--- title: "eyanpen (@eyanpen) | Hashnode" description: "eyanpen (@eyanpen) writes on Hashnode. Read their latest articles and follow their work." url: "https://hashnode.com/@eyanpen" --- @eyanpen # eyanpen @eyanpen · Shanghai, China · Joined April 2026 ### [Why Does Semantic Chunking Need an Embedding API?](https://ai-is-coming.hashnode.dev/why-does-semantic-chunking-need-an-embedding-api?utm_source=hashnode&utm_medium=feed) 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 ... 11 min read · [ai-is-coming.hashnode.dev](https://ai-is-coming.hashnode.dev/why-does-semantic-chunking-need-an-embedding-api?utm_source=hashnode&utm_medium=feed) [May 4](https://hashnode.com/posts/why-does-semantic-chunking-need-an-embedding-api/69f834a197097cf18534a2cc) ### [Multiple Independent Questions: Batch Into One Request or Split Into Many? — An Analysis of LLM Concurrent Processing](https://ai-is-coming.hashnode.dev/multiple-independent-questions-batch-into-one-request-or-split-into-many-an-analysis-of-llm-concurrent-processing?utm_source=hashnode&utm_medium=feed) When 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... 6 min read · [ai-is-coming.hashnode.dev](https://ai-is-coming.hashnode.dev/multiple-independent-questions-batch-into-one-request-or-split-into-many-an-analysis-of-llm-concurrent-processing?utm_source=hashnode&utm_medium=feed) [May 3](https://hashnode.com/posts/multiple-independent-questions-batch-into-one-request-or-split-into-many-an-analysis-of-llm-concurrent-processing/69f69488bf43b2821c73cbc3) ### [What Is GraphRAG Really Doing? — A Deep Dive into Microsoft's Blog Post](https://ai-is-coming.hashnode.dev/what-is-graphrag-really-doing-a-deep-dive-into-microsofts-blog-post?utm_source=hashnode&utm_medium=feed) Original: 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... 8 min read · [ai-is-coming.hashnode.dev](https://ai-is-coming.hashnode.dev/what-is-graphrag-really-doing-a-deep-dive-into-microsofts-blog-post?utm_source=hashnode&utm_medium=feed) [Apr 24](https://hashnode.com/posts/what-is-graphrag-really-doing-a-deep-dive-into-microsofts-blog-post/69eb59ec6a21c6862c7b7b16) ### [The Biggest Pitfall in GraphRAG: One Entity, Seven Identities](https://ai-is-coming.hashnode.dev/the-biggest-pitfall-in-graphrag-one-entity-seven-identities?utm_source=hashnode&utm_medium=feed) You 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... 9 min read · [ai-is-coming.hashnode.dev](https://ai-is-coming.hashnode.dev/the-biggest-pitfall-in-graphrag-one-entity-seven-identities?utm_source=hashnode&utm_medium=feed) [Apr 24](https://hashnode.com/posts/the-biggest-pitfall-in-graphrag-one-entity-seven-identities/69eb59eaa2256331b856186b) ### [Why Do We Need GraphRAG? — The Evolution from "Search" to "Understanding"](https://ai-is-coming.hashnode.dev/why-do-we-need-graphrag-the-evolution-from-search-to-understanding?utm_source=hashnode&utm_medium=feed) 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 ... 6 min read · [ai-is-coming.hashnode.dev](https://ai-is-coming.hashnode.dev/why-do-we-need-graphrag-the-evolution-from-search-to-understanding?utm_source=hashnode&utm_medium=feed) [Apr 24](https://hashnode.com/posts/why-do-we-need-graphrag-the-evolution-from-search-to-understanding/69eb58d4d2ce9abe7de7043f)