[v1.15.0] Text index documentation (#1698)

* phrase matching documentation * mention incompatibility with prefix tokenizer * nvm, it works well * fix rust snippet * fix python snippet * Update qdrant-landing/content/documentation/headless/snippets/create-payload-index/simple-full-text/csharp.md * [1.15] Text Index Documentation (#1796) * wip * add snippets for simple text index creation and phrase index separatelly * add some stopwords snippets + stopwords description * add stemmer snippets * docs: Stemmer, stop words Go snippets Signed-off-by: Anush008 <anushshetty90@gmail.com> * docs: Stemmer, stop words Java snippets Signed-off-by: Anush008 <anushshetty90@gmail.com> * docs: Stemmer, stop words C# snippets Signed-off-by: Anush008 <anushshetty90@gmail.com> * fix: http, TS stemmer snippets Signed-off-by: Anush008 <anushshetty90@gmail.com> * docs: Nit fixes indexing.md Signed-off-by: Anush008 <anushshetty90@gmail.com> * lowercase stemmer is intended for consistency --------- Signed-off-by: Anush008 <anushshetty90@gmail.com> Co-authored-by: Anush008 <anushshetty90@gmail.com> --------- Signed-off-by: Anush008 <anushshetty90@gmail.com> Co-authored-by: Anush <anushshetty90@gmail.com> Co-authored-by: Andrey Vasnetsov <andrey@vasnetsov.com>
2026-10-10 21:38:30 +02:00 · 2025-07-18 13:24:00 +02:00
parent fe7a45a4ad
commit ef31a4afe0
39 changed files with 697 additions and 61 deletions
@@ -0,0 +1,2 @@
+This code snippet demonstrates how to create a full-text index for a specified field in a collection with stemmer configuration.
+Stemmer configuration allows to apply stemming to input words, stemmer configuration contains 2 options - type of the stemmer (snowball), and desired language (english).
@@ -0,0 +1,26 @@
+```csharp
+using Qdrant.Client;
+using Qdrant.Client.Grpc;
+
+var client = new QdrantClient("localhost", 6334);
+
+await client.CreatePayloadIndexAsync(
+	collectionName: "{collection_name}",
+	fieldName: "name_of_the_field_to_index",
+	schemaType: PayloadSchemaType.Text,
+	indexParams: new PayloadIndexParams
+	{
+		TextIndexParams = new TextIndexParams
+		{
+			Tokenizer = TokenizerType.Word,
+			Stemmer = new StemmingAlgorithm
+			{
+				Snowball = new SnowballParams
+				{
+					Language = "english"
+				}
+			}
+		}
+	}
+);
+```
@@ -0,0 +1,25 @@
+```go
+import (
+    "context"
+
+    "github.com/qdrant/go-client/qdrant"
+)
+
+client, err := qdrant.NewClient(&qdrant.Config{
+    Host: "localhost",
+    Port: 6334,
+})
+
+client.CreateFieldIndex(context.Background(), &qdrant.CreateFieldIndexCollection{
+	CollectionName: "{collection_name}",
+	FieldName:      "name_of_the_field_to_index",
+	FieldType:      qdrant.FieldType_FieldTypeText.Enum(),
+	FieldIndexParams: qdrant.NewPayloadIndexParamsText(
+		&qdrant.TextIndexParams{
+			Tokenizer: qdrant.TokenizerType_Word,
+			Stemmer: qdrant.NewStemmingAlgorithmSnowball(&qdrant.SnowballParams{
+				Language: "english",
+			}),
+		}),
+})
+```
@@ -0,0 +1,14 @@
+```http
+PUT /collections/{collection_name}/index
+{
+    "field_name": "name_of_the_field_to_index",
+    "field_schema": {
+        "type": "text",
+        "tokenizer": "word",
+        "stemmer": {
+            "type": "snowball",
+            "language": "english"
+        }
+    }
+}
+```
@@ -0,0 +1,34 @@
+```java
+import io.qdrant.client.QdrantClient;
+import io.qdrant.client.QdrantGrpcClient;
+import io.qdrant.client.grpc.Collections.PayloadIndexParams;
+import io.qdrant.client.grpc.Collections.PayloadSchemaType;
+import io.qdrant.client.grpc.Collections.SnowballParams;
+import io.qdrant.client.grpc.Collections.StemmingAlgorithm;
+import io.qdrant.client.grpc.Collections.TextIndexParams;
+import io.qdrant.client.grpc.Collections.TokenizerType;
+
+QdrantClient client =
+    new QdrantClient(QdrantGrpcClient.newBuilder("localhost", 6334, false).build());
+
+client
+    .createPayloadIndexAsync(
+        "{collection_name}",
+        "name_of_the_field_to_index",
+        PayloadSchemaType.Text,
+        PayloadIndexParams.newBuilder()
+            .setTextIndexParams(
+                TextIndexParams.newBuilder()
+                    .setTokenizer(TokenizerType.Word)
+                    .setStemmer(
+                        StemmingAlgorithm.newBuilder()
+                            .setSnowball(
+                                SnowballParams.newBuilder().setLanguage("english").build())
+                            .build())
+                    .build())
+            .build(),
+        true,
+        null,
+        null)
+    .get();
+```
@@ -0,0 +1,18 @@
+```python
+from qdrant_client import QdrantClient, models
+
+client = QdrantClient(url="http://localhost:6333")
+
+client.create_payload_index(
+    collection_name="{collection_name}",
+    field_name="name_of_the_field_to_index",
+    field_schema=models.TextIndexParams(
+        type="text",
+        tokenizer=models.TokenizerType.WORD,
+        stemmer=models.SnowballParams(
+            type=models.Snowball.SNOWBALL,
+            language=models.SnowballLanguage.ENGLISH
+        )
+    ),
+)
+```
@@ -0,0 +1,24 @@
+```rust
+use qdrant_client::qdrant::{
+    CreateFieldIndexCollectionBuilder,
+    TextIndexParamsBuilder,
+    FieldType,
+    TokenizerType,
+};
+use qdrant_client::Qdrant;
+
+let client = Qdrant::from_url("http://localhost:6334").build()?;
+
+let text_index_params = TextIndexParamsBuilder::new(TokenizerType::Word)
+    .snowball_stemmer("english".to_string());
+
+client
+    .create_field_index(
+        CreateFieldIndexCollectionBuilder::new(
+            "{collection_name}",
+            "{field_name}",
+            FieldType::Text,
+        ).field_index_params(text_index_params.build()),
+    )
+    .await?;
+```
@@ -0,0 +1,17 @@
+```typescript
+import { QdrantClient } from "@qdrant/js-client-rest";
+
+const client = new QdrantClient({ host: "localhost", port: 6333 });
+
+client.createPayloadIndex("{collection_name}", {
+  field_name: "name_of_the_field_to_index",
+  field_schema: {
+    type: "text",
+    tokenizer: "word",
+    stemmer: {
+      type: "snowball",
+      language: "english"
+    }
+  }
+});
+```