Merge pull request #2853 from redpanda-data/examples

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

@@ -78,6 +78,36 @@ By default, the processor starts and runs a locally installed Ollama server. Alt
 
 For more information, see the https://github.com/ollama/ollama/tree/main/docs[Ollama documentation^].
 
+== Examples
+
+[tabs]
+======
+Store embedding vectors in Qdrant::
++
+--
+
+Compute embeddings for some generated data and store it within xrefs:component:outputs/qdrant.adoc[Qdrant]
+
+```yamlinput:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - ollama_embeddings:
+      model: snowflake-artic-embed
+      text: "${!this.text}"
+output:
+  qdrant:
+    grpc_host: localhost:6334
+    collection_name: "example_collection"
+    id: "root = uuid_v4()"
+    vector_mapping: "root = this"```
+
+--
+======
+
 == Fields
 
 === `model`

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

@@ -42,6 +42,37 @@ This processor sends text strings to the OpenAI API, which generates vector embe
 
 To learn more about vector embeddings, see the https://platform.openai.com/docs/guides/embeddings[OpenAI API documentation^].
 
+== Examples
+
+[tabs]
+======
+Store embedding vectors in Pinecone::
++
+--
+
+Compute embeddings for some generated data and store it within xrefs:component:outputs/pinecone.adoc[Pinecone]
+
+```yamlinput:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - openai_embeddings:
+      model: text-embedding-3-large
+      api_key: "${OPENAI_API_KEY}"
+      text_mapping: "root = this.text"
+output:
+  pinecone:
+    host: "${PINECONE_HOST}"
+    api_key: "${PINECONE_API_KEY}"
+    id: "root = uuid_v4()"
+    vector_mapping: "root = this"```
+
+--
+======
+
 == Fields
 
 === `server_address`

internal/impl/ollama/embeddings_processor.go

@@ -49,7 +49,26 @@ For more information, see the https://github.com/ollama/ollama/tree/main/docs[Ol
 			service.NewInterpolatedStringField(oepFieldText).
 				Description("The text you want to create vector embeddings for. By default, the processor submits the entire payload as a string.").
 				Optional(),
-		).Fields(commonFields()...)
+		).Fields(commonFields()...).
+		Example(
+			"Store embedding vectors in Qdrant",
+			"Compute embeddings for some generated data and store it within xrefs:component:outputs/qdrant.adoc[Qdrant]",
+			`input:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - ollama_embeddings:
+      model: snowflake-artic-embed
+      text: "${!this.text}"
+output:
+  qdrant:
+    grpc_host: localhost:6334
+    collection_name: "example_collection"
+    id: "root = uuid_v4()"
+    vector_mapping: "root = this"`)
 }
 
 func makeOllamaEmbeddingProcessor(conf *service.ParsedConfig, mgr *service.Resources) (service.Processor, error) {

internal/impl/openai/embeddings_processor.go

@@ -56,7 +56,27 @@ To learn more about vector embeddings, see the https://platform.openai.com/docs/
 			service.NewIntField(oepFieldDims).
 				Description("The number of dimensions the resulting output embeddings should have. Only supported in `text-embedding-3` and later models.").
 				Optional(),
-		)
+		).
+		Example(
+			"Store embedding vectors in Pinecone",
+			"Compute embeddings for some generated data and store it within xrefs:component:outputs/pinecone.adoc[Pinecone]",
+			`input:
+  generate:
+    interval: 1s
+    mapping: |
+      root = {"text": fake("paragraph")}
+pipeline:
+  processors:
+  - openai_embeddings:
+      model: text-embedding-3-large
+      api_key: "${OPENAI_API_KEY}"
+      text_mapping: "root = this.text"
+output:
+  pinecone:
+    host: "${PINECONE_HOST}"
+    api_key: "${PINECONE_API_KEY}"
+    id: "root = uuid_v4()"
+    vector_mapping: "root = this"`)
 }
 
 func makeEmbeddingsProcessor(conf *service.ParsedConfig, mgr *service.Resources) (service.Processor, error) {