community[patch]: Add maritalk streaming (sync and async) (#19203)

Co-authored-by: RosevalJr <rdmalajr@gmail.com>
Co-authored-by: Roseval Donisete Malaquias Junior <roseval@maritaca.ai>

docs/docs/integrations/chat/maritalk.ipynb

@@ -33,7 +33,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install langchain langchain-core langchain-community"
+    "!pip install langchain langchain-core langchain-community httpx"
    ]
   },
   {
@@ -89,6 +89,58 @@
     "print(response)  # should answer something like \"1. Max\\n2. Bella\\n3. Charlie\\n4. Rocky\""
    ]
   },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Stream Generation\n",
+    "\n",
+    "For tasks involving the generation of long text, such as creating an extensive article or translating a large document, it can be advantageous to receive the response in parts, as the text is generated, instead of waiting for the complete text. This makes the application more responsive and efficient, especially when the generated text is extensive. We offer two approaches to meet this need: one synchronous and another asynchronous.\n",
+    "\n",
+    "#### Synchronous:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "messages = [HumanMessage(content=\"Suggest 3 names for my dog\")]\n",
+    "\n",
+    "for chunk in llm.stream(messages):\n",
+    "    print(chunk.content, end=\"\", flush=True)"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### Asynchronous:"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain_core.messages import HumanMessage\n",
+    "\n",
+    "\n",
+    "async def async_invoke_chain(animal: str):\n",
+    "    messages = [HumanMessage(content=f\"Suggest 3 names for my {animal}\")]\n",
+    "    async for chunk in llm._astream(messages):\n",
+    "        print(chunk.message.content, end=\"\", flush=True)\n",
+    "\n",
+    "\n",
+    "await async_invoke_chain(\"dog\")"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},