OpenAI

This documentation describes the integration of MindsDB with OpenAI, an AI research organization known for developing AI models like GPT-3 and GPT-4. The integration allows for the deployment of OpenAI models within MindsDB, providing the models with access to data from various data sources.

Prerequisites

Before proceeding, ensure the following prerequisites are met:

Install MindsDB locally via Docker or Docker Desktop.
To use OpenAI within MindsDB, install the required dependencies following this instruction.
Obtain the OpenAI API key required to deploy and use OpenAI models within MindsDB. Follow the instructions for obtaining the API key.

Setup

Create an AI engine from the OpenAI handler.

CREATE ML_ENGINE openai_engine
FROM openai
USING
      openai_api_key = 'api-key-value';

Create a model using openai_engine as an engine.

CREATE MODEL openai_model
PREDICT target_column
USING
      engine = 'openai_engine',  -- engine name as created via CREATE ML_ENGINE
      mode = 'mode_name', -- optional, ...
      model_name = 'openai_model_name',  -- optional with default value of gpt-3.5-turbo
      question_column = 'question',  -- optional, column name that stores user input
      context_column = 'context',  -- optional, column that stores context of the user input
      prompt_template = 'input message to the model here', -- optional, user provides instructions to the model here
      max_tokens = 100, -- optional, token limit for answer
      temperature = 0.3, -- temp
      json_struct = {
        'key': 'value',
        ...
      }'

If you want to update the prompt_template parameter, you do not have to recreate the model. Instead, you can override the prompt_template parameter at prediction time like this:

SELECT question, answer
FROM openai_model
WHERE question = 'input question here'
USING prompt_template = 'input new message to the model here';

The following parameters are available to use when creating an OpenAI model:

Usage

The following usage examples utilize openai_engine to create a model with the CREATE MODEL statement.

Here is how to create a model that answers questions without context.

CREATE MODEL openai_model
PREDICT answer
USING
    engine = 'openai_engine',
    question_column = 'question';

Query the model to get predictions.

SELECT question, answer
FROM openai_model
WHERE question = 'Where is Stockholm located?';

Here is the output:

+---------------------------+-------------------------------+
|question                   |answer                         |
+---------------------------+-------------------------------+
|Where is Stockholm located?|Stockholm is located in Sweden.|
+---------------------------+-------------------------------+

Here is how to create a model that answers questions with context.

CREATE MODEL openai_model
PREDICT answer
USING
    engine = 'openai_engine',
    question_column = 'question',
    context_column = 'context';

Query the model to get predictions.

SELECT context, question, answer
FROM openai_model
WHERE context = 'Answer accurately'
AND question = 'How many planets exist in the solar system?';

On execution, we get:

+-------------------+-------------------------------------------+----------------------------------------------+
|context            |question                                   |answer                                        |
+-------------------+-------------------------------------------+----------------------------------------------+
|Answer accurately  |How many planets exist in the solar system?| There are eight planets in the solar system. |
+-------------------+-------------------------------------------+----------------------------------------------+

Here is how to create a model that offers the most flexible mode of operation. It answers any query provided in the prompt_template parameter.

Good prompts are the key to getting great completions out of large language models like the ones that OpenAI offers. For best performance, we recommend you read their prompting guide before trying your hand at prompt templating.

Let’s look at an example that reuses the openai_model model created earlier and overrides parameters at prediction time.

SELECT instruction, answer
FROM openai_model
WHERE instruction = 'Speculate extensively'
USING
    prompt_template = '{{instruction}}. What does Tom Hanks like?',
    max_tokens = 100,
    temperature = 0.5;

On execution, we get:

+----------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|instruction           |answer                                                                                                                                                                                                                         |
+----------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
|Speculate extensively |Some people speculate that Tom Hanks likes to play golf, while others believe that he enjoys acting and directing. It is also speculated that he likes to spend time with his family and friends, and that he enjoys traveling.|
+----------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+

Next Steps

Follow this tutorial on sentiment analysis and this tutorial on finetuning OpenAI models to see more use case examples.

Troubleshooting Guide

Authentication Error

Symptoms: Failure to authenticate to the OpenAI API.
Checklist:
1. Make sure that your OpenAI account is active.
2. Confirm that your API key is correct.
3. Ensure that your API key has not been revoked.
4. Ensure that you have not exceeded the API usage or rate limit.

SQL statement cannot be parsed by mindsdb_sql

Symptoms: SQL queries failing or not recognizing table and model names containing spaces or special characters.

Checklist:

Ensure table names with spaces or special characters are enclosed in backticks. Examples:

Incorrect:

SELECT input.text, output.sentiment
FROM integration.travel data AS input
JOIN openai_engine AS output

Incorrect:

SELECT input.text, output.sentiment
FROM integration.'travel data' AS input
JOIN openai_engine AS output

Correct:

SELECT input.text, output.sentiment
FROM integration.`travel data` AS input
JOIN openai_engine AS output

Integrations

Data Sources

AI Engines

Prerequisites

Setup

Usage

Troubleshooting Guide

Integrations

Data Sources

AI Engines

​Prerequisites

​Setup

​Usage

​Troubleshooting Guide

Prerequisites

Setup

Usage

Troubleshooting Guide