Merge pull request #2883 from redpanda-data/clicky

docs/modules/components/pages/processors/aws_bedrock_embeddings.adoc

@@ -71,6 +71,43 @@ aws_bedrock_embeddings:
 This processor sends text to your chosen large language model (LLM) and computes vector embeddings, using the AWS Bedrock API.
 For more information, see the https://docs.aws.amazon.com/bedrock/latest/userguide[AWS Bedrock documentation^].
 
+== Examples
+
+[tabs]
+======
+Store embedding vectors in Clickhouse::
++
+--
+
+Compute embeddings for some generated data and store it within https://clickhouse.com/[Clickhouse^]
+
+```yamlinput:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - branch:
+      request_map: |
+        root = this.text
+      processors:
+      - aws_bedrock_embeddings:
+          model: amazon.titan-embed-text-v1
+      result_map: |
+        root.embeddings = this
+output:
+  sql_insert:
+    driver: clickhouse
+    dsn: "clickhouse://localhost:9000"
+    table: searchable_text
+    columns: ["id", "text", "vector"]
+    args_mapping: "root = [uuid_v4(), this.text, this.embeddings]"
+```
+
+--
+======
+
 == Fields
 
 === `region`

docs/modules/components/pages/processors/ollama_embeddings.adoc

@@ -103,7 +103,38 @@ output:
     grpc_host: localhost:6334
     collection_name: "example_collection"
     id: "root = uuid_v4()"
-    vector_mapping: "root = this"```
+    vector_mapping: "root = this"
+```
+
+--
+Store embedding vectors in Clickhouse::
++
+--
+
+Compute embeddings for some generated data and store it within https://clickhouse.com/[Clickhouse^]
+
+```yamlinput:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - branch:
+      processors:
+      - ollama_embeddings:
+          model: snowflake-artic-embed
+          text: "${!this.text}"
+      result_map: |
+        root.embeddings = this
+output:
+  sql_insert:
+    driver: clickhouse
+    dsn: "clickhouse://localhost:9000"
+    table: searchable_text
+    columns: ["id", "text", "vector"]
+    args_mapping: "root = [uuid_v4(), this.text, this.embeddings]"
+```
 
 --
 ======

internal/impl/aws/enterprise/processor_bedrock_embeddings.go

@@ -48,7 +48,33 @@ For more information, see the https://docs.aws.amazon.com/bedrock/latest/usergui
 			Description("The model ID to use. For a full list see the https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html[AWS Bedrock documentation^].")).
 		Field(service.NewStringField(bedepFieldText).
 			Description("The prompt you want to generate a response for. By default, the processor submits the entire payload as a string.").
-			Optional())
+			Optional()).
+		Example(
+			"Store embedding vectors in Clickhouse",
+			"Compute embeddings for some generated data and store it within https://clickhouse.com/[Clickhouse^]",
+			`input:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - branch:
+      request_map: |
+        root = this.text
+      processors:
+      - aws_bedrock_embeddings:
+          model: amazon.titan-embed-text-v1
+      result_map: |
+        root.embeddings = this
+output:
+  sql_insert:
+    driver: clickhouse
+    dsn: "clickhouse://localhost:9000"
+    table: searchable_text
+    columns: ["id", "text", "vector"]
+    args_mapping: "root = [uuid_v4(), this.text, this.embeddings]"
+`)
 }
 
 func newBedrockEmbeddingsProcessor(conf *service.ParsedConfig, mgr *service.Resources) (service.Processor, error) {

internal/impl/ollama/embeddings_processor.go

@@ -68,7 +68,33 @@ output:
     grpc_host: localhost:6334
     collection_name: "example_collection"
     id: "root = uuid_v4()"
-    vector_mapping: "root = this"`)
+    vector_mapping: "root = this"
+`).
+		Example(
+			"Store embedding vectors in Clickhouse",
+			"Compute embeddings for some generated data and store it within https://clickhouse.com/[Clickhouse^]",
+			`input:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - branch:
+      processors:
+      - ollama_embeddings:
+          model: snowflake-artic-embed
+          text: "${!this.text}"
+      result_map: |
+        root.embeddings = this
+output:
+  sql_insert:
+    driver: clickhouse
+    dsn: "clickhouse://localhost:9000"
+    table: searchable_text
+    columns: ["id", "text", "vector"]
+    args_mapping: "root = [uuid_v4(), this.text, this.embeddings]"
+`)
 }
 
 func makeOllamaEmbeddingProcessor(conf *service.ParsedConfig, mgr *service.Resources) (service.Processor, error) {