DoorDash 如何利用 LLMs 提升搜索检索
At DoorDash, users commonly conduct searches using precise queries that compound multiple requirements. As a result, our search system has to be flexible enough to generalize well to novel queries while also allowing us to enforce specific rules to ensure search result quality.
在DoorDash，用户通常使用精确的查询进行搜索，这些查询合并了多个要求。因此，我们的搜索系统必须足够灵活，以便能够很好地泛化到新查询，同时还允许我们执行特定规则以确保搜索结果的质量。
For instance, a query such as “vegan chicken sandwich,” for which a retrieval system that relies on document similarity — such as an embedding-based system — could retrieve documents (i.e., items) such as:
例如，查询“素食鸡肉三明治，”对于依赖文档相似性的检索系统——例如基于嵌入的系统——可以检索到的文档（即商品）如下：
- Vegan sandwiches
- 素食三明治
- Vegetarian sandwiches
- 素食三明治
- Chicken sandwiches
- 鸡肉三明治
- Vegan chicken sandwiches
- 素食鸡肉三明治
For these keywords only the last set on that list matches the user intent exactly. But preferences may vary for different attributes. For instance, a consumer might be open to considering any vegan sandwich as an alternative but would reject a chicken sandwich that is not vegan; dietary restrictions often take precedence over other attributes, like protein choices. Several approaches could be used to show users only the most relevant results. At DoorDash, we believe a flexible hybrid system is most likely to meet our needs; a keyword-based retrieval system, combined with robust document and keyword understanding, can effectively enforce such rules as ensuring that only vegan items are retrieved. Here, we will detail how we have used large language models, or LLMs, to improve our retrieval system and give consumers more accurate search results.
对于这些关键词，只有列表中的最后一组完全符合用户意图。但不同属性的偏好可能会有所不同。例如，消费者可能愿意考虑任何素食三明治作为替代品，但会拒绝非素食的鸡肉三明治；饮食限制通常优先于其他属性，如蛋白质选择。可以使用几种方法向用户展示最相关的结果。在DoorDash，我们相信灵活的混合系统最有可能满足我们的需求；基于关键词的检索系统，结合强大的文档和关键词理解，可以有效地执行确保仅检索素食项目等规则。在这里，我们将详细说明我们如何使用大型语言模型（LLMs）来改善我们的检索系统，并为消费者提供更准确的搜索结果。
Typical search engines contain different stages, which can be separated into two main journeys: one for documents and another for queries. At DoorDash, documents refer to items or stores/r...