Connect a source.
S3, webhooks, or a crawl. Chunking policies live in the dataset.
Search and RAG API
Glean the index. Rank with intent.
Gleanor is hybrid search, RAG, and recommendations with knobs a merchandiser can turn. Engineers connect the source. Operators bias recency, tags, and synonyms from Studio, and the API reads the published profile.
Method
How Gleanor ships
Publish a profile.
Operators set weights. Engineers keep the query shape.
Serve.
Search, rag, and recommend endpoints share one corpus id.
Stack
Product pillars
Hybrid
Sparse plus dense, fused. Date recency and field weights in the same query.
RAG
Cited chunks sized for the window. Filters that survive the generator.
Recommend
Item-to-item and user-to-item from the same index.
Studio
Non-engineers tune ranking. The API reads the same published profile.
Start
A working key in one afternoon.
Write founder@gleanor.biz. You get a test token, a sample project, and a 30-minute walkthrough on the product you actually want to run.
See pricing