Laya for search and RAG
In retrieval pipelines Laya works best as a judge: is this passage relevant, does this evidence support the claim, should traversal continue. Projects use it to filter results and gate hallucinations. One published experiment found it is not a good general-purpose re-ranker.
88 projects
job-classifier-search
NoNFake
Ranks Danish job listings against a candidate profile using the Laya decision model
product_search_bench
Wanke15
Compares BM25, Jev, Qwen, and Laya for product search and reranking
jev-router
drycool
Provides a multi-tier routing gateway for RAG and agent workflows with an optional Laya classifier
laya-retrieval
Sharjeelbaig
Selects evidence passages with Laya in an experimental two-stage retrieval system
laya-local-lab
torresnicolas0
Reproduces local evaluations of three Laya variants across support, guardrails, RAG, and model selection
simplotel-guest-concierge
Itachi-1824
A hotel guest assistant combines retrieval, Laya classification, and validated availability
identity-jev
clawdreyhepburn
Fine-tunes Laya to rank identity and authentication standards from plain-language queries
layagrep
marksomething
Searches files and stdin by asking Laya whether each line matches a natural-language description
laya-scraper
qxZap
Uses Laya to find publication pages and extract publication details with a browser-capable crawler
laya-ecosystem
MiguelFAraujo
Provides utilities for supervision, context compaction, search, and UI decisions using Laya and Jev
-Semantic-Firewall-laya
manas95826
Authorizes AI-agent tool calls using retrieved security context and Laya decisions
ai-experiments
nadeem4
A collection of documented AI experiments reports protocols and results for model evaluations
laya-demo-0921
2045max
Demonstrates Laya decisions for routing, triage, moderation, RAG filtering, and other tasks
decision-model-eval
relevan-dev
An evaluation compares Laya, Jev, and Claude on search-index configuration decisions
mahabodi
jollypk
Combines topology memory and ONNX Runtime-based Laya decisions in a System-1 engine for AI agents
layarank
akashmitra
Filters and reranks search results locally using Laya neural routers
rag-laya-poc
Mr-PU
Compares standard RAG with a pipeline that uses Laya to rerank retrieved passages
laya-bsky-feed
KaidevLabs
Filters and scores Bluesky posts with Laya in a self-hosted feed pipeline
layarerank
anguyenbus
Reranks documents in batches with Laya decision models and evaluates fine-tuned checkpoints
laya-seo
emmanuelnurit
Provides SEO and GEO audits through a Jev-based CLI and MCP, with a local Laya scoring bridge
jev-laya-benchmarks
stemirkhan
Benchmarks Jev and Laya against specialized rerankers on BEIR datasets
laya-first-try
diemrt
Finds and ranks local files with Laya, with CPU and OpenVINO inference options
eval_laya_mcp
Ayanshefeek
A Python package and MCP server use Laya to judge agent and RAG outputs
routewise-support-agent
sami-rk
Routes customer-support messages with local Laya decisions and handles replies, tools, and knowledge retrieval
Filter and verify search results
zero-api-key-web-search searches the web without API keys and can add a local Laya relevance sieve:
pip install "zero-api-key-web-search[laya]" # pulls laya + torch
zero-search "react state management" --laya --laya-threshold 0.6 --json
zero-verify "Python 3.13 is the latest stable release" --laya --json
Without Laya installed, it falls back to a lexical verifier.
RAG claim checking
layaAsRagJudge runs the whole pipeline in the browser: chunking, MiniLM embeddings, top-k retrieval, then a Laya question asking whether the evidence supports the claim. An evaluation page scores 72 labelled claims.
GraphRAG
laya-jev-GraphRAG uses score, noul and choice questions for edge verification, entity disambiguation, A* traversal and a hallucination gate. It works across Neo4j, Memgraph, Apache AGE and Kùzu, with local Laya or cloud Jev.
Code retrieval
laya-codex ranks code for Claude Code with tree-sitter, BM25 and a Laya re-ranker (tindang/laya-code).
Long documents
laya-multilingual reads up to 8,192 tokens with max_len=8192. The core README reports 16 to 18 of 20 requests correct with up to about 4,000 tokens of text, and more variable results beyond that.
result = router.predict(long_document, questions, model="multilingual", max_len=8192)
Caveat: re-ranking
ai-experiments (nadeem4) re-ranked BM25 results for all 323 BEIR NFCorpus test queries. Jev improved nDCG@10 by +0.0347 and a MiniLM cross-encoder by +0.0204, while both Laya checkpoints ranked worse than doing nothing. Use Laya for yes/no relevance gates and claim checks. Measure before using it to reorder a ranked list.
More ways to use Laya