Better decision making with always up-to-date vector databases
summary
Mantium automates an end-to-end pipeline that pulls Slack, Notion, and Zoom, applies Whisper transcription, GPT-3.5-Turbo summarization, cleaning and splitting, then generates OpenAI embeddings and pushes vectors to Pinecone with an hourly sync. The demo builds combined datasets, creates a ChatGPT plugin endpoint, and shows summaries, reconstructed P&L tables and charts — all working live. Connectors also support Redis, Milvus and Faiss for flexible vector storage.
AI-written summary · about
chapters (7)
- 0:00Introduction to mantium
- 2:02Architecture and overview
- 3:41Data connection process
- 5:44Data transformation steps
- 9:18Building the AI plugin
- 11:46Querying the AI model
- 15:58Conclusion and summary
related talks
01h 03mWhat comes after ChatGPT? Vector Databases - the Simple and powerful future of ML?
50mWhat Comes After ChatGPT? Vector Databases - the Simple & Powerful Future of ML?
36mUnleashing the Power of Vector Databases for AI-Driven Applications
58mDemystifying GenAI: Build a ChatGPT App with Vector Store
29mFrom Quick Wins to Revolutionising Productivity & CX with GenAI
45mManaging Data & Analytics Projects Effectively
17mThe keys to success with Generative AI and Vector Databases
48mA fun and absurd introduction to Vector Databases