Building Persistent AI Memory for API Specifications Using Cognee and Fern

Описание и применение

Создано постоянное знание о API с помощью Cognee и Fern, позволяющее ИИ-агентам выполнять многошаговый поиск по архитектуре API.

Задача

Standard vector retrieval (RAG) treats API endpoint schemas as plain text, fragmenting path parameters from query parameters, request bodies from response types, and error definitions from endpoint paths, preventing AI agents from accessing structured API knowledge.

Результат

The Fern connector enabled AI agents to persistently remember and reason over entire API ecosystems, providing structured, multi-hop architectural memory.

Рабочий процесс

• 1. Install cognee-community-connector-fern and cognee via pip.
• 2. Point fern_source to the Fern workspace directory.
• 3. Ingest API definitions and guides with cognee.add().
• 4. Cognify the ingested data into a knowledge graph with cognee.cognify().
• 5. Query the graph using cognee.search() with INSIGHTS query type.

Доказательства

Standard vector retrieval (RAG) fails. It treats endpoint schemas as plain text, fragmenting path parameters from query parameters, request bodies from response types, and error definitions from endpoint paths.

Источник

We built the official Fern API Documentation Connector for Cognee.

Источник

pip install cognee-community-connector-fern cognee

Источник

await cognee.search(query_type="INSIGHTS", query_text="What endpoints handle user authentication and what error types can they throw?")

Источник