I Built a QuickBooks Connector for an AI Knowledge Graph — Here’s What I Learned

说明与用途

构建 QuickBooks 连接器，将财务记录导入 Cognee AI 知识图谱，实现增量同步、删除检测和自动化测试。

问题

Integrate QuickBooks Online financial data into an AI knowledge graph while maintaining data consistency and handling authentication, sync, and deletion.

结果

Implemented a robust QuickBooks connector with incremental sync, deletion detection, retry handling, and automated tests, enabling seamless ingestion of financial records into Cognee’s AI knowledge graph.

工作流

• Authenticate via OAuth 2.0 and refresh tokens
• Retrieve records from QuickBooks API
• Format records into Markdown documents
• Send documents through Cognee ingestion workflow
• Incrementally sync using Metadata.LastUpdatedTime
• Detect deletions via QuickBooks CDC
• Reconcile on empty sync to avoid accidental deletions
• Handle retries and safeguard against accidental deletion

证据

I worked on a connector that brings QuickBooks financial records into Cognee's AI memory workflow.

来源

The connector supports: Ingesting invoices, vendor bills, and credit memos. OAuth 2.0 authentication and token refresh. Incremental sync to retrieve new and updated records. Deletion detection to help remove outdated information. Retry handling and safeguards against accidental deletion. Automated tests and offline pipeline verification using DuckDB.

来源

The submitted test suite documents 12 passing tests, covering data formatting, synchronization, deletion handling, and retry behavior.

来源

This contribution taught me that building a data connector is about much more than calling an API.

来源