ecommerce_ops · ecommerce · workflow

DoorDash improves search retrieval using LLMs and RAG, increasing dish carousel trigger rate by ~30%

DoorDash's search system had to handle complex multi-requirement queries while enforcing hard retrieval rules such as dietary restrictions, but traditional query segmentation methods (PMI, n-gram analysis) fell short on complex or ambiguous queries, and embedding-based retrieval systems returned imprecise candidate sets that ignored hard constraints.

How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · User submits search query
Users commonly conduct searches using precise queries that compound multiple requirements.
Tools used
LLMsRAGANNBM25knowledge graph
Outcome

After deploying LLM-based query understanding with RAG entity linking, DoorDash achieved nearly a 30% increase in dish carousel trigger rate, more than a 2% increase in whole page relevance for dish-intent queries, and a further 1.6% WPR improvement from a retrained ranker, with same-day conversions also rising.

What failed first

Traditional statistical query segmentation methods (PMI and n-gram analysis) could not capture contextual relationships in complex queries, and standalone embedding-based retrieval systems returned imprecise results that ignored hard constraints such as dietary preferences.

Results
Time savedrise in same-day conversions
Volumeless than one percent
Source

https://careersatdoordash.com/blog/how-doordash-leverages-llms-for-better-search-retrieval/

How we source this →

Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes.
data extractionknowledge searchragknowledge baseproduct cataloghuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedecommerceaccuracy improvementconversion increasethroughput increasetechnical build writeupecommerce opsextract classify routerag answering