search

Significant-Gravitas / AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.
https://agpt.co
MIT License
166.1k stars 43.98k forks source link

Unable to use the Azure OPEN AI #3047

Closed securigeek closed 1 year ago

securigeek commented 1 year ago

⚠️ Search for existing issues first ⚠️

Which Operating System are you using?

Windows

Which version of Auto-GPT are you using?

Stable (branch)

GPT-3 or GPT-4?

GPT-3.5

Steps to reproduce 🕹

I downloaded the V.0.2.2 stable release from github. Then followed the steps to install the requirements and followed the steps to configure azure.yaml as well as .env On .env I have changed following values : USE_AZURE=True OPENAI_API_KEY=

under azure.yaml the configuration is as followed :

azure_api_type: "azure" azure_api_base: "https://securigeekopenai.openai.azure.com" azure_api_version: "2023-03-15-preview" azure_model_map: fast_llm_model_deployment_id: "TechncialGPT3-5" smart_llm_model_deployment_id: "TechnicalGPT4Assistant" embedding_model_deployment_id: "text-embedding-ada-002"

Current behavior 😯

PS C:\Users\secu-user\Auto-GPT-0.2.2> python -m autogpt Warning: The file 'auto-gpt.json' does not exist. Local memory would not be saved to a file. NEWS: Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here. If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag Welcome back! Would you like me to return to being ceo? Continue with the last settings? Name: ceo Role: owner of a cloud security company Goals: ['search for the cyber attacks which happened in last 7 days', 'terminate'] Continue (y/n): y Using memory of type: LocalCache Using Browser: chrome THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days to determine if any of our clients have been affected. REASONING: I can use Google search to find recent news articles about cyber attacks and then analyze the information to determine if any of our clients have been affected. PLAN:

Expected behavior 🤔

Soon as I replace the API key with my open AI api key and set USE_AZURE=False , it starts working fine

Your prompt 📝

# Paste your prompt here

Your Logs 📒

2023-04-22 09:55:43,389 INFO NEWS:   ::UPDATED:: Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-22 09:55:43,894 INFO Welcome to Auto-GPT!  run with '--help' for more information.
2023-04-22 09:55:44,127 INFO Create an AI-Assistant: Enter the name of your AI and its role below. Entering nothing will load defaults.
2023-04-22 09:55:44,521 INFO Name your AI:  For example, 'Entrepreneur-GPT'
2023-04-22 09:56:06,305 INFO ceo here! I am at your service.
2023-04-22 09:56:06,469 INFO Describe your AI's role:  For example, 'an AI designed to autonomously develop and run businesses with the sole goal of increasing your net worth.'
2023-04-22 09:56:13,973 INFO Enter up to 5 goals for your AI:  For example: 
Increase net worth, Grow Twitter Account, Develop and manage multiple businesses autonomously'
2023-04-22 09:56:28,465 INFO Using memory of type: LocalCache
2023-04-22 09:56:28,678 INFO Using Browser: chrome
2023-04-22 10:02:41,762 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-22 10:02:42,286 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-22 10:02:44,845 INFO Using memory of type: LocalCache
2023-04-22 10:02:45,032 INFO Using Browser: chrome
2023-04-22 10:03:38,648 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-22 10:03:39,171 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-22 10:03:42,737 INFO Using memory of type: LocalCache
2023-04-22 10:03:42,912 INFO Using Browser: chrome
2023-04-22 10:03:50,681 INFO  THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days. I will use Google search to find relevant news articles.
2023-04-22 10:03:51,202 INFO REASONING: Google search is a quick and efficient way to find relevant news articles about recent cyber attacks. This will help me stay up to date on the latest threats and vulnerabilities.
2023-04-22 10:03:51,734 INFO PLAN: 
2023-04-22 10:03:51,798 INFO -  Use Google search to find news articles about recent cyber attacks
2023-04-22 10:03:52,126 INFO -  Save important information to files for future reference
2023-04-22 10:03:52,316 INFO CRITICISM: I need to make sure I am using specific search terms to find the most relevant articles. I also need to be careful not to spend too much time reading articles that are not relevant to my work.
2023-04-22 10:03:52,876 INFO NEXT ACTION:  COMMAND = google  ARGUMENTS = {'input': 'recent cyber attacks news'}
2023-04-22 10:03:54,877 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-22 10:05:05,651 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-22 10:05:06,193 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-22 10:05:07,946 INFO Using memory of type: LocalCache
2023-04-22 10:05:08,117 INFO Using Browser: chrome
2023-04-22 10:05:17,786 INFO  THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days. I will use Google search to find relevant news articles.
2023-04-22 10:05:18,296 INFO REASONING: Google search is a quick and efficient way to find relevant news articles about recent cyber attacks. This will help me stay up to date on the latest threats and vulnerabilities.
2023-04-22 10:05:18,860 INFO PLAN: 
2023-04-22 10:05:18,933 INFO -  Use Google search to find news articles about recent cyber attacks
2023-04-22 10:05:19,197 INFO -  Save important information to files for future reference
2023-04-22 10:05:19,407 INFO CRITICISM: I need to make sure I am using specific search terms to find the most relevant articles. I also need to be careful not to spend too much time reading articles that are not relevant to my work.
2023-04-22 10:05:19,945 INFO NEXT ACTION:  COMMAND = google  ARGUMENTS = {'input': 'recent cyber attacks news'}
2023-04-22 10:05:21,782 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-22 10:09:41,939 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-22 10:09:42,464 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-22 10:09:44,889 INFO Using memory of type: LocalCache
2023-04-22 10:09:45,022 INFO Using Browser: chrome
2023-04-22 10:09:54,734 INFO  THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days. I will use Google search to find relevant news articles.
2023-04-22 10:09:55,170 INFO REASONING: Google search is a quick and efficient way to find relevant news articles about recent cyber attacks. This will help me stay up to date on the latest threats and vulnerabilities.
2023-04-22 10:09:55,713 INFO PLAN: 
2023-04-22 10:09:55,772 INFO -  Use Google search to find news articles about recent cyber attacks
2023-04-22 10:09:56,120 INFO -  Save important information to files for future reference
2023-04-22 10:09:56,367 INFO CRITICISM: I need to make sure I am using the most relevant keywords in my search to ensure I find the most accurate and up-to-date information.
2023-04-22 10:09:56,873 INFO NEXT ACTION:  COMMAND = google  ARGUMENTS = {'input': 'recent cyber attacks news'}
2023-04-22 10:10:03,907 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-23 19:26:02,829 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-23 19:26:03,359 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-23 19:26:05,379 INFO Using memory of type: LocalCache
2023-04-23 19:26:05,534 INFO Using Browser: chrome
2023-04-23 19:26:13,347 INFO  THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days to determine if any of our clients have been affected.
2023-04-23 19:26:13,857 INFO REASONING: I can use Google search to find recent news articles about cyber attacks and then analyze the information to determine if any of our clients have been affected.
2023-04-23 19:26:14,302 INFO PLAN: 
2023-04-23 19:26:14,347 INFO -  Use Google search to find recent news articles about cyber attacks
2023-04-23 19:26:14,617 INFO -  Analyze the information to determine if any of our clients have been affected
2023-04-23 19:26:14,943 INFO CRITICISM: I need to be careful to only use reliable sources of information and to analyze the information thoroughly to avoid any false positives or negatives.
2023-04-23 19:26:15,393 INFO NEXT ACTION:  COMMAND = google  ARGUMENTS = {'input': 'cyber attacks in the last 7 days'}
2023-04-23 19:26:17,193 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-23 19:37:31,492 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-23 19:37:32,048 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-23 19:37:34,704 INFO Using memory of type: LocalCache
2023-04-23 19:37:34,884 INFO Using Browser: chrome
2023-04-23 19:38:17,773 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-23 19:38:18,391 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-23 19:38:20,943 INFO Using memory of type: LocalCache
2023-04-23 19:38:21,091 INFO Using Browser: chrome
2023-04-23 19:38:27,449 INFO  THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days to determine if any of our clients have been affected.
2023-04-23 19:38:27,957 INFO REASONING: I can use Google search to find recent news articles about cyber attacks and then analyze the information to determine if any of our clients have been affected.
2023-04-23 19:38:28,430 INFO PLAN: 
2023-04-23 19:38:28,469 INFO -  Use Google search to find recent news articles about cyber attacks
2023-04-23 19:38:28,756 INFO -  Analyze the information to determine if any of our clients have been affected
2023-04-23 19:38:29,096 INFO CRITICISM: I need to be careful to only use reliable sources of information and to analyze the information thoroughly to avoid any false positives or negatives.
2023-04-23 19:38:29,583 INFO NEXT ACTION:  COMMAND = google  ARGUMENTS = {'input': 'cyber attacks last 7 days'}
2023-04-23 19:38:33,184 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-23 19:38:34,907 INFO SYSTEM:  Command google returned: [
    {
        "title": "Latest cyber-attack news | The Daily Swig",
        "href": "https://portswigger.net/daily-swig/cyber-attacks",
        "body": "From DDoS assaults to cybersecurity exploits that result in a data breach, cyber-attacks present a growing threat to businesses, governments, and individuals.. Whether they come from so-called hacktivist groups or state-sponsored cyber warfare units, this type of attack is increasingly giving cause for concern.. The Daily Swig provides day-to-day coverage of recent cyber-attacks, arming ..."
    },
    {
        "title": "Top data breaches and cyber attacks of 2022 | TechRadar",
        "href": "https://www.techradar.com/features/top-data-breaches-and-cyber-attacks-of-2022",
        "body": "Computing giant Microsoft is no stranger to cyberattacks, and on March 20th 2022 the firm was targeted by a hacking collective called Lapsus$. The group posted a screenshot on Telegram to indicate..."
    },
    {
        "title": "Significant Cyber Incidents | Strategic Technologies Program | CSIS",
        "href": "https://www.csis.org/programs/strategic-technologies-program/significant-cyber-incidents",
        "body": "Hackers launched a ransomware attack against Technion University, Israel's top technology education program. Hackers demanded 80 bitcoin ($1.7 million USD) to decrypt the university's files. Israeli cybersecurity officials blamed Iranian state-sponsored hackers for the attack. February 2023."
    },
    {
        "title": "2021 has broken the record for zero-day hacking attacks",
        "href": "https://www.technologyreview.com/2021/09/23/1036140/2021-record-zero-day-hacks-reasons/",
        "body": "The limited data available, such as Zerodium's public zero-day prices, shows as much as a 1,150% rise in the cost of the highest-end hacks over the last three years. But even if zero-day attacks ..."
    },
    {
        "title": "Data Breaches That Have Happened in 2023 So Far - Updated List - Tech.co",
        "href": "https://tech.co/news/data-breaches-updated-list",
        "body": "Apple, Meta, and Twitter have all disclosed cybersecurity attacks over the past 12 months. We track the latest data breaches. Written by Aaron Drapkin Updated on April 11, 2023 Data breaches..."
    },
    {
        "title": "Recent Cyber Attacks in 2022 | Fortinet",
        "href": "https://www.fortinet.com/resources/cyberglossary/recent-cyber-attacks",
        "body": "One of the most significant cyber attacks that occurred in 2020 was through a hacker known as ShinyHunters. The hacker stole around 386 million user records from 18 different companies between the start of the year and July. The attacker posted links to these companies' databases, made them freely available to download, and sold data online."
    },
    {
        "title": "Cybersecurity in 2022 - A Fresh Look at Some Very Alarming Stats - Forbes",
        "href": "https://www.forbes.com/sites/chuckbrooks/2022/01/21/cybersecurity-in-2022--a-fresh-look-at-some-very-alarming-stats/",
        "body": "Frequency of attacks: 66% have experienced a cyber attack in the past 12 months. Background of attacks : 69% say that cyber attacks are becoming more targeted. The most common types of attacks on ..."
    },
    {
        "title": "How Many Cyber Attacks Happen Per Day in 2023? - Techjury",
        "href": "https://techjury.net/blog/how-many-cyber-attacks-per-day/",
        "body": "314 days is the total time it takes from the breach to the containment of a successful cyber attack. It takes an average of 7 months to identify a breach, and another 4 months to contain such a breach."
    }
]
2023-04-23 19:38:44,007 INFO  THOUGHTS: I need to analyze the information from the Google search to determine if any of our clients have been affected by the cyber attacks mentioned in the articles. I can use GPT agents to help me with this task.
2023-04-23 19:38:44,555 INFO REASONING: Analyzing the information from the Google search will require reading and understanding the articles, which can be time-consuming. GPT agents can help me by summarizing the articles and identifying any mentions of our clients or their industries.
2023-04-23 19:38:45,131 INFO PLAN: 
2023-04-23 19:38:45,196 INFO -  Use GPT agents to summarize the articles and identify any mentions of our clients or their industries
2023-04-23 19:38:45,552 INFO -  Review the summaries and mentions to determine if any of our clients have been affected
2023-04-23 19:38:45,904 INFO CRITICISM: I need to ensure that the GPT agents are properly trained and that their summaries and identifications are accurate. I also need to be careful to protect the privacy of our clients and not disclose any sensitive information.
2023-04-23 19:38:46,481 INFO NEXT ACTION:  COMMAND = start_agent  ARGUMENTS = {'name': 'cyber_attack_analysis', 'task': 'Summarize articles and identify mentions of clients', 'prompt': 'Please summarize the following article and identify any mentions of our clients or their industries: '}
2023-04-23 19:39:32,427 INFO SYSTEM:  Human feedback: its not specefic to our clients but any impacted organization due to a cloud breach or attack 
2023-04-23 19:39:41,020 INFO  THOUGHTS: I need to use the GPT agent to summarize the articles and identify any mentions of organizations impacted by the cyber attacks. I can then use this information to determine if any of our clients have been affected.
2023-04-23 19:39:41,543 INFO REASONING: The GPT agent can help me by summarizing the articles and identifying any mentions of organizations impacted by the cyber attacks. I can then review the summaries and mentions to determine if any of our clients have been affected.
2023-04-23 19:39:42,111 INFO PLAN: 
2023-04-23 19:39:42,184 INFO -  Use the GPT agent to summarize the articles and identify any mentions of organizations impacted by the cyber attacks
2023-04-23 19:39:42,606 INFO -  Review the summaries and mentions to determine if any of our clients have been affected
2023-04-23 19:39:42,957 INFO CRITICISM: I need to ensure that the GPT agent is properly trained and that its summaries and identifications are accurate. I also need to be careful to protect the privacy of our clients and not disclose any sensitive information.
2023-04-23 19:39:43,562 INFO NEXT ACTION:  COMMAND = message_agent  ARGUMENTS = {'key': 'cyber_attack_analysis', 'message': 'Please summarize the following article and identify any mentions of organizations impacted by the cyber attacks: '}
2023-04-23 19:40:09,173 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-23 19:40:09,719 INFO SYSTEM:  Command message_agent returned: Invalid key, must be an integer.
2023-04-23 19:40:19,988 INFO  THOUGHTS: I need to create a new GPT agent to summarize the articles and identify any mentions of organizations impacted by the cyber attacks. I can then review the summaries and mentions to determine if any of our clients have been affected.
2023-04-23 19:40:20,563 INFO REASONING: Creating a new GPT agent will allow me to train it specifically for this task and ensure that its summaries and identifications are accurate. I can then use the agent to summarize the articles and identify any mentions of organizations impacted by the cyber attacks.
2023-04-23 19:40:21,142 INFO PLAN: 
2023-04-23 19:40:21,200 INFO -  Create a new GPT agent to summarize the articles and identify any mentions of organizations impacted by the cyber attacks
2023-04-23 19:40:21,635 INFO -  Train the agent specifically for this task
2023-04-23 19:40:21,899 INFO -  Use the agent to summarize the articles and identify any mentions of organizations impacted by the cyber attacks
2023-04-23 19:40:22,305 INFO -  Review the summaries and mentions to determine if any of our clients have been affected
2023-04-23 19:40:22,675 INFO CRITICISM: I need to ensure that the GPT agent is properly trained and that its summaries and identifications are accurate. I also need to be careful to protect the privacy of our clients and not disclose any sensitive information.
2023-04-23 19:40:23,221 INFO NEXT ACTION:  COMMAND = start_agent  ARGUMENTS = {'name': 'cyber_attack_analysis', 'task': 'Summarize articles and identify mentions of organizations impacted by cyber attacks', 'prompt': 'Please summarize the following article and identify any mentions of organizations impacted by the cyber attacks: '}
2023-04-23 19:47:14,669 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-23 19:47:16,689 INFO SYSTEM:  Command start_agent returned: Agent cyber_attack_analysis created with key 0. First response: I'm sorry, but you haven't provided me with an article to summarize. Please provide me with the article you want me to summarize.
2023-04-23 19:47:24,662 INFO  THOUGHTS: I need to provide the GPT agent with an article to summarize and identify any mentions of organizations impacted by the cyber attacks.
2023-04-23 19:47:25,167 INFO REASONING: Providing the GPT agent with an article to summarize and identify any mentions of organizations impacted by the cyber attacks will allow it to perform the task I have assigned to it.
2023-04-23 19:47:25,741 INFO PLAN: 
2023-04-23 19:47:25,823 INFO -  Provide the GPT agent with an article to summarize and identify any mentions of organizations impacted by the cyber attacks
2023-04-23 19:47:26,298 INFO CRITICISM: I need to ensure that the article I provide to the GPT agent is relevant to the cyber attacks I am investigating. I also need to be careful to protect the privacy of our clients and not disclose any sensitive information.
2023-04-23 19:47:26,833 INFO NEXT ACTION:  COMMAND = message_agent  ARGUMENTS = {'key': 0, 'message': 'Please summarize the following article and identify any mentions of organizations impacted by the cyber attacks: '}
2023-04-23 19:47:27,481 INFO DOUBLE CHECK CONFIGURATION Please double check that you have setup a PAID OpenAI API Account. You can read more here: https://github.com/Significant-Gravitas/Auto-GPT#openai-api-keys-configuration
2023-04-23 19:47:41,343 INFO SYSTEM:  Command message_agent returned: I'm sorry, but you still haven't provided me with an article to summarize. Please provide me with the article you want me to summarize.
2023-04-23 19:47:42,501 INFO DOUBLE CHECK CONFIGURATION Please double check that you have setup a PAID OpenAI API Account. You can read more here: https://github.com/Significant-Gravitas/Auto-GPT#openai-api-keys-configuration
2023-04-23 19:48:35,514 INFO NEWS:  Welcome to Auto-GPT! We'll keep you informed of the latest news and features by printing messages here.
If you don't wish to see this message, you can run Auto-GPT with the --skip-news flag
2023-04-23 19:48:36,053 INFO Welcome back!  Would you like me to return to being ceo?
2023-04-23 19:48:46,710 INFO Using memory of type: LocalCache
2023-04-23 19:48:46,885 INFO Using Browser: chrome
2023-04-23 19:48:52,438 INFO  THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days to determine if any of our clients were affected.
2023-04-23 19:48:52,929 INFO REASONING: I can use Google search to find recent news articles about cyber attacks and then analyze the information to determine if any of our clients were affected.
2023-04-23 19:48:53,425 INFO PLAN: 
2023-04-23 19:48:53,495 INFO -  Use Google search to find recent news articles about cyber attacks
2023-04-23 19:48:53,799 INFO -  Analyze the information to determine if any of our clients were affected
2023-04-23 19:48:54,124 INFO CRITICISM: I need to be efficient in my search and analysis to ensure that I am not wasting time on irrelevant information.
2023-04-23 19:48:54,563 INFO NEXT ACTION:  COMMAND = google  ARGUMENTS = {'input': 'cyber attacks in the last 7 days'}
2023-04-23 19:50:00,236 INFO SYSTEM:  Human feedback: its not related to our clients but in general this researc is for the purpose of a linkedln post where the intent is to share awareness around the latest cloud security attacks happened and the learnings from them
2023-04-23 19:50:06,759 INFO  THOUGHTS: I will browse websites to find information about the latest cloud security attacks and their impact on businesses.
2023-04-23 19:50:07,175 INFO REASONING: Browsing websites will allow me to find more detailed information about the latest cloud security attacks and their impact on businesses, which will be useful for my LinkedIn post.
2023-04-23 19:50:07,709 INFO PLAN: 
2023-04-23 19:50:07,777 INFO -  Browse websites to find information about the latest cloud security attacks and their impact on businesses
2023-04-23 19:50:08,168 INFO CRITICISM: I need to be efficient in my browsing to ensure that I am not wasting time on irrelevant information.
2023-04-23 19:50:08,587 INFO NEXT ACTION:  COMMAND = browse_website  ARGUMENTS = {'url': 'https://www.darkreading.com/cloud', 'question': 'What are the latest cloud security attacks and their impact on businesses?'}
2023-04-23 19:50:23,076 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-23 19:50:44,513 INFO SYSTEM:  Command browse_website returned: ('Answer gathered from website: The article covers various cloud security attacks, including the "GhostToken" vulnerability in Google Cloud Platform, the Legion malware that compromises SMTP services, and the emerging "proxyjacking" attack that exploits Log4j. It also highlights the need for CISOs to detect and block attacks in even less time and provides insights into upcoming seminars and keynotes at the RSA Conference 2023. Additionally, the article covers new cloud security capabilities launched by Elastic and F5, and the SASE market\'s projected worth of $5.9 billion by 2028. \n \n Links: [\' (https://www.darkreading.com/)\', \'The Edge (https://www.darkreading.com/edge)\', \'DR Tech (https://www.darkreading.com/dr-tech)\', \'The Edge (https://www.darkreading.com/edge)\', \'Dark Reading Technology (https://www.darkreading.com/dr-tech)\']', <selenium.webdriver.chrome.webdriver.WebDriver (session="67db09092b9e37e6a4c61779f114989d")>)
2023-04-23 19:50:53,676 INFO  THOUGHTS: I will analyze the information gathered from the website to determine the most relevant and impactful cloud security attacks to include in my LinkedIn post.
2023-04-23 19:50:54,168 INFO REASONING: Analyzing the information will allow me to determine the most relevant and impactful cloud security attacks to include in my LinkedIn post, which will help to raise awareness and educate others about the importance of cloud security.
2023-04-23 19:50:54,697 INFO PLAN: 
2023-04-23 19:50:54,741 INFO -  Analyze the information gathered from the website to determine the most relevant and impactful cloud security attacks to include in my LinkedIn post
2023-04-23 19:50:55,235 INFO CRITICISM: I need to be thorough in my analysis to ensure that I am not overlooking any important information.
2023-04-23 19:50:55,599 INFO NEXT ACTION:  COMMAND = analyze_code  ARGUMENTS = {'code': 'The article covers various cloud security attacks, including the "GhostToken" vulnerability in Google Cloud Platform, the Legion malware that compromises SMTP services, and the emerging "proxyjacking" attack that exploits Log4j. It also highlights the need for CISOs to detect and block attacks in even less time and provides insights into upcoming seminars and keynotes at the RSA Conference 2023. Additionally, the article covers new cloud security capabilities launched by Elastic and F5, and the SASE market\'s projected worth of $5.9 billion by 2028.'}
2023-04-23 19:51:31,830 INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-= 
2023-04-23 19:51:32,469 INFO SYSTEM:  Command analyze_code returned: Error: The model: `gpt-4` does not exist
2023-04-23 19:51:40,368 INFO  THOUGHTS: I need to search for the cyber attacks which happened in the last 7 days to determine if any of our clients were affected.
2023-04-23 19:51:40,840 INFO REASONING: I can use Google search to find recent news articles about cyber attacks and then analyze the information to determine if any of our clients were affected.
2023-04-23 19:51:41,305 INFO PLAN: 
2023-04-23 19:51:41,368 INFO -  Use Google search to find recent news articles about cyber attacks
2023-04-23 19:51:41,622 INFO -  Analyze the information to determine if any of our clients were affected
2023-04-23 19:51:41,932 INFO CRITICISM: I need to be efficient in my search and analysis to ensure that I am not wasting time on irrelevant information.
2023-04-23 19:51:42,360 INFO NEXT ACTION:  COMMAND = google  ARGUMENTS = {'input': 'cyber attacks in the last 7 days'}
securigeek commented 1 year ago

Can anyone please help ?

ntindle commented 1 year ago

None of us have azure keys. Connect me to your rep and I’ll see if I can get a fix in but until we get an account we are depending on community fixes for these

securigeek commented 1 year ago

How shall I do that ? DO you want me to give you a temporary Azure Key ?

jtac commented 1 year ago

I got Azure OpenAI working in the following way:

.env:

OPENAI_API_KEY=<redacted, put yours here> USE_AZURE=True

azure.yaml:

azure_api_type: azure azure_api_base: https://.openai.azure.com/ azure_api_version: 2023-03-15-preview azure_model_map: fast_llm_model_deployment_id: <deploy gpt35turbo and put the name here, not an id> smart_llm_model_deployment_id: <deploy gpt4 and put the name here, not an id> embedding_model_deployment_id: <deploy embedding and put the name here, not an id>

After these changes, looks like it's running OK.

Remember you have to setup stuff on Azure side as well, make sure you have the deployments and resources setup correctly and that your API key is valid, re-generate it if nothing else seems to work, this helped me earlier when setting up.

ntindle commented 1 year ago

Got an Azure key and can't replicate your issue. Guessing your embedding model needs to be deployed

ntindle commented 1 year ago

@jtac will you update the docs with that, its far more clear

securigeek commented 1 year ago

Using Browser: chrome Traceback (most recent call last): File "", line 198, in _run_module_as_main File "", line 88, in _run_code File "C:\Users\secu-user\OneDrive - Securigeek\Desktop\Auto-GPT-0.3.0\autogpt__main.py", line 5, in autogpt.cli.main() File "C:\Users\secu-user\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1130, in call return self.main(*args, kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1055, in main rv = self.invoke(ctx) ^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1635, in invoke rv = super().invoke(ctx) ^^^^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 1404, in invoke return ctx.invoke(self.callback, ctx.params) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\core.py", line 760, in invoke return callback(*args, *kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\AppData\Local\Programs\Python\Python311\Lib\site-packages\click\decorators.py", line 26, in new_func return f(get_current_context(), args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\OneDrive - Securigeek\Desktop\Auto-GPT-0.3.0\autogpt\cli.py", line 90, in main run_auto_gpt( File "C:\Users\secu-user\OneDrive - Securigeek\Desktop\Auto-GPT-0.3.0\autogpt\main.py", line 171, in run_auto_gpt agent.start_interaction_loop() File "C:\Users\secu-user\OneDrive - Securigeek\Desktop\Auto-GPT-0.3.0\autogpt\agent\agent.py", line 94, in start_interaction_loop assistant_reply = chat_with_ai( ^^^^^^^^^^^^^ File "C:\Users\secu-user\OneDrive - Securigeek\Desktop\Auto-GPT-0.3.0\autogpt\llm\chat.py", line 237, in chat_with_ai assistant_reply = create_chat_completion( ^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\OneDrive - Securigeek\Desktop\Auto-GPT-0.3.0\autogpt\llm\llm_utils.py", line 159, in create_chat_completion deployment_id=cfg.get_azure_deployment_id_for_model(model), ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "C:\Users\secu-user\OneDrive - Securigeek\Desktop\Auto-GPT-0.3.0\autogpt\config\config.py", line 158, in get_azure_deployment_id_for_model return self.azure_model_to_deployment_id_map[ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ TypeError: 'NoneType' object is not subscriptable

securigeek commented 1 year ago

I am still getting this error message

securigeek commented 1 year ago

Azure.yaml : azure_api_type: azure azure_api_base: https://.openai.azure.com/ azure_api_version: 2023-03-15-preview azure_model_map: fast_llm_model_deployment_id: SecurGPT3-5 smart_llm_model_deployment_id: SecurkAssistant embedding_model_deployment_id: SdeployADA

securigeek commented 1 year ago

.env : ################################################################################

AUTO-GPT - GENERAL SETTINGS

################################################################################

EXECUTE_LOCAL_COMMANDS - Allow local command execution (Default: False)

RESTRICT_TO_WORKSPACE - Restrict file operations to workspace ./auto_gpt_workspace (Default: True)

EXECUTE_LOCAL_COMMANDS=False

RESTRICT_TO_WORKSPACE=True

USER_AGENT - Define the user-agent used by the requests library to browse website (string)

USER_AGENT="Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/83.0.4103.97 Safari/537.36"

AI_SETTINGS_FILE - Specifies which AI Settings file to use (defaults to ai_settings.yaml)

AI_SETTINGS_FILE=ai_settings.yaml

AUTHORISE COMMAND KEY - Key to authorise commands

AUTHORISE_COMMAND_KEY=y

EXIT_KEY - Key to exit AUTO-GPT

EXIT_KEY=n

################################################################################

LLM PROVIDER

################################################################################

OPENAI

OPENAI_API_KEY - OpenAI API Key (Example: my-openai-api-key)

TEMPERATURE - Sets temperature in OpenAI (Default: 0)

USE_AZURE - Use Azure OpenAI or not (Default: False)

OPENAI_API_KEY=

TEMPERATURE=0

USE_AZURE= True

AZURE

moved to azure.yaml.template

################################################################################

LLM MODELS

################################################################################

SMART_LLM_MODEL - Smart language model (Default: gpt-4)

FAST_LLM_MODEL - Fast language model (Default: gpt-3.5-turbo)

SMART_LLM_MODEL=gpt-4

FAST_LLM_MODEL=gpt-3.5-turbo

LLM MODEL SETTINGS

FAST_TOKEN_LIMIT - Fast token limit for OpenAI (Default: 4000)

SMART_TOKEN_LIMIT - Smart token limit for OpenAI (Default: 8000)

When using --gpt3only this needs to be set to 4000.

FAST_TOKEN_LIMIT=4000

SMART_TOKEN_LIMIT=8000

EMBEDDINGS

EMBEDDING_MODEL - Model to use for creating embeddings

EMBEDDING_TOKENIZER - Tokenizer to use for chunking large inputs

EMBEDDING_TOKEN_LIMIT - Chunk size limit for large inputs

EMBEDDING_MODEL=text-embedding-ada-002

EMBEDDING_TOKENIZER=cl100k_base

EMBEDDING_TOKEN_LIMIT=8191

################################################################################

MEMORY

################################################################################

MEMORY_BACKEND - Memory backend type

local - Default

pinecone - Pinecone (if configured)

redis - Redis (if configured)

milvus - Milvus (if configured - also works with Zilliz)

MEMORY_INDEX - Name of index created in Memory backend (Default: auto-gpt)

MEMORY_BACKEND=local

MEMORY_INDEX=auto-gpt

PINECONE

PINECONE_API_KEY - Pinecone API Key (Example: my-pinecone-api-key)

PINECONE_ENV - Pinecone environment (region) (Example: us-west-2)

PINECONE_API_KEY=your-pinecone-api-key

PINECONE_ENV=your-pinecone-region

REDIS

REDIS_HOST - Redis host (Default: localhost, use "redis" for docker-compose)

REDIS_PORT - Redis port (Default: 6379)

REDIS_PASSWORD - Redis password (Default: "")

WIPE_REDIS_ON_START - Wipes data / index on start (Default: True)

REDIS_HOST=localhost

REDIS_PORT=6379

REDIS_PASSWORD=

WIPE_REDIS_ON_START=True

WEAVIATE

MEMORY_BACKEND - Use 'weaviate' to use Weaviate vector storage

WEAVIATE_HOST - Weaviate host IP

WEAVIATE_PORT - Weaviate host port

WEAVIATE_PROTOCOL - Weaviate host protocol (e.g. 'http')

USE_WEAVIATE_EMBEDDED - Whether to use Embedded Weaviate

WEAVIATE_EMBEDDED_PATH - File system path were to persist data when running Embedded Weaviate

WEAVIATE_USERNAME - Weaviate username

WEAVIATE_PASSWORD - Weaviate password

WEAVIATE_API_KEY - Weaviate API key if using API-key-based authentication

WEAVIATE_HOST="127.0.0.1"

WEAVIATE_PORT=8080

WEAVIATE_PROTOCOL="http"

USE_WEAVIATE_EMBEDDED=False

WEAVIATE_EMBEDDED_PATH="/home/me/.local/share/weaviate"

WEAVIATE_USERNAME=

WEAVIATE_PASSWORD=

WEAVIATE_API_KEY=

MILVUS

MILVUS_ADDR - Milvus remote address (e.g. localhost:19530, https://xxx-xxxx.xxxx.xxxx.zillizcloud.com:443)

MILVUS_USERNAME - username for your Milvus database

MILVUS_PASSWORD - password for your Milvus database

MILVUS_SECURE - True to enable TLS. (Default: False)

Setting MILVUS_ADDR to a https:// URL will override this setting.

MILVUS_COLLECTION - Milvus collection, change it if you want to start a new memory and retain the old memory.

MILVUS_ADDR=localhost:19530

MILVUS_USERNAME=

MILVUS_PASSWORD=

MILVUS_SECURE=

MILVUS_COLLECTION=autogpt

################################################################################

IMAGE GENERATION PROVIDER

################################################################################

OPEN AI

IMAGE_PROVIDER - Image provider (Example: dalle)

IMAGE_SIZE - Image size (Example: 256)

DALLE: 256, 512, 1024

IMAGE_PROVIDER=dalle

IMAGE_SIZE=256

HUGGINGFACE

HUGGINGFACE_IMAGE_MODEL - Text-to-image model from Huggingface (Default: CompVis/stable-diffusion-v1-4)

HUGGINGFACE_API_TOKEN - HuggingFace API token (Example: my-huggingface-api-token)

HUGGINGFACE_IMAGE_MODEL=CompVis/stable-diffusion-v1-4

HUGGINGFACE_API_TOKEN=your-huggingface-api-token

STABLE DIFFUSION WEBUI

SD_WEBUI_AUTH - Stable diffusion webui username:password pair (Example: username:password)

SD_WEBUI_URL - Stable diffusion webui API URL (Example: http://127.0.0.1:7860)

SD_WEBUI_AUTH=

SD_WEBUI_URL=http://127.0.0.1:7860

################################################################################

AUDIO TO TEXT PROVIDER

################################################################################

HUGGINGFACE

HUGGINGFACE_AUDIO_TO_TEXT_MODEL=facebook/wav2vec2-base-960h

################################################################################

GIT Provider for repository actions

################################################################################

GITHUB

GITHUB_API_KEY - Github API key / PAT (Example: github_pat_123)

GITHUB_USERNAME - Github username

GITHUB_API_KEY=github_pat_123

GITHUB_USERNAME=your-github-username

################################################################################

WEB BROWSING

################################################################################

BROWSER

HEADLESS_BROWSER - Whether to run the browser in headless mode (default: True)

USE_WEB_BROWSER - Sets the web-browser driver to use with selenium (default: chrome).

Note: set this to either 'chrome', 'firefox', or 'safari' depending on your current browser

HEADLESS_BROWSER=True

USE_WEB_BROWSER=chrome

BROWSE_CHUNK_MAX_LENGTH - When browsing website, define the length of chunks to summarize (in number of tokens, excluding the response. 75 % of FAST_TOKEN_LIMIT is usually wise )

BROWSE_CHUNK_MAX_LENGTH=3000

BROWSE_SPACY_LANGUAGE_MODEL is used to split sentences. Install additional languages via pip, and set the model name here. Example Chinese: python -m spacy download zh_core_web_sm

BROWSE_SPACY_LANGUAGE_MODEL=en_core_web_sm

GOOGLE

GOOGLE_API_KEY - Google API key (Example: my-google-api-key)

CUSTOM_SEARCH_ENGINE_ID - Custom search engine ID (Example: my-custom-search-engine-id)

GOOGLE_API_KEY=your-google-api-key

CUSTOM_SEARCH_ENGINE_ID=your-custom-search-engine-id

################################################################################

TTS PROVIDER

################################################################################

MAC OS

USE_MAC_OS_TTS - Use Mac OS TTS or not (Default: False)

USE_MAC_OS_TTS=False

STREAMELEMENTS

USE_BRIAN_TTS - Use Brian TTS or not (Default: False)

USE_BRIAN_TTS=False

ELEVENLABS

ELEVENLABS_API_KEY - Eleven Labs API key (Example: my-elevenlabs-api-key)

ELEVENLABS_VOICE_1_ID - Eleven Labs voice 1 ID (Example: my-voice-id-1)

ELEVENLABS_VOICE_2_ID - Eleven Labs voice 2 ID (Example: my-voice-id-2)

ELEVENLABS_API_KEY=your-elevenlabs-api-key

ELEVENLABS_VOICE_1_ID=your-voice-id-1

ELEVENLABS_VOICE_2_ID=your-voice-id-2

################################################################################

TWITTER API

################################################################################

TW_CONSUMER_KEY=

TW_CONSUMER_SECRET=

TW_ACCESS_TOKEN=

TW_ACCESS_TOKEN_SECRET=

################################################################################

ALLOWLISTED PLUGINS

################################################################################

ALLOWLISTED_PLUGINS - Sets the listed plugins that are allowed (Example: plugin1,plugin2,plugin3)

ALLOWLISTED_PLUGINS=

################################################################################

CHAT PLUGIN SETTINGS

################################################################################

CHAT_MESSAGES_ENABLED - Enable chat messages (Default: False)

CHAT_MESSAGES_ENABLED=False

securigeek commented 1 year ago

Please help