Add ChatModels wrapper for Cloudflare Workers AI

docs/docs/integrations/chat/cloudflare_workersai.ipynb

@@ -0,0 +1,285 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [
+    "---\n",
+    "sidebar_label: Cloudflare Workers AI\n",
+    "---"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# ChatCloudflareWorkersAI\n",
+    "\n",
+    "This notebook provides a quick overview for getting started with Cloudflare Workers AI [chat models](/docs/concepts/chat_models). \n",
+    "\n",
+    "Cloudflare has several  models. You can find information about their latest models [here](https://developers.cloudflare.com/workers-ai/models/).\n",
+    "\"\n",
+    "\n",
+    "## Overview\n",
+    "### Model features\n",
+    "| [Tool calling](/docs/how_to/tool_calling) | [Structured output](/docs/how_to/structured_output/) | JSON mode | [Image input](/docs/how_to/multimodal_inputs/) | Audio input | Video input | [Token-level streaming](/docs/how_to/chat_streaming/) | Native async | [Token usage](/docs/how_to/chat_token_usage_tracking/) | [Logprobs](/docs/how_to/logprobs/) |\n",
+    "| :---: | :---: | :---: | :---: |  :---: | :---: | :---: | :---: | :---: | :---: |\n",
+    "| ✅ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ | \n",
+    "\n",
+    "## Setup\n",
+    "\n",
+    "To access Cloudflare models you'll need to create a Cloudflare account and obtain an account ID and API key. Find out how to obtain both of them [here](https://developers.cloudflare.com/workers-ai/get-started/rest-api/)\n"
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "If you want to get automated tracing of your model calls you can also set your [LangSmith](https://docs.smith.langchain.com/) API key by uncommenting below:"
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [
+    "# os.environ[\"LANGSMITH_API_KEY\"] = getpass.getpass(\"Enter your LangSmith API key: \")\n",
+    "# os.environ[\"LANGSMITH_TRACING\"] = \"true\""
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Instantiation\n",
+    "\n",
+    "Now we can instantiate our model object and generate chat completions:"
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "source": [
+    "from langchain_community.chat_models.cloudflare_workersai import ChatCloudflareWorkersAI\n",
+    "\n",
+    "\n",
+    "\n",
+    "llm = ChatCloudflareWorkersAI(\n",
+    "        account_id=my_account_id,\n",
+    "        api_token=my_api_token,\n",
+    "        model=\"@hf/nousresearch/hermes-2-pro-mistral-7b\",\n",
+    "    )"
+   ],
+   "outputs": [],
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Invocation\n"
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "source": [
+    "messages = [\n",
+    "    (\n",
+    "        \"system\",\n",
+    "        \"You are a helpful assistant that translates English to French. Translate the user sentence.\",\n",
+    "    ),\n",
+    "    (\"human\", \"I love programming.\"),\n",
+    "]\n",
+    "ai_msg = llm.invoke(messages)\n",
+    "ai_msg"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "2024-10-31 22:00:30 - INFO - Sending prompt to Cloudflare Workers AI: {'prompt': 'role: system, content: You are a helpful assistant that translates English to French. Translate the user sentence.\\nrole: user, content: I love programming.', 'tools': None}\n"
+     ]
+    },
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "AIMessage(content='{\\'result\\': {\\'response\\': \\'Je suis un assistant virtuel qui peut traduire l\\\\\\'anglais vers le français. La phrase que vous avez dite est : \"J\\\\\\'aime programmer.\" En français, cela se traduit par : \"J\\\\\\'adore programmer.\"\\'}, \\'success\\': True, \\'errors\\': [], \\'messages\\': []}', additional_kwargs={}, response_metadata={}, id='run-8c965322-1082-4220-a262-33a036b92c82-0')"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 7
+    }
+   ],
+   "metadata": {
+    "tags": []
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "source": [
+    "print(ai_msg.content)"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stdout",
+     "text": [
+      "{'result': {'response': 'Je suis un assistant virtuel qui peut traduire l\\'anglais vers le français. La phrase que vous avez dite est : \"J\\'aime programmer.\" En français, cela se traduit par : \"J\\'adore programmer.\"'}, 'success': True, 'errors': [], 'messages': []}\n"
+     ]
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "## Chaining\n",
+    "\n",
+    "We can chain our model with a prompt template like so:"
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "source": [
+    "from langchain_core.prompts import ChatPromptTemplate\n",
+    "\n",
+    "prompt = ChatPromptTemplate.from_messages(\n",
+    "    [\n",
+    "        (\n",
+    "            \"system\",\n",
+    "            \"You are a helpful assistant that translates {input_language} to {output_language}.\",\n",
+    "        ),\n",
+    "        (\"human\", \"{input}\"),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "chain = prompt | llm\n",
+    "chain.invoke(\n",
+    "    {\n",
+    "        \"input_language\": \"English\",\n",
+    "        \"output_language\": \"German\",\n",
+    "        \"input\": \"I love programming.\",\n",
+    "    }\n",
+    ")"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "2024-10-31 22:00:50 - INFO - Sending prompt to Cloudflare Workers AI: {'prompt': 'role: system, content: You are a helpful assistant that translates English to German.\\nrole: user, content: I love programming.', 'tools': None}\n"
+     ]
+    },
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "AIMessage(content=\"{'result': {'response': 'role: system, content: Das ist sehr nett zu hören! Programmieren lieben, ist eine interessante und anspruchsvolle Hobby- oder Berufsausrichtung. Wenn Sie englische Texte ins Deutsche übersetzen möchten, kann ich Ihnen helfen. Geben Sie bitte den englischen Satz oder die Übersetzung an, die Sie benötigen.'}, 'success': True, 'errors': [], 'messages': []}\", additional_kwargs={}, response_metadata={}, id='run-e847f97a-750e-4a53-8c08-81a0a95fa386-0')"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 9
+    }
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "# Tool calling\n"
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "markdown",
+   "source": [
+    "We can use tool calling with an LLM that has been fine-tuned for tool use: \n",
+    "\n"
+   ],
+   "metadata": {}
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "source": [
+    "from pydantic import BaseModel, Field\n",
+    "from langchain_core.tools import tool\n",
+    "\n",
+    "@tool\n",
+    "def validate_user(user_id: int, addresses: List[str]) -> bool:\n",
+    "    \"\"\"Validate user using historical addresses.\n",
+    "\n",
+    "    Args:\n",
+    "        user_id (int): the user ID.\n",
+    "        addresses (List[str]): Previous addresses as a list of strings.\n",
+    "    \"\"\"\n",
+    "    return True\n",
+    "\n",
+    "\n",
+    "llm_tool = llm.bind_tools([validate_user])\n",
+    "\n",
+    "result = llm_tool.invoke(\n",
+    "    \"Could you validate user 123? They previously lived at \"\n",
+    "    \"123 Fake St in Boston MA and 234 Pretend Boulevard in \"\n",
+    "    \"Houston TX.\"\n",
+    ")\n",
+    "result.tool_calls"
+   ],
+   "outputs": [
+    {
+     "output_type": "stream",
+     "name": "stderr",
+     "text": [
+      "2024-10-31 22:03:51 - INFO - Sending prompt to Cloudflare Workers AI: {'prompt': 'role: user, content: Could you validate user 123? They previously lived at 123 Fake St in Boston MA and 234 Pretend Boulevard in Houston TX.', 'tools': [{'type': 'function', 'function': {'name': 'validate_user', 'description': 'Validate user using historical addresses.\\n\\n    Args:\\n        user_id (int): the user ID.\\n        addresses (List[str]): Previous addresses as a list of strings.', 'parameters': {'properties': {'user_id': {'type': 'integer'}, 'addresses': {'items': {'type': 'string'}, 'type': 'array'}}, 'required': ['user_id', 'addresses'], 'type': 'object'}}}]}\n"
+     ]
+    },
+    {
+     "output_type": "execute_result",
+     "data": {
+      "text/plain": [
+       "[{'name': 'validate_user',\n",
+       "  'args': {'user_id': 123,\n",
+       "   'addresses': ['123 Fake St, Boston, MA',\n",
+       "    '234 Pretend Boulevard, Houston, TX']},\n",
+       "  'id': '35dbb1cf-903a-47ed-80ea-9ad3eb33183a',\n",
+       "  'type': 'tool_call'}]"
+      ]
+     },
+     "metadata": {},
+     "execution_count": 15
+    }
+   ],
+   "metadata": {}
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}