Spring/spring-ai
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

updated sample code in chroma documentation (#291)

Browse Source
This commit is contained in:
Ricken BAZOLO
2024-02-06 04:38:16 +01:00
committed by GitHub
parent dfbea8cee1
commit 0e58b10128
1 changed files with 16 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
spring-ai-docs/src/main/antora/modules/ROOT/pages/api/vectordbs/chroma.adoc
View File

@@ -65,7 +65,7 @@ public RestTemplate restTemplate() {
@Bean
public ChromaApi chromaApi(RestTemplate restTemplate) {
String chromaUrl = "http://localhost:8000";
ChromaApi chromaApi = ChromaApi(chromaUrl, restTemplate);
ChromaApi chromaApi = new ChromaApi(chromaUrl, restTemplate);
return chromaApi;
}
----
@@ -101,14 +101,14 @@ Add the documents to your vector store:
[source,java]
----
vectorStore.add(List.of(document));
vectorStore.add(documents);
----
And finally, retrieve documents similar to a query:
[source,java]
----
List<Document> results = vectorStore.similaritySearch("Spring", 5);
List<Document> results = vectorStore.similaritySearch("Spring");
----
If all goes well, you should retrieve the document containing the text "Spring AI rocks!!".
@@ -121,8 +121,12 @@ For example, you can use either the text expression language:
[source,java]
----
vectorStore.similaritySearch("The World", TOP_K, SIMILARITY_THRESHOLD,
"author in ['john', 'jill'] && article_type == 'blog'");
vectorStore.similaritySearch(
SearchRequest.defaults()
.withQuery("The World")
.withTopK(TOP_K)
.withSimilarityThreshold(SIMILARITY_THRESHOLD)
.withFilterExpression("author in ['john', 'jill'] && article_type == 'blog'"));
----
or programmatically using the `Filter.Expression` DSL:
@@ -131,10 +135,13 @@ or programmatically using the `Filter.Expression` DSL:
----
FilterExpressionBuilder b = new FilterExpressionBuilder();
vectorStore.similaritySearch("The World", TOP_K, SIMILARITY_THRESHOLD,
b.and(
b.in(List.of("john", "jill")),
b.eq("article_type", "blog")).build());
vectorStore.similaritySearch(SearchRequest.defaults()
.withQuery("The World")
.withTopK(TOP_K)
.withSimilarityThreshold(SIMILARITY_THRESHOLD)
.withFilterExpression(b.and(
b.in("john", "jill"),
b.eq("article_type", "blog")).build()));
----
NOTE: Those (portable) filter expressions get automatically converted into the proprietary Chroma `where` link:https://docs.trychroma.com/usage-guide#using-where-filters[filter expressions].