Cohere guides for WordPress & WooCommerce

Fine-tuning a reranker with synthetic LLM generated data and LLM+human annotations

Great post from HumanSignal labelstud.io to fine-tune a Cohere reranker with synthetic LLM generated data and LLM+human annotations: Generate synthetic queries from documents with a LLM (OpenAI gpt4-o here) Extract results from your retrieval system for all synthetic queries Create a label project for reranking tasks with triplet-loss (positive, hard-negative) Upload query/results in the label studio Pre-label query/results with a LLM reranker’s back-end (OpenAI gpt4-o here) Let humans complete the pre-labeling Send labeled query/results to a LLM reranking fine-tuner (Cohere here) Test your new fine-tuned reranked retrieva Original post: https://labelstud.io/blog/improving-rag-document-search-quality-with-cohere-re-ranking/

Multi-modal WooCommerce search: Elasticsearch orders + Weaviate Cohere products + Weaviate CLIP media.

— Current solution — Just finished upgrading a WooCommerce client, who already had a front-end products multi-lingual Weaviate + Cohere search, and also a 200,000 orders/coupons Elasticsearch admin search. — Needs — The client’s team had troubles searching in thousands of unlabelled media images. — New solution — After upgrading the Weaviate Kubernetes cluster to enable the CLIP module, we indexed the thousands of images. This was relatively fast, on CPUs. — Results — Now the team can search images from their content, rather than from titles and captions. This was done thanks to the WPSOLR “views”, each setup with a dedicated index. WPSOLR + Weaviate + Cohere + CLIP: https://wpsolr.com #search #clip #cohere #weaviate #woocommerce