---
title: "#search articles | Hashnode"
description: "Explore 536 articles tagged #search on Hashnode. Tutorials, guides, and how-tos from the community."
url: "https://hashnode.com/tag/search"
---

Tag

# #search

536 posts · 21 followers

[Sunnatulla E.](https://hashnode.com/@sunnatulla) · [4h ago](https://hashnode.com/posts/google-custom-search-api-shutdown-25-apps/6afc2a7dba5e61fb23c8c49b)

### [Google's Custom Search API shuts off on January 1. I read the code of 25 apps that still call it.](https://sunnatulla.hashnode.dev/google-custom-search-api-shutdown-25-apps?utm_source=hashnode&utm_medium=feed)

If your app sends requests to https://www.googleapis.com/customsearch/v1, you have about six weeks. Google's overview page says the Custom Search JSON API "is closed to new customers" and that existin

8 min read · [sunnatulla.hashnode.dev](https://sunnatulla.hashnode.dev/google-custom-search-api-shutdown-25-apps?utm_source=hashnode&utm_medium=feed)

[Ofer](https://hashnode.com/@signify) · [1d ago](https://hashnode.com/posts/natural-language-search-best-series-on-netflix/6afafd80c666cdd9a163afe0)

### [How I Turned "Best Thriller Series on Netflix 2025" Into a Database Query](https://what2c.hashnode.dev/natural-language-search-best-series-on-netflix?utm_source=hashnode&utm_medium=feed)

Building a plain-language search for TV series and movies: 43 intent types, year math, and the bugs that return nothing at all.

7 min read · [what2c.hashnode.dev](https://what2c.hashnode.dev/natural-language-search-best-series-on-netflix?utm_source=hashnode&utm_medium=feed)

[Sayam Jain](https://hashnode.com/@sayamjain) · [23h ago](https://hashnode.com/posts/rag-is-a-search-problem-first/6afb20d43fe6fb1cd9863ed0)

### [RAG is a search problem first](https://sayamjain.hashnode.dev/rag-is-a-search-problem-first?utm_source=hashnode&utm_medium=feed)

I copied my Nagamese glossary lookup into a demo with 24 labelled posts, then used an oracle to separate retrieval failures from generation failures.

13 min read · [sayamjain.hashnode.dev](https://sayamjain.hashnode.dev/rag-is-a-search-problem-first?utm_source=hashnode&utm_medium=feed)

[windflash](https://hashnode.com/@windflash) · [1d ago](https://hashnode.com/posts/i-built-a-jane-austen-site-with-311-chapters-and-no-database/6afa8552a596505fb2caca96)

### [I Built a Jane Austen Site With 311 Chapters and No Database](https://windflashlab.hashnode.dev/i-built-a-jane-austen-site-with-311-chapters-and-no-database?utm_source=hashnode&utm_medium=feed)

How static content collections, cross-references, and a build-time search index keep a full-text archive navigable.

5 min read · [windflashlab.hashnode.dev](https://windflashlab.hashnode.dev/i-built-a-jane-austen-site-with-311-chapters-and-no-database?utm_source=hashnode&utm_medium=feed)

[Ankit Sharma](https://hashnode.com/@growthhacking) · [1d ago](https://hashnode.com/posts/same-question-two-ai-engines-two-different-winners-why-chatgpt-and-gemini-disagree/6af9cb42d896b9fac00cdd0e)

### [Same question, two AI engines, two different winners: why ChatGPT and Gemini disagree](https://growthmindset.hashnode.dev/same-question-two-ai-engines-two-different-winners-why-chatgpt-and-gemini-disagree?utm_source=hashnode&utm_medium=feed)

On 12 November 2026 I asked ChatGPT and Gemini the same question, both with web search switched on, both from the US: "What is the best smartwatch for fitness tracking?" ChatGPT put Garmin first, the

4 min read · [growthmindset.hashnode.dev](https://growthmindset.hashnode.dev/same-question-two-ai-engines-two-different-winners-why-chatgpt-and-gemini-disagree?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/same-question-two-ai-engines-two-different-winners-why-chatgpt-and-gemini-disagree/6af9cb42d896b9fac00cdd0e)

[Hu Jin](https://hashnode.com/@whoai) · [2d ago](https://hashnode.com/posts/reranking-for-rag-using-cross-encoders-to-improve-top-results/6af9a8b82b7173cdce112615)

### [Reranking for RAG: Using Cross-Encoders to Improve Top Results](https://whoai.hashnode.dev/reranking-for-rag-using-cross-encoders-to-improve-top-results?utm_source=hashnode&utm_medium=feed)

A beginner-friendly look at why first-pass retrieval is rough, how cross-encoder rerankers refine the list, and how to balance candidate count vs latency.

4 min read · [whoai.hashnode.dev](https://whoai.hashnode.dev/reranking-for-rag-using-cross-encoders-to-improve-top-results?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/reranking-for-rag-using-cross-encoders-to-improve-top-results/6af9a8b82b7173cdce112615)

[Tristan Manchester](https://hashnode.com/@tristanmanchester) · [3d ago](https://hashnode.com/posts/how-i-took-gravity-s-search-from-0-to-99/6af85242e72c3fafbf538785)

### [How I took Gravity's search from 0% to 99%](https://gravitynotes.hashnode.dev/how-i-took-gravity-s-search-from-0-to-99?utm_source=hashnode&utm_medium=feed)

A 200-case search eval, a 17 MB embedding model, and one search contract for iPhone, Android, Mac, the CLI and Claude.

21 min read · [gravitynotes.hashnode.dev](https://gravitynotes.hashnode.dev/how-i-took-gravity-s-search-from-0-to-99?utm_source=hashnode&utm_medium=feed)

[ToolPotion](https://hashnode.com/@toolpotion) · [3d ago](https://hashnode.com/posts/perplexity-vs-chatgpt-search-vs-google-ai-mode/6af7c6748cbf6d1eb5394e97)

### [AI Search Showdown: Perplexity vs ChatGPT Search vs Google AI Mode](https://toolpotion.hashnode.dev/perplexity-vs-chatgpt-search-vs-google-ai-mode?utm_source=hashnode&utm_medium=feed)

AI Search Showdown: Perplexity vs ChatGPT Search vs Google AI Mode For most everyday questions, Google AI Mode is a sensible starting point, ChatGPT search is strong when you need to talk a problem th

5 min read · [toolpotion.hashnode.dev](https://toolpotion.hashnode.dev/perplexity-vs-chatgpt-search-vs-google-ai-mode?utm_source=hashnode&utm_medium=feed)

[1](https://hashnode.com/posts/perplexity-vs-chatgpt-search-vs-google-ai-mode/6af7c6748cbf6d1eb5394e97)

[windflash](https://hashnode.com/@windflash) · [3d ago](https://hashnode.com/posts/i-built-a-searchable-archive-of-351-government-uap-files-here-s-how-i-structured-the-unknown/6af7234df428da010651d1a1)

### [I Built a Searchable Archive of 351 Government UAP Files — Here's How I Structured the Unknown](https://windflashlab.hashnode.dev/i-built-a-searchable-archive-of-351-government-uap-files-here-s-how-i-structured-the-unknown?utm_source=hashnode&utm_medium=feed)

The hard part wasn't collecting PDFs. It was keeping provenance, uncertainty, and search from collapsing into one confident story.

6 min read · [windflashlab.hashnode.dev](https://windflashlab.hashnode.dev/i-built-a-searchable-archive-of-351-government-uap-files-here-s-how-i-structured-the-unknown?utm_source=hashnode&utm_medium=feed)

[Hu Jin](https://hashnode.com/@whoai) · [5d ago](https://hashnode.com/posts/hybrid-search-in-rag-combining-bm25-keyword-and-vector-retrieval/6af5b86e5a4226c50b2bc977)

### [Hybrid Search in RAG: Combining BM25 Keyword and Vector Retrieval](https://whoai.hashnode.dev/hybrid-search-in-rag-combining-bm25-keyword-and-vector-retrieval?utm_source=hashnode&utm_medium=feed)

Why vector search alone misses exact terms, how BM25 and embeddings complement each other, and how to fuse ranks with Reciprocal Rank Fusion.

4 min read · [whoai.hashnode.dev](https://whoai.hashnode.dev/hybrid-search-in-rag-combining-bm25-keyword-and-vector-retrieval?utm_source=hashnode&utm_medium=feed)

[2](https://hashnode.com/posts/hybrid-search-in-rag-combining-bm25-keyword-and-vector-retrieval/6af5b86e5a4226c50b2bc977)
