Eeyanpeninai-is-coming.hashnode.dev·May 4 · 11 min readWhy Does Semantic Chunking Need an Embedding API?Fixed-length chunking requires no external services, yet semantic chunking absolutely needs an Embedding API — why? The Short Answer The core idea of semantic chunking is to split text at semantic boundaries. Determining whether "two pieces of text ...00
Eeyanpeninai-is-coming.hashnode.dev·May 3 · 6 min readMultiple Independent Questions: Batch Into One Request or Split Into Many? — An Analysis of LLM Concurrent ProcessingWhen you have 5 unrelated questions, should you pack them into one message to the LLM, or send 5 requests simultaneously? Which is faster? The Short Answer Splitting into multiple independent parallel requests is almost always faster. This isn't a g...00
Eeyanpeninai-is-coming.hashnode.dev·Apr 24 · 8 min readWhat Is GraphRAG Really Doing? — A Deep Dive into Microsoft's Blog PostOriginal: GraphRAG: Unlocking LLM discovery on narrative private data - Microsoft Research In early 2024, Microsoft published a technical blog post. The core message boils down to one sentence: Traditional RAG falls short with complex data, and Gra...00
Eeyanpeninai-is-coming.hashnode.dev·Apr 24 · 9 min readThe Biggest Pitfall in GraphRAG: One Entity, Seven IdentitiesYou thought the hardest part of GraphRAG was "building the graph." In reality, the hardest part is "assigning entity types" — even when you've predefined a strict type schema. 1. A Real-World Dataset We ran GraphRAG entity extraction on 3GPP TS 23.5...00
Eeyanpeninai-is-coming.hashnode.dev·Apr 24 · 6 min readWhy Do We Need GraphRAG? — The Evolution from "Search" to "Understanding"When AI stops just "looking things up" and starts truly "understanding" your question. 1. Let's Start with an Everyday Scenario Imagine you're a new employee at a company. On your first day, you want to know "the most important project updates from ...00
