1. Home
  2. Database
  3. Oracle
  4. Machine Learning
  5. Oracle Data Science Agent

Oracle Machine Learning Data Science Agent

Data Science Agent is an intelligent built-in conversational chatbot integrated with Oracle Machine Learning UI included in your Oracle Autonomous AI Database subscription. You must provide the LLM, whether from a third-party AI provider, OCI GenAI Service, or one you privately host. You can run complete data science workflows using natural language in the Data Science Agent chat.

Tasks

Create AI Credentials and AI Profile

An AI credential stores authentication details that the database uses to access the selected AI provider or related cloud resources. Depending on the provider, it may contain an API key, OCI signing key details, or other provider-specific authentication fields. An AI Profile is a named configuration object that specifies how the database connects to an LLM — including the provider, (for example, openai, oci), credential, model, and optional parameters such as temperature and max_tokens and so on.

Create a Data Science Agent Conversation

A conversation is a set of interactions with Data Science Agent in the chat interface. Learn how to create your Data Science Agent conversation to interact with the agent on various areas of data science and machine learning - Data profiling, data wrangling and transformation, statistical analysis of variable relationships, feature importance, classification, regression, XGBoost, clustering, anomaly detection, model training, model evaluation, and inference on new data.

Add Objects to your Conversation

The objects are tables, views, and machine learning models. You can associate multiple objects with the conversation. Learn how to add objects to your conversation and improve the precision and efficiency of Data Science Agent's responses.

Issue prompts to build and deploy a machine learning model

Learn how Data Science Agent supports a data analyst in exploring a dataset, and in building and evaluating a machine learning model. It also shows the effectiveness of Natural Language to SQL (NL2SQL) in Data Science Agent.