I Thought We Were Building a Chatbot. We Were Building Something Else.

说明与用途

Meena 是面向大学生的 AI 助手，通过引入印度文化色彩的 UI、重排层、Gemini 嵌入、Tavily 网页搜索、工具使用限制以及轻量级可观测性层，提升了相关性、成本效益和可靠性。

问题

The original AI assistant Meena was functional but lacked cultural relevance, personalized context, and robust tool‑use handling, limiting daily adoption among college students.

结果

Meena now provides culturally relevant, context‑aware answers with reduced noise and cost, and its architecture supports future personalization.

工作流

• 1. Redesign UI with Indian visual culture colors and campus motifs.
• 2. Add reranking layer using Jina to filter retrieved chunks before LLM.
• 3. Switch to Gemini embeddings for richer multimodal representation.
• 4. Integrate Tavily web‑search tool for up‑to‑date information.
• 5. Implement tool‑calling boundaries: max turns, fallbacks, final synthesis.
• 6. Build lightweight observability to log model calls, retrievals, tool usage, and failures.
• 7. Plan for user‑context personalization to tailor responses per student.

证据

We added another layer. Reranking. Jina became part of that pipeline…

来源

We gave Meena tools… Tavily became part of the tool layer…

来源

We built our own lightweight observability layer…

来源