docs: Add RAG example using OllamaEmbeddings and ChatOllama (#337)

docs/modules/model_io/models/chat_models/integrations/ollama.md

@@ -128,3 +128,52 @@ final res = await chatModel.invoke(PromptValue.chat([prompt]));
 print(res.firstOutputAsString);
 // -> 'An Apple'
 ```
+
+## RAG (Retrieval-Augmented Generation) pipeline
+
+We can easily create a fully local RAG pipeline using `OllamaEmbeddings` and `ChatOllama`.
+
+```dart
+// 1. Create a vector store and add documents to it
+final vectorStore = MemoryVectorStore(
+  embeddings: OllamaEmbeddings(model: 'llama2'),
+);
+await vectorStore.addDocuments(
+  documents: [
+    Document(pageContent: 'LangChain was created by Harrison'),
+    Document(pageContent: 'David ported LangChain to Dart in LangChain.dart'),
+  ],
+);
+
+// 2. Construct a RAG prompt template
+final promptTemplate = ChatPromptTemplate.fromTemplates([
+  (ChatMessageType.system, 'Answer the question based on only the following context:\n{context}'),
+  (ChatMessageType.human, '{question}'),
+]);
+
+// 3. Define the model to use and the vector store retriever
+final chatModel = ChatOllama(
+  defaultOptions: ChatOllamaOptions(model: 'llama2'),
+);
+final retriever = vectorStore.asRetriever(
+  defaultOptions: VectorStoreRetrieverOptions(
+    searchType: VectorStoreSimilaritySearch(k: 1),
+  ),
+);
+
+// 4. Create a Runnable that combines the retrieved documents into a single string
+final docCombiner = Runnable.fromFunction<List<Document>, String>((docs, _) {
+  return docs.map((d) => d.pageContent).join('\n');
+});
+
+// 4. Define the RAG pipeline
+final chain = Runnable.fromMap<String>({
+  'context': retriever.pipe(docCombiner),
+  'question': Runnable.passthrough(),
+}).pipe(promptTemplate).pipe(chatModel).pipe(StringOutputParser());
+
+// 5. Run the pipeline
+final res = await chain.invoke('Who created LangChain.dart?');
+print(res);
+// Based on the context provided, David created LangChain.dart.
+```

examples/docs_examples/bin/modules/model_io/models/chat_models/integrations/ollama.dart

@@ -10,6 +10,7 @@ void main(final List<String> arguments) async {
   await _chatOllamaStreaming();
   await _chatOllamaJsonMode();
   await _chatOllamaMultimodal();
+  await _rag();
 }
 
 Future<void> _chatOllama() async {
@@ -108,3 +109,54 @@ Future<void> _chatOllamaMultimodal() async {
   print(res.firstOutputAsString);
   // -> 'An Apple'
 }
+
+Future<void> _rag() async {
+  // 1. Create a vector store and add documents to it
+  final vectorStore = MemoryVectorStore(
+    embeddings: OllamaEmbeddings(model: 'llama2'),
+  );
+  await vectorStore.addDocuments(
+    documents: [
+      const Document(pageContent: 'LangChain was created by Harrison'),
+      const Document(
+        pageContent: 'David ported LangChain to Dart in LangChain.dart',
+      ),
+    ],
+  );
+
+  // 2. Construct a RAG prompt template
+  final promptTemplate = ChatPromptTemplate.fromTemplates(const [
+    (
+      ChatMessageType.system,
+      'Answer the question based on only the following context:\n{context}',
+    ),
+    (ChatMessageType.human, '{question}'),
+  ]);
+
+  // 3. Define the model to use and the vector store retriever
+  final chatModel = ChatOllama(
+    defaultOptions: const ChatOllamaOptions(model: 'llama2'),
+  );
+  final retriever = vectorStore.asRetriever(
+    defaultOptions: const VectorStoreRetrieverOptions(
+      searchType: VectorStoreSimilaritySearch(k: 1),
+    ),
+  );
+
+  // 4. Create a Runnable that combines the retrieved documents into a single string
+  final docCombiner =
+      Runnable.fromFunction<List<Document>, String>((final docs, final _) {
+    return docs.map((final d) => d.pageContent).join('\n');
+  });
+
+  // 4. Define the RAG pipeline
+  final chain = Runnable.fromMap<String>({
+    'context': retriever.pipe(docCombiner),
+    'question': Runnable.passthrough(),
+  }).pipe(promptTemplate).pipe(chatModel).pipe(const StringOutputParser());
+
+  // 5. Run the pipeline
+  final res = await chain.invoke('Who created LangChain.dart?');
+  print(res);
+  // Based on the context provided, David created LangChain.dart.
+}

packages/langchain/README.md

@@ -85,7 +85,7 @@ dependencies:
   ...
 ```
 
-The most basic building block of LangChain.dart is calling an LLM on some prompt. LangChain.dart provides a unified interface for calling different LLMs. For example, we can use `ChatGoogleGenerativeAI` to call Google's Gemini model: 
+The most basic building block of LangChain.dart is calling an LLM on some prompt. LangChain.dart provides a unified interface for calling different LLMs. For example, we can use `ChatGoogleGenerativeAI` to call Google's Gemini model:
 
 ```dart
 final model = ChatGoogleGenerativeAI(apiKey: googleApiKey);
@@ -116,7 +116,7 @@ final promptTemplate = ChatPromptTemplate.fromTemplates([
 
 // 3. Create a Runnable that combines the retrieved documents into a single string
 final docCombiner = Runnable.fromFunction<List<Document>, String>((docs, _) {
-  return docs.map((final d) => d.pageContent).join('\n');
+  return docs.map((d) => d.pageContent).join('\n');
 });
 
 // 4. Define the RAG pipeline
@@ -143,7 +143,9 @@ print(res);
 
 ## Community
 
-Stay up-to-date on the latest news and updates on the field, have great discussions, and get help in the official [LangChain.dart Discord](https://discord.gg/x4qbhqecVR).
+Stay up-to-date on the latest news and updates on the field, have great discussions, and get help in the official [LangChain.dart Discord server](https://discord.gg/x4qbhqecVR).
+
+[![LangChain.dart Discord server](https://invidget.switchblade.xyz/x4qbhqecVR?theme=light)](http://discord.gg/x4qbhqecVR)
 
 ## Contribute
 

packages/langchain_openai/test/chat_models/open_router_test.dart

@@ -32,7 +32,6 @@ void main() {
         'mistralai/mistral-small',
       ];
       for (final model in models) {
-        print('Testing model: $model');
         final res = await chatModel.invoke(
           PromptValue.string(
             'List the numbers from 1 to 9 in order. '