Spaces:
Runtime error
Runtime error
File size: 5,583 Bytes
2ef1d57 |
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 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"from langchain import OpenAI\n",
"from langchain.memory import ConversationKGMemory\n",
"\n",
"\n",
"llm = OpenAI(temperature=0)\n",
"from langchain.prompts.prompt import PromptTemplate\n",
"from langchain.chains import ConversationChain\n",
"\n",
"template = \"\"\"The following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"{history}\n",
"\n",
"Conversation:\n",
"Human: {input}\n",
"AI:\"\"\"\n",
"prompt = PromptTemplate(\n",
" input_variables=[\"history\", \"input\"], template=template\n",
")\n",
"conversation_with_kg = ConversationChain(\n",
" llm=llm, \n",
" verbose=True, \n",
" prompt=prompt,\n",
" memory=ConversationKGMemory(llm=llm)\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"\n",
"\n",
"Conversation:\n",
"Human: 你好\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' 你好！很高兴见到你。我是一个AI，我可以回答你的问题。你想问我什么？'"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_kg.predict(input=\"你好\")"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"\n",
"\n",
"Conversation:\n",
"Human: 我叫李振，我正在帮助张三写作业，他是一名小学生。\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' 哦，你好李振！很高兴认识你。我知道张三是一名小学生，他有多大了？'"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_kg.predict(input=\"我叫李振，我正在帮助张三写作业，他是一名小学生。\")"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
"\n",
"On 张三: 张三 是 一名小学生.\n",
"\n",
"Conversation:\n",
"Human: 关于张三，你了解多少\n",
"AI:\u001b[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
]
},
{
"data": {
"text/plain": [
"' 我知道张三是一名小学生。'"
]
},
"execution_count": 24,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"conversation_with_kg.predict(input=\"关于张三，你了解多少\")"
]
}
],
"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
}
|