Forem

Aparna Pradhan profile picture

Aparna Pradhan

A full-stack web and React Native developer specializing in AI integration with TensorFlow.js and TFLite, as well as LLM API integration. Experienced in building AI agents, retrieval-augmented generat

Location india, west bengal Joined Joined on  Personal website https://main--aparnapradhanportfolio.netlify.app/
ElevenLabs: $99/mo vs. Kokoro + VoxCPM: $0 (Better Quality) 🎙️
Cover image for ElevenLabs: $99/mo vs. Kokoro + VoxCPM: $0 (Better Quality) 🎙️
_aparna_pradhan_ profile

ElevenLabs: $99/mo vs. Kokoro + VoxCPM: $0 (Better Quality) 🎙️

#tts #selfhost
Comments
3 min read
COST EFFECTIVE AI IN GCP
Cover image for COST EFFECTIVE AI IN GCP
_aparna_pradhan_ profile

COST EFFECTIVE AI IN GCP

#ai #cloudcomputing #gemini #serverless
Comments
2 min read
COOLIFY : THE DEPLOYMENT ARBITRAGE RECLAIMING STARTUP RUNWAY FROM VERCEL
Cover image for COOLIFY : THE DEPLOYMENT ARBITRAGE RECLAIMING STARTUP RUNWAY FROM VERCEL
_aparna_pradhan_ profile

COOLIFY : THE DEPLOYMENT ARBITRAGE RECLAIMING STARTUP RUNWAY FROM VERCEL

#vercel #coolify #selfhost #hetzner
Comments
4 min read
Ditch Cloudflare's $5k/Mo Bills: Self-Host Workers at 1/100th Cost in 2 Hours 🚀
Cover image for Ditch Cloudflare's $5k/Mo Bills: Self-Host Workers at 1/100th Cost in 2 Hours 🚀
_aparna_pradhan_ profile

Ditch Cloudflare's $5k/Mo Bills: Self-Host Workers at 1/100th Cost in 2 Hours 🚀

#cloudflare #openworker #hetzner #selfhost
Comments
3 min read
The $20 Billion Strategic Warning Shot: Why NVIDIA Fused the LPU into the CUDA Empire
Cover image for The $20 Billion Strategic Warning Shot: Why NVIDIA Fused the LPU into the CUDA Empire
_aparna_pradhan_ profile

The $20 Billion Strategic Warning Shot: Why NVIDIA Fused the LPU into the CUDA Empire

#inference #cuda #groq #nvidia
1
Comments
4 min read
Clone Your CTO: The Architecture of an 'AI Twin' (DSPy + Unsloth)
Cover image for Clone Your CTO: The Architecture of an 'AI Twin' (DSPy + Unsloth)
_aparna_pradhan_ profile

Clone Your CTO: The Architecture of an 'AI Twin' (DSPy + Unsloth)

#ai #llm #rag #agenticai
Comments
3 min read
🚀 GLM 4.7 : Is the era of "expensive-only" SOTA models ending?
_aparna_pradhan_ profile

🚀 GLM 4.7 : Is the era of "expensive-only" SOTA models ending?

#llm #ai #glm #zai
Comments
2 min read
The Perfect Extraction: Unlocking Unstructured Data with Docling + LangExtract 🚀
_aparna_pradhan_ profile

The Perfect Extraction: Unlocking Unstructured Data with Docling + LangExtract 🚀

#docling #langextract #ai #rag
1
Comments
3 min read
🤯 Stop Paying Cloud Bills: How Transformers.js & WASM Shifts RAG Compute to the Browser (Client-Side AI)
Cover image for 🤯 Stop Paying Cloud Bills: How Transformers.js & WASM Shifts RAG Compute to the Browser (Client-Side AI)
_aparna_pradhan_ profile

🤯 Stop Paying Cloud Bills: How Transformers.js & WASM Shifts RAG Compute to the Browser (Client-Side AI)

Comments
4 min read
The Research: MiniMax M2.1 (The "Linear" Revolution)
_aparna_pradhan_ profile

The Research: MiniMax M2.1 (The "Linear" Revolution)

#llm #openai #rag #ai
Comments
3 min read
Why We Replaced Our Orchestrator with a 'Regex' Switch
Cover image for Why We Replaced Our Orchestrator with a 'Regex' Switch
_aparna_pradhan_ profile

Why We Replaced Our Orchestrator with a 'Regex' Switch

#regex #litellm #llm #orchastration
Comments
4 min read
Why LLMs Fall Short: Why Large Language Models Aren't Ideal for AI Agent Applications
Cover image for Why LLMs Fall Short: Why Large Language Models Aren't Ideal for AI Agent Applications
_aparna_pradhan_ profile

Why LLMs Fall Short: Why Large Language Models Aren't Ideal for AI Agent Applications

#ai #rag #llm
Comments
3 min read
loading...