File size: 8,989 Bytes
cfd3735
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Human as a tool\n",
    "\n",
    "Human are AGI so they can certainly be used as a tool to help out AI agent \n",
    "when it is confused."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "from langchain.chat_models import ChatOpenAI\n",
    "from langchain.llms import OpenAI\n",
    "from langchain.agents import load_tools, initialize_agent\n",
    "from langchain.agents import AgentType\n",
    "\n",
    "llm = ChatOpenAI(temperature=0.0)\n",
    "math_llm = OpenAI(temperature=0.0)\n",
    "tools = load_tools(\n",
    "    [\"human\", \"llm-math\"], \n",
    "    llm=math_llm,\n",
    ")\n",
    "\n",
    "agent_chain = initialize_agent(\n",
    "    tools,\n",
    "    llm,\n",
    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
    "    verbose=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In the above code you can see the tool takes input directly from command line.\n",
    "You can customize `prompt_func` and `input_func` according to your need (as shown below)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mI don't know Eric's surname, so I should ask a human for guidance.\n",
      "Action: Human\n",
      "Action Input: \"What is Eric's surname?\"\u001b[0m\n",
      "\n",
      "What is Eric's surname?\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " Zhu\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Observation: \u001b[36;1m\u001b[1;3mZhu\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI now know Eric's surname is Zhu.\n",
      "Final Answer: Eric's surname is Zhu.\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "\"Eric's surname is Zhu.\""
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(\"What's my friend Eric's surname?\")\n",
    "# Answer with 'Zhu'"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configuring the Input Function\n",
    "\n",
    "By default, the `HumanInputRun` tool uses the python `input` function to get input from the user.\n",
    "You can customize the input_func to be anything you'd like.\n",
    "For instance, if you want to accept multi-line input, you could do the following:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def get_input() -> str:\n",
    "    print(\"Insert your text. Enter 'q' or press Ctrl-D (or Ctrl-Z on Windows) to end.\")\n",
    "    contents = []\n",
    "    while True:\n",
    "        try:\n",
    "            line = input()\n",
    "        except EOFError:\n",
    "            break\n",
    "        if line == \"q\":\n",
    "            break\n",
    "        contents.append(line)\n",
    "    return \"\\n\".join(contents)\n",
    "\n",
    "\n",
    "# You can modify the tool when loading\n",
    "tools = load_tools(\n",
    "    [\"human\", \"ddg-search\"], \n",
    "    llm=math_llm,\n",
    "    input_func=get_input\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Or you can directly instantiate the tool\n",
    "from langchain.tools import HumanInputRun\n",
    "\n",
    "tool = HumanInputRun(input_func=get_input)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "agent_chain = initialize_agent(\n",
    "    tools,\n",
    "    llm,\n",
    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
    "    verbose=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "\u001b[32;1m\u001b[1;3mI should ask a human for guidance\n",
      "Action: Human\n",
      "Action Input: \"Can you help me attribute a quote?\"\u001b[0m\n",
      "\n",
      "Can you help me attribute a quote?\n",
      "Insert your text. Enter 'q' or press Ctrl-D (or Ctrl-Z on Windows) to end.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " vini\n",
      " vidi\n",
      " vici\n",
      " q\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Observation: \u001b[36;1m\u001b[1;3mvini\n",
      "vidi\n",
      "vici\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI need to provide more context about the quote\n",
      "Action: Human\n",
      "Action Input: \"The quote is 'Veni, vidi, vici'\"\u001b[0m\n",
      "\n",
      "The quote is 'Veni, vidi, vici'\n",
      "Insert your text. Enter 'q' or press Ctrl-D (or Ctrl-Z on Windows) to end.\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      " oh who said it \n",
      " q\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Observation: \u001b[36;1m\u001b[1;3moh who said it \u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI can use DuckDuckGo Search to find out who said the quote\n",
      "Action: DuckDuckGo Search\n",
      "Action Input: \"Who said 'Veni, vidi, vici'?\"\u001b[0m\n",
      "Observation: \u001b[33;1m\u001b[1;3mUpdated on September 06, 2019. \"Veni, vidi, vici\" is a famous phrase said to have been spoken by the Roman Emperor Julius Caesar (100-44 BCE) in a bit of stylish bragging that impressed many of the writers of his day and beyond. The phrase means roughly \"I came, I saw, I conquered\" and it could be pronounced approximately Vehnee, Veedee ... Veni, vidi, vici (Classical Latin: [we藧ni藧 wi藧di藧 wi藧ki藧], Ecclesiastical Latin: [藞veni 藞vidi 藞vit蕛i]; \"I came; I saw; I conquered\") is a Latin phrase used to refer to a swift, conclusive victory.The phrase is popularly attributed to Julius Caesar who, according to Appian, used the phrase in a letter to the Roman Senate around 47 BC after he had achieved a quick victory in his short ... veni, vidi, vici Latin quotation from Julius Caesar ve路 ni, vi路 di, vi路 ci 藢w膩-n膿 藢w膿-d膿 藞w膿-k膿 藢v膩-n膿 藢v膿-d膿 藞v膿-ch膿 : I came, I saw, I conquered Articles Related to veni, vidi, vici 'In Vino Veritas' and Other Latin... Dictionary Entries Near veni, vidi, vici Venite veni, vidi, vici Veniz茅los See More Nearby Entries Cite this Entry Style The simplest explanation for why veni, vidi, vici is a popular saying is that it comes from Julius Caesar, one of history's most famous figures, and has a simple, strong meaning: I'm powerful and fast. But it's not just the meaning that makes the phrase so powerful. Caesar was a gifted writer, and the phrase makes use of Latin grammar to ... One of the best known and most frequently quoted Latin expression, veni, vidi, vici may be found hundreds of times throughout the centuries used as an expression of triumph. The words are said to have been used by Caesar as he was enjoying a triumph.\u001b[0m\n",
      "Thought:\u001b[32;1m\u001b[1;3mI now know the final answer\n",
      "Final Answer: Julius Caesar said the quote \"Veni, vidi, vici\" which means \"I came, I saw, I conquered\".\u001b[0m\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'Julius Caesar said the quote \"Veni, vidi, vici\" which means \"I came, I saw, I conquered\".'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "agent_chain.run(\"I need help attributing a quote\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.11.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}