4.5.2 Viewing Chat Session Details

This section describes how to view a chat session details.

Before You Begin

• Complete the steps for Running the Chat.

Viewing Details

To view the chat session details, perform the following step:

• Inspect the @chat_options variable:

  select JSON_PRETTY(@chat_options);

The output includes the following details about a chat session:

• Vector store tables: in the database which were referenced by HeatWave Chat.

• Text segments: that were retrieved from the vector store and used as context to prepare responses for your queries.

• Chat history: which includes both your queries and responses generated by HeatWave Chat.

• LLM details: which was used by the routine to generate the responses.

The output looks similar to the following:

| {
  "tables": [
    {
      "table_name": "`demo_embeddings`",
      "schema_name": "`demo_db`"
    }
  ],
  "response": " HeatWave AutoML uses a variety of machine learning algorithms. It
  leverages Oracle AutoML technology which includes a range of algorithms such as
  decision trees, random forests, neural networks, and support vector machines (SVMs).
  The specific algorithm used by HeatWave AutoML depends on the characteristics of
  the data being analyzed and the goals of the model being created.",
  "documents": [
    {
      "id": "https://objectstorage.Region.oraclecloud.com/n/Namespace/b/BucketName/o/Path/heatwave-en.a4.pdf",
      "title": "heatwave-en.a4.pdf",
      "segment": "3.1 HeatWave AutoML Features HeatWave AutoML makes it easy to use
      machine learning, whether you are a novice user or an experienced ML practitioner.
      You provide the data, and HeatWave AutoML analyzes the characteristics of the
      data and creates an optimized machine learning model that you can use to
      generate predictions and explanations.",
      "distance": 0.18456566333770752
    },
    {
      "id": "https://objectstorage.Region.oraclecloud.com/n/Namespace/b/BucketName/o/Path/heatwave-en.a4.pdf",
      "title": "heatwave-en.a4.pdf",
      "segment": "The HeatWave AutoML ML_TRAIN routine leverages Oracle AutoML technology
      to automate the process of training a machine learning model. Oracle AutoML replaces
      the laborious and time consuming tasks of the data analyst whose workflow is as
      follows:\n1. Selecting a model from a large number of viable candidate models.\n2.
      For each model, tuning hyperparameters.\n3. Selecting only predictive features
      to speed up the pipeline and reduce over-fitting.\n99",
      "distance": 0.22687965631484985
    },
    {
      "id": "https://objectstorage.Region.oraclecloud.com/n/Namespace/b/BucketName/o/Path/heatwave-en.a4.pdf",
      "title": "heatwave-en.a4.pdf",
      "segment": "3.1.1 HeatWave AutoML Supervised Learning\nHeatWave AutoML supports supervised
      machine learning. That is, it creates a machine learning model by analyzing a labeled
      dataset to learn patterns that enable it to predict labels based on the features of the 
      dataset. For example, this guide uses the Census Income Data Set in its examples, where
      features such as age, education, occupation, country, and so on, are used to predict the
      income of an individual (the label).",
      "distance": 0.2275727391242981
    }
  ],
  "chat_history": [
    {
      "user_message": "What is HeatWave AutoML?",
      "chat_query_id": "99471681-387f-11ef-96d7-020017331ed6",
      "chat_bot_message": " HeatWave AutoML is a feature of MySQL HeatWave that makes
      it easy to use machine learning, whether you are a novice user or an experienced ML
      practitioner. It analyzes the characteristics of the data and creates an optimized
      machine learning model that can be used to generate predictions and explanations. The data
      and models never leave MySQL HeatWave, saving time and effort while keeping the data
      and models secure. HeatWave AutoML is optimized for HeatWave shapes and scaling,
      and all processing is performed on the HeatWave Cluster."
    },
    {
      "user_message": "What learning algorithms does it use?",
      "chat_query_id": "c59140f5-387f-11ef-96d7-020017331ed6",
      "chat_bot_message": " HeatWave AutoML uses a variety of machine learning algorithms.
      It leverages Oracle AutoML technology which includes a range of algorithms such
      as decision trees, random forests, neural networks, and support vector machines (SVMs).
      The specific algorithm used by HeatWave AutoML depends on the characteristics of the
      data being analyzed and the goals of the model being created."
    }
  ],
  "model_options": {
    "model_id": "mistral-7b-instruct-v1"
  },
  "request_completed": true
} |