ยินดีต้อนรับสู่พื้นที่เก็บข้อมูลนี้ ซึ่งคุณจะได้เรียนรู้วิธีดึงข้อมูลจากฟอรัมชุมชนเพื่อหาข้อมูลที่น่าทึ่งซึ่งคุณสามารถใช้ปรับแต่งโมเดล chatGPT ของคุณได้ นี่เป็นโปรเจ็กต์เจ๋งๆ ที่แสดงให้คุณเห็นถึงวิธีสร้างโซลูชัน AI ตั้งแต่เริ่มต้น ตั้งแต่การรวบรวมข้อมูลไปจนถึงการนำโมเดลไปใช้
นี่เป็นส่วนแรกของชุดตัวอย่างการปรับแต่งแบบละเอียดตั้งแต่ต้น ส่วนที่สองอยู่ที่นี่: https://github.com/BenderScript/techGPT
ก่อนที่เราจะเข้าสู่ส่วนที่สนุกสนานของ GenAI เราจำเป็นต้องได้รับข้อมูลก่อน และไม่ใช่แค่ข้อมูลใด ๆ แต่เป็นข้อมูลคุณภาพสูงที่เกี่ยวข้องและเป็นประโยชน์สำหรับงานของเรา
การคัดลอกฟอรัมไม่ใช่เรื่องง่ายอย่างที่คิด มีความท้าทายและการตัดสินใจมากมายที่เราต้องเผชิญ เช่น:
อย่างที่คุณเห็น มีหลายสิ่งที่ต้องคำนึงถึงก่อนที่เราจะเริ่มคัดลอกข้อมูลได้
เมื่อเราขูดและล้างข้อมูลแล้ว เราต้องเตรียมข้อมูลสำหรับการฝึกอบรม ซึ่งหมายความว่าเราจำเป็นต้องแปลงข้อมูลให้อยู่ในรูปแบบที่ GenAI สามารถเข้าใจได้ กล่าวอีกนัยหนึ่ง เราจำเป็นต้องเรียบเรียงคำถามและคำตอบใหม่ในลักษณะที่คงความหมายและน้ำเสียงไว้
ตัวอย่างเช่น คำถามเช่น: " ฉันพยายามกำหนดค่า AP ไร้สายใหม่ และฉันจำเป็นต้องรู้วิธีกำหนดค่า SSID และรหัสผ่าน ใครสามารถช่วยฉันได้บ้าง " จำเป็นต้องเรียบเรียงใหม่เป็น: "ฉันจะตั้งค่า SSID และ รหัสผ่านบน AP ไร้สายใหม่?”
เช่นเดียวกับคำตอบ เราจำเป็นต้องเรียบเรียงถ้อยคำใหม่ให้ชัดเจนและกระชับ
แนวทางที่ฉันใช้ในพื้นที่เก็บข้อมูลนี้คือใช้ประโยชน์จาก chatGPT เพื่อล้างและเรียบเรียงคำถามและคำตอบใหม่
ในตอนแรก ฉันลองเขียนโค้ดนิพจน์ regex ที่ซับซ้อนเพื่อล้างข้อมูล แต่หลังจากการทดสอบหลายครั้ง ฉันพบว่า chatGPT ทำงานได้ดีกว่า
ฉันยังพบว่าการทำสองขั้นตอนนั้นดีกว่า ก่อนอื่น ฉันขอให้ chatGPT ล้างข้อมูล จากนั้นฉันก็ขอให้เปลี่ยนถ้อยคำใหม่ ใช่ การดำเนินการนี้ใช้เวลานานกว่านั้น แต่ผลลัพธ์ก็คุ้มค่า
โอเค นี่คือเวอร์ชันที่เขียนใหม่ที่เป็นไปได้ของส่วนนั้น:
เพื่อให้พื้นที่เก็บข้อมูลนี้ทำงานได้ คุณต้องมี Python 3.9 ขึ้นไปบนคอมพิวเตอร์ของคุณ คุณต้องได้รับไลบรารี Python ใน Requirements.txt โดยใช้ pip:
คุณต้องมีไฟล์ .env
พร้อมด้วยคีย์ OpenAI API ของคุณ
OPENAI_API_KEY= < your api key >
หากต้องการรันด้วยการตั้งค่าเริ่มต้น เพียงพิมพ์:
python3 main.py
ตัวอย่างไฟล์ JSON Lines ที่บันทึกไว้
{"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)."}]}
หากคุณคิดว่าสิ่งนี้น่าสนใจและต้องการมีส่วนร่วมหรือแนะนำวิธีที่ดีกว่าในการทำความสะอาดและเตรียมข้อมูล ฉันก็พร้อมรับฟัง!