Building AI Agent Memory for Prefect Workflows with Cognee and dlt

说明与用途

将 Prefect 与 Cognee 连接，安全同步工作流元数据，使 AI 代理能够即时获取流程和错误的上下文。

问题

AI assistants lack contextual memory of orchestration topology, making debugging and failure analysis difficult.

结果

The connector securely syncs Prefect metadata into Cognee, enabling AI agents to query pipeline states, detect failures, and perform root‑cause analysis without leaking secrets.

工作流

• Install cognee and connector via pip
• Configure PREFECT_API_URL (and PREFECT_API_KEY for Cloud)
• Create a prefect_source with desired resources and states
• Run cognee.remember to ingest data
• Query Cognee with cognee.search for insights

证据

Strict Zero-Secret Parameter Policy: The connector parses parameters on deployments and runs, strictly rendering parameter keys only (e.g. Parameters (keys only): batch_size, target_table), ensuring zero passwords or API keys are ever committed to memory.

来源

Merge Disposition with Tombstones: Configured with write_disposition="merge" and columns={"_deleted": {"data_type": "bool", "hard_delete": True}}. When an entity is deleted upstream, a tombstone row is emitted, enabling Cognee's orphan_cleanup to purge it from relational, graph, and vector stores without wiping the dataset.

来源

42 passed in 22.84s

来源