Loading pattern preview
BlocksTools & Utilities
Jev Search Filter
Jev Search Filter
Filter a closed catalog with one Jev boolean per item. Matches rise out of the pile when their probability clears a floor.
Use this when you want semantic search over a known catalog, such as emoji or icons, without building embeddings, scoring each item with a boolean.
Loading pattern preview
Problems solved
Technical challenges this implementation handles out of the box.
- Filter a closed catalog with one boolean per item
- Keep the match floor in application code
- Leave non-matches in place instead of inventing results
Use cases
Products and workflows this pattern is designed to support.
- Semantic filters over a known catalog
- Emoji or icon search without embeddings
- Teaching Jev boolean probabilities across many items
Compare with
Similar patterns, and when each one is the better fit.
Jev Email TagsUse this when you are multi-label tagging a known set of messages, such as an inbox, without writing a classifier prompt or allowing invented labels.
Jev Table QueryUse this when users type filter or sort requests over a fixed table, with column sorts run in code and other phrases scored by the model per row.
Jev Action GateFreeUse this when you are deciding whether to auto-approve one proposed action at a time, using a single Jev probability against a floor you control.
Jev Best-of-N JudgeUse this when you already have several candidate replies to one prompt and need one chosen, or none at all if the pick is too close to call.
Setup
Requirements, wiring steps, and what this pattern adds to your project.
Getting started
Pick how you want to pull this pattern in. Then wire env vars and routes the same way.
- 1
Download → Next.js app
Use Download → Next.js app in the preview toolbar. You get a zip scaffold (Pro downloads rewrite preview `/view/.../api/*` paths to `/api/*` automatically).
- 2
Extract the zip and install dependencies
Unzip the archive, then run `pnpm install` (or npm / yarn) in the project folder.
- 3
Fill .env.local
The download includes .env.local placeholders when needed. Add real values for: AI_GATEWAY_API_KEY.
- 4
Customize the agent and tool files
Adapt prompts, tools, and stop conditions in the generated project for your product.
- 5
Run the app and open the pattern route
Run `pnpm dev`, open the setup/checklist page if present, then navigate to the generated pattern route and verify responses.
Environment variables
AI_GATEWAY_API_KEYGet key
Capabilities
AI SDK APIs
experimental_evaluateProviders
Jev
External services
gatewayvercel-ai-gatewayUpstash
Files added
14 files
app/page.tsxapp/layout.tsxapp/api/search/route.tscomponents/search-filter-demo.tsxcomponents/catalog-pile.tsxcomponents/typesafe-ai.tsxhooks/use-search-filter.tslib/catalog.tslib/filter-questions.tslib/filter-policy.tslib/pile-layout.tslib/rate-limit.tslib/request-utils.tsREADME.md
Dependencies
7 total
npm packages
6UpstashAISDKlucide-reactmotionNext.jsReact
Registry components
button
Critical files
4 files
lib/filter-policy.tsPure decideFilter policy: keep a catalog id only when P(match) >= 0.70. A missing answer stays out. Do not call Jev from unit tests. Use Experimental_EvaluationMockModelV4.
lib/filter-questions.tsbuildFilterQuestions writes one boolean per catalog item. The item name and hint live in the instructions. MATCH_FLOOR is 0.70 and stays in application code.
lib/catalog.tsClosed emoji catalog. Jev may only answer these ids. Do not let the model invent items.
search/route.tsRate-limited experimental_evaluate call through AI Gateway model typesafe-ai/jev with zeroDataRetention. Returns decideFilter matches, never a free-text list.
Requirements
- Complexity
- Beginner
- Setup time
- ~5 minutes
- Node
- 24+
- Memory
- 256MB
Upstash Redis for deployed demo rate limiting
