Generalize Comment on Streaming Support for LLM Implementations and add examples (#8115)

The example provided demonstrates the usage of the
HuggingFaceTextGenInference implementation with streaming enabled.

docs/extras/modules/model_io/models/llms/integrations/huggingface_textgen_inference.ipynb

@@ -48,6 +48,36 @@
     ")\n",
     "llm(\"What did foo say about bar?\")"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Streaming"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.llms import HuggingFaceTextGenInference\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler\n",
+    "\n",
+    "\n",
+    "llm = HuggingFaceTextGenInference(\n",
+    "    inference_server_url=\"http://localhost:8010/\",\n",
+    "    max_new_tokens=512,\n",
+    "    top_k=10,\n",
+    "    top_p=0.95,\n",
+    "    typical_p=0.95,\n",
+    "    temperature=0.01,\n",
+    "    repetition_penalty=1.03,\n",
+    "    stream=True\n",
+    ")\n",
+    "llm(\"What did foo say about bar?\", callbacks=[StreamingStdOutCallbackHandler()])"
+   ]
   }
  ],
  "metadata": {