Node.js Semantic Search for Product Support — Stable Chat Contracts for Messy Catalogs

说明与用途

内部聊天机器人使用嵌入进行对混乱产品描述的语义搜索，在调用聊天模型前执行租户过滤，并按每个阶段跟踪使用情况，提供单一凭证和账单。

问题

In‑app customer‑support chatbots need to retrieve relevant catalog items from messy product descriptions while keeping per‑tenant cost visibility and a stable API contract across provider changes.

结果

The chatbot now handles paraphrased queries with semantic search, enforces tenant boundaries before prompting the model, and tracks cost per tenant across ingestion, query, retrieval, and generation. A single credential and bill simplify operations while allowing provider flexibility.

工作流

• Normalize each catalog description and attach tenant ID
• Create and store an embedding for each description
• Embed incoming support question
• Retrieve top candidate records within tenant boundary
• Send selected records and question to chat model for answer

证据

Embeddings give the description and the incoming question comparable semantic representations.

来源

Similarity is not authorization. The tenant filter must run before the result reaches the prompt.

来源

Use one ledger row per stage. An import event needs an import ID. A live question needs a request ID.

来源

The single-key, one-bill model covers 295 routes across 20 modules.

来源