Skip to main content


Showing posts with the label Tips and Tricks

Tips To Improve LLM-Based Applications

Large Language Models (LLMs) are powerful AI systems that can understand and generate natural language. They have many applications in various domains, such as natural language processing, machine translation, and healthcare. However, building LLM-based applications is not a trivial task. It requires careful consideration of several factors, such as the choice of the LLM, the data quality, the evaluation metrics, and the ethical implications.  In this blog post, I will share some tips to solve most common problems. How to extract correct content from LLM Problem says that, although the answer is present in the content, but model fails to extract that.  Here are the quick tips to resolve this problem: Prompt compression Remove irrelevant data Rectify typos and grammatical errors Remove duplicate data Use data cleaning libraries Problem of missing top ranked documents Problem states that correct document was not rankled while ranking the documents. Here are the few suggestions, which can

How To Give Name To A Size Column In Python

It is quite common to use size() in Python. size() function gives you a total number of elements. Now, if it is that easy and straight forward, then why am I writing about it? Isn't it? Well, calculating the size or getting the output of the size() function is very straight forward, but when it comes to labeling this value, things become more complicated. Let's understand this with the help of an example. Input Data Here is how our sample data looks like. It is in the form of CSV: Scenario Explained The idea is to group data based on 2 columns named 'type_school' and 'interest' and then show their item count in a separate column. Here is the sample code to achieve this: import pandas as pd df = pd . read_csv ( 'data.csv' ) data = df . groupby ( [ 'type_school' , 'interest' ] ) data [ 'size' ] = data . size ( ) print ( data ) Python Copy The above code looks all good but you will end up seeing an error in it's execu

Screen Capture Using Python

Nowadays, screen capturing is one of the common tasks which most of us are doing in our day-to-day routine and there are instances where in we need to automate this task. In this article, I'll explain you about how can we automate screen capturing using Python. To get started, first of all we need to grab all the required packages and install them. Required packages To automate screenshot capturing, we need to install a package named pyautogui and this can be installed using pip as shown below: pip install pyautogui     Import packages Once required packages are installed, we need to import them into our code. Here we need to import two packages - one for screenshot capturing and another one is for timer as we need to capture our screen after certain seconds of our application launch. Here is the code: import pyautogui import time Implementation  Now we have all the packages imported, we can go ahead and make a call to required function. We will start by calling a function screen

Effective ways to sort Python iterables

The traditional way to sort iterables is by using loops, like for loop or while loop. As part of this article, I am not going to cover this traditional way, rather I will be focusing on a better way to implement sorting. And that better way is by using sorted function . Let's take a look at below list holding some numbers: numbers = [ 2 , 3 , 6 , 4 , 9 , 1 ] Python Copy To sort this list, we just need to call a function as shown below:  numbers = sorted ( numbers ) Python Copy To sort this list in reverse order, we need to pass an additional parameter: numbers = sorted ( numbers , reverse = True ) Python Copy Apart from this simple case, we can also handle some complex scenarios wherein we have a list containing key-value pairs as shown: studentDetails = [ { “Name” : “Nick” , “Marks” : 23 } , { “Name” : “Roy” , “Marks” : 2 } , { “Name” : “Honey” , “Marks” : 45 } ] Python Copy Now, say you want to sort studentDetails based on Marks. So, the only code you n

Tips for Effective Code Reviews

In the field of software development, code review plays a very vital role. It not only enhances the code quality, but also identifies issues before the code goes into the tester’s hand. T hroughout my development experience, I came across many amazing guidelines that can contribute to an effective code review. So, as part of this article I’m going to list down all those points. Naming Conventions, Data types, Sizes and Comments V ariable names should be small but self-explanatory. Based on the language and platform, standards and casing should be followed. Always prefer field names using adjective or noun. Prefer to use PascalCasing for resource keys. Always prefer to name events with a verb. It’s good to think about tense while naming events, i.e. rendered, rendering, etc. Keep method size as small as possible. I personally prefer, size of method body of <=12 lines. So, that complete method can be seen without scrolling the screen. All the parameters should pass validation check be