File:Retrieval-Augmented Generation chatbot, part 2 - LangChain, Hugging Face, OpenSearch, AWS.webm

Uploaded by Prototyperspective
Upload date 2024-09-11T15:47:56Z
MIME type video/webm
Dimensions 1920 × 1080 px
File size 71.0 MB

Summary

Description
English: We'll walk you through the creation of a Retrieval-Augmented Generation (RAG) chatbot using open-source tools and AWS services like LangChain, Hugging Face, Amazon SageMaker, and Amazon OpenSearch Serverless.

Part 1: LangChain, Hugging Face, FAISS, Amazon SageMaker, and Amazon TextTract.

⭐️⭐️⭐️ Don't forget to subscribe to be notified of future videos. Follow me on Medium at https://julsimon.medium.com or Substack at https://julsimon.substack.com. ⭐️⭐️⭐️

We start by deploying Mistral 7B, a cutting-edge open-source LLM, onto a SageMaker endpoint. Following this, we work with the Reuters dataset, a Hugging Face dataset comprising 20,000 news articles. We break down these articles into smaller sections and apply bge-small, a compact open-source embedding model, to them.

Next, we proceed to index these sections into an Amazon OpenSearch Serverless vector index, which we then query through LangChain.

Additionally, aside from the RAG demonstration, we delve into some vital yet often overlooked steps related to authentication and security for OpenSearch Serverless.

- Notebook: https://gitlab.com/juliensimon/huggingface-demos/-/tree/main/langchain/rag-demo-sagemaker-opensearch - LangChain: https://www.langchain.com/ - Amazon OpenSearch Serverless: https://docs.aws.amazon.com/opensearch-service/latest/developerguide/serverless.html - Embedding leaderboard: https://huggingface.co/spaces/mteb/leaderboard - Embedding model: https://huggingface.co/BAAI/bge-small-en-v1.5

- LLM: https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1
Date
Source YouTube: Retrieval-Augmented Generation chatbot, part 2 - LangChain, Hugging Face, OpenSearch, AWS – View/save archived versions on archive.org
Author Julien Simon

Licensing

This video, screenshot or audio excerpt was released under the Creative Commons license option on YouTube before August 2025. (YouTube changed the license version from CC BY 3.0 to 4.0 on August 1; this was not retroactive.)
For videos uploaded or licensed after July 2025 use {{YouTube CC-BY 4.0}}
To the uploader: You must provide a link (URL) to the original file and the authorship information if available.
w:en:Creative Commons
attribution
This file is licensed under the Creative Commons Attribution 3.0 Unported license.
Attribution:
Julien Simon
You are free:
  • to share – to copy, distribute and transmit the work
  • to remix – to adapt the work
Under the following conditions:
  • attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
This file, which was originally posted to an external website, has not yet been reviewed by an administrator or reviewer to confirm that the above license is valid. See Category:License review needed for further instructions.

Captions

Add a one-line explanation of what this file represents

Items portrayed in this file

depicts

2 November 2023

video/webm

74,424,576 byte

1,282.724 second

1,080 pixel

1,920 pixel

df4e9823c5018360de22252ff59343768b595f60