meraki_genai_community_scraper
1.0.0
Bienvenido a este repositorio, donde aprenderá cómo crear un foro comunitario para obtener datos sorprendentes que puede utilizar para ajustar su modelo chatGPT. Este es un proyecto interesante que le muestra cómo crear una solución de inteligencia artificial desde cero, desde la recopilación de datos hasta la implementación del modelo.
Esta es la primera parte de una serie de ejemplos completos de ajuste desde cero. La segunda parte está aquí: https://github.com/BenderScript/techGPT
Antes de pasar a la parte divertida de GenAI, primero debemos obtener algunos datos. Y no datos cualquiera, sino datos de calidad, relevantes y útiles para nuestra tarea.
Eliminar un foro no es tan fácil como parece. Hay muchos desafíos y decisiones que debemos enfrentar, tales como:
Como puede ver, hay muchas cosas en las que pensar antes de que podamos comenzar a recopilar datos.
Una vez que hayamos extraído y limpiado los datos, debemos prepararlos para el entrenamiento. Esto significa que necesitamos transformar los datos a un formato que GenAI pueda entender. En otras palabras, debemos reformular las preguntas y respuestas de manera que preserven su significado y tono.
Por ejemplo, una pregunta como: " Intenté configurar un nuevo AP inalámbrico y necesito saber cómo configurar el SSID y la contraseña. ¿Alguien puede ayudarme? " debe reformularse como: "¿Cómo configuro el SSID y ¿Contraseña en un nuevo AP inalámbrico?"
Lo mismo ocurre con las respuestas. Necesitamos reformularlos de manera clara y concisa.
El enfoque que utilicé en este repositorio es aprovechar el propio chatGPT para limpiar y reformular las preguntas y respuestas.
Al principio, intenté codificar una expresión regular compleja para limpiar los datos, pero después de muchas pruebas, me di cuenta de que chatGPT podría hacer un mejor trabajo.
También descubrí que hacerlo en dos pasos era mejor. Primero, le pedí a chatGPT que limpiara los datos y luego le pedí que los reformulara. Sí, esto lleva más tiempo, pero los resultados valen la pena.
Bien, aquí hay una posible versión reescrita de esa parte:
Para que este repositorio funcione, necesita Python 3.9 o superior en su computadora. También necesitas obtener las bibliotecas de Python en requisitos.txt usando pip:
Necesita un archivo .env con su clave API OpenAI como en
OPENAI_API_KEY= < your api key >Para ejecutarlo con la configuración predeterminada, simplemente escriba:
python3 main.pyEjemplos de archivos de líneas JSON guardados
{"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)."}]}Si cree que esto es interesante y desea contribuir o sugerir mejores formas de limpiar y preparar datos, ¡soy todo oídos!
