利用 Oracle Database 23ai 实现智能搜索和助手应用 [PRE1110]（1）.pdf

1、 Oracle AI Vector Search Deep Dive Oracle Vector Search and OCI Generative AISean KimSenior Principal Database&Exadata InstructorOracle UniversityOct 13,2025The following is intended to outline our general product direction.It is intended for information purposes only,and may not be incorporated int

2、o any contract.It is not a commitment to deliver any material,code,or functionality,and should not be relied upon in making purchasing decisions.The development,release,timing,and pricing of any features or functionality described for Oracles products may change and remains at the sole discretion of

3、 Oracle Corporation.Safe harbor statement2Copyright 2025,Oracle and/or its affiliates|Confidential:Internal/Restricted/Highly RestrictedOracle Vector Search and OCI Generative AIUsing PythonOCI Generative AI Service4Copyright 2025,Oracle and/or its affiliates|Confidential:Internal/Restricted/Highly

4、RestrictedTransform user questions into augmented retrieval contentLeverage Oracle AI Vector Search to retrieve contextually relevant informationCreate prompts as inputs for retrieving using a Large Language Model(LLM)RAG with Python Step SummaryHere are the typical steps:1.Load and prepare the docu

5、ment2.Generate embeddings3.Create a vector table in Oracle Database 23ai4.Insert embeddings into Oracle Vector Store5.Handle user question6.Perform similarity search7.Construct the LLM prompt8.Call OCI GenAI9.Display result and timing5Copyright 2025,Oracle and/or its affiliates|Confidential:Internal

6、/Restricted/Highly RestrictedPreparation stepsQuery stepsStep 1-1:Load and prepare the documentPython code snippet:6Copyright 2025,Oracle and/or its affiliates|Confidential:Internal/Restricted/Highly Restrictedimport osdef loadFAQs(directory_path):faqs=for filename in os.listdir(directory_path):if f