GoldenMatch

Find duplicate records in 30 seconds.

От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Analyze Data: Profile data, detect domain, recommend ER strategy
  • Auto Configure: Generate optimal matching config from data analysis
  • Agent Deduplicate: Run full ER pipeline with confidence gating and reasoning

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Find duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.

Список инструментов сервера (27)

Технические названия из tools/list. Нужны только разработчикам.

analyze_dataProfile data, detect domain, recommend ER strategy
auto_configureGenerate optimal matching config from data analysis
agent_deduplicateRun full ER pipeline with confidence gating and reasoning
agent_match_sourcesMatch two files with intelligent strategy selection
agent_explain_pairNatural language explanation for a record pair
agent_explain_clusterExplain why records are in the same cluster
agent_review_queueGet borderline pairs awaiting approval
agent_approve_rejectApprove or reject a review queue pair
agent_compare_strategiesCompare ER strategies on your data
suggest_pprlCheck if data needs privacy-preserving matching
get_statsGet dataset statistics: record count, cluster count, match rate, cluster sizes.
find_duplicatesFind duplicate matches for a record. Provide field values to search against the loaded dataset.
explain_matchExplain why two records match or don't match. Shows per-field score breakdown.
list_clustersList duplicate clusters found in the dataset. Returns cluster IDs, sizes, and member counts.
get_clusterGet details of a specific cluster: all member records and their field values.
get_golden_recordGet the merged golden (canonical) record for a cluster.
match_recordMatch a single record against the loaded dataset in real-time. Paste a record's fields and instantly see if it matches any existing record. Uses the configured matchkeys, scorers, and thresholds. Example: {"name": "John Smith", "email": "john@test.com", "zip": "10001"}
unmerge_recordRemove a record from its cluster. The record becomes a singleton. Remaining cluster members are re-clustered using stored pair scores. Use this to fix bad merges.
shatter_clusterBreak an entire cluster into individual records. All members become singletons. Use when a cluster is completely wrong.
suggest_configAnalyze bad merges and suggest config changes. Provide examples of incorrect merges (pairs that should NOT have matched) and GoldenMatch will identify which fields/thresholds to tighten. Example: [{"record_a": {...}, "record_b": {...}, "reason": "different people"}]
profile_dataGet data quality profile: column types, null rates, unique counts, sample values.
export_resultsExport matching results to a file (CSV or JSON).
list_domainsList available domain extraction rulebooks (built-in + user-defined).
create_domainCreate a custom domain extraction rulebook. Define patterns for a specific data domain (medical devices, automotive parts, real estate, etc.).
test_domainTest a domain extraction rulebook against sample records. Shows what features would be extracted from the loaded data.
pprl_auto_configAnalyze the loaded dataset and recommend optimal PPRL (privacy-preserving record linkage) configuration. Returns recommended fields, bloom filter parameters, threshold, and explanation.
pprl_linkRun privacy-preserving record linkage between two parties' data. Computes bloom filters, matches records without sharing raw data. Specify fields, threshold, and security level.
GoldenMatch: подключить к Claude, ChatGPT, Cursor · Connectors.fun