
            MAX(tempMaster.Acct_Nbr) OVER(PARTITION BY tempMaster.state ORDER BY tempMaster.state, tempMaster.Acct_Nbr) MaxAccountByState,
            MIN(tempMaster.Acct_Nbr) OVER(PARTITION BY tempMaster.state ORDER BY tempMaster.state, tempMaster.Acct_Nbr) MinAccountByState,
            CASE WHEN tempMaster.total < 70 THEN 'SILVER' ELSE 'GOLD' END CategoryStat,
            SUM(customerMaster.Balance) OVER(PARTITION BY tempMaster.state) SumBalance
            FROM tempMaster
            JOIN customerMaster USING (user_id)
            ORDER BY tempMaster.state
            """

            res_1 = ctx_1.execute(querySQL_1, eager=True)

            finDF = res_1.to_pandas()

            print('Result 2:')
            print(finDF)

            return 0
        except Exception as e:
            discussedTopic = []
            x = str(e)
            print('Error: ', x)

            return 1

If we go through some of the key lines, we will understand how this entire package works.

But, before that, let us understand the source data –

Let us understand the steps –

  1. Join orderMaster, stateMaster & accountMaster and fetch the selected attributes. Store this in a temporary data frame named tempMaster.
  2. Join tempMaster & customerMaster and fetch the relevant attributes with some more aggregation, which is required for the business KPIs.
ctx = pl.SQLContext(accountMaster = pl.scan_csv(fullAcctFile),
orderMaster = pl.scan_csv(fullOrderFile),
stateMaster = pl.scan_csv(fullStateWiseReportFile))

The above method will create three temporary tables by reading the source files – AccountAddress.csv, Orders.csv & StateCityWiseReport.csv.

And, let us understand the supported SQLs –

SELECT  orderMaster.order_id,
        orderMaster.total,
        stateMaster.state,
        accountMaster.Acct_Nbr,
        accountMaster.Name,
        accountMaster.Email,
        accountMaster.user_id,
        COUNT(*) TotalCount
FROM orderMaster
JOIN stateMaster USING (city)
JOIN accountMaster USING (user_id)
ORDER BY stateMaster.state

In this step, we’re going to store the output of the above query into a temporary view named – tempMaster data frame.

Since this is a polar data frame, we’re converting it to the pandas data frame.

res_Pandas = res.to_pandas()

Finally, let us understand the next part –

ctx_1 = pl.SQLContext(customerMaster = pl.scan_csv(fullCustomerFile),
tempMaster=pl.from_pandas(res_Pandas))

In the above section, one source is getting populated from the CSV file, whereas the other source is feeding from a pandas data frame populated in the previous step.

Now, let us understand the SQL supported by this package, which is impressive –

SELECT  tempMaster.order_id,
        tempMaster.total,
        tempMaster.state,
        tempMaster.Acct_Nbr,
        tempMaster.Name,
        tempMaster.Email,
        tempMaster.TotalCount,
        tempMaster.user_id,
        COUNT(*) OVER(PARTITION BY tempMaster.state ORDER BY tempMaster.state, tempMaster.Acct_Nbr) StateWiseCount,
        MAX(tempMaster.Acct_Nbr) OVER(PARTITION BY tempMaster.state ORDER BY tempMaster.state, tempMaster.Acct_Nbr) MaxAccountByState,
        MIN(tempMaster.Acct_Nbr) OVER(PARTITION BY tempMaster.state ORDER BY tempMaster.state, tempMaster.Acct_Nbr) MinAccountByState,
        CASE WHEN tempMaster.total < 70 THEN 'SILVER' ELSE 'GOLD' END CategoryStat,
        SUM(customerMaster.Balance) OVER(PARTITION BY tempMaster.state) SumBalance
FROM tempMaster
JOIN customerMaster USING (user_id)
ORDER BY tempMaster.state

As you can see it has the capability of all the advanced analytics SQL using partitions, and CASE statements.

The only problem with COUNT(*) with the partition is not working as expected. Not sure, whether that is related to any version issues or not.

COUNT(*) OVER(PARTITION BY tempMaster.state ORDER BY tempMaster.state, tempMaster.Acct_Nbr) StateWiseCount

I’m trying to get more information on this. Except for this statement, everything works perfectly.

  • 1_testSQL.py (Main class file that contains how to use the SQL)
#########################################################
#### Written By: SATYAKI DE                          ####
#### Written On: 27-Jun-2023                         ####
#### Modified On 28-Oct-2023                         ####
####                                                 ####
#### Objective: This is the main class that invokes  ####
#### advanced analytic SQL in python.                ####
####                                                 ####
#########################################################

from clsConfigClient import clsConfigClient as cf
import clsL as log
import clsSQL as ccl

from datetime import datetime, timedelta

# Disbling Warning
def warn(*args, **kwargs):
    pass

import warnings
warnings.warn = warn

###############################################
###           Global Section                ###
###############################################

#Initiating Logging Instances
clog = log.clsL()
cl = ccl.clsSQL()

var = datetime.now().strftime(".%H.%M.%S")

documents = []

###############################################
###    End of Global Section                ###
###############################################
def main():
    try:
        var = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
        print('*'*120)
        print('Start Time: ' + str(var))
        print('*'*120)

        r1 = cl.execSQL()

        if r1 == 0:
            print()
            print('Successfully SQL-enabled!')
        else:
            print()
            print('Failed to senable SQL!')

        print('*'*120)
        var1 = datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
        print('End Time: ' + str(var1))

    except Exception as e:
        x = str(e)
        print('Error: ', x)

if __name__ == '__main__':
    main()

As this is extremely easy to understand & self-explanatory.

To learn more about this package, please visit the following link.

So, finally, we’ve done it. I know that this post is relatively smaller than my earlier post. But, I think, you can get a good hack to improve some of your long-running jobs by applying this trick.

I’ll bring some more exciting topics in the coming days from the Python verse. Please share & subscribe to my post & let me know your feedback.

Till then, Happy Avenging!  🙂

Note: All the data & scenarios posted here are representational data & scenarios & available over the internet & for educational purposes only. Some of the images (except my photo) we’ve used are available over the net. We don’t claim ownership of these images. There is always room for improvement & especially in the prediction quality.