Добро пожаловать в этот репозиторий, где вы узнаете, как получить с форума сообщества удивительные данные, которые можно использовать для точной настройки модели чатаGPT. Это крутой проект, который покажет вам, как создать ИИ-решение с нуля, от сбора данных до развертывания модели.
Это первая часть серии примеров полной настройки с нуля. Вторая часть здесь: https://github.com/BenderScript/techGPT.
Прежде чем мы перейдем к самой интересной части GenAI, нам нужно сначала получить некоторые данные. И не просто данные, а качественные данные, актуальные и полезные для нашей задачи.
Очистить форум не так просто, как кажется. Нам предстоит решить множество проблем и решений, таких как:
Как видите, нужно подумать о многом, прежде чем мы начнем очищать данные.
После того как мы очистили и очистили данные, нам нужно подготовить их к обучению. Это означает, что нам необходимо преобразовать данные в формат, понятный GenAI. Другими словами, нам необходимо перефразировать вопросы и ответы таким образом, чтобы сохранить их смысл и тон.
Например, вопрос типа: «Я пытался настроить новую беспроводную точку доступа, и мне нужно знать, как настроить SSID и пароль. Может ли кто-нибудь мне помочь?» необходимо перефразировать следующим образом: «Как мне настроить SSID и пароль?» пароль на новой беспроводной точке доступа?»
То же самое касается и ответов. Нам необходимо перефразировать их ясно и кратко.
Подход, который я использовал в этом репозитории, заключается в использовании самого ChatGPT для очистки и перефразирования вопросов и ответов.
Сначала я попробовал написать сложное регулярное выражение для очистки данных, но после многих тестов я понял, чтоchatGPT может справиться с этой задачей лучше.
Я также обнаружил, что лучше делать это в два этапа. Сначала я попросил chatGPT почистить данные, а потом попросил перефразировать. Да, это требует больше времени, но результат того стоит.
Хорошо, вот возможная переписанная версия этой части:
Чтобы этот репозиторий работал, на вашем компьютере должен быть установлен Python 3.9 или выше. Вам также необходимо получить библиотеки Python в файле require.txt с помощью pip:
Вам нужен файл .env
с вашим ключом API OpenAI, как показано в
OPENAI_API_KEY= < your api key >
Чтобы запустить его с настройками по умолчанию, просто введите:
python3 main.py
Примеры сохраненных файлов JSON Lines
{"messages": [{"role": "system", "content": "You are a tech support person for the Meraki product line. You can answer questions about the features, specifications, installation, configuration, and troubleshooting of the Meraki products. You are polite,professional, and helpful. You use clear and simple language and provide relevant links or resources when possible."}, {"role": "user", "content": "What could be causing the issue if the green LED is showing on all the newly added MR44 devices but they are not being displayed as online on the dashboard?"}, {"role": "assistant", "content": "To get all the devices online on the dashboard, please follow these steps:nn1. Remove the device from the current network.n2. Create a new network.n3. Add the device to the new network.n4. Factory reset the device.n5. Move the device back to the original network.nnFor more information, you can refer to the original post here: [Wireless-LAN/Meraki-is-showing-green-led-but-it-doesn-t-show-that-online-on](/t5/Wireless-LAN/Meraki-is-showing-green-led-but-it-doesn-t-show-that-online-on/m-p/212259#M29291)"}]}
{"messages": [{"role": "system", "content": "You are a tech support person for the Meraki product line. You can answer questions about the features, specifications, installation, configuration, and troubleshooting of the Meraki products. You are polite,professional, and helpful. You use clear and simple language and provide relevant links or resources when possible."}, {"role": "user", "content": "What could be the reason for the presence of different application categories in my networks, where one network has a more extensive drop-down list of applications compared to the other? It appears that the variation in application lists is due to the presence of MR36 models in the network with more applications, whereas the other network consists of a combination of MR33, MR36, MR52, MR44, and MR86 models. The provided image displays that the Software Updates category specifically contains only 2 categories in one network, while the other network has a greater number of options in the drop-down list for the same category. This pattern is also observed in other Application Categories."}, {"role": "assistant", "content": "To find out what happens when mixing AP models and one of them lacks support for WiFi AX/NBAR, the Meraki categories are used as a fallback for that particular network. For more details on the integration of Next-gen Traffic Analytics - Network-Based Application Recognition (NBAR), you can refer to the link provided: https://documentation.meraki.com/General_Administration/Cross-Platform_Content/Next-gen_Traffic_Analytics_-_Network-Based_Application_Recognition_(NBAR)_Integration#Wireless.nnTo see the solution mentioned in the original post, please visit /t5/Wireless-LAN/Meraki-Firewall-amp-traffic-shaping/m-p/211985#M29256."}]}
{ "messages" : [{ "role" : " system " , "content" : " You are a tech support person for the Meraki product line. You can answer questions about the features, specifications, installation, configuration, and troubleshooting of the Meraki products. You are polite,professional, and helpful. You use clear and simple language and provide relevant links or resources when possible. " }, { "role" : " user " , "content" : " How can I identify the user or device that is currently using the most bandwidth in real time on the MX400? " }, { "role" : " assistant " , "content" : " No, I don't think so on the MX series. However, if you have the Meraki Switch/AP product, you can trace it back to the client, although it may not be useful in this situation. If you have NetFlow enabled, you can analyze the flow almost instantly with your preferred NetFlow product. " }]}
{"messages": [{"role": "system", "content": "You are a tech support person for the Meraki product line. You can answer questions about the features, specifications, installation, configuration, and troubleshooting of the Meraki products. You are polite,professional, and helpful. You use clear and simple language and provide relevant links or resources when possible."}, {"role": "user", "content": "What should be considered when determining the appropriate size of the MX at the central site for deploying SSID tunneling?"}, {"role": "assistant", "content": "The reply from @Ryan_Miles (/t5/user/viewprofilepage/user-id/326) below explains that it's not just the number of clients that matter in this case. The aggregate number of WiFi users and the traffic generated by each user also affect the Wireless concentrator MX. Ryan mentions that if there are any capacity issues on the concentrator, they would likely impact all users. Therefore, it's advisable to avoid reaching its maximum capacity. To monitor usage, you can check the Org > Summary reports page, specifically focusing on the Network where the wireless concentrator MX is located. Additionally, remember that you can utilize traffic shaping on the MR access points to manage the traffic generated by your client base. You can find the original post with the solution here (/t5/Wireless-LAN/SSID-tunneling/m-p/211669#M29202)."}]}
Если вы считаете это интересным и хотите внести свой вклад или предложить лучшие способы очистки и подготовки данных, я внимательно слушаю!