File size: 2,997 Bytes
d7ed536
 
 
 
ebe91e9
d7ed536
 
 
 
 
 
 
 
 
 
 
 
 
ebe91e9
d7ed536
 
 
 
 
 
 
 
 
 
 
 
 
 
ebe91e9
d7ed536
 
 
 
 
 
 
 
ebe91e9
d7ed536
 
 
 
 
 
 
 
 
ebe91e9
d7ed536
 
 
 
 
 
 
 
 
 
ebe91e9
d7ed536
 
 
 
 
 
 
 
ebe91e9
d7ed536
 
 
 
 
 
 
ebe91e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d7ed536
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.prompts import PromptTemplate, ChatPromptTemplate, HumanMessagePromptTemplate\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.output_parsers import PydanticOutputParser\n",
    "from pydantic import BaseModel, Field, validator\n",
    "from typing import List"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "class Actor(BaseModel):\n",
    "    name: str = Field(description=\"name of an actor\")\n",
    "    film_names: List[str] = Field(description=\"list of names of films they starred in\")\n",
    "        \n",
    "actor_query = \"Generate the filmography for a random actor.\"\n",
    "\n",
    "parser = PydanticOutputParser(pydantic_object=Actor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "misformatted = \"{'name': \\\"Tom Hanks\\\", \\\"film_names\\\": [\\\"Forrest Gump\\\"]}\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 将报解析错误。\n",
    "# parser.parse(misformatted)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "from langchain.output_parsers import OutputFixingParser\n",
    "\n",
    "new_parser = OutputFixingParser.from_llm(parser=parser, llm=OpenAI())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Actor(name='Tom Hanks', film_names=['Forrest Gump'])"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "new_parser.parse(misformatted)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Actor(name='Tom Hanks', film_names=['Forrest Gump', 'Saving Private Ryan'])"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# test_str = '{\"name\": \"Tom Hanks\", \"film_names\": [\"Forrest Gump\"]}'\n",
    "test_str = '{\"name\": \"Tom Hanks\"}'\n",
    "# parser.parse(test_str)\n",
    "\n",
    "new_parser.parse(test_str)"
   ]
  }
 ],
 "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
}