How to Ingest REST API Data & Build a Graph-Based RAG with dlt + Cognee: From Raw Docs to Reasoning
Want to move beyond plain vector search? During this workshop, AI engineer Hiba Jamal shows how to take raw CSV files and messy API documentation, pipe them through Data Load Tool (dlt), and turn everything into a query‑ready knowledge graph with Cognee.
You’ll see how to:
Ingest and process data with dlt.
Build a knowledge graph from your data using Cognee.
Use node sets to organize and filter information.
Apply an ontology for better structure and more accurate results.
Push your graph to Neo4j and run queries with Cypher.
We’ll cover practical steps for working with both structured datasets and unstructured sources. You’ll also learn why knowledge graphs improve retrieval and how to scale your pipeline efficiently.
Links:
Workshop: https://github.com/DataTalksClub/llm-...
Notebook: https://colab.research.google.com/dri...
Cognee other LLM models: https://docs.cognee.ai/how-to-guides/...
Timecodes:
00:00 Hiba’s background and agenda
05:18 Intro to DT and data ingestion
08:46 Rag systems and Cognney overview
15:24 Rag challenges and Cognney vs LLM
27:10 Node sets and NYC taxi demo
41:23 Taxi graph exploration and costs
50:51 Knowledge graph queries and API doc demo
57:43 Ontology and API doc sources
1:04:40 API data in Cognney and Neo4j demo
1:14:39 Query examples and demo comparison
1:20:44 Q&A, large-scale DT use, project ideas
1:27:19 Datasets, project ideas, and closing
Connect with DataTalks.Club:
Join the community - https://datatalks.club/slack.html
Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/...
Check other upcoming events - https://lu.ma/dtc-events
GitHub: https://github.com/DataTalksClub
LinkedIn - / datatalks-club
Twitter - / datatalksclub
Website - https://datatalks.club/
Connect with Alexey
Twitter - / al_grigor
Linkedin - / agrigorev
Check our free online courses:
ML Engineering course - http://mlzoomcamp.com
Data Engineering course - https://github.com/DataTalksClub/data... uj7jh1c6xg
MLOps course - https://github.com/DataTalksClub/mlop...
Analytics in Stock Markets - https://github.com/DataTalksClub/stoc...
LLM course - https://github.com/DataTalksClub/llm-...
Open-source LLM course: https://github.com/DataTalksClub/open...
AI Dev Tools course: https://github.com/DataTalksClub/ai-d...
👉🏼 Read about all our courses in one place - https://datatalks.club/blog/guide-to-...
👋🏼 Support/inquiries
If you want to support our community, use this link - https://github.com/sponsors/alexeygri...
If you’re a company, reach us at [email protected]