ecommerce_ops · ecommerce · workflow
Picnic enhances grocery search retrieval with LLMs and precomputed embeddings
Picnic needed to serve a high volume of grocery search queries across multiple countries with different languages and culinary preferences, while handling typos, vague inputs, and the latency demands of real-time as-you-type search.
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 · Customer submits search query
Customers use search to navigate Picnic's broad product and recipe assortment, with millions of different search terms used in the process.
Tools used
GPT3.5-turbotext-embedding-3-smallOpenSearch
Outcome
Picnic implemented LLM-powered prompt-based description generation with precomputed embeddings and OpenSearch retrieval, aiming to improve conversion rates, click-through rates, and customer satisfaction, validated through iterative A/B testing.
Results
Volume99%
Source
https://blog.picnic.nl/enhancing-search-retrieval-with-large-language-models-llms-7c3748b26d72
Grounding & classification
Source type: technical build writeup
21 fields verified against source quotes.
content generationragproduct catalognamed customerproduction runtime claimedsource backedtools describedworkflow describedecommerceretailconversion increasecustomer satisfactiontechnical build writeupecommerce opsrag answering