File size: 12,614 Bytes
f9bd6e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a href=\"https://colab.research.google.com/github/microsoft/autogen/blob/main/notebook/agentchat_groupchat.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Auto Generated Agent Chat: Group Chat\n",
    "\n",
    "AutoGen offers conversable agents powered by LLM, tool or human, which can be used to perform tasks collectively via automated chat. This framwork allows tool use and human participance through multi-agent conversation.\n",
    "Please find documentation about this feature [here](https://microsoft.github.io/autogen/docs/Use-Cases/agent_chat).\n",
    "\n",
    "This notebook is modified based on https://github.com/microsoft/FLAML/blob/4ea686af5c3e8ff24d9076a7a626c8b28ab5b1d7/notebook/autogen_multiagent_roleplay_chat.ipynb\n",
    "\n",
    "## Requirements\n",
    "\n",
    "AutoGen requires `Python>=3.8`. To run this notebook example, please install:\n",
    "```bash\n",
    "pip install pyautogen\n",
    "```"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 105,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%capture --no-stderr\n",
    "# %pip install pyautogen~=0.1.0"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Set your API Endpoint\n",
    "\n",
    "The [`config_list_from_json`](https://microsoft.github.io/autogen/docs/reference/oai/openai_utils#config_list_from_json) function loads a list of configurations from an environment variable or a json file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 106,
   "metadata": {},
   "outputs": [],
   "source": [
    "import autogen\n",
    "\n",
    "config_list_gpt4 = autogen.config_list_from_json(\n",
    "    \"OAI_CONFIG_LIST\",\n",
    "    filter_dict={\n",
    "        \"model\": [\"gpt-4\", \"gpt-4-0314\", \"gpt4\", \"gpt-4-32k\", \"gpt-4-32k-0314\", \"gpt-4-32k-v0314\"],\n",
    "    },\n",
    ")\n",
    "# config_list_gpt35 = autogen.config_list_from_json(\n",
    "#     \"OAI_CONFIG_LIST\",\n",
    "#     filter_dict={\n",
    "#         \"model\": {\n",
    "#             \"gpt-3.5-turbo\",\n",
    "#             \"gpt-3.5-turbo-16k\",\n",
    "#             \"gpt-3.5-turbo-0301\",\n",
    "#             \"chatgpt-35-turbo-0301\",\n",
    "#             \"gpt-35-turbo-v0301\",\n",
    "#         },\n",
    "#     },\n",
    "# )"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "It first looks for environment variable \"OAI_CONFIG_LIST\" which needs to be a valid json string. If that variable is not found, it then looks for a json file named \"OAI_CONFIG_LIST\". It filters the configs by models (you can filter by other keys as well). Only the gpt-4 models are kept in the list based on the filter condition.\n",
    "\n",
    "The config list looks like the following:\n",
    "```python\n",
    "config_list = [\n",
    "    {\n",
    "        'model': 'gpt-4',\n",
    "        'api_key': '<your OpenAI API key here>',\n",
    "    },\n",
    "    {\n",
    "        'model': 'gpt-4',\n",
    "        'api_key': '<your Azure OpenAI API key here>',\n",
    "        'api_base': '<your Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },\n",
    "    {\n",
    "        'model': 'gpt-4-32k',\n",
    "        'api_key': '<your Azure OpenAI API key here>',\n",
    "        'api_base': '<your Azure OpenAI API base here>',\n",
    "        'api_type': 'azure',\n",
    "        'api_version': '2023-06-01-preview',\n",
    "    },\n",
    "]\n",
    "```\n",
    "\n",
    "If you open this notebook in colab, you can upload your files by clicking the file icon on the left panel and then choose \"upload file\" icon.\n",
    "\n",
    "You can set the value of config_list in other ways you prefer, e.g., loading from a YAML file."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Construct Agents"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 107,
   "metadata": {},
   "outputs": [],
   "source": [
    "llm_config = {\"config_list\": config_list_gpt4, \"seed\": 42}\n",
    "user_proxy = autogen.UserProxyAgent(\n",
    "   name=\"User_proxy\",\n",
    "   system_message=\"A human admin.\",\n",
    "   code_execution_config={\"last_n_messages\": 2, \"work_dir\": \"groupchat\"},\n",
    "   human_input_mode=\"TERMINATE\"\n",
    ")\n",
    "coder = autogen.AssistantAgent(\n",
    "    name=\"Coder\",\n",
    "    llm_config=llm_config,\n",
    ")\n",
    "pm = autogen.AssistantAgent(\n",
    "    name=\"Product_manager\",\n",
    "    system_message=\"Creative in software product ideas.\",\n",
    "    llm_config=llm_config,\n",
    ")\n",
    "groupchat = autogen.GroupChat(agents=[user_proxy, coder, pm], messages=[], max_round=12)\n",
    "manager = autogen.GroupChatManager(groupchat=groupchat, llm_config=llm_config)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Start Chat"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 108,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[33mUser_proxy\u001b[0m (to chat_manager):\n",
      "\n",
      "Find a latest paper about gpt-4 on arxiv and find its potential applications in software.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mCoder\u001b[0m (to chat_manager):\n",
      "\n",
      "To find the latest paper about GPT-4 on arxiv, I'll provide you with a Python code that fetches the most recent papers from the arxiv API and filters the results to get the most relevant paper related to GPT-4. After fetching the paper, I'll extract the information for potential applications in software. Please execute the following Python code:\n",
      "\n",
      "```python\n",
      "import requests\n",
      "from bs4 import BeautifulSoup\n",
      "import re\n",
      "\n",
      "def fetch_arxiv_papers(query):\n",
      "    base_url = \"http://export.arxiv.org/api/query?\"\n",
      "    search_query = \"all:\" + query\n",
      "    response = requests.get(base_url, params={\"search_query\": search_query, \"sortBy\": \"submittedDate\", \"sortOrder\": \"descending\"})\n",
      "    return BeautifulSoup(response.content, \"xml\")\n",
      "\n",
      "def find_gpt4_paper():\n",
      "    papers = fetch_arxiv_papers(\"gpt-4\")\n",
      "    for entry in papers.find_all(\"entry\"):\n",
      "        title = entry.title.text.strip()\n",
      "        summary = entry.summary.text.strip()\n",
      "        if \"gpt-4\" in title.lower() or \"gpt-4\" in summary.lower():\n",
      "            return {\"title\": title, \"summary\": summary}\n",
      "\n",
      "gpt4_paper = find_gpt4_paper()\n",
      "if gpt4_paper:\n",
      "    print(\"Title:\", gpt4_paper[\"title\"])\n",
      "    print(\"Summary:\", gpt4_paper[\"summary\"])\n",
      "else:\n",
      "    print(\"No recent GPT-4 papers found.\")\n",
      "```\n",
      "\n",
      "Once we have the paper details, I'll analyze the summary to identify potential applications in software development.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[31m\n",
      ">>>>>>>> EXECUTING CODE BLOCK 0 (inferred language is python)...\u001b[0m\n",
      "\u001b[33mUser_proxy\u001b[0m (to chat_manager):\n",
      "\n",
      "exitcode: 0 (execution succeeded)\n",
      "Code output: \n",
      "Title: FIMO: A Challenge Formal Dataset for Automated Theorem Proving\n",
      "Summary: We present FIMO, an innovative dataset comprising formal mathematical problem\n",
      "statements sourced from the International Mathematical Olympiad (IMO)\n",
      "Shortlisted Problems. Designed to facilitate advanced automated theorem proving\n",
      "at the IMO level, FIMO is currently tailored for the Lean formal language. It\n",
      "comprises 149 formal problem statements, accompanied by both informal problem\n",
      "descriptions and their corresponding LaTeX-based informal proofs. Through\n",
      "initial experiments involving GPT-4, our findings underscore the existing\n",
      "limitations in current methodologies, indicating a substantial journey ahead\n",
      "before achieving satisfactory IMO-level automated theorem proving outcomes.\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mProduct_manager\u001b[0m (to chat_manager):\n",
      "\n",
      "Based on the paper titled \"FIMO: A Challenge Formal Dataset for Automated Theorem Proving\" and its summary, the potential applications of GPT-4 in software development can be related to the field of automated theorem proving.\n",
      "\n",
      "1. **Automated theorem proving**: GPT-4 can be utilized in the development of automated theorem proving software that attempts to prove complex mathematical problems taken from International Mathematical Olympiad (IMO) or other challenging sources. By fine-tuning GPT-4 with a dataset like FIMO consisting of formal mathematical problems, the model can potentially better understand the problem statements and generate appropriate proofs.\n",
      "\n",
      "2. **Mathematical problem-solving assistants**: Software tools can be developed using GPT-4 to guide users in solving complex mathematical problems. The AI model can be integrated into educational platforms, online math tutoring services, or even standalone tools to help make solving problems easier and faster for students and professionals alike.\n",
      "\n",
      "3. **Formal language translation**: GPT-4 can potentially be integrated into software for translating between formal languages, assisting in the understanding and comparison of various formal systems. This would be especially useful in research communities employing different formal languages and wanting to share ideas and results.\n",
      "\n",
      "4. **Mathematical proof checking**: GPT-4 can be employed in proof-checking software to identify and correct inconsistencies. By improving the correctness of proofs, this application would ultimately help users save time and contribute to the overall quality of mathematical research.\n",
      "\n",
      "Please note that this paper highlights the current limitations of GPT-4 in the context of IMO-level theorem proving. Nevertheless, these potential applications suggest directions for further research and software development as the model and related techniques continue to improve.\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mUser_proxy\u001b[0m (to chat_manager):\n",
      "\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[31m\n",
      ">>>>>>>> USING AUTO REPLY...\u001b[0m\n",
      "\u001b[33mUser_proxy\u001b[0m (to chat_manager):\n",
      "\n",
      "\n",
      "\n",
      "--------------------------------------------------------------------------------\n",
      "\u001b[33mCoder\u001b[0m (to chat_manager):\n",
      "\n",
      "TERMINATE\n",
      "\n",
      "--------------------------------------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "user_proxy.initiate_chat(manager, message=\"Find a latest paper about gpt-4 on arxiv and find its potential applications in software.\")\n",
    "# type exit to terminate the chat"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "flaml",
   "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": "3.9.17"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}