Reranking guides for WordPress & WooCommerce

Provide better search and generative AI experiences with Vertex AI Search

Vertex AI search is (finally) catching up with advanced RAG features like VLM document parsing, chunking, citations, re-ranking, grounding generation/verification. As usual, you will have to choose between an all-in-one closed-source monolytic solution like this or aggregating the best open-source solutions. But this now looks, at least on paper, like a solid RAG/search solution with the key advantage of being serverless and scalable end-to-end. Similar to the new features of Amazon Bedrock knowledge bases https://aws.amazon.com/bedrock/knowledge-bases/. It is not easy to clone this with disparate components without investing time and money. Contact us if you want to build a RAG in your WordPress.

Did you know that you can “officially” rerank Opensearch search (AWS or locally hosted) with Amazon Personalize?

Steps: 1. Install the “opensearch-search-processor” plugin into Opensearch 2. Create an Opensearch reranking pipeline targeting an Amazon Personalize campaign 3. Configure Opensearch queries to use the reranking pipeline 4. Pass meta informations to queries like the user-id And now the good news for WordPress lovers: both OpenSearch search (AWS and open source) and Amazon Personalize are integrated into WPSolr Enterprise.

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/