Add Streaming for GPT4All (#2642)

- Adds  support for callback handlers in GPT4All models
- Updates notebook and docs

docs/modules/models/llms/integrations/gpt4all.ipynb

@@ -4,7 +4,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# GPT4all\n",
+    "# GPT4All\n",
     "\n",
     "This example goes over how to use LangChain to interact with GPT4All models"
    ]
@@ -15,7 +15,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "!pip install pyllamacpp"
+    "%pip install pyllamacpp > /dev/null"
    ]
   },
   {
@@ -24,8 +24,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "from langchain import PromptTemplate, LLMChain\n",
     "from langchain.llms import GPT4All\n",
-    "from langchain import PromptTemplate, LLMChain"
+    "from langchain.callbacks.base import CallbackManager\n",
+    "from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler"
    ]
   },
   {
@@ -41,15 +43,70 @@
     "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Specify Model\n",
+    "\n",
+    "To run locally, download a compatible ggml-formatted model. For more info, visit https://github.com/nomic-ai/pyllamacpp\n",
+    "\n",
+    "Note that new models are uploaded regularly - check the link above for the most recent `.bin` URL"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
-    "# You'll need to download a compatible model and convert it to ggml.\n",
-    "# See: https://github.com/nomic-ai/gpt4all for more information.\n",
-    "llm = GPT4All(model=\"./models/gpt4all-model.bin\")"
+    "local_path = './models/gpt4all-lora-quantized-ggml.bin'  # replace with your desired local file path"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Uncomment the below block to download a model. You may want to update `url` to a new version."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import requests\n",
+    "\n",
+    "# from pathlib import Path\n",
+    "# from tqdm import tqdm\n",
+    "\n",
+    "# Path(local_path).parent.mkdir(parents=True, exist_ok=True)\n",
+    "\n",
+    "# # Example model. Check https://github.com/nomic-ai/pyllamacpp for the latest models.\n",
+    "# url = 'https://the-eye.eu/public/AI/models/nomic-ai/gpt4all/gpt4all-lora-quantized-ggml.bin'\n",
+    "\n",
+    "# # send a GET request to the URL to download the file. Stream since it's large\n",
+    "# response = requests.get(url, stream=True)\n",
+    "\n",
+    "# # open the file in binary mode and write the contents of the response to it in chunks\n",
+    "# # This is a large file, so be prepared to wait.\n",
+    "# with open(local_path, 'wb') as f:\n",
+    "#     for chunk in tqdm(response.iter_content(chunk_size=8192)):\n",
+    "#         if chunk:\n",
+    "#             f.write(chunk)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Callbacks support token-wise streaming\n",
+    "callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])\n",
+    "# Verbose is required to pass to the callback manager\n",
+    "llm = GPT4All(model=local_path, callback_manager=callback_manager, verbose=True)"
    ]
   },
   {
@@ -89,7 +146,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.1"
+   "version": "3.11.2"
   }
  },
  "nbformat": 4,