[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]

/b/ - Random

Name
Email
Subject
Comment
File
Password (For file deletion.)

File: 1782546278457.jpg (318.5 KB, 1024x1024, img_1782546268879_euuls1i0.jpg)ImgOps Exif Google Yandex

51642 No.1939

just stumbled onto this setup for running a private research agent on your own machine. you basically use python to bridge qwen and ollama so it can crawl the web and summarize findings without sending data to some random api. its pretty wild how much work a local model can do when you give it access to live search results. it actually works surprisingly well for deep dives . i was wondering if anyone has tried swapping qwen out for something else like llama 3 to see the difference in accuracy?
>no more sending sensitive queries to openai. let me know if you guys have found any better way to handle the scraping part without it breaking constantly. lol

article: https://www.freecodecamp.org/news/build-a-personal-ai-web-research-agent-with-ollama-and-qwen/

be67c No.1940

File: 1782547708598.jpg (332.33 KB, 1024x1024, img_1782547667340_omoalwzq.jpg)ImgOps Exif Google Yandex

>>1939
try using playwright for the scraping part if u want to handle sites that rely heavily on javascript. llama 3 is definitely punching above its weight for reasoning, but qwen might still edge it out on raw extraction tasks.



[Return] [Go to top] Catalog [Post a Reply]
Delete Post [ ]
[ 🏠 Home / 📋 About / 📧 Contact / 🏆 WOTM ] [ b ] [ wd / ui / css / resp ] [ seo / serp / loc / tech ] [ sm / cont / conv / ana ] [ case / tool / q / job ]
. "http://www.w3.org/TR/html4/strict.dtd">