@sanity/embeddings-index-ui 1.1.2 → 1.1.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +7 -7
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -1,10 +1,11 @@
|
|
|
1
|
-
#
|
|
1
|
+
# Sanity Embeddings Index UI
|
|
2
2
|
|
|
3
|
-
>
|
|
3
|
+
> Using this feature requires Sanity to send data to OpenAI[.]com, and Pinecone[.]io for storing vector interpretations of documents.
|
|
4
4
|
|
|
5
|
-
Sanity Studio plugins that interact with the `/embeddings-index` HTTP API.
|
|
5
|
+
Sanity Studio v3 plugins that interact with the `/embeddings-index` HTTP API.
|
|
6
|
+
|
|
7
|
+
The Embeddings Index API enables creating named embeddings vector indexes.
|
|
6
8
|
|
|
7
|
-
The embeddings index API allows the creation of named embeddings vector indexes.
|
|
8
9
|
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.
|
|
9
10
|
A [GROQ projection](https://www.sanity.io/docs/query-cheat-sheet) is applied to matching documents before vectorization.
|
|
10
11
|
|
|
@@ -28,15 +29,14 @@ npm install @sanity/embeddings-index-ui
|
|
|
28
29
|
* [embeddingsIndexReferenceInput](#embeddings-index-reference-input): semantic search mode for reference inputs
|
|
29
30
|
* [embeddingsIndexDashboard](#embeddings-index-dashboard): manage indexes in a Sanity Studio UI tool
|
|
30
31
|
|
|
31
|
-
For more information about
|
|
32
|
+
For more information about using the plugins, see the relevant sections below.
|
|
32
33
|
|
|
33
34
|
## Embeddings index reference input
|
|
34
35
|
|
|
35
36
|
<img width="619" alt="image" src="https://github.com/sanity-io/sanity/assets/835514/55d372fe-c5fe-40dd-882b-10c6e8794442">
|
|
36
37
|
|
|
37
38
|
The `embeddingsIndexReferenceInput` plugin allows reference fields to opt in to embeddings index search.
|
|
38
|
-
This enables users to search for references using natural language, and to retrieve documents based on semantic meaning,
|
|
39
|
-
rather than exact word matches.
|
|
39
|
+
This enables users to search for references using natural language, and to retrieve documents based on semantic meaning, rather than exact word matches.
|
|
40
40
|
|
|
41
41
|
### Usage
|
|
42
42
|
|