community: Add ChatGLM3 (#15265)

Add [ChatGLM3](https://github.com/THUDM/ChatGLM3) and updated
[chatglm.ipynb](https://python.langchain.com/docs/integrations/llms/chatglm)

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>

docs/docs/integrations/llms/chatglm.ipynb

@@ -11,7 +11,102 @@
     "\n",
     "[ChatGLM2-6B](https://github.com/THUDM/ChatGLM2-6B) is the second-generation version of the open-source bilingual (Chinese-English) chat model ChatGLM-6B. It retains the smooth conversation flow and low deployment threshold of the first-generation model, while introducing the new features like better performance, longer context and more efficient inference.\n",
     "\n",
-    "This example goes over how to use LangChain to interact with ChatGLM2-6B Inference for text completion.\n",
+    "[ChatGLM3](https://github.com/THUDM/ChatGLM3) is a new generation of pre-trained dialogue models jointly released by Zhipu AI and Tsinghua KEG. ChatGLM3-6B is the open-source model in the ChatGLM3 series"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Install required dependencies\n",
+    "\n",
+    "%pip install -qU langchain langchain-community"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## ChatGLM3\n",
+    "\n",
+    "This examples goes over how to use LangChain to interact with ChatGLM3-6B Inference for text completion."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.chains import LLMChain\n",
+    "from langchain.prompts import PromptTemplate\n",
+    "from langchain.schema.messages import AIMessage\n",
+    "from langchain_community.llms.chatglm3 import ChatGLM3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "template = \"\"\"{question}\"\"\"\n",
+    "prompt = PromptTemplate(template=template, input_variables=[\"question\"])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "endpoint_url = \"http://127.0.0.1:8000/v1/chat/completions\"\n",
+    "\n",
+    "messages = [\n",
+    "    AIMessage(content=\"我将从美国到中国来旅游，出行前希望了解中国的城市\"),\n",
+    "    AIMessage(content=\"欢迎问我任何问题。\"),\n",
+    "]\n",
+    "\n",
+    "llm = ChatGLM3(\n",
+    "    endpoint_url=endpoint_url,\n",
+    "    max_tokens=80000,\n",
+    "    prefix_messages=messages,\n",
+    "    top_p=0.9,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'北京和上海是中国两个不同的城市,它们在很多方面都有所不同。\\n\\n北京是中国的首都,也是历史悠久的城市之一。它有着丰富的历史文化遗产,如故宫、颐和园等,这些景点吸引着众多游客前来观光。北京也是一个政治、文化和教育中心,有很多政府机构和学术机构总部设在北京。\\n\\n上海则是一个现代化的城市,它是中国的经济中心之一。上海拥有许多高楼大厦和国际化的金融机构,是中国最国际化的城市之一。上海也是一个美食和购物天堂,有许多著名的餐厅和购物中心。\\n\\n北京和上海的气候也不同。北京属于温带大陆性气候,冬季寒冷干燥,夏季炎热多风;而上海属于亚热带季风气候,四季分明,春秋宜人。\\n\\n北京和上海有很多不同之处,但都是中国非常重要的城市,每个城市都有自己独特的魅力和特色。'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
+    "question = \"北京和上海两座城市有什么不同？\"\n",
+    "\n",
+    "llm_chain.run(question)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## ChatGLM and ChatGLM2\n",
+    "\n",
+    "The following example shows how to use LangChain to interact with the ChatGLM2-6B Inference to complete text.\n",
     "ChatGLM-6B and ChatGLM2-6B has the same api specs, so this example should work with both."
    ]
   },
@@ -106,7 +201,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "langchain-dev",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -120,9 +215,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.12"
+   "version": "3.9.1"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }