{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "01f7ced5-2962-43b9-aaf4-8e88829e86c6",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import json,os\n",
    "import boto3\n",
    "import requests\n",
    "from requests_aws4auth import AWS4Auth,AWS4SigningKey\n",
    "from IPython.display import display, Markdown\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 670,
   "id": "9bc257a2-924d-4a86-9c70-408571add9a4",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def printMD(string):\n",
    "    display(Markdown(string))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 790,
   "id": "2ca55fe2-aa4e-4c71-82ae-6c1e2e516ba9",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def get_awsauth():\n",
    "    credentials = boto3.Session().get_credentials()\n",
    "    region = boto3.Session().region_name\n",
    "    awsauth = AWS4Auth(credentials.access_key, credentials.secret_key, region, 'lambda', session_token=credentials.token)\n",
    "    return awsauth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 671,
   "id": "54d12a3d-f41e-442b-970a-e87a5d0b17e7",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# !pip install requests_aws4auth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 672,
   "id": "6a6030d7-34eb-437e-93e0-67f0bb870be3",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# print(awsauth.access_id)  \n",
    "# print(awsauth.region)        \n",
    "# print(awsauth.service )     \n",
    "# print(awsauth.date )       \n",
    "# print(awsauth.signing_key.scope)  \n",
    "# print(awsauth.signing_key.key) \n",
    "# print(awsauth.signing_key.date)  \n",
    "# # print(awsauth.get_canonical_headers('host;x-amz-content-sha256;x-amz-date'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "f5f88bb4-e981-4ab2-8c06-a1f11d1e23f1",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "url = 'https://343vvxctf2qepvy5s4dpmje27a0umyuo.lambda-url.us-east-2.on.aws/todos/river'"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "42fcc8d2-ca51-4693-908b-8f4123cbbfcb",
   "metadata": {
    "tags": []
   },
   "source": [
    "## OPENAPI tool test"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4769a0e6-fab9-4da6-9026-5f4342be48da",
   "metadata": {},
   "source": [
    "### init ChatGPT"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "7c21adae-eac9-4e8b-a255-9d0348751dae",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.chains import LLMChain\n",
    "from langchain.prompts import PromptTemplate\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "7b8bfe82-e7dd-4024-a312-761b79d7e4a2",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "os.environ[\"OPENAI_API_KEY\"] = 'sk-'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 141,
   "id": "6cecd427-1ef8-4620-9f67-f2a8d90e00b9",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "llm = ChatOpenAI()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "id": "02b0b907-6386-404e-8d6b-196613f28d55",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "prompt = PromptTemplate(\n",
    "    input_variables=[\"input\"],\n",
    "    template=\"{input}\",\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "id": "1ae847ac-3ddb-4cca-bc57-09f3aa0da058",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "chain = LLMChain(llm=llm, prompt=prompt,verbose=True )"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "id": "f759b515-9681-4e78-9083-58f3065e1673",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3mhello\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Hello! How can I assist you today?'"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "chain.run({'input':'hello'})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6d41bd3a-6b37-4982-b1a9-410b9ba86859",
   "metadata": {},
   "source": [
    "## init sagemaker"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 117,
   "id": "76994a69-325e-4bcf-b086-9cc391ffd677",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.llms.sagemaker_endpoint import LLMContentHandler\n",
    "from langchain import PromptTemplate, SagemakerEndpoint\n",
    "from typing import Dict, List\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 813,
   "id": "a8005df2-dfa2-4cdb-98bc-7fc2528ee526",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "class llmContentHandler(LLMContentHandler):\n",
    "    parameters = {\n",
    "        \"max_length\": 2048,\n",
    "        \"temperature\": 0.01,\n",
    "    }\n",
    "    def transform_input(self, prompt: str, model_kwargs: Dict) -> bytes:\n",
    "        #ChatGLM参考typescript api描述，进行结构化提取时，有\\t会导致失败，需要把\\t替换成空格\n",
    "        input_str = json.dumps({'inputs': prompt,'history':[],**model_kwargs})\n",
    "        return input_str.encode('utf-8')\n",
    "    \n",
    "    def transform_output(self, output: bytes) -> str:\n",
    "        response_json = json.loads(output.read().decode(\"utf-8\"))\n",
    "        return response_json[\"outputs\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 814,
   "id": "6e86103d-cd75-44b9-9383-c118c1fe2da0",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "llmcontent_handler = llmContentHandler()\n",
    "llm_sg=SagemakerEndpoint(\n",
    "        endpoint_name='chatglm-2023-05-25-06-22-30-689-endpoint', \n",
    "        region_name='us-east-2', \n",
    "        model_kwargs={'parameters':llmcontent_handler.parameters},\n",
    "        content_handler=llmcontent_handler\n",
    "    )"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "79702556-73b2-47cf-bcf7-e0928ad22125",
   "metadata": {
    "tags": []
   },
   "source": [
    "### openapichain"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 676,
   "id": "3fbfca4e-a3f2-4ebb-b8dd-af98e8709790",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.tools import OpenAPISpec, APIOperation\n",
    "from langchain.chains import OpenAPIEndpointChain\n",
    "from langchain.requests import Requests\n",
    "from langchain.requests import TextRequestsWrapper\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 678,
   "id": "22549edc-5ae1-4f1b-a614-8d1f64e51fd2",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from typing import Any, Dict, Optional\n",
    "\n",
    "import aiohttp\n",
    "import requests\n",
    "from pydantic import BaseModel, Extra\n",
    "\n",
    "class AWSRequests(Requests):\n",
    "    \"\"\"Wrapper around requests to handle auth and async.\n",
    "\n",
    "    The main purpose of this wrapper is to handle authentication (by saving\n",
    "    headers) and enable easy async methods on the same base object.\n",
    "    \"\"\"\n",
    "\n",
    "    headers: Optional[Dict[str, str]] = None\n",
    "    auth: Optional[Any] = None\n",
    "    # aiosession: Optional[aiohttp.ClientSession] = None\n",
    "\n",
    "    class Config:\n",
    "        \"\"\"Configuration for this pydantic object.\"\"\"\n",
    "        extra = Extra.allow\n",
    "        arbitrary_types_allowed = True\n",
    "    \n",
    "    def get(self, url: str, **kwargs: Any) -> requests.Response:\n",
    "        \"\"\"GET the URL and return the text.\"\"\"\n",
    "        return requests.get(url, headers=self.headers,auth=self.auth, **kwargs)\n",
    "\n",
    "    def post(self, url: str, data: Dict[str, Any], **kwargs: Any) -> requests.Response:\n",
    "        \"\"\"POST to the URL and return the text.\"\"\"\n",
    "        return requests.post(url, json=data, headers=self.headers,auth=self.auth,  **kwargs)\n",
    "\n",
    "    def patch(self, url: str, data: Dict[str, Any], **kwargs: Any) -> requests.Response:\n",
    "        \"\"\"PATCH the URL and return the text.\"\"\"\n",
    "        return requests.patch(url, json=data, headers=self.headers,auth=self.auth,  **kwargs)\n",
    "\n",
    "    def put(self, url: str, data: Dict[str, Any], **kwargs: Any) -> requests.Response:\n",
    "        \"\"\"PUT the URL and return the text.\"\"\"\n",
    "        return requests.put(url, json=data, headers=self.headers,auth=self.auth,  **kwargs)\n",
    "\n",
    "    def delete(self, url: str, **kwargs: Any) -> requests.Response:\n",
    "        \"\"\"DELETE the URL and return the text.\"\"\"\n",
    "        return requests.delete(url, headers=self.headers,auth=self.auth,  **kwargs)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a1d720e5-b1c8-4478-8f80-76c98779f1e7",
   "metadata": {},
   "source": [
    "## 读取api 文件"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 683,
   "id": "6180ee15-8a5c-4505-bfe4-155eeb63d313",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n",
      "Attempting to load an OpenAPI 3.0.2 spec.  This may result in degraded performance. Convert your OpenAPI spec to 3.1.* spec for better support.\n"
     ]
    }
   ],
   "source": [
    "openai_api_spec = OpenAPISpec.from_file('api.yaml')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 684,
   "id": "9a1903e4-3101-44ad-bbb7-68e761452e38",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/* Get the list of todos */\\ntype getTodos = (_: {\\n/* The name of the user. */\\n\\t\\tusername: string,\\n}) => any;'"
      ]
     },
     "execution_count": 684,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "operation = APIOperation.from_openapi_spec(openai_api_spec, '/todos/{username}', \"get\")\n",
    "operation.to_typescript()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "44713942-51ab-43d1-8b8d-7b5a07b5b509",
   "metadata": {
    "tags": []
   },
   "source": [
    "## overwrite prompt template"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 804,
   "id": "caef07a5-a98d-4386-b99d-6e3ebad39e6b",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "REQUEST_TEMPLATE = \"\"\"你是一个AI助手。请根据用户指令提取出传递给 agentFunc() 函数的 JSON 参数。\n",
    "\n",
    "参考API_SCHEMA:\n",
    "```typescript\n",
    "{schema}\n",
    "```\n",
    "\n",
    "用户指令: \"{instructions}\"\n",
    "\n",
    "你的参数必须是以 Markdown 块形式的纯JSON。\n",
    "\n",
    "例如\n",
    "参数: ```json\n",
    "{{符合API_SCHEMA的有效的json}}\n",
    "```\n",
    "\n",
    "开始\n",
    "-----\n",
    "参数:\n",
    "\"\"\"\n",
    "\n",
    "RESPONSE_TEMPLATE = \"\"\"请根据以下API响应，根据用户的指令回答.\n",
    "API响应: {response}\n",
    "\n",
    "用户指令: \"{instructions}\"\n",
    "\n",
    "你必须根据API响应来回答问题\n",
    "答案:\n",
    "---\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5008d6a5-a24d-4e6d-a03a-f92b9f10703e",
   "metadata": {},
   "source": [
    "## 定制output parser"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 805,
   "id": "10e4c0cd-017e-45d0-bdf8-93524102cc9d",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.schema import BaseOutputParser\n",
    "import re\n",
    "class ChatGLMAPIResponderOutputParser(BaseOutputParser):\n",
    "    \"\"\"Parse the response and error tags.\"\"\"\n",
    "\n",
    "\n",
    "    def parse(self, llm_output: str) -> str:\n",
    "        \"\"\"Parse the response and error tags.\"\"\"\n",
    "        return llm_output\n",
    "        # json_match = re.search(r\"```json(.*?)```\", llm_output, re.DOTALL)\n",
    "        # if json_match:\n",
    "        #     return self._load_json_block(json_match.group(1).strip())\n",
    "        # else:\n",
    "        #     # raise ValueError(f\"No response found in output: {llm_output}.\")\n",
    "        #     return llm_output\n",
    "\n",
    "    @property\n",
    "    def _type(self) -> str:\n",
    "        return \"api_responder\"\n",
    "    \n",
    "class ChatGLMAPIRequesterOutputParser(BaseOutputParser):\n",
    "    \"\"\"Parse the request and error tags.\"\"\"\n",
    "\n",
    "    def _load_json_block(self, serialized_block: str) -> str:\n",
    "        try:\n",
    "            return json.dumps(json.loads(serialized_block, strict=False))\n",
    "        except json.JSONDecodeError:\n",
    "            return \"ERROR serializing request.\"\n",
    "\n",
    "    def parse(self, llm_output: str) -> str:\n",
    "        \"\"\"Parse the request and error tags.\"\"\"\n",
    "        print(f'llm_output:{llm_output}')\n",
    "\n",
    "        json_match = re.search(r\"```json(.*?)```\", llm_output, re.DOTALL)\n",
    "        if json_match:\n",
    "            return self._load_json_block(json_match.group(1).strip())\n",
    "        message_match = re.search(r\"```text(.*?)```\", llm_output, re.DOTALL)\n",
    "        if message_match:\n",
    "            return f\"MESSAGE: {message_match.group(1).strip()}\"\n",
    "        return \"ERROR making request\"\n",
    "\n",
    "    @property\n",
    "    def _type(self) -> str:\n",
    "        return \"api_requester\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bada3ff8-329d-442f-aac0-153ca95cd294",
   "metadata": {},
   "source": [
    "### 测试get"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 815,
   "id": "70f21f55-ca99-40e9-89e3-8b78d19c550f",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new OpenAPIEndpointChain chain...\u001b[0m\n",
      "\n",
      "\n",
      "\u001b[1m> Entering new APIRequesterChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3m你是一个AI助手。请根据用户指令提取出传递给 agentFunc() 函数的 JSON 参数。\n",
      "\n",
      "参考API_SCHEMA:\n",
      "```typescript\n",
      "/* Get the list of todos */\n",
      "type getTodos = (_: {\n",
      "/* The name of the user. */\n",
      "\t\tusername: string,\n",
      "}) => any;\n",
      "```\n",
      "\n",
      "用户指令: \"列出river的todos\"\n",
      "\n",
      "你的参数必须是以 Markdown 块形式的纯JSON。\n",
      "\n",
      "例如\n",
      "参数: ```json\n",
      "{符合API_SCHEMA的有效的json}\n",
      "```\n",
      "\n",
      "开始\n",
      "-----\n",
      "参数:\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m{\"username\": \"river\"}\u001b[0m\n",
      "\u001b[36;1m\u001b[1;3m[{\"username\": \"river\", \"todos\": \"[\\\"item1\\\", \\\"item2\\\", \\\"item3\\\", \\\"item3\\\", \\\"eat\\\", \\\"eat\\\", \\\"eat\\\", \\\"item3\\\", \\\"item3\\\", \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d\\\", \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d2\\\", \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d3\\\", \\\"eat4\\\", \\\"sleep\\\", \\\"sleep\\\", \\\"sleep\\\"]\"}]\u001b[0m\n",
      "\n",
      "\n",
      "\u001b[1m> Entering new APIResponderChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3m请根据以下API响应，根据用户的指令回答.\n",
      "API响应: [{\"username\": \"river\", \"todos\": \"[\\\"item1\\\", \\\"item2\\\", \\\"item3\\\", \\\"item3\\\", \\\"eat\\\", \\\"eat\\\", \\\"eat\\\", \\\"item3\\\", \\\"item3\\\", \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d\\\", \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d2\\\", \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d3\\\", \\\"eat4\\\", \\\"sleep\\\", \\\"sleep\\\", \\\"sleep\\\"]\"}]\n",
      "\n",
      "用户指令: \"列出river的todos\"\n",
      "\n",
      "你必须根据API响应来回答问题\n",
      "答案:\n",
      "---\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\u001b[33;1m\u001b[1;3m根据API响应，可以得出River的todos为：\n",
      "\n",
      "- \\\"item1\\\"\n",
      "- \\\"item2\\\"\n",
      "- \\\"item3\\\"\n",
      "- \\\"item3\\\"\n",
      "- \\\"eat\\\"\n",
      "- \\\"eat\\\"\n",
      "- \\\"eat\\\"\n",
      "- \\\"item3\\\"\n",
      "- \\\"item3\\\"\n",
      "- \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d\\\"\n",
      "- \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d2\\\"\n",
      "- \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d3\\\"\n",
      "- \\\"eat4\\\"\n",
      "- \\\"sleep\\\"\n",
      "- \\\"sleep\\\"\n",
      "\n",
      "因此，River的todos为上述列表中的所有内容。\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "operation = APIOperation.from_openapi_spec(openai_api_spec, '/todos/{username}', \"get\")\n",
    "chain = OpenAPIEndpointChain.from_api_operation(\n",
    "    operation, \n",
    "    llm_sg, \n",
    "    requests=AWSRequests(auth=get_awsauth()), \n",
    "    verbose=True,\n",
    "    return_intermediate_steps=True # Return request and response text\n",
    ")\n",
    "chain.api_request_chain.prompt.template=REQUEST_TEMPLATE\n",
    "# chain.api_request_chain.prompt.output_parser = ChatGLMAPIRequesterOutputParser()\n",
    "chain.api_response_chain.prompt.template=RESPONSE_TEMPLATE\n",
    "chain.api_response_chain.prompt.output_parser = ChatGLMAPIResponderOutputParser()\n",
    "answer = chain(\"列出river的todos\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 816,
   "id": "870af2b7-f95e-4dca-84d9-749dcfec49b2",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "根据API响应，可以得出River的todos为：\n",
       "\n",
       "- \\\"item1\\\"\n",
       "- \\\"item2\\\"\n",
       "- \\\"item3\\\"\n",
       "- \\\"item3\\\"\n",
       "- \\\"eat\\\"\n",
       "- \\\"eat\\\"\n",
       "- \\\"eat\\\"\n",
       "- \\\"item3\\\"\n",
       "- \\\"item3\\\"\n",
       "- \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d\\\"\n",
       "- \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d2\\\"\n",
       "- \\\"\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d3\\\"\n",
       "- \\\"eat4\\\"\n",
       "- \\\"sleep\\\"\n",
       "- \\\"sleep\\\"\n",
       "\n",
       "因此，River的todos为上述列表中的所有内容。"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "printMD(answer['output'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 610,
   "id": "f67156b2-cbdc-4249-a71d-ee22d6afcee7",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'回家吃饭3'"
      ]
     },
     "execution_count": 610,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "my_bytes = '\\\\u56de\\\\u5bb6\\\\u5403\\\\u996d3'\n",
    "my_bytes.encode('utf-8').decode('unicode_escape')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "39dc7ed0-939e-4e02-87f6-441199295b7b",
   "metadata": {},
   "source": [
    "### 测试post"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 726,
   "id": "139777fe-0fdf-4a75-ae7c-64d916d2588f",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new OpenAPIEndpointChain chain...\u001b[0m\n",
      "\n",
      "\n",
      "\u001b[1m> Entering new APIRequesterChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3m你是一个AI助手。请根据用户指令提取出传递给 agentFunc() 函数的 JSON 参数。\n",
      "\n",
      "参考API_SCHEMA:\n",
      "```typescript\n",
      "/* Add a todo to the list */\n",
      "type addTodo = (_: {\n",
      "/* The todo to add to the list. */\n",
      "  todo: string,\n",
      "/* The name of the user. */\n",
      "\t\tusername: string,\n",
      "}) => any;\n",
      "```\n",
      "\n",
      "用户指令: \"请给river增加一个todo，内容是‘sleep and getup’\"\n",
      "\n",
      "你的参数必须是以 Markdown 块形式的纯JSON。\n",
      "\n",
      "例如\n",
      "参数: ```json\n",
      "{符合API_SCHEMA的有效的json}\n",
      "```\n",
      "\n",
      "开始\n",
      "-----\n",
      "参数:\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3m{\"todo\": \"sleep and getup\"}\u001b[0m\n",
      "\u001b[36;1m\u001b[1;3m\"add todo list success\"\u001b[0m\n",
      "\n",
      "\n",
      "\u001b[1m> Entering new APIResponderChain chain...\u001b[0m\n",
      "Prompt after formatting:\n",
      "\u001b[32;1m\u001b[1;3m请根据以下API响应，根据用户的指令回答.\n",
      "API响应: \"add todo list success\"\n",
      "\n",
      "用户指令: \"请给river增加一个todo，内容是‘sleep and getup’\"\n",
      "\n",
      "你必须根据API响应来回答问题\n",
      "答案:\n",
      "---\n",
      "\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "\u001b[33;1m\u001b[1;3m给River增加一个todo，内容是“sleep and getup”，成功。\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "operation = APIOperation.from_openapi_spec(openai_api_spec, '/todos/{username}', \"post\")\n",
    "chain = OpenAPIEndpointChain.from_api_operation(\n",
    "    operation, \n",
    "    llm_sg, \n",
    "    requests=AWSRequests(auth=get_awsauth()), \n",
    "    verbose=True,\n",
    "    return_intermediate_steps=True # Return request and response text\n",
    ")\n",
    "chain.api_request_chain.prompt.template=REQUEST_TEMPLATE\n",
    "chain.api_response_chain.prompt.template=RESPONSE_TEMPLATE\n",
    "chain.api_response_chain.prompt.output_parser = ChatGLMAPIResponderOutputParser()\n",
    "answer = chain(\"请给river增加一个todo，内容是‘sleep and getup’\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7bc1f506-0e6e-4b47-905e-51dcf8682491",
   "metadata": {
    "tags": []
   },
   "source": [
    "## 测试LLM基础能力 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 862,
   "id": "13b014b8-79a3-46f1-8591-92bdb29b1127",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "#chatglm\n",
    "\n",
    "REQUEST_TEMPLATE = \"\"\"你是一个AI助手。请参考API_SCHEMA:\n",
    "```typescript\n",
    "{schema}\n",
    "```\n",
    "\n",
    "根据用户指令提取出传递给 agentFunc() 函数的JSON 参数\n",
    "\n",
    "用户指令: \"{instructions}\"\n",
    "\n",
    "你的参数必须是以 Markdown形式的纯JSON。\n",
    "\n",
    "参数: ```json\n",
    "{{符合API_SCHEMA的有效的json}}\n",
    "```\n",
    "\n",
    "开始\n",
    "-----\n",
    "参数:\n",
    "\"\"\"\n",
    "\n",
    "prompt = PromptTemplate(\n",
    "    input_variables=[\"instructions\",\"schema\"],\n",
    "    template=REQUEST_TEMPLATE,\n",
    ")\n",
    "\n",
    "api_schema = \"\"\"/* Add a todo to the list */\n",
    "type addTodo = (_: {\n",
    "/* The todo to add to the list. */\n",
    "  todo: string,\n",
    "/* The name of the user. */\n",
    "\t\tusername: string,\n",
    "}) => any;\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 863,
   "id": "d7f2317c-c69b-4709-b398-be0cbfb6fb0a",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "input_str = \"给xiao增加一个todo，内容是‘sleep and sleep’\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e969c489-b78d-4ff1-8d76-17c4ff6afd7d",
   "metadata": {
    "tags": []
   },
   "source": [
    "### chatglm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 864,
   "id": "dae1079a-c8cc-401a-b9aa-56740152ee51",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "```json\n",
       "{\n",
       "  \"todo\": \"sleep and sleep\"\n",
       "}\n",
       "```"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "chain = LLMChain(llm=llm_sg, prompt=prompt,verbose=False )\n",
    "resp = chain.run({'instructions':input_str, \"schema\":api_schema})\n",
    "printMD(resp)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cf5255b0-741c-4002-ae85-237a9795c1cd",
   "metadata": {},
   "source": [
    "### chatgpt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 861,
   "id": "d41d7229-6a05-4691-b721-d918e3f803a2",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "text/markdown": [
       "```json\n",
       "{\"username\":\"xiao\",\"todo\":\"sleep and sleep\"}\n",
       "```"
      ],
      "text/plain": [
       "<IPython.core.display.Markdown object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "chain = LLMChain(llm=llm, prompt=prompt,verbose=False )\n",
    "resp = chain.run({'instructions':input_str,\"schema\":api_schema})\n",
    "printMD(resp)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "086a98bf-dcb5-4544-b1e3-befb9e20e9eb",
   "metadata": {},
   "source": [
    "## OpenAPI agents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 147,
   "id": "54abb3e0-4b97-41b8-9b77-d11ac18e41a8",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import os, yaml\n",
    "from langchain.agents.agent_toolkits.openapi.spec import reduce_openapi_spec"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 276,
   "id": "bac08485-c639-4b13-aa2c-86002a4c321a",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "with open(\"api.yaml\") as f:\n",
    "    raw_openai_api_spec = yaml.load(f, Loader=yaml.Loader)\n",
    "openai_api_spec = reduce_openapi_spec(raw_openai_api_spec)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 277,
   "id": "07cd5e2d-1542-479c-9b2c-3468b26faeea",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.agents.agent_toolkits.openapi import planner\n",
    "from langchain.requests import RequestsWrapper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 278,
   "id": "ff416be9-b11d-427b-8fa1-82864c2dd091",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[0;32m/tmp/ipykernel_10634/3107926051.py\u001b[0m in \u001b[0;36m<cell line: 6>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mtodo_agent\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mplanner\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_openapi_agent\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mopenai_api_spec\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maws_requests\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mllm_sg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0muser_query\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m\"list all river's todo.\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0mtodo_agent\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrun\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0muser_query\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/base.py\u001b[0m in \u001b[0;36mrun\u001b[0;34m(self, callbacks, *args, **kwargs)\u001b[0m\n\u001b[1;32m    234\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    235\u001b[0m                 \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"`run` supports only one positional argument.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 236\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutput_keys\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    237\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    238\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mkwargs\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0margs\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/base.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m    138\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    139\u001b[0m             \u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_chain_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 140\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    141\u001b[0m         \u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_chain_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    142\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprep_outputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moutputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreturn_only_outputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/base.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m    132\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m             outputs = (\n\u001b[0;32m--> 134\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    135\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mnew_arg_supported\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    136\u001b[0m                 \u001b[0;32melse\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/agents/agent.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m    951\u001b[0m         \u001b[0;31m# We now enter the agent loop (until it returns something).\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    952\u001b[0m         \u001b[0;32mwhile\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_should_continue\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0miterations\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtime_elapsed\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 953\u001b[0;31m             next_step_output = self._take_next_step(\n\u001b[0m\u001b[1;32m    954\u001b[0m                 \u001b[0mname_to_tool_map\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    955\u001b[0m                 \u001b[0mcolor_mapping\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/agents/agent.py\u001b[0m in \u001b[0;36m_take_next_step\u001b[0;34m(self, name_to_tool_map, color_mapping, inputs, intermediate_steps, run_manager)\u001b[0m\n\u001b[1;32m    760\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    761\u001b[0m             \u001b[0;31m# Call the LLM to see what to do.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 762\u001b[0;31m             output = self.agent.plan(\n\u001b[0m\u001b[1;32m    763\u001b[0m                 \u001b[0mintermediate_steps\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    764\u001b[0m                 \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_child\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_manager\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/agents/agent.py\u001b[0m in \u001b[0;36mplan\u001b[0;34m(self, intermediate_steps, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    441\u001b[0m         \"\"\"\n\u001b[1;32m    442\u001b[0m         \u001b[0mfull_inputs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_full_inputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mintermediate_steps\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 443\u001b[0;31m         \u001b[0mfull_output\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mllm_chain\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mfull_inputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    444\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutput_parser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mparse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfull_output\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    445\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/llm.py\u001b[0m in \u001b[0;36mpredict\u001b[0;34m(self, callbacks, **kwargs)\u001b[0m\n\u001b[1;32m    211\u001b[0m                 \u001b[0mcompletion\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mllm\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0madjective\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m\"funny\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    212\u001b[0m         \"\"\"\n\u001b[0;32m--> 213\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutput_key\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    214\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    215\u001b[0m     \u001b[0;32masync\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mapredict\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mCallbacks\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mAny\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m->\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/base.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m    138\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    139\u001b[0m             \u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_chain_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 140\u001b[0;31m             \u001b[0;32mraise\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    141\u001b[0m         \u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_chain_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    142\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprep_outputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moutputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreturn_only_outputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/base.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs, return_only_outputs, callbacks)\u001b[0m\n\u001b[1;32m    132\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m             outputs = (\n\u001b[0;32m--> 134\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    135\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mnew_arg_supported\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    136\u001b[0m                 \u001b[0;32melse\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/llm.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, inputs, run_manager)\u001b[0m\n\u001b[1;32m     67\u001b[0m         \u001b[0mrun_manager\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mOptional\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mCallbackManagerForChainRun\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     68\u001b[0m     ) -> Dict[str, str]:\n\u001b[0;32m---> 69\u001b[0;31m         \u001b[0mresponse\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     70\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_outputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponse\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     71\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/chains/llm.py\u001b[0m in \u001b[0;36mgenerate\u001b[0;34m(self, input_list, run_manager)\u001b[0m\n\u001b[1;32m     77\u001b[0m         \u001b[0;34m\"\"\"Generate LLM result from inputs.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     78\u001b[0m         \u001b[0mprompts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstop\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprep_prompts\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minput_list\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 79\u001b[0;31m         return self.llm.generate_prompt(\n\u001b[0m\u001b[1;32m     80\u001b[0m             \u001b[0mprompts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_child\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mrun_manager\u001b[0m \u001b[0;32melse\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     81\u001b[0m         )\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/llms/base.py\u001b[0m in \u001b[0;36mgenerate_prompt\u001b[0;34m(self, prompts, stop, callbacks)\u001b[0m\n\u001b[1;32m    132\u001b[0m     ) -> LLMResult:\n\u001b[1;32m    133\u001b[0m         \u001b[0mprompt_strings\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;34m[\u001b[0m\u001b[0mp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_string\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mp\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mprompts\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 134\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgenerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprompt_strings\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstop\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcallbacks\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    135\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    136\u001b[0m     async def agenerate_prompt(\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/llms/base.py\u001b[0m in \u001b[0;36mgenerate\u001b[0;34m(self, prompts, stop, callbacks)\u001b[0m\n\u001b[1;32m    189\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mKeyboardInterrupt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mException\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    190\u001b[0m                 \u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_llm_error\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 191\u001b[0;31m                 \u001b[0;32mraise\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    192\u001b[0m             \u001b[0mrun_manager\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mon_llm_end\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    193\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0moutput\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/llms/base.py\u001b[0m in \u001b[0;36mgenerate\u001b[0;34m(self, prompts, stop, callbacks)\u001b[0m\n\u001b[1;32m    183\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    184\u001b[0m                 output = (\n\u001b[0;32m--> 185\u001b[0;31m                     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_generate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprompts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstop\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    186\u001b[0m                     \u001b[0;32mif\u001b[0m \u001b[0mnew_arg_supported\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    187\u001b[0m                     \u001b[0;32melse\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_generate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprompts\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstop\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/llms/base.py\u001b[0m in \u001b[0;36m_generate\u001b[0;34m(self, prompts, stop, run_manager)\u001b[0m\n\u001b[1;32m    434\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0mprompt\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mprompts\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    435\u001b[0m             text = (\n\u001b[0;32m--> 436\u001b[0;31m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprompt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstop\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrun_manager\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrun_manager\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    437\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mnew_arg_supported\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    438\u001b[0m                 \u001b[0;32melse\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mprompt\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstop\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/langchain/llms/sagemaker_endpoint.py\u001b[0m in \u001b[0;36m_call\u001b[0;34m(self, prompt, stop, run_manager)\u001b[0m\n\u001b[1;32m    232\u001b[0m         \u001b[0;31m# send request\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    233\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 234\u001b[0;31m             response = self.client.invoke_endpoint(\n\u001b[0m\u001b[1;32m    235\u001b[0m                 \u001b[0mEndpointName\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mendpoint_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    236\u001b[0m                 \u001b[0mBody\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/client.py\u001b[0m in \u001b[0;36m_api_call\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m    528\u001b[0m                 )\n\u001b[1;32m    529\u001b[0m             \u001b[0;31m# The \"self\" in this scope is referring to the BaseClient.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 530\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_make_api_call\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moperation_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    531\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    532\u001b[0m         \u001b[0m_api_call\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpy_operation_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/client.py\u001b[0m in \u001b[0;36m_make_api_call\u001b[0;34m(self, operation_name, api_params)\u001b[0m\n\u001b[1;32m    945\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    946\u001b[0m             \u001b[0mapply_request_checksum\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest_dict\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 947\u001b[0;31m             http, parsed_response = self._make_request(\n\u001b[0m\u001b[1;32m    948\u001b[0m                 \u001b[0moperation_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_context\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    949\u001b[0m             )\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/client.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, operation_model, request_dict, request_context)\u001b[0m\n\u001b[1;32m    968\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_make_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_context\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    969\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 970\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_endpoint\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmake_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moperation_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest_dict\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    971\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    972\u001b[0m             self.meta.events.emit(\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36mmake_request\u001b[0;34m(self, operation_model, request_dict)\u001b[0m\n\u001b[1;32m    117\u001b[0m             \u001b[0mrequest_dict\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    118\u001b[0m         )\n\u001b[0;32m--> 119\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_send_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    120\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    121\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mcreate_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_send_request\u001b[0;34m(self, request_dict, operation_model)\u001b[0m\n\u001b[1;32m    197\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_update_retries_context\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mcontext\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mattempts\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    198\u001b[0m         \u001b[0mrequest\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcreate_request\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest_dict\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 199\u001b[0;31m         success_response, exception = self._get_response(\n\u001b[0m\u001b[1;32m    200\u001b[0m             \u001b[0mrequest\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    201\u001b[0m         )\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_get_response\u001b[0;34m(self, request, operation_model, context)\u001b[0m\n\u001b[1;32m    239\u001b[0m         \u001b[0;31m# If an exception occurs then the success_response is None.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    240\u001b[0m         \u001b[0;31m# If no exception occurs then exception is None.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 241\u001b[0;31m         success_response, exception = self._do_get_response(\n\u001b[0m\u001b[1;32m    242\u001b[0m             \u001b[0mrequest\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moperation_model\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcontext\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    243\u001b[0m         )\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_do_get_response\u001b[0;34m(self, request, operation_model, context)\u001b[0m\n\u001b[1;32m    279\u001b[0m             \u001b[0mhttp_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mfirst_non_none_response\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mresponses\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    280\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mhttp_response\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 281\u001b[0;31m                 \u001b[0mhttp_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_send\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    282\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0mHTTPClientError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    283\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/endpoint.py\u001b[0m in \u001b[0;36m_send\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    375\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    376\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_send\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 377\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhttp_session\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msend\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    378\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    379\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/botocore/httpsession.py\u001b[0m in \u001b[0;36msend\u001b[0;34m(self, request)\u001b[0m\n\u001b[1;32m    463\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    464\u001b[0m             \u001b[0mrequest_target\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_request_target\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mproxy_url\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 465\u001b[0;31m             urllib_response = conn.urlopen(\n\u001b[0m\u001b[1;32m    466\u001b[0m                 \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrequest\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    467\u001b[0m                 \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mrequest_target\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36murlopen\u001b[0;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[1;32m    701\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    702\u001b[0m             \u001b[0;31m# Make the request on the httplib connection object.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 703\u001b[0;31m             httplib_response = self._make_request(\n\u001b[0m\u001b[1;32m    704\u001b[0m                 \u001b[0mconn\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    705\u001b[0m                 \u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m    447\u001b[0m                     \u001b[0;31m# Python 3 (including for exceptions like SystemExit).\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    448\u001b[0m                     \u001b[0;31m# Otherwise it looks like a bug in the code.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 449\u001b[0;31m                     \u001b[0msix\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mraise_from\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    450\u001b[0m         \u001b[0;32mexcept\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0mSocketTimeout\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mBaseSSLError\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mSocketError\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    451\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_raise_timeout\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0murl\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0murl\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtimeout_value\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mread_timeout\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/urllib3/packages/six.py\u001b[0m in \u001b[0;36mraise_from\u001b[0;34m(value, from_value)\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/site-packages/urllib3/connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[0;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[1;32m    442\u001b[0m                 \u001b[0;31m# Python 3\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    443\u001b[0m                 \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 444\u001b[0;31m                     \u001b[0mhttplib_response\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconn\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    445\u001b[0m                 \u001b[0;32mexcept\u001b[0m \u001b[0mBaseException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    446\u001b[0m                     \u001b[0;31m# Remove the TypeError from the exception chain in\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/http/client.py\u001b[0m in \u001b[0;36mgetresponse\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1375\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1376\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1377\u001b[0;31m                 \u001b[0mresponse\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbegin\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1378\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mConnectionError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1379\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/http/client.py\u001b[0m in \u001b[0;36mbegin\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    318\u001b[0m         \u001b[0;31m# read until we get a non-100 response\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    319\u001b[0m         \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 320\u001b[0;31m             \u001b[0mversion\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstatus\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mreason\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_read_status\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    321\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mCONTINUE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    322\u001b[0m                 \u001b[0;32mbreak\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/http/client.py\u001b[0m in \u001b[0;36m_read_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    279\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    280\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_read_status\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 281\u001b[0;31m         \u001b[0mline\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreadline\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0m_MAXLINE\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"iso-8859-1\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    282\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mline\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0m_MAXLINE\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    283\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mLineTooLong\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"status line\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/socket.py\u001b[0m in \u001b[0;36mreadinto\u001b[0;34m(self, b)\u001b[0m\n\u001b[1;32m    702\u001b[0m         \u001b[0;32mwhile\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    703\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 704\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sock\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mb\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    705\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    706\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_timeout_occurred\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/ssl.py\u001b[0m in \u001b[0;36mrecv_into\u001b[0;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[1;32m   1240\u001b[0m                   \u001b[0;34m\"non-zero flags not allowed in calls to recv_into() on %s\"\u001b[0m \u001b[0;34m%\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1241\u001b[0m                   self.__class__)\n\u001b[0;32m-> 1242\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnbytes\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1243\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1244\u001b[0m             \u001b[0;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbuffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnbytes\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/pytorch_p39/lib/python3.9/ssl.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, len, buffer)\u001b[0m\n\u001b[1;32m   1098\u001b[0m         \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1099\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0mbuffer\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1100\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1101\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1102\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "requests_wrapper = RequestsWrapper(headers={'Content-Type':'application/json'})\n",
    "\n",
    "\n",
    "todo_agent = planner.create_openapi_agent(openai_api_spec, aws_requests, llm_sg)\n",
    "user_query = \"list all river's todo.\"\n",
    "todo_agent.run(user_query)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "24f717d6-292c-45ff-a76c-8bd1e37413d6",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "conda_pytorch_p39",
   "language": "python",
   "name": "conda_pytorch_p39"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}