Turning Meeting Transcripts into an AI Knowledge Graph with tl;dv & Cognee

Описание и применение

Коннектор tl;dv и Cognee объединяют записи встреч в единый документ Markdown, извлекают сущности и строят граф знаний, позволяя выполнять точные запросы по участникам и задачам.

Задача

Engineering and product teams lose vital context from meetings because recordings and notes are scattered and not easily searchable.

Результат

The connector transforms raw meeting data into a knowledge graph, enabling entity‑grounded queries such as identifying who volunteered for a project and their blockers, which plain vector search cannot resolve.

Рабочий процесс

• 1. Use tl;dv API to fetch meetings, transcripts, and notes via /meetings, /meetings/{id}/transcript, /meetings/{id}/notes.
• 2. Synthesize data into a single Markdown document per meeting.
• 3. Annotate the document with DOCUMENT_SOURCE_ATTR="tldv_document" for Cognee ingestion.
• 4. Add the source to Cognee dataset and run cognify to extract entities and build the graph.
• 5. Query the knowledge graph with natural language questions via Cognee search.

Доказательства

Engineering and product teams spend dozens of hours every week in meetings. Crucial technical decisions get debated, architectural tradeoffs get resolved, and action items get assigned.

Источник

If you store meeting transcripts as plain vector chunks, multi‑speaker reasoning falls apart.

Источник

Our connector fetches and synthesizes these into a single unified Markdown document per meeting

Источник

By annotating the dlt resource with DOCUMENT_SOURCE_ATTR = "tldv_document", Cognee treats each meeting as a document node, running its NLP extraction pipeline over the executive takeaways and dialogue.

Источник

uv run pytest packages/connector/tldv/tests/test_tldv.py -v

Источник