AI Explorer
The Oracle AI Explorer for Apps (the AI Explorer) consists of an API Server (ai-explorer-server) and an optional web-based GUI (ai-explorer-client) component. Both the API Server and GUI can be run on bare-metal or inside containers.
The following additional components, not delivered with the AI Explorer, are also required. These can be run On-Premises or in the Cloud:
- Oracle Database 23ai, including Oracle Database 23ai Free
- Access to at least one Large Language Model
- Access to at least one Embedding Model (for Retrieval Augmented Generation)
The AI Explorer is specifically designed to run in container orchestration systems, such as Kubernetes. For more information on deploying the AI Explorer in Kubernetes, using a Helm Chart, please review the Advanced - Microservices documentation.
API Server (AI Explorer Server)
The workhorse of the AI Explorer is the API Server, referred to as the AI Explorer Server. By default, the AI Explorer Server will start on port 8000
All the docs
The AI Explorer Server API documentation can be accessed at http://<IP Address>:<Port>/v1/docs#
of a running instance.
Powered by FastAPI and Uvicorn, the AI Explorer Server acts as an intermediary between the clients, AI Models, and the Oracle Database.
Client (AI Explorer Client)
The provided web-based GUI client is built with Streamlit and interacts with the API Server via REST calls.
BYO Client
You can develop and replace the provided client with any REST capable client.
Database
Oracle Database 23ai, including Oracle Database 23ai Free provides a persistent data store for the AI Explorer.
Reduced capabilities
The AI Explorer can be used to interact with language models without having the database configured, but additional functionality such as RAG, will not be available without the database.
The 23ai database provides:
- the Vector Store for split and embedded documents used for Retrieval Augmented Generation (RAG).
- storage for the Testbed Q&A Test Sets and Evaluations
- storage of AI Explorer settings and configuration
Document Source
Access to document sources for the purpose of embedding and populating the Vector Storage is provided. Documents can be accessed from your local storage, OCI Object Storage, or from a web page.
AI Models
The AI Explorer provides the ability to connect to any language or embedding model to be used for completions and creating vectors. Adding, Deleting, and Modifying access to AI Models is quick and easy.