Scaling Recommender Systems with Vector Database Infrastructure

farfetch · E-commerce · 2024 · source Agentic: no · promotional bias: low · summary-only (no fetched source) · extracted with prompt 0.5.6 (schema v2)

Generated from extraction.json — do not edit by hand. Every claim cites verbatim source evidence; stated means the quote directly asserts the claim, implied means it supports it indirectly.

Problem

Domain: recommendation infrastructure

The original Farfetch engineering article is unavailable, so the only grounded claim is that a deleted Medium post appeared to concern scaling recommender systems with Vespa/vector infrastructure.

Constraints:

The original source returns a 410 deleted-by-author page.
No implementation architecture, metrics, or outcomes are recoverable from the source.
Any extraction must avoid inferring Farfetch-specific technical details beyond the metadata summary.

Architecture

No source-backed implementation architecture is available. The ZenML summary says the deleted article appeared to discuss Farfetch using Vespa for recommender systems, but the source cannot support detailed extraction.

Gotchas (what bit them)

Deleted upstream sources block grounded technical extraction.

Root cause: The Medium article returns a 410 deleted-by-author page.

Resolution: Keep the extraction summary-only and avoid implementation claims that cannot be cited.

“The original article, titled "Scaling Recommenders Systems with Vespa," has been deleted by its author and returns a 410 Gone HTTP error.”summary, stated

Evaluation

No evaluation approach is recoverable from the deleted source.

“no technical details, results, or specific implementation information can be extracted as the content is no longer available.”summary, stated

Outcomes

Summary-only extraction. The fetched source exists but contains a 410 deleted-by-author page, not the case study content.

“This entry serves primarily as a placeholder and acknowledgment that valuable technical content from Farfetch's engineering team on scaling recommendation systems existed but is no longer publicly available.”summary, stated