With Large Language Models (LLMs), we can integrate domain-specific data to answer questions. This is especially useful for data unavailable to the model during its initial training, like a company's internal documentation or knowledge base.
This article helps you understand how to implement this architecture using LLMs and a Vector Database. We can significantly decrease the hallucinations that are commonly associated with LLMs.
Check out my Generative AI Series:
Generative AI — Getting Started with PaLM 2
/ generative-ai-getting-started-with-palm2
Generative AI — The Evolution of Machine Learning Engineering
/ how-to-approach-ml-problems-in-times-of-ge...
Generative AI — Best Practices for LLM Prompt Engineering
/ generative-ai-best-practices-for-llm-promp...
Generative AI — Document Retrieval and Question Answering with LLMs
/ generative-ai-document-retrieval-and-quest...
Generative AI — Mastering the Language Model Parameters for Better Outputs
/ generative-ai-mastering-the-language-model...
Generative AI - Understand and Mitigate Hallucinations in LLMs
/ generative-ai-understand-and-mitigate-hall...
📓 Notebook: https://colab.research.google.com/dri...
📖 Article: / generative-ai-document-retrieval-and-quest...
If you enjoyed this video, please subscribe to the channel ❤️
🎉 Subscribe for Article and Video Updates!
/ subscribe
/ member. .
You can find me here:
LinkedIn: / saschaheyer
If you or your company is looking for advice on the cloud or ML, check out the company I work for.
https://www.doit.com/
We offer consulting, workshops, and training at zero cost. Imagine an extension for your team without additional costs.
#vertexai #googlecloud #machinelearning #mlengineer #doit
▬ My current recording equipment ▬▬▬▬▬▬▬▬
► Camera for recording and streaming in 4K https://amzn.to/3QQzwiN
► Lens with nice background blur https://amzn.to/3dVDAjb
► Connect the camera to PC 4K https://amzn.to/3ciYyrE
► Light https://amzn.to/3Rb065M
► Most flexible way to mount your camera + mic https://amzn.to/3TedZC5
► Microphone (I love it) https://amzn.to/3QV3mmb
► Audio Interface https://amzn.to/3CBxj5M
Support my channel if you buy with those links on Amazon
▬ Timestamps ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
00:00 Introduction
00:27 Architecture
01:16 Languages
01:45 Indexing vs. Tuning
03:33 Langchain
04:19 Data
04:40 Get data
05:10 LangChain chunking
06:02 Embedding and Vectordatabase
11:06 LLM answers questions
13:00 Bye
Смотрите видео Generative AI / LLM - Document Retrieval and Question Answering онлайн, длительностью часов минут секунд в хорошем качестве, которое загружено на канал ML Engineer 22 Июнь 2023. Делитесь ссылкой на видео в социальных сетях, чтобы ваши подписчики и друзья так же посмотрели это видео. Данный видеоклип посмотрели 21,411 раз и оно понравилось 401 посетителям.