Cognee organizes your data into AI memory. It builds structured AI memory by transforming raw data into a modular, queryable knowledge graph powered by embeddings. Like any complex system, it depends on many hyperparameters that shape performance in subtle ways. This talk shows how systematic tuning can improve AI memory, what current evaluation methods reveal (and miss), and why future progress will depend as much on better evaluation and optimization as on new architectures.
talk-data.com
Topic
embeddings
1
tagged
Activity Trend
4
peak/qtr
2020-Q1
2026-Q1
Top Events
Google Cloud Next '25
2
Event-driven architecture for AI with SurrealDB
1
BLISS x Neo4j: Powering GenAI with Knowledge Graphs
1
Build Your Own CLI Chatbot with RAG Support — An All-Code, No-Slides Session
1
Agentic AI Workshop | New York City
1
AI Agents from Scratch: A Beginner's LLM Workshop
1
AI Agent Meetup Berlin: Context Engineering
1
Data Science Retreat Demo Day #41
1
AI Agents from Scratch: A Beginner's LLM Workshop
1
Session #9: Google AI Seminar (Virtual)
1
10 PyData Piraeus Meetup: LLMs with Knowledge Graphs and Information Retrieval
1
(Virtual EMEA) Do you really need a Vector Search Database?
1
Filtering by:
Lazar Obradovic
×