9 Work with LLM-Powered APIs and Retrieval Augmentation Generation
You can use Vector Utility PL/SQL APIs for prompting Large Language Models (LLMs) with textual prompts, using LLM-powered chat interfaces. You can also communicate with LLMs through the implementation of Retrieval Augmentation Generation (RAG), which helps to generate more accurate and informative responses.
- Use LLM-Powered APIs to Generate Summaries and Text
In these examples, you can see how to summarize a textual extract and provide a descriptive answer for a given prompt. - Use Retrieval Augmented Generation to Complement LLMs
RAG lets you mitigate the inaccuracies and hallucinations faced when using LLMs. Oracle AI Vector Search enables RAG within Oracle Database using theDBMS_VECTOR_CHAIN
PL/SQL package or through popular frameworks (such as LangChain).