- Introduces embeviz - a simple side project for exploring text embeddings
- Uses backend API with GoFiber framework and frontend UI with React and React Router
- Provides interactive charts for visualizing computed projections
- Can label texts and select options for both projections and chunking
- Offers swagger docs for the API, in-memory data store, and persistent data store with QDrant
- Uses backend API with GoFiber framework and frontend UI with React and React Router
- Provides interactive charts for visualizing computed projections
- Can label texts and select options for both projections and chunking
- Offers swagger docs for the API, in-memory data store, and persistent data store with QDrant
The article discusses the use of large language models (LLMs) as reasoning engines for powering agent workflows, focusing specifically on ReAct agents. It explains how these agents combine reasoning and action capabilities and provides examples of how they function. Challenges faced while implementing such agents are also mentioned, along with ways to overcome them. Additionally, the integration of open-source models within LangChain is highlighted.
