File size: 2,738 Bytes
fdb9357
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from typing import Any, Dict\n",
    "\n",
    "from langchain.agents import AgentType, initialize_agent\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.tools.requests.tool import RequestsGetTool, TextRequestsWrapper\n",
    "from pydantic import BaseModel, Field, root_validator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm = OpenAI(temperature=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tldextract\n",
    "\n",
    "_APPROVED_DOMAINS = {\n",
    "    \"langchain\",\n",
    "    \"wikipedia\",\n",
    "}\n",
    "\n",
    "class ToolInputSchema(BaseModel):\n",
    "\n",
    "    url: str = Field(...)\n",
    "    \n",
    "    @root_validator\n",
    "    def validate_query(cls, values: Dict[str, Any]) -> Dict:\n",
    "        url = values[\"url\"]\n",
    "        domain = tldextract.extract(url).domain\n",
    "        if domain not in _APPROVED_DOMAINS:\n",
    "            raise ValueError(f\"Domain {domain} is not on the approved list:\"\n",
    "                             f\" {sorted(_APPROVED_DOMAINS)}\")\n",
    "        return values\n",
    "    \n",
    "tool = RequestsGetTool(args_schema=ToolInputSchema, requests_wrapper=TextRequestsWrapper())\n",
    "# tool = RequestsGetTool( requests_wrapper=TextRequestsWrapper())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "agent = initialize_agent([tool], llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The main title on langchain.com is \"LANG CHAIN πŸ¦œοΈπŸ”— Official Home Page\".\n"
     ]
    }
   ],
   "source": [
    "# This will succeed, since there aren't any arguments that will be triggered during validation\n",
    "answer = agent.run(\"What's the main title on langchain.com?\")\n",
    "print(answer)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "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": "3.10.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}