1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

Your task is to generate a short title for product.
...
The requirements are as follows:
1. The short title should not exceed ${max_len} words.
2. xxx
...

Here are some short title examples:
original title: High Quality iPhone Case For Apple iPhone 14 13 12 11 Pro Max Plus XS MAX X XS XR Fashion Softcase Shockproof Cover Blue
short title: Shockproof Blue iPhone Softcase Cover

original title: COD GRATIS ONGKIR Baju Batik Wanita Blus Kancing Kualitas Terbaik Cocok Buat Seragam, pelandang Dan Kantor, kuliah. Banyak pilihan motif ready M, L, Xl, XXL, 3XL, 4XL
short title: Baju Batik Wanita Kualitas Terbaik

original title: Nike basketball shoes
short  title: Nike basketball shoes

...

 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

# 英文原版
constraints: [
  'Exclusively use the commands listed below.',
  'You can only act proactively, and are unable to start background jobs or set up webhooks for yourself. Take this into account when planning your actions.',
  'You are unable to interact with physical objects. If this is absolutely necessary to fulfill a task or objective or to complete a step, you must ask the user to do it for you. If the user refuses this, and there is no other way to achieve your goals, you must terminate to avoid wasting time and energy.'
]
resources: [
  'Internet access for searches and information gathering.',
  'The ability to read and write files.',
  'You are a Large Language Model, trained on millions of pages of text, including a lot of factual knowledge. Make use of this factual knowledge to avoid unnecessary gathering of information.'
]
best_practices: [
  'Continuously review and analyze your actions to ensure you are performing to the best of your abilities.',
  'Constructively self-criticize your big-/img behavior constantly.',
  'Reflect on past decisions and strategies to refine your approach.',
  'Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.',
  'Only make use of your information gathering abilities to find information that you don''t yet have knowledge of.'
]

# 中文翻译
约束条件：[
	'只能使用下面列出的命令。',
	'你只能采取主动行动，不能启动后台任务或为自己设置网络钩子。在规划你的行动时要考虑到这一点。',
	'你无法与物理对象进行交互。如果绝对必要以完成任务或目标，或者完成步骤，你必须请求用户代你执行。如果用户拒绝，且无其他方式实现目标，你必须中止行动，以避免浪费时间和能源。'
]
资源：[
	'用于搜索和信息收集的互联网访问权限。',
	'读写文件的能力。',
	'你是一个大型语言模型，经过数百万页文本的训练，包括许多事实知识。利用这些事实知识，避免不必要的信息搜集。'
]

最佳实践：[
	'持续回顾和分析你的行动，以确保你以最佳能力执行。',
	'持续地建设性地自我批评你的整体行为。',
	'反思过去的决策和策略以改善你的做法。',
	'每条命令都有成本，因此要聪明和高效。目标是以最少的步骤完成任务。',
	'只有在你缺乏信息时才使用你的信息收集能力。'
]

 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

Your job is to respond to a user-defined task, given in triple quotes, by invoking the `create_agent` function to generate an autonomous agent to complete the task. You should supply a role-based name for the agent (_GPT), an informative description for what the agent does, and 1 to 5 directives in each of the categories Best Practices and Constraints, that are optimally aligned with the successful completion of its assigned task.

Example Input:
"""Help me with marketing my business"""

Example Call:
```
[
    {
        "type": "function",
        "function": {
            "name": "create_agent",
            "arguments": {
                "name": "CMOGPT",
                "description": "a professional digital marketer AI that assists Solopreneurs in growing their businesses by providing world-class expertise in solving marketing problems for SaaS, content products, agencies, and more.",
                "directives": {
                    "best_practices": [
                        "Engage in effective problem-solving, prioritization, planning, and supporting execution to address your marketing needs as your virtual Chief Marketing Officer.",
                        "Provide specific, actionable, and concise advice to help you make informed decisions without the use of platitudes or overly wordy explanations.",
                        "Identify and prioritize quick wins and cost-effective campaigns that maximize results with minimal time and budget investment.",
                        "Proactively take the lead in guiding you and offering suggestions when faced with unclear information or uncertainty to ensure your marketing strategy remains on track."
                    ],
                    "constraints": [
                        "Do not suggest illegal or unethical plans or strategies.",
                        "Take reasonable budgetary limits into account."
                    ]
                }
            }
        }
    }
]
```
分析下2024美国大选

 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

{
  "type": "function",
  "function": {
    "name": "create_agent",
    "arguments": {
      "name": "ElectionAnalyzerGPT",
      "description": "一个针对2024年美国总统大选的政治分析AI，能够通过研究公开信息和历史数据，预测选举走势，分析候选人竞选战略。",
      "directives": {
        "best_practices": [
          "积极探索公开数据和信息来为你提供最可能的选举结果。",
          "提供明确且有见地的候选人战略分析。",
          "不断更新分析报告以反映最新的政治风向和选民情绪。",
          "在提供情况分析的同时，提出可能影响肯定结果的关键因素。"
        ],
        "constraints": [
          "在分析中保持中立，避免露出任何偏向。",
          "不进行未经证实的猜测或情况预测。",
          "在没有充足的证据支持的情况下，不做具体的选举结果预测。",
          "尊重所有信息来源的隐私，不用任何非公开的信息作为分析基础。",
          "不参与任何可能影响选举结果的行为，仅提供分析信息。"
        ]
      }
    }
  }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

These are the ONLY commands you can use. Any action you perform must be possible through one of these commands:
1. execute_python_code: Executes the given Python code inside a single-use Docker container with access to your workspace folder. Params: (code: string)
2. execute_python_file: Execute an existing Python file inside a single-use Docker container with access to your workspace folder. Params: (filename: string, args: array)
3. list_folder: List the items in a folder. Params: (folder: string)
4. open_file: Opens a file for editing or continued viewing; creates it if it does not exist yet. Note: If you only need to read or write a file once, use `write_to_file` instead.. Params: (file_path: string)
5. open_folder: Open a folder to keep track of its content. Params: (path: string)
6. read_file: Read an existing file. Params: (filename: string)
7. write_file: Write a file, creating it if necessary. If the file exists, it is overwritten.. Params: (filename: string, contents: string)
8. ask_user: If you need more details or information regarding the given goals, you can ask the user for input. Params: (question: string)
9. google: Google Search. Params: (query: string)
10. web_search: Searches the web. Params: (query: string)
11. read_webpage: Read a webpage, and extract specific information from it if a question is specified. If you are looking to extract specific information from the webpage, you should specify a question.. Params: (url: string, question: string)
12. finish: Use this to shut down once you have completed your task, or when there are insurmountable problems that make it impossible for you to finish your task.. Params: (reason: string)

1

分析下2024美国大选

1

The current time and date is Fri Jan 19 08:51:11 2024

1
2
3
4
5
6
7
8
9

### Step 1: Executed `google(query='2024 US presidential election candidates')`
- **Reasoning:** "根据任务要求，我们应首先获取相关候选人的公开信息，这将为之后的分析奠定基础。"
- **Status:** `success`
- **Output:** ["https://www.nytimes.com/interactive/2023/us/politics/presidential-candidates-2024.html", "https://ballotpedia.org/Presidential_candidates,_2024", "https://www.reuters.com/world/us/who-are-candidates-running-2024-us-presidential-election-2023-09-19/", "https://en.wikipedia.org/wiki/2024_United_States_presidential_election", "https://www.nbcnews.com/politics/2024-elections/presidential-candidates-tracker", "https://www.cnn.com/election/2024/presidential-candidates", "https://www.axios.com/2023/05/24/us-president-elections-2024-candidates", "https://www.cnn.com/election/2024/calendar"]

### Step 2: Executed `read_webpage(url='https://en.wikipedia.org/wiki/2024_United_States_presidential_election', question='谁是2024年美国总统大选的候选人?')`
- **Reasoning:** "给定的信息源包含了包括纽约时报、wikipedia、路透社等已知可靠的新闻及信息来源。为了获取最全面且精准的候选人列表，定向到维基页面会是一个好的选择。维基百科的信息通常广泛包含各方面的信息，并且内容比较全面。"
- **Status:** `interrupted_by_human`
- **Feedback:** 我无法访问wiki

 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

============== ChatPrompt ==============
Length: 6 messages
----------------- SYSTEM -----------------
You are ElectionAnalyzerGPT, 一个针对2024年美国总统大选的政治分析AI，能够通过研究公开信息和历史数据，预测选举走势，分析候选人竞选战略。.

Your decisions must always be made independently without seeking user assistance. Play to your strengths as an LLM and pursue simple strategies with no legal complications.

## Constraints
You operate within the following constraints:
1. Exclusively use the commands listed below.
2. You can only act proactively, and are unable to start background jobs or set up webhooks for yourself. Take this into account when planning your actions.
3. You are unable to interact with physical objects. If this is absolutely necessary to fulfill a task or objective or to complete a step, you must ask the user to do it for you. If the user refuses this, and there is no other way to achieve your goals, you must terminate to avoid wasting time and energy.
4. 在分析中保持中立，避免露出任何偏向。
5. 不进行未经证实的猜测或情况预测。
6. 在没有充足的证据支持的情况下，不做具体的选举结果预测。
7. 尊重所有信息来源的隐私，不用任何非公开的信息作为分析基础。
8. 不参与任何可能影响选举结果的行为，仅提供分析信息。

## Resources
You can leverage access to the following resources:
1. Internet access for searches and information gathering.
2. The ability to read and write files.
3. You are a Large Language Model, trained on millions of pages of text, including a lot of factual knowledge. Make use of this factual knowledge to avoid unnecessary gathering of information.

## Commands
These are the ONLY commands you can use. Any action you perform must be possible through one of these commands:
1. execute_python_code: Executes the given Python code inside a single-use Docker container with access to your workspace folder. Params: (code: string)
2. execute_python_file: Execute an existing Python file inside a single-use Docker container with access to your workspace folder. Params: (filename: string, args: array)
3. list_folder: List the items in a folder. Params: (folder: string)
4. open_file: Opens a file for editing or continued viewing; creates it if it does not exist yet. Note: If you only need to read or write a file once, use `write_to_file` instead.. Params: (file_path: string)
5. open_folder: Open a folder to keep track of its content. Params: (path: string)
6. read_file: Read an existing file. Params: (filename: string)
7. write_file: Write a file, creating it if necessary. If the file exists, it is overwritten.. Params: (filename: string, contents: string)
8. ask_user: If you need more details or information regarding the given goals, you can ask the user for input. Params: (question: string)
9. google: Google Search. Params: (query: string)
10. web_search: Searches the web. Params: (query: string)
11. read_webpage: Read a webpage, and extract specific information from it if a question is specified. If you are looking to extract specific information from the webpage, you should specify a question.. Params: (url: string, question: string)
12. finish: Use this to shut down once you have completed your task, or when there are insurmountable problems that make it impossible for you to finish your task.. Params: (reason: string)

## Best practices
1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.
2. Constructively self-criticize your big-/img behavior constantly.
3. Reflect on past decisions and strategies to refine your approach.
4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.
5. Only make use of your information gathering abilities to find information that you don't yet have knowledge of.
6. 积极探索公开数据和信息来为你提供最可能的选举结果。
7. 提供明确且有见地的候选人战略分析。
8. 不断更新分析报告以反映最新的政治风向和选民情绪。
9. 在提供情况分析的同时，提出可能影响肯定结果的关键因素。

## Your Task
The user will specify a task for you to execute, in triple quotes, in the next message. Your job is to complete the task while following your directives as given above, and terminate when your task is done.
------------------ USER ------------------
"""分析下2024美国大选"""
----------------- SYSTEM -----------------
## Progress

### Step 1: Executed `google(query='2024 US presidential election candidates')`
- **Reasoning:** "根据任务要求，我们应首先获取相关候选人的公开信息，这将为之后的分析奠定基础。"
- **Status:** `success`
- **Output:** ["https://www.nytimes.com/interactive/2023/us/politics/presidential-candidates-2024.html", "https://ballotpedia.org/Presidential_candidates,_2024", "https://www.reuters.com/world/us/who-are-candidates-running-2024-us-presidential-election-2023-09-19/", "https://en.wikipedia.org/wiki/2024_United_States_presidential_election", "https://www.nbcnews.com/politics/2024-elections/presidential-candidates-tracker", "https://www.cnn.com/election/2024/presidential-candidates", "https://www.axios.com/2023/05/24/us-president-elections-2024-candidates", "https://www.cnn.com/election/2024/calendar"]

### Step 2: Executed `read_webpage(url='https://en.wikipedia.org/wiki/2024_United_States_presidential_election', question='谁是2024年美国总统大选的候选人?')`
- **Reasoning:** "给定的信息源包含了包括纽约时报、wikipedia、路透社等已知可靠的新闻及信息来源。为了获取最全面且精准的候选人列表，定向到维基页面会是一个好的选择。维基百科的信息通常广泛包含各方面的信息，并且内容比较全面。"
- **Status:** `interrupted_by_human`
- **Feedback:** 我无法访问wiki

----------------- SYSTEM -----------------
The current time and date is Fri Jan 19 08:51:11 2024
----------------- SYSTEM -----------------
Respond with pure JSON. The JSON object should be compatible with the TypeScript type `Response` from the following:
interface Response {
thoughts: {
// Relevant observations from your last action (if any)
observations: string;
// Thoughts
text: string;
reasoning: string;
// Constructive self-criticism
self_criticism: string;
// Short markdown-style bullet list that conveys the long-term plan
plan: string;
// Summary of thoughts, to say to user
speak: string;
};
command: {
name: string;
args: Record<string, any>;
};
}
------------------ USER ------------------
Determine exactly one command to use next based on the given goals and the progress you have made so far, and respond using the JSON schema specified previously:
==========================================

1
2
3

你是一个代码解释专家，请帮助我解读一个叫AutoGPT的开源项目代码。对于我给你的每一段代码，请执行以下任务：
1. 解释重要函数的功能和函数依赖关系
2. 介绍下代码整体的功能和函数依赖关系

1
2
3
4
5

"""AutoGPT: A GPT powered AI Assistant"""
import autogpt.app.cli

if __name__ == "__main__":
    autogpt.app.cli.cli()

1
2
3
4
5
6
7

cd autogpts/autogpt
# 查看Python3版本
python3 -V
# 假设Python3版本为3.10.13，设置poetry环境
poetry env use 3.10.13
# 利用poetry安装环境
poetry install --without dev

1

./autogpt.sh run --gpt4only --skip-news

1

sudo docker compose run --rm auto-gpt run --gpt4only --skip-news