✳flâneur — a map of the web's best reading
Leveraging Vector Embeddings and Similarity Search to Supplement ChatGPT’s Training Data - DEV Community
dev.to · 2,121 words · saved by 1 readers
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
Explore this link on the map →related reading
- Embeddings: What they are and why they mattersimonwillison.net
- Introducing text and code embeddings | OpenAIopenai.com
- Vector embeddings | OpenAI APIdevelopers.openai.com
- Vector databases explained | Lantern Bloglantern.dev
- Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
- Meet AI’s multitool: Vector embeddings | Google Cloud Blogcloud.google.com
- Vector embeddings | OpenAI APIplatform.openai.com
- Patterns for Building LLM-based Systems & Productseugeneyan.com
- From prototype to production: Vector databases in generative AI applications - Stack Overflowstackoverflow.blog
- Semantic Search - Sentence Transformers documentationsbert.net
- Faiss: A library for efficient similarity search - Engineering at Metaengineering.fb.com
- Google Colabcolab.research.google.com