Forem

Parth Sarthi Sharma profile picture

Parth Sarthi Sharma

Lead Software Engineer working on AI platforms, agentic systems, and cloud-native architectures. I write about: • Distributed systems & system design • LangChain, LangGraph, and real-world AI agents

Joined Joined on 

Pronouns

He/Him

Work

Lead Software Engineer

Self-RAG vs Adaptive RAG vs Corrective RAG
Cover image for Self-RAG vs Adaptive RAG vs Corrective RAG
parth_sarthisharma_105e7 profile

Self-RAG vs Adaptive RAG vs Corrective RAG

#ai #rag #vectordatabase #softwareengineering
Comments
3 min read
LangChain vs LangGraph vs Semantic Kernel vs Google AI ADK vs CrewAI
Cover image for LangChain vs LangGraph vs Semantic Kernel vs Google AI ADK vs CrewAI
parth_sarthisharma_105e7 profile

LangChain vs LangGraph vs Semantic Kernel vs Google AI ADK vs CrewAI

#ai #rag #softwareengineering #llm
1
Comments
3 min read
Local RAG vs Cloud RAG: What Changes When You Leave the Demo
Cover image for Local RAG vs Cloud RAG: What Changes When You Leave the Demo
parth_sarthisharma_105e7 profile

Local RAG vs Cloud RAG: What Changes When You Leave the Demo

#ai #rag #vectordatabase #softwareengineering
Comments
3 min read
Prompt Routing & Context Engineering: Letting the System Decide What It Needs
Cover image for Prompt Routing & Context Engineering: Letting the System Decide What It Needs
parth_sarthisharma_105e7 profile

Prompt Routing & Context Engineering: Letting the System Decide What It Needs

#ai #promptengineering #vectordatabase #rag
Comments
3 min read
Simple RAG vs Agentic RAG: What Problem Are You Actually Solving?
Cover image for Simple RAG vs Agentic RAG: What Problem Are You Actually Solving?
parth_sarthisharma_105e7 profile

Simple RAG vs Agentic RAG: What Problem Are You Actually Solving?

#ai #rag #llm #softwareengineering
Comments
2 min read
Chunking, Batching & Indexing: The Hidden Costs of RAG Systems
Cover image for Chunking, Batching & Indexing: The Hidden Costs of RAG Systems
parth_sarthisharma_105e7 profile

Chunking, Batching & Indexing: The Hidden Costs of RAG Systems

#ai #rag #llm #softwareengineering
Comments
2 min read
Why “Lost in the Middle” Breaks Most RAG Systems
Cover image for Why “Lost in the Middle” Breaks Most RAG Systems
parth_sarthisharma_105e7 profile

Why “Lost in the Middle” Breaks Most RAG Systems

#ai #rag #vectordatabase #machinelearning
Comments
2 min read
Loaders, Splitters & Embeddings — How Bad Chunking Breaks Even Perfect RAG Systems
parth_sarthisharma_105e7 profile

Loaders, Splitters & Embeddings — How Bad Chunking Breaks Even Perfect RAG Systems

#ai #rag #vectordatabase #llm
Comments
3 min read
How LLMs Actually “See” Context (Tokens, Chunks, Windows)
parth_sarthisharma_105e7 profile

How LLMs Actually “See” Context (Tokens, Chunks, Windows)

#ai #rag #llm #genai
Comments
3 min read
Vector Dimensions, Cosine Similarity, Dot Product — and Why Your Distance Metric Silently Ruins Relevance
parth_sarthisharma_105e7 profile

Vector Dimensions, Cosine Similarity, Dot Product — and Why Your Distance Metric Silently Ruins Relevance

#ai #vectordatabase #rag #generativeai
Comments
2 min read
Dense vs Sparse Vector Stores: Which One Should You Use — and When?
parth_sarthisharma_105e7 profile

Dense vs Sparse Vector Stores: Which One Should You Use — and When?

#langchain #rag #ai #vectordatabase
Comments
2 min read
ReAct vs Tool Calling: Why Your LLM Should Decide — But Never Execute
parth_sarthisharma_105e7 profile

ReAct vs Tool Calling: Why Your LLM Should Decide — But Never Execute

#ai #langchain #llm #systemdesign
Comments
2 min read
loading...