I built a Read.ai connector for Cognee. Importing once wasn’t enough

说明与用途

为 Cognee 构建的 Read.ai 连接器，通过完整的上游对账和增量下游处理，保持会议报告的最新状态，避免重复处理未更改的文档。

问题

Meeting reports imported into Cognee become stale when later edited, because the connector only imports once and does not detect changes.

结果

The connector successfully keeps the Cognee database in sync with Read.ai reports, handling updates, deletions, and permission errors while avoiding unnecessary re‑processing of unchanged documents.

工作流

• Select meeting IDs or a date range and optional summary/transcript/metrics inclusion
• Run sync_read_ai() which ingests, recovers, processes with Cognee, and verifies completion
• During sync, re‑fetch selected reports, render content, compute hashes, compare to stored hashes
• If hash differs, re‑process and replace document; if report missing, delete document
• After successful ingestion and verification, advance the successful checkpoint

证据

importing meeting reports is useful, but those reports do not stop changing once they reach your database.

来源

full upstream reconciliation with incremental downstream processing

来源

The successful checkpoint comes last—after ingestion, Cognee’s processing step, and verification.

来源

149 passing tests on Python 3.12.15, with no failures, errors, or skips.

来源