Bienvenue dans ce référentiel, où vous apprendrez à récupérer sur un forum communautaire des données étonnantes que vous pourrez utiliser pour affiner votre modèle chatGPT. Il s'agit d'un projet intéressant qui vous montre comment créer une solution d'IA à partir de zéro, de la collecte de données au déploiement du modèle.
Il s'agit de la première partie d'une série d'exemples complets de mise au point à partir de zéro. La deuxième partie est ici : https://github.com/BenderScript/techGPT
Avant d'aborder la partie amusante de GenAI, nous devons d'abord obtenir quelques données. Et pas n’importe quelles données, mais des données de qualité, pertinentes et utiles à notre tâche.
Scraper un forum n'est pas aussi simple qu'il y paraît. Nous devons faire face à de nombreux défis et décisions, tels que :
Comme vous pouvez le constater, il y a beaucoup de choses à prendre en compte avant de pouvoir commencer à récupérer les données.
Une fois que nous avons récupéré et nettoyé les données, nous devons les préparer pour la formation. Cela signifie que nous devons transformer les données dans un format que GenAI peut comprendre. En d’autres termes, nous devons reformuler les questions et les réponses de manière à préserver leur sens et leur ton.
Par exemple, une question telle que : « J'ai essayé de configurer un nouveau point d'accès sans fil et j'ai besoin de savoir comment configurer le SSID et le mot de passe. Quelqu'un peut-il m'aider ? » doit être reformulée comme suit : « Comment configurer le SSID et le mot de passe. mot de passe sur un nouveau point d'accès sans fil ? »
Il en va de même pour les réponses. Nous devons les reformuler de manière claire et concise.
L'approche que j'ai utilisée dans ce référentiel consiste à exploiter chatGPT lui-même pour nettoyer et reformuler les questions et réponses.
Au début, j'ai essayé de coder une expression regex complexe pour nettoyer les données, mais après de nombreux tests, j'ai réalisé que chatGPT pouvait faire un meilleur travail.
J’ai aussi découvert qu’il était préférable de le faire en deux étapes. Tout d’abord, j’ai demandé à chatGPT de nettoyer les données, puis je lui ai demandé de les reformuler. Oui, cela prend plus de temps, mais les résultats en valent la peine.
D'accord, voici une possible version réécrite de cette partie :
Pour faire fonctionner ce référentiel, vous avez besoin de Python 3.9 ou supérieur sur votre ordinateur. Vous devez également obtenir les bibliothèques Python dans Requirements.txt en utilisant pip :
Vous avez besoin d'un fichier .env
avec votre clé API OpenAI comme dans
OPENAI_API_KEY= < your api key >
Pour l'exécuter avec les paramètres par défaut, tapez simplement :
python3 main.py
Exemples de fichiers JSON Lines enregistrés
{"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 vous pensez que cela est intéressant et que vous souhaitez contribuer ou suggérer de meilleures façons de nettoyer et de préparer les données, je suis tout ouïe !