Full-Text Search taste — ChatGPT prompt for search design
Full-Text Search taste — a prompt for ChatGPT that sets out principles for building full-text search. It covers indexing, ranking, access control, and result delivery.
CC0-1.0 ★ 178,201 updated 2026-10-24
Open on GitHubWhat Full-Text Search taste does
The prompt offers design guidance for full-text search in a backend system. It recommends starting with the database’s built-in search, such as PostgreSQL tsvector, and adding a dedicated search engine when relevance or scale calls for it.
Its guidance covers versioned indexes with alias switching, updates through a change feed, outbox, or queue, language-specific analyzers, and access filters inside the search query. It suggests a separate prefix field for autocomplete and cursor pagination for deep pages. The search engine should sit behind your own API with rate limits, not be exposed directly to browsers.
What it helps with
- choose between database search and a dedicated engine
- design index updates and rebuilds
- tune ranking, analyzers, and access filters
- test relevance changes against a query set in CI
Example prompts for the agent
- Design full-text search for a PostgreSQL catalog.
- Suggest a queue-based index update flow with version switching and no downtime.
- Review ranking, access filters, and autocomplete for a search system.
How to install Full-Text Search taste
How to use
Paste the text at the start of a chat or into project instructions
Manually: put the files in place
.claude/commands/prompts.csv.mdQuestions about Full-Text Search taste
How do I install Full-Text Search taste in Claude Code?
Add the prompt to .claude/commands/prompts.csv.md.
What does Full-Text Search taste do?
It provides design guidance for full-text search, covering indexing, ranking, access control, monitoring, and relevance testing.
What is its approach to securing search results?
It recommends enforcing access control in the search query itself and routing requests through your own API with rate limits, rather than exposing the search engine to browsers.
Source text
prompts.csv · CC0-1.0
# Full-Text Search taste of a search-focused backend engineer - Start with the database's built-in full-text search, such as PostgreSQL tsvector, and add a dedicated search engine only when relevance or scale really needs it. Confidence: 0.85 - Treat the search index as a derived copy that can be rebuilt at any time from the primary database. Confidence: 0.95 - Keep the index in sync with a change feed, outbox table or queue, never with dual writes from request handlers. Confidence: 0.90 - Write to a new versioned index and switch an alias to it for mapping changes, so reindexing never causes downtime. Confidence: 0.90 - Define explicit field mappings and analyzers instead of relying on dynamic mapping guesses. Confidence: 0.90 - Store exact-match fields like IDs, slugs and statuses as keyword fields, separate from analyzed text fields. Confidence: 0.90 - Pick analyzers per language, with stemming and stop words chosen for that language, instead of one default analyzer for all content. Confidence: 0.80 - Boost title matches above body matches, and tune field weights with real queries rather than intuition alone. Confidence: 0.85 - Use filters for structured conditions like category, date or permissions so they are cached and do not affect scoring. Confidence: 0.85 - Apply access control inside the search query itself, never by filtering results after they come back. Confidence: 0.95 - Add typo tolerance with fuzzy matching only for terms longer than a few characters to avoid noisy results. Confidence: 0.75 - Serve autocomplete from a dedicated edge n-gram or prefix field, not from wildcard queries on the main text field. Confidence: 0.80 - Manage synonyms in a reviewed file or table under version control, not by editing them directly in production. Confidence: 0.75 - Use search_after or cursor pagination for deep result pages instead of large from and size offsets. Confidence: 0.85 - Log every query, its result count and its clicks so zero-result and low-click queries can be fixed. Confidence: 0.90 - Keep a small judged set of queries and expected results, and run it in CI before shipping any relevance change. Confidence: 0.80 - Try hybrid search that combines keyword and vector results only after the keyword baseline is measured. Confidence: 0.70 - Show highlighted snippets and clear facet counts so users understand why a result matched. Confidence: 0.80 - Set timeouts on search requests and fall back to a simpler query or cached results when the cluster is slow. Confidence: 0.80 - Monitor query latency percentiles, indexing lag and index size, and alert when indexing falls behind. Confidence: 0.85 - Never expose the search engine directly to browsers, and always put it behind your own API with rate limits. Confidence: 0.95
© f · CC0-1.0 · f/prompts.chat