From 176a59faf97be5490ae0a0b1d58d7d96712a285c Mon Sep 17 00:00:00 2001 From: Marco Spinello Date: Thu, 14 Sep 2023 22:26:23 +0200 Subject: [PATCH] fix(docs): update UI Readme to make it more consistent with CLI Readme (#4) * Make UI and CLI Readmes more consistent * Add "usage implies consent" notice to Readme --- README.md | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/README.md b/README.md index 1a5af7d..915a1d5 100644 --- a/README.md +++ b/README.md @@ -1,10 +1,11 @@ -# @sanity/embeddings-index-ui +# Sanity Embeddings Index UI -> This package contains plugins for **Sanity Studio v3**. +> Using this feature requires Sanity to send data to OpenAI[.]com, and Pinecone[.]io for storing vector interpretations of documents. -Sanity Studio plugins that interact with the `/embeddings-index` HTTP API. +Sanity Studio v3 plugins that interact with the `/embeddings-index` HTTP API. + +The Embeddings Index API enables creating named embeddings vector indexes. -The embeddings index API allows the creation of named embeddings vector indexes. An embeddings index contains embeddings for all Sanity documents matching a configured [GROQ filter](https://www.sanity.io/docs/how-queries-work) in a dataset. A [GROQ projection](https://www.sanity.io/docs/query-cheat-sheet) is applied to matching documents before vectorization. @@ -28,15 +29,14 @@ npm install @sanity/embeddings-index-ui * [embeddingsIndexReferenceInput](#embeddings-index-reference-input): semantic search mode for reference inputs * [embeddingsIndexDashboard](#embeddings-index-dashboard): manage indexes in a Sanity Studio UI tool -For more information about how to use the plugins, see the relevant sections below. +For more information about using the plugins, see the relevant sections below. ## Embeddings index reference input image The `embeddingsIndexReferenceInput` plugin allows reference fields to opt in to embeddings index search. -This enables users to search for references using natural language, and to retrieve documents based on semantic meaning, -rather than exact word matches. +This enables users to search for references using natural language, and to retrieve documents based on semantic meaning, rather than exact word matches. ### Usage