How RAG (Retrieval-Augmented Generation) talks with your private data using LLM | AI Heroes 2023

🎟️ 2024 ticket SPECIAL PRICE: https://ticket.synesthesia.it/events/aih-24/
More information: https://aiheroes.it/2024/

⏩ Chapter:
00:00 intro
03:13 Retrieval-Augmented Generation (RAG)
03:42 Generation part
05:48 Retrieval-Augmented
07:10 RAG diagram
09:09 What is a vector & Similarity?
12:21 Embedding
14:34 Vector databases available
15:24 Vector database + LLM
16:41 Split the documents in chunk
17:45 Text splitter
19:18 LangChain
21:15 DEMO: Build a RAG using LangChain + ChatGPT + Elasticsearch
23:20 Installing some dependencies
25:04 Compare vectors
27:10 Loading PDF document
27:55 Split the document in Chunks
29:14 Vector search
29:54 Chat with your data and get the answers with document and resource

In this presentation, we will introduce a recent proposal in AI that is called Retrieval-Augmented Generation (RAG).
This technique is able to leverage the natural language capabilities of Large Language Model (LLM) such as ChatGPT in order to query a private database. You can literally ask question about your data, without the need to fine-tune an LLM with all your private data. We will show also an example of RAG using Langchain, an open source framework for writing applications for LLM. We will execute a demo with a few lines of Python to chat with private data using a vector database like Chroma or Elasticsearch.
🎤 ENRICO ZIMUEL, Principal Software Engineer, Elastic


📍AI Heroes was hosted in Turin, 1 December. Attended by 240+ participants and broadcast to an additional 50+ participants. The event was highly interactive with excellent presentations, high value networking and lots of engagement between the participants.

✅ Tweet: https://twitter.com/AIHeroes_it
✅ Connect: https://www.linkedin.com/showcase/aiheroes-it/
✅ Read: https://t.me/aiheroes

#aiheroes #RetrievalAugmentedGeneration #machinelearning #langchain #aimodels #chatgpt #llms #elasticsearch #VectorDatabase #aiengineering #pythondevelopment