Fast and Precise Business and Semantic Data Search with AI Vector Search

As more businesses develop and deploy AI-driven applications, there’s a strategic decision to make: What vector database do we use? Vectors, which are unique strings of numbers calculated to represent unstructured data, let companies add context to generic large language models (LLMs). Vectors enable rapid semantic search of the unstructured data they represent, a critical capability for use cases such as making product recommendations or showing correlations among data or objects.
Oracle recently added vector data to the growing list of data types incorporated into Oracle Database. This support comes in the form of a new capability in Oracle Database 23c called “AI Vector Search.” It includes vectors as a native data type, as well as vector indexes and vector search SQL operators, which together make it possible to store the semantic content of unstructured data as vectors. You can then run fast similarity queries on documents, images, and any other unstructured data represented as vectors.
Oracle’s AI Vector Search supports Retrieval Augmented Generation (RAG), an advanced generative AI technique that combines large language models (LLMs) and private business data to deliver responses to natural language questions. RAG provides higher accuracy and avoids having to expose private data by including it in the LLM training data.

[@jaanireel]

00:01 Vector search allows finding similar or related things.
02:55 Oracle AI Vector Search allows for similarity search using neural networks and vectors.
08:46 Using similarity search for any technology
11:26 Vector distance determines relevance
17:11 Large language models have various uses and limitations
19:34 Vector databases can add new facts to large language models based on private, up-to-date information.
24:20 Oracle AI Vector search will be released as part of Oracle database 23.4.
26:50 Oracle AI Vector search adds Vector capabilities to the Oracle database.
31:39 Storing vectors in the Oracle database for retrieval augmented generation
33:48 Embeddings for query and data need to be the same for similarity search.
39:00 Perform similarity search across database and file system data.
41:21 Oracle AI Vector Search converts data to plain text and creates vector embeddings using psql table functions.
46:09 AI Vector search is a new feature of Oracle database 23.4
48:33 Choosing the best embedding model for language and business use case
53:07 Oracle Vector search in 23c is different from LL index and Lang chain
55:20 Oracle AI Vector Search allows using your favorite SQL API and language to handle images, audio, and videos.

[@Mukesh11416]

Kindly share the Github link for the demo project shown in this video.

[@SergiiShcheteniuk]

How can I get access to or download LA1 Oracle 23c Free (23.4) software?

[@krishnasahu2901]

Can we have Github link for demo projects which shows in this video

[@sichen4049]

could you please share the Github link of resources in this video? Thanks.

[@shahn1310]

please share Github details , many people are asking this details sine weeks n months