Тёмный

Implementing RAG using  

AI Bites
Подписаться 9 тыс.
Просмотров 2,1 тыс.
50% 1

Опубликовано:

 

21 окт 2024

Поделиться:

Ссылка:

Скачать:

Готовим ссылку...

Добавить в:

Мой плейлист
Посмотреть позже
Комментарии : 6   
@explorer945
@explorer945 6 месяцев назад
What's your recommendation on using frameworks like Langchain (extra dependency, vulnerabilities, latency, cost and control)
@AIBites
@AIBites 6 месяцев назад
Hey if it makes our lives easier as developers, we do need to use them. For example, frameworks like django have a steep learning curve. But people tend to use it to make appealing applications 😊
@explorer945
@explorer945 6 месяцев назад
@@AIBites that's exactly the point I am mentioning. It's not analogous to use if pytorch or other libraries which doesn't have any drawbacks. But langchain is been heavily criticized many times by community. Look at the concerns I mentioned. Those ones. It's great for quick prototyping, but do we take the risk for production on cost, latency, vulnerabilities etc.
@yolgezerisvicrede
@yolgezerisvicrede 6 месяцев назад
Is there a page or blog that u post those codes? Btw, great explanation.
@AIBites
@AIBites 6 месяцев назад
Thanks! Here is the notebook for this video: github.com/ai-bites/generative-ai-course/blob/main/simple_rag.ipynb Please checkout the same repo for notebooks for other videos. More to come. So please watch/star the repo. Btw, on what topic would you like future videos/tutorials to be on?
@yolgezerisvicrede
@yolgezerisvicrede 6 месяцев назад
@@AIBites i personally interest into multi modal stuff. It would be interesting to see any multi modal combined chatting with models
Далее
Меня знают уже все соседи😅
00:34
Кольцо Всевластия от Samsung
01:00
Просмотров 528 тыс.
RAG But Better: Rerankers with Cohere AI
23:43
Просмотров 61 тыс.
OpenAI Embeddings and Vector Databases Crash Course
18:41
Python RAG Tutorial (with Local LLMs): AI For Your PDFs
21:33
Меня знают уже все соседи😅
00:34