top of page
Codersarts Blog.
What’s new and exciting at Codersarts
Search
OpenAI Whisper + FastAPI Integration: Working Example (2026)
Complete OpenAI Whisper + FastAPI integration example with audio upload, MIME-type handling, async wrapping, and Safari/Chrome compatibility.
Pranav S
May 196 min read
Explore Codersarts' Professional Coding Services
When you need expert help with coding tasks, it can be tough to find the right support. Whether you are working on assignments, debugging complex code, or building a new product, having a reliable partner makes all the difference. I want to guide you through how you can leverage professional coding services to get your projects done faster and better. Let’s explore how these services work and how you can benefit from them. What Are Professional Coding Services? Professional c
Codersarts
May 184 min read
Understanding AI Project Execution Pricing Models: A Guide to ai project cost analysis
When you start an AI project, one of the first questions you ask is: How much will this cost? Understanding the pricing models behind AI project execution is crucial. It helps you plan your budget, set realistic expectations, and avoid surprises. In this post, I will walk you through the key concepts of AI project cost analysis. I will explain different pricing models, what affects costs, and how to choose the right approach for your project. Let’s dive in and make AI project
Codersarts
May 185 min read
Learn Vector Databases Before Building Your Next AI Project
At a high level, a vector database is a special type of database designed to store and search something called embeddings. And before that word scares you away, don’t worry — embeddings are much simpler than they sound.
Pratibha
May 1518 min read
How to Build an LLM from Scratch with PyTorch: A TinyGPT Tutorial
Introduction: You Use LLMs Every Day — But Do You Know What's Inside? You call openai.ChatCompletion.create(...) and a response appears. You paste code into Copilot and a completion materialises. It feels like magic, and for most developers it stays magic indefinitely — because none of the hosted APIs ever ask you to care about tokens, attention masks, or training loss. That gap between using a language model and understanding one is quietly becoming a career bottleneck. Inte
Pranav S
May 1513 min read
How to Build a CNN From Scratch in Python: Conv2D, TinyResNet, CIFAR-10, and Grad-CAM
1. Introduction: The "Black Box" Problem in Computer Vision You open a PyTorch tutorial. Four lines of code, a pretrained ResNet, and — boom — 94 % CIFAR-10 accuracy. You follow along, copy the snippet, get the number. Then someone asks: "What does a convolution actually do?" and you realise you have no idea. This is the most common frustration in beginner computer vision. Frameworks are deliberately designed to hide implementation details, and that abstraction is great for s
Pranav S
May 1513 min read
How to Build Speech Recognition From Scratch with Python, PyTorch, MFCCs, and OpenAI TTS
Introduction You have watched enough "speech recognition in 5 minutes" videos. Every tutorial starts the same way: pip install openai-whisper, load a model, call transcribe(), done. That is not learning speech recognition — it is calling someone else's black box. When the transcription is wrong, when latency is too high, or when you need to run entirely offline on a Raspberry Pi, you have no idea where to start debugging because you never understood what actually happens betw
Pranav S
May 1512 min read
The Beginner’s Guide to MCP for AI Engineers and Builders
MCP stands for Model Context Protocol.
MCP is basically a standardized way for AI models to connect with tools, applications, databases, APIs, and external systems.
Pratibha
May 1420 min read
How to Build DeepSeek-R1 from Scratch - GRPO Reinforcement Learning Explained
Introduction: The Techniques Behind 2026's Most Impressive AI Systems Are Still a Black Box If you have spent the last several months watching reasoning models outperform every benchmark in sight, you have probably asked the same question most ML engineers ask: how, exactly, does this work? The honest answer — after reading every public paper, blog post, and GitHub repo — is that most explanations stop precisely where the interesting part begins. You get the high-level pitch
Pranav S
May 1413 min read
How to Build a Chain-of-Thought Reasoning Model from Scratch (PyTorch + GSM8K)
1. The Problem: Your LLM Gives Confident, Fluent, Wrong Answers You feed a language model a math word problem. It returns an answer instantly — beautifully formatted, grammatically perfect, completely wrong. No working. No intermediate steps. Just a number, stated with the quiet confidence of a student who copied from the back of the book. This is not a corner case. It is the default behaviour of any model trained purely on next-token prediction. The model has learned to patt
Pranav S
May 1411 min read
How to Build a Vernacular Loan Origination System with Sarvam-105B and Sarvam Vision
Introduction Picture this: a small dairy farmer in Nagpur uploads his Aadhaar card — handwritten back-side details in Devanagari — along with six months of bank statements packed with narrations like UPI/PayTM/SAL CR JAN, EMI ICICI HOM, and ATM WDL KOTAK. Your backend passes it to a global OCR vendor and a frontier LLM. The OCR misreads half the Devanagari glyphs. The LLM hallucinates a salary figure. The application gets flagged for manual review. The farmer waits three week
Pranav S
May 1313 min read
![30+ LangChain & LangGraph Project Ideas to Build in 2026 [Beginner to Advanced]](https://static.wixstatic.com/media/90b6f2_16f0f8bc03de436cb1f668f0a87424dc~mv2.png/v1/fill/w_1672,h_940,fp_0.50_0.50,q_35,blur_30,enc_avif,quality_auto/90b6f2_16f0f8bc03de436cb1f668f0a87424dc~mv2.png)
![30+ LangChain & LangGraph Project Ideas to Build in 2026 [Beginner to Advanced]](https://static.wixstatic.com/media/90b6f2_16f0f8bc03de436cb1f668f0a87424dc~mv2.png/v1/fill/w_1252,h_704,fp_0.50_0.50,q_95,enc_avif,quality_auto/90b6f2_16f0f8bc03de436cb1f668f0a87424dc~mv2.png)
30+ LangChain & LangGraph Project Ideas to Build in 2026 [Beginner to Advanced]
31 LangChain and LangGraph project ideas for 2026, structured from beginner chains to production-grade agent systems. Every project includes a 4-step architecture, complete tech stack, estimated build time, and a mapped real-world use case. Plus a free downloadable developer handbook covering all 31 builds.
Codersarts
May 1326 min read
How to Build a Multilingual Insurance Claims Triage System with Sarvam Vision and Sarvam-105B
Introduction Every day, a claims processor at a mid-sized Indian health insurer opens a WhatsApp message and finds a photograph of a doctor's prescription — written in looping Devanagari on a torn notepad, half-smudged, with Latin drug abbreviations mixed in. She types what she can read into a legacy system, guesses at the rest, and moves to the next claim. Multiply that across millions of motor and health claims annually, in Hindi, Marathi, Tamil, Bengali, Gujarati, and seve
Pranav S
May 1312 min read
How to Build a Vernacular E-commerce Catalog Localization Engine with Mayura and Sarvam-30B
Introduction You've just been handed a catalog of two million SKUs and a deadline: launch vernacular UX in Hindi, Tamil, Telugu, Kannada, and seven more Indian languages before the next festive sale season. Your first instinct is to send it all to Google Translate. Three days later, QA flags that "BoAt" is now appearing as "नाव" (the Hindi word for boat), "500 g" has become "500 ग्राम" on some items and "500gms" on others, half the ₹ prices have dropped their currency symbol,
Pranav S
May 1313 min read
How to Build a Vernacular Contact-Center QA Platform with Saaras v3 and Sarvam-105B
1. The Problem: 98% of Indian Customer Calls Are Never Reviewed Picture a collections team at a mid-size Indian bank. Every day, hundreds of agents call borrowers in Hinglish, Bhojpuri-Hindi, Tanglish, and Marathinglish. Every one of those calls is recorded — and stored. Yet the QA team manually reviews fewer than two percent of them. The rest disappear into a storage bucket, reviewed only when a customer complaint or RBI audit forces someone to dig in. This is the normal sta
Pranav S
May 1312 min read
How to Build a Vernacular Citizen-Service Platform with Sarvam AI and the WhatsApp Business API
Section 1 — Introduction: The Pothole That Never Gets Fixed Picture this: a resident of ward 47 in Bengaluru photographs a gaping pothole, sends it on WhatsApp in Kannada, and waits. The message arrives at a call-centre agent who types it into a legacy portal in English, assigns it to the wrong ward because the geotag was off, and closes it as a duplicate of a three-month-old ticket. No acknowledgement reaches the resident. The SLA clock was never started. The pothole is stil
Pranav S
May 1313 min read
How to Build an Agentic Reasoning System Like Claude Extended Thinking or o3 Deep Research
Introduction: The Gap Between "Smart" and "Useful" You've seen the demos. A model reasons through a hard problem, cites live sources, runs code to verify its math, and lands on a correct, grounded answer all in one fluid session. That's Claude Extended Thinking. That's o3 Deep Research. That's Perplexity's reasoning mode. Now you try to build something similar. You chain a few LLM calls, bolt on a Wikipedia lookup, and get a system that occasionally hallucinates its tool call
Pranav S
May 1312 min read
How RAG Works Internally: Embeddings, Vector Databases, and Retrieval | Part 2
In this guide, we’ll break down the major internal components of a RAG pipeline step by step in plain English.
We’ll cover:
chunking,
embeddings,
vector databases,
similarity search,
retrieval,
and context injection into LLMs.
Pratibha
May 1313 min read
200+ MCP Project Ideas — Build AI-Powered Apps with Claude Desktop
The most comprehensive curated list of Model Context Protocol (MCP) project ideas — from beginner-friendly to advanced.
Whether you're a developer looking to break into AI-powered tooling, a startup founder exploring automation, or a student building your portfolio, this list has something for every skill level. Browse by category, filter by difficulty, and start shipping.
Pratibha
May 137 min read
How to Build a Unit Test Generation Agent with LangGraph, AST Parsing, and a Validation Loop
The Unit Test Generation Agent is a LangGraph-powered autonomous pipeline that scans a codebase, extracts every function signature using AST parsing, generates a complete unit test suite tailored to the detected language and framework, runs the tests in a sandboxed subprocess, iteratively refines the failures, and produces a coverage gap report — all without human involvement beyond pointing it at a directory.
Pratibha
May 1217 min read
Why Fine-Tuning Alone Isn’t Enough: Enter RAG
A fine-tuned model can become much better at understanding domain-specific language, following certain workflows, or generating responses in a particular style.
Traditional fine-tuning approaches tried to push knowledge into the model.
RAG flips the approach completely. Instead of permanently storing information inside model weights, RAG allows the AI to retrieve relevant information dynamically at runtime.
Pratibha
May 1211 min read
bottom of page