The world of search is changing very quickly. ChatGPT has cemented generative AI's place in making finding data faster. We'll use Elasticsearch and LangChain to build a private trivia bot on fun Star Wars trivia data.

How it will work

Setting up the Python and Elasticsearch environment

Step 1. Scraping the data

Step 2A. Loading embeddings in Elasticsearch

Step 2B. Saving time and money with Hosted Trained Models

Step 3. Win at Star Wars trivia

Conclusion

LangChain is a Python and JavaScript framework for developing applications powered by large language models.

What is Langchain?

Privacy-first AI search using LangChain and Elasticsearch

Learn about the supply chain vulnerabilities of artificial intelligence large language models (LLMs) and how the AI retrieval techniques of search engines can be used to fight misinformation and intentional tampering of AI.

The poison LLM attack

The fact supply chain

Retrieval vs. poison

Proposed solutions and architectures

You can protect against AI supply chain attacks by using Retrieval Augmented Generation (RAG) techniques. This will allow you to mitigate the risk of a poisoned LLM.

How can I protect against AI supply chain attacks?

LLM poisoning: Combatting AI supply chain attacks

Retrieval vs. poison — Fighting AI supply chain attacks

Author

Dave Erickson

Articles

Privacy-first AI search using LangChain and Elasticsearch

Retrieval vs. poison — Fighting AI supply chain attacks