Awesome
Ballerina OpenAI Assistants connector
Overview
OpenAI, an AI research organization focused on creating friendly AI for humanity, offers the OpenAI API to access its powerful AI models for tasks like natural language processing and image generation.
The ballarinax/openai.assistants
connector allows developers to seamlessly integrate OpenAI's advanced language models into their applications by interacting with OpenAI REST API v1. This connector provides tools to build powerful OpenAI Assistants capable of performing a wide range of tasks, such as generating human-like text, managing conversations with persistent threads, and utilizing multiple tools in parallel. OpenAI has recently announced a variety of new features and improvements to the Assistants API, moving their Beta to a new API version, OpenAI-Beta: assistants=v2
. The users can interact with both the API v1 and v2 by passing the respective API version header with the request.
Setup guide
To use the OpenAI Connector, you must have access to the OpenAI API through a OpenAI Platform account and a project under it. If you do not have a OpenAI Platform account, you can sign up for one here.
-
Open the OpenAI Platform Dashboard.
-
Navigate to Dashboard -> API keys <img src=https://raw.githubusercontent.com/ballerina-platform/module-ballerinax-openai.assistants/main/docs/setup/resources/navigate-api-key-dashboard.png alt="OpenAI Platform" style="width: 70%;">
-
Click on the "Create new secret key" button <img src=https://raw.githubusercontent.com/ballerina-platform/module-ballerinax-openai.assistants/main/docs/setup/resources/api-key-dashboard.png alt="OpenAI Platform" style="width: 70%;">
-
Fill the details and click on Create secret key <img src=https://raw.githubusercontent.com/ballerina-platform/module-ballerinax-openai.assistants/main/docs/setup/resources/create-new-secret-key.png alt="OpenAI Platform" style="width: 70%;">
-
Store the API key securely to use in your application <img src=https://raw.githubusercontent.com/ballerina-platform/module-ballerinax-openai.assistants/main/docs/setup/resources/saved-key.png alt="OpenAI Platform" style="width: 70%;">
Quickstart
To use the OpenAI Assistants
connector in your Ballerina application, update the .bal
file as follows:
Step 1: Import the module
Import the openai.assistants
module.
import ballerinax/openai.assistants;
Step 2: Instantiate a new connector
Create a assistants:ConnectionConfig
with the obtained access token and initialize the connector with it.
configurable string token = ?;
final assistants:Client openAIAssistant = check new ({
auth: {
token
}
});
Setting HTTP Headers in Ballerina
Calls to the Assistants API require that you pass a beta HTTP header. In Ballerina, you can define the header as follows:
const record {string OpenAI\-Beta;} headers = {
OpenAI\-Beta: "assistants=v2"
};
Step 3: Invoke the connector operations
Now, utilize the available connector operations.
public function main() returns error? {
// define the required tool
assistants:AssistantToolsCode tool = {
type: "code_interpreter"
};
// define the assistant request object
assistants:CreateAssistantRequest request = {
model: "gpt-3.5-turbo",
name: "Math Tutor",
description: "An Assistant for personal math tutoring",
instructions: "You are a personal math tutor. Help the user with their math questions.",
tools: [tool]
};
// call the `post assistants` resource to create an Assistant
assistants:AssistantObject assistant = check openaiAssistant->/assistants.post(headers,request);
}
Step 4: Run the Ballerina application
bal run
Examples
The OpenAI Assistants
connector provides practical examples illustrating usage in various scenarios. Explore these examples, covering the following use cases:
-
Math tutor bot - Create an assistant to solve mathematical problems with step-by-step solutions and interactive guidance.
-
Weather assistant - Develop an assistant to provide weather information by leveraging function calls for temperature and rain probability.
Build from the source
Setting up the prerequisites
-
Download and install Java SE Development Kit (JDK) version 17. You can download it from either of the following sources:
Note: After installation, remember to set the
JAVA_HOME
environment variable to the directory where JDK was installed. -
Download and install Ballerina Swan Lake.
-
Download and install Docker.
Note: Ensure that the Docker daemon is running before executing any tests.
-
Export Github Personal access token with read package permissions as follows,
export packageUser=<Username> export packagePAT=<Personal access token>
Build options
Execute the commands below to build from the source.
-
To build the package:
./gradlew clean build
-
To run the tests:
./gradlew clean test
-
To build the without the tests:
./gradlew clean build -x test
-
To run tests against different environments:
./gradlew clean test -Pgroups=<Comma separated groups/test cases>
-
To debug the package with a remote debugger:
./gradlew clean build -Pdebug=<port>
-
To debug with the Ballerina language:
./gradlew clean build -PbalJavaDebug=<port>
-
Publish the generated artifacts to the local Ballerina Central repository:
./gradlew clean build -PpublishToLocalCentral=true
-
Publish the generated artifacts to the Ballerina Central repository:
./gradlew clean build -PpublishToCentral=true
Contribute to Ballerina
As an open-source project, Ballerina welcomes contributions from the community.
For more information, go to the contribution guidelines.
Code of conduct
All the contributors are encouraged to read the Ballerina Code of Conduct.
Useful links
- For more information go to the
openai.assistants
package. - For example demonstrations of the usage, go to Ballerina By Examples.
- Chat live with us via our Discord server.
- Post all technical questions on Stack Overflow with the #ballerina tag.