Uploaded August 2025 | Updated September 2026, 8 hours ago
Elysia is Weaviate's new open source, agentic RAG framework that goes way beyond simple text-in, text-out chatbots. It dynamically displays data, learns from user feedback, and chunks documents on-demand. Built with pure Python logic and DSPy, it's designed to be the next evolution beyond traditional RAG pipelines.
What it does:
• Uses decision trees to choose the right tools and display formats
• Analyzes your data structure to understand what you're working with
• Learns from user feedback to improve responses over time
• Provides transparency into its decision-making process
• Works as both a full-featured web app and Python library
The system connects to Weaviate Cloud instances and automatically generates search filters and parameters from natural language queries. Installation is simple with `pip install elysia-ai` .
GitHub: github.com/weaviate/elysia
Demo: elysia.weaviate.io
Blog post: weaviate.io/blog/elysia-agentic-rag
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT WITH US ▬▬▬▬▬▬▬▬▬▬▬▬
- Visit weaviate.io
- Star us on GitHub github.com/weaviate/weaviate
- Stay updated and subscribe to our newsletter: newsletter.weaviate.io
- Try out Weaviate Cloud for free here: https://console.weaviate.cloud/
Got a question?
- Forum: forum.weaviate.io
- Slack: weaviate.io/slack
Connect with us on
- Twitter: twitter.com/weaviate_io
- LinkedIn: linkedin.com/company/weaviate-io
00:00 - Introduction
01:17 - Overview of the framework
02:13 - Agentic decision tree architecture
03:20 - Dynamic data displays
04:01 - Automatic data expertise
04:26 - Real-world example: powering Glowe's chat
05:29 - Other cool features
06:39 - Online demo
09:55 - Installation and setup
12:25 - Using Elysia as a Python framework
13:04 - Outro
Elysia is Weaviate's new open source, agentic RAG framework that goes way beyond simple text-in, text-out chatbots. It dynamically displays data, learns from user feedback, and chunks documents on-demand. Built with pure Python logic and DSPy, it's designed to be the next evolution beyond traditional RAG pipelines.
What it does:
• Uses decision trees to choose the right tools and display formats
• Analyzes your data structure to understand what you're working with
• Learns from user feedback to improve responses over time
• Provides transparency into its decision-making process
• Works as both a full-featured web app and Python library
The system connects to Weaviate Cloud instances and automatically generates search filters and parameters from natural language queries. Installation is simple with `pip install elysia-ai` .
GitHub: github.com/weaviate/elysia
Demo: elysia.weaviate.io
Blog post: weaviate.io/blog/elysia-agentic-rag
▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT WITH US ▬▬▬▬▬▬▬▬▬▬▬▬
- Visit weaviate.io
- Star us on GitHub github.com/weaviate/weaviate
- Stay updated and subscribe to our newsletter: newsletter.weaviate.io
- Try out Weaviate Cloud for free here: https://console.weaviate.cloud/
Got a question?
- Forum: forum.weaviate.io
- Slack: weaviate.io/slack
Connect with us on
- Twitter: twitter.com/weaviate_io
- LinkedIn: linkedin.com/company/weaviate-io
00:00 - Introduction
01:17 - Overview of the framework
02:13 - Agentic decision tree architecture
03:20 - Dynamic data displays
04:01 - Automatic data expertise
04:26 - Real-world example: powering Glowe's chat
05:29 - Other cool features
06:39 - Online demo
09:55 - Installation and setup
12:25 - Using Elysia as a Python framework
13:04 - Outro
