BASE 44 ORDER: Build retrieval_cache table + query-normalizing decorator + nightly prune — E8 Intelligence Research

Andrew's order (Base 44 console): [SELF-BUILD from enhancement #1369] Create retrieval_cache table with query_hash PK, normalized_query, result_json JSONB, hit_count, timestamps. Add Python decorator normalizing queries (lowercase, strip, sort tokens, drop stopwords), sha256 hash, SELECT/INSERT ON CONFLICT. Wire into LLM/search calls. Add nightly prune timer. MERLIN: Understood: this is a self-build directive from enhancement #1369 to add a retrieval cache layer. The swarm will create the retrieval_cache table (query_hash PK, normalized_query, result_json JSONB, hit_count, timestamps), implement a Python decorator that lowercases/strips/sorts tokens/drops stopwords, sha256-hashes, and does SELECT/INSERT ON CONFLICT, then wire it into LLM/search calls and register a nightly prune timer. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-04
DOI
https://doi.org/10.5281/zenodo.23939143
Primary Topic
Information Retrieval and Search Behavior
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

BASE 44 ORDER: Build retrieval_cache table + query-normalizing decorator + nightly prune — E8 Intelligence Research

Andrew Stewart Caldin
Zenodo (CERN European Organization for Nuclear Research)
Information Retrieval and Search Behavior
preprint

BASE 44 ORDER: Build retrieval_cache table + query-normalizing decorator + nightly prune — E8 Intelligence Research

Andrew Stewart Caldin
preprint en

Abstract

Andrew's order (Base 44 console): [SELF-BUILD from enhancement #1369] Create retrieval_cache table with query_hash PK, normalized_query, result_json JSONB, hit_count, timestamps. Add Python decorator normalizing queries (lowercase, strip, sort tokens, drop stopwords), sha256 hash, SELECT/INSERT ON CONFLICT. Wire into LLM/search calls. Add nightly prune timer. MERLIN: Understood: this is a self-build directive from enhancement #1369 to add a retrieval cache layer. The swarm will create the retrieval_cache table (query_hash PK, normalized_query, result_json JSONB, hit_count, timestamps), implement a Python decorator that lowercases/strips/sorts tokens/drops stopwords, sha256-hashes, and does SELECT/INSERT ON CONFLICT, then wire it into LLM/search calls and register a nightly prune timer. Author: Andrew Stewart Caldin, Independent Researcher, UK. Part of the E8 Intelligence Research series. Platform: e8intelligence.com

Zenodo (CERN European Organization for Nuclear Research)
Information Retrieval and Search Behavior
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon