Canny + Cognee: a feedback connector for AI agent memory

Описание и применение

После синхронизации Canny‑посты, включая голосования и комментарии, попадают в граф знаний Cognee, позволяя задавать вопросы о наиболее популярных запросах и причинах их популярности.

Задача

Product teams need to answer what users want most and why, but Canny’s comments are scattered across posts.

Результат

After syncing, Cognee can answer complex questions about feature requests, combining vote counts and comment analysis in a single query.

Рабочий процесс

• Install cognee-community-connector-canny (pins cognee==1.4.0).
• Export CANNY_API_KEY and LLM_API_KEY (or pass api_key=).
• Call cognee.remember(canny_source(), dataset_name="canny").
• Query with cognee.search(query_text="Which feature requests have the most votes, and why do users want them?", query_type=cognee.SearchType.GRAPH_COMPLETION, datasets=["canny"]).

Доказательства

Short answer: install cognee-community-connector-canny, set CANNY_API_KEY and LLM_API_KEY, and pass canny_source() to cognee.remember().

Источник

After a sync, cognee.search answers questions against the graph.

Источник

Canny’s posts/list endpoint has no "updated after" filter, and Canny has no feed of deleted posts.

Источник