docs[patch]: Update GPT4All docs (#24044)

CC @efriis

docs/docs/integrations/llms/gpt4all.ipynb

@@ -14,21 +14,13 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "metadata": {
     "tags": []
    },
-   "outputs": [
+   "outputs": [],
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Note: you may need to restart the kernel to use updated packages.\n"
-     ]
-    }
-   ],
    "source": [
-    "%pip install --upgrade --quiet  gpt4all > /dev/null"
+    "%pip install --upgrade --quiet langchain-community gpt4all"
    ]
   },
   {
@@ -47,9 +39,7 @@
    },
    "outputs": [],
    "source": [
-    "from langchain.chains import LLMChain\n",
     "from langchain_community.llms import GPT4All\n",
-    "from langchain_core.callbacks import StreamingStdOutCallbackHandler\n",
     "from langchain_core.prompts import PromptTemplate"
    ]
   },
@@ -92,64 +82,79 @@
     "\n",
     "For more info, visit https://github.com/nomic-ai/gpt4all.\n",
     "\n",
-    "---"
+    "---\n",
+    "\n",
+    "This integration does not yet support streaming in chunks via the [`.stream()`](https://python.langchain.com/v0.2/docs/how_to/streaming/) method. The below example uses a callback handler with `streaming=True`:"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
     "local_path = (\n",
-    "    \"./models/ggml-gpt4all-l13b-snoozy.bin\"  # replace with your desired local file path\n",
+    "    \"./models/Meta-Llama-3-8B-Instruct.Q4_0.gguf\"  # replace with your local file path\n",
     ")"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 10,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Token:  Justin\n",
+      "Token:  Bieber\n",
+      "Token:  was\n",
+      "Token:  born\n",
+      "Token:  on\n",
+      "Token:  March\n",
+      "Token:  \n",
+      "Token: 1\n",
+      "Token: ,\n",
+      "Token:  \n"
+     ]
+    }
+   ],
    "source": [
-    "# Callbacks support token-wise streaming\n",
+    "from langchain_core.callbacks import BaseCallbackHandler\n",
-    "callbacks = [StreamingStdOutCallbackHandler()]\n",
+    "\n",
+    "count = 0\n",
+    "\n",
+    "\n",
+    "class MyCustomHandler(BaseCallbackHandler):\n",
+    "    def on_llm_new_token(self, token: str, **kwargs) -> None:\n",
+    "        global count\n",
+    "        if count < 10:\n",
+    "            print(f\"Token: {token}\")\n",
+    "            count += 1\n",
+    "\n",
     "\n",
     "# Verbose is required to pass to the callback manager\n",
-    "llm = GPT4All(model=local_path, callbacks=callbacks, verbose=True)\n",
+    "llm = GPT4All(model=local_path, callbacks=[MyCustomHandler()], streaming=True)\n",
     "\n",
     "# If you want to use a custom model add the backend parameter\n",
     "# Check https://docs.gpt4all.io/gpt4all_python.html for supported backends\n",
-    "llm = GPT4All(model=local_path, backend=\"gptj\", callbacks=callbacks, verbose=True)"
+    "# llm = GPT4All(model=local_path, backend=\"gptj\", callbacks=callbacks, streaming=True)\n",
-   ]
+    "\n",
-  },
+    "chain = prompt | llm\n",
-  {
+    "\n",
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "llm_chain = LLMChain(prompt=prompt, llm=llm)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "metadata": {},
-   "outputs": [],
-   "source": [
     "question = \"What NFL team won the Super Bowl in the year Justin Bieber was born?\"\n",
     "\n",
-    "llm_chain.run(question)"
+    "# Streamed tokens will be logged/aggregated via the passed callback\n",
+    "res = chain.invoke({\"question\": question})"
    ]
   },
   {
-   "attachments": {},
+   "cell_type": "code",
-   "cell_type": "markdown",
+   "execution_count": null,
    "metadata": {},
-   "source": [
+   "outputs": [],
-    "Justin Bieber was born on March 1, 1994. In 1994, The Cowboys won Super Bowl XXVIII."
+   "source": []
-   ]
   }
  ],
  "metadata": {

docs/docs/integrations/providers/gpt4all.mdx

@@ -7,7 +7,7 @@ This page covers how to use the `GPT4All` wrapper within LangChain. The tutorial
 - Install the Python package with `pip install gpt4all`
 - Download a [GPT4All model](https://gpt4all.io/index.html) and place it in your desired directory
 
-In this example, We are using `mistral-7b-openorca.Q4_0.gguf`(Best overall fast chat model):
+In this example, we are using `mistral-7b-openorca.Q4_0.gguf`:
 
 ```bash
 mkdir models
@@ -30,7 +30,7 @@ model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
 response = model.invoke("Once upon a time, ")
 ```
 
-You can also customize the generation parameters, such as n_predict, temp, top_p, top_k, and others.
+You can also customize the generation parameters, such as `n_predict`, `temp`, `top_p`, `top_k`, and others.
 
 To stream the model's predictions, add in a CallbackManager.
 
@@ -45,11 +45,11 @@ callbacks = [StreamingStdOutCallbackHandler()]
 model = GPT4All(model="./models/mistral-7b-openorca.Q4_0.gguf", n_threads=8)
 
 # Generate text. Tokens are streamed through the callback manager.
-model("Once upon a time, ", callbacks=callbacks)
+model.invoke("Once upon a time, ", callbacks=callbacks)
 ```
 
 ## Model File
 
-You can find links to model file downloads in the [https://gpt4all.io/](https://gpt4all.io/index.html).
+You can download model files from the GPT4All client. You can download the client from the [GPT4All](https://gpt4all.io/index.html) website.
 
 For a more detailed walkthrough of this, see [this notebook](/docs/integrations/llms/gpt4all)