Yogyashri Patil

@yogyashri

Developer, GenAI expert

Joined April 2025

About

Nothing here yet.

Available for

Nothing here yet.

Yogyashri Patil's blogs

Decoding AI jargon's with Sholay moviedecoding-ai-jargons-with-sholay-movie.hashnode.dev1 post

Effective Prompt Writing for AI Resultseffective-prompt-writing-for-ai-results.hashnode.dev1 post

fine tuning and LoRA Fine tuningfine-tuning-and-lora-fine-tuning.hashnode.dev1 post

Rag with Chaiaurcoderag-with-chaiaurcode.hashnode.dev1 post

Parallel Query in RAGparallel-query-in-rag.hashnode.dev1 post

Articles Comments

Recently published

YPYogyashri Patilhypothetical-document-embeddings.hashnode.devApr 23, 2025 · 4 min read

HyDE (Hypothetical Document Embeddings)

Description In Hypothetical Document Embeddings (HyDE), the approach differs from traditional techniques. Instead of generating alternative questions based on the user’s original query, HyDE prompts the model to produce a direct answer to the query. ...

0

YPYogyashri Patilchain-of-thought.hashnode.devApr 23, 2025 · 5 min read

Structured Thinking in RAG: Unlocking Chain of Thought for Smarter AI

In Chain of Thought RAG, step by step reasoning is layered on top of a Retrieval Augmented Generation system. The model retrieves relevant knowledge first, then reasons through it methodically before generating its final output. A technique that enha...

0

YPYogyashri Patilstep-back-prompting.hashnode.devApr 23, 2025 · 3 min read

Strategic Step Back Prompting: Enhancing LLM Outputs with Smarter Queries

What is Step Back Prompting? Step Back Prompting in Retrieval-Augmented Generation (RAG) involves rephrasing a user’s specific query into a broader, more generalized question before initiating the search process. By taking a moment to "step back," th...

0

YPYogyashri Patilreciprocal-rank-fusionrrf.hashnode.devApr 23, 2025 · 9 min read

Reciprocal Rank Fusion (RRF)- The Rank Symphony

In this article, we’ll dive into another clever approach to enhance search result quality when dealing with large text datasets, leveraging a technique known as Reciprocal Rank Fusion (RRF). Similar to Fan-Out Retrieval from our earlier blog(https://...

0

YPYogyashri Patilparallel-query-in-rag.hashnode.devApr 22, 2025 · 7 min read

Parallel Query Magic: Boosting RAG Quality with Gemini & Qdrant

In this post, we’ll explore a smart way to boost the quality of search results when working with large text datasets, using a method called Fan-Out Retrieval (also known as Parallel Query Expansion). We'll combine tools like LangChain, Google’s Gemin...

0

Yogyashri Patil

About

Available for

Yogyashri Patil's blogs

Recently published

HyDE (Hypothetical Document Embeddings)

Structured Thinking in RAG: Unlocking Chain of Thought for Smarter AI

Strategic Step Back Prompting: Enhancing LLM Outputs with Smarter Queries

Reciprocal Rank Fusion (RRF)- The Rank Symphony

Parallel Query Magic: Boosting RAG Quality with Gemini & Qdrant

Search Hashnode

Yogyashri Patil

About

Available for

Yogyashri Patil's blogs

Recently published

HyDE (Hypothetical Document Embeddings)

Structured Thinking in RAG: Unlocking Chain of Thought for Smarter AI

Strategic Step Back Prompting: Enhancing LLM Outputs with Smarter Queries

Reciprocal Rank Fusion (RRF)- The Rank Symphony

Parallel Query Magic: Boosting RAG Quality with Gemini & Qdrant