I gave an AI assistant a memory of PubMed - and learned why "forgetting" is the hard part

Описание и применение

Автор создал коннектор PubMed для cognee, чтобы автоматически загружать и обновлять литературу о резистентности к KRAS G12C, решая проблему «запоминания» новых статей.

Задача

A frozen LLM cannot keep up with rapidly evolving cancer research literature, such as resistance mechanisms to KRAS G12C inhibitors.

Результат

The connector ingests 155 records in 7 s, performs zero re‑fetch on the second sync, and correctly handles 10,000‑result limits, time‑zone offsets, and retractions.

Рабочий процесс

• 1. Define PubMed query string
• 2. Call cognee.remember with pubmed_source(term, mindate)
• 3. Cognee ingests XML, parses to Markdown, extracts entities
• 4. Run cognee.search with GRAPH_COMPLETION query
• 5. Agent answers using updated memory

Доказательства

The query matches 253 PubMed records in total. Limiting it to records added since 2024 left 155.

Источник

The first sync stored all 155 in about 7 seconds, using just two EFetch batches.

Источник

The second sync made zero EFetch calls and finished in about 2.4 seconds. Nothing had changed, so nothing was downloaded or sent to the LLM again.

Источник

ESearch never returns more than 10,000 PMIDs for a query.

Источник

NCBI assigns those dates in US Eastern time, though, so a run just after midnight UTC can miss records added late on the previous Eastern day.

Источник