Leveraging Vector Embeddings and Similarity Search to Supplement ChatGPT’s Training Data - DEV Community

Since the release of OpenAI’s ChatGPT, and later its REST API, the technology world has been...

Since the release of OpenAI’s ChatGPT, and later its REST API, the technology world has been enveloped by the vast capabilities of this paradigm-shifting technology and pushing it to its limits. However, for as many strengths as it has, ChatGPT has two pronounced weaknesses: 1) its training data cutoff is 2021, meaning it has no knowledge of the information in more recent times, and 2) it is prone to hallucinations or making up information. To circumvent this issue, software developers and prompt engineers alike have taken on the task of supplementing ChatGPT’s knowledge base with additional i

related reading

• From prototype to production: Vector databases in generative AI applications - Stack Overflowstackoverflow.blog
• Vector embeddings | OpenAI APIdevelopers.openai.com
• Embeddings: What they are and why they mattersimonwillison.net
• Vector embeddings | OpenAI APIplatform.openai.com
• Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
• Vector databases explained | Lantern Bloglantern.dev
• Deep Dive into LLMs like ChatGPTyoutube.com
• Sentence Embeddings. Introduction to Sentence Embeddings – hackerllamaosanseviero.github.io
• GPT in 60 Lines of NumPy | Jay Modyjaykmody.com
• Faiss: A library for efficient similarity search - Engineering at Metaengineering.fb.com
• Meet AI’s multitool: Vector embeddings | Google Cloud Blogcloud.google.com
• Comparison of different Word Embeddings on Text Similarity — A use case in NLP | by Intellica.AI | Mediumintellica-ai.medium.com