GREEN-API Go demo chatbot#

Go chatbot demo this is an example of a chatbot written using Go chatbot Whatsapp library, which is designed specifically for writing chatbots using the GREEN-API service.

The chatbot clearly demonstrates the use of the API to send text messages, files, pictures, locations and contacts.

Scan the QR code or follow the link to start communicating with the chatbot

To launch a chatbot on your own Whatsapp account, follow the instructions:

Content#

1. Installation
2. Launching a chatbot
3. Setup
4. Usage
5. Code structure
6. Message handling
7. GPT functionality

1. Installation#

To run the chatbot, you need to install the Golang environment. Download the latest release suitable for your operating system from official website. Follow the default settings and complete the environment installation.

After completion, you need to check whether the environment was deployed correctly. To do this, open a command line (for example, cmd or bash) and enter the query:

     go version

     go version go 1.19

Download and unzip the zip archive of the project or clone it with the version control system command:

git clone https://github.com/green-api/whatsapp-demo-chatbot-golang

Open the project in any IDE.

The environment for launching the chatbot is ready, now you need to configure and launch the chatbot on your Whatsapp account.

2. Launching a chatbot#

In order to set up a chatbot on your Whatsapp account, you need to go to console and register. For new users, instructions are provided for setting up an instance and obtaining the parameters necessary for the chatbot to work, namely:

     idInstance
     apiTokenInstance

You'll also need an OpenAI API key to use the GPT functionality. You can obtain one from the OpenAI platform.

Create a .env file in the project root with the following variables:

ID_INSTANCE=your_instance_id
AUTH_TOKEN=your_api_token
OPENAI_API_KEY=your_openai_api_key

Don't forget to enable all notifications in your instance settings so that the chatbot can start receiving messages immediately. Data initialization is necessary to link the bot with your Whatsapp account:

     bot := chatbot.NewBot("{INSTANCE}", "{TOKEN}")

Next, you can run the program by clicking start in the IDE interface or entering the following query in the command line:

    go run main.go

The whatsapp-chatbot-golang library has a mechanism for changing instance settings using the SetSettings method, which is launched when the chatbot is enabled.

All settings for receiving notifications are disabled by default, the chatbot will enable the following settings:

     "incomingWebhook": "yes",
     "pollMessageWebhook": "yes",
     "markIncomingMessagesReaded": "yes"

The process of changing settings takes several minutes, during which time the instance will be unavailable. Messages sent to the chatbot during this time will not be processed.

After the settings are applied, notifications about previously received incoming messages will be deleted. This process is also written in the library whatsapp-chatbot-golang and starts automatically after changing the settings.

This is necessary so that the chatbot does not start processing messages from old chats.

After changing the settings and deleting incoming notifications, the chatbot will begin to respond to messages as standard. In total, this process takes no more than 5 minutes.

To stop the chatbot, use the keyboard shortcut Ctrl + C in the command line.

3. Setup#

By default, the chatbot uses links todownloading files from the network, however, users can add their own links to files, one for a file of any extension pdf / docx /... and one for a picture.

Links must lead to files from cloud storage or public access. In the file endpoints.go there is the following code to send the file:

case "2":
     message.AnswerWithUrlFile(
         "https://images.rawpixel.com/image_png_1100/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIzLTExL3Jhd3BpeGVsb2ZmaWNlMTlfcGhvdG9fb2ZfY29yZ2lzX2luX2NocmlzdG1hc19zd2Vhd GVyX2luX2FfcGFydF80YWM1ODk3Zi1mZDMwLTRhYTItYWM5NS05YjY3Yjg1MTFjZmUucG5n.png",
         "corgi.png",
         util.GetString([]string{"send_file_message", lang})+util.GetString([]string{"links", lang, "send_file_documentation"}))

case "2":
     message.AnswerWithUrlFile(
         "https://...somefile.pdf",
         "somefile.pdf",
         util.GetString([]string{"send_file_message", lang})+util.GetString([]string{"links", lang, "send_file_documentation"}))

All changes must be saved, after which you can launch the chatbot. To launch the chatbot, return to step 2

4. Usage#

If the previous steps have been completed, then the chatbot should be working on your Whatsapp account. It is important to remember that the user must be authorized in console.

Now you can send messages to the chatbot!

The chatbot will respond to any message sent to your account. Since the chatbot supports several languages, before greeting the interlocutor, the chatbot will ask you to select a language of communication:

1 - English
2 - Kazakh
3 - Russian

Welcome to GREEN-API chatbot, user! GREEN-API provides the following types of data sending. Select a number from the list to check how the sending method works

1. Text message 📩
2. File 📋
3. Picture 🖼
4. Audio 🎵
5. Video 📽
6. ...
14. 🔥 Conversation with ChatGPT 🤖

To return to the beginning write stop or 0

For example, by sending 1, the user will receive in response:

This message was sent via the sendMessage method.

To find out how the method works, follow the link
https://green-api.com/docs/api/sending/SendMessage/

Sorry, I didn't quite understand you 😔, write a menu to see possible options

Thank you for using the GREEN-API chatbot, user!

GPT Chat Mode#

By selecting option 14, you can interact with OpenAI's GPT model:

🤖 You have started a conversation with ChatGPT.
Ask any questions, and ChatGPT will try to answer them.
To return to the main menu, type *menu*, *exit*, *stop*, or *back*.

In this mode, your messages will be processed by GPT, and you'll receive intelligent responses. The conversation history is maintained throughout your session, allowing for contextual interactions.

To exit GPT mode and return to the main menu, type any of the exit commands like "menu", "exit", "back", etc.

5. Code structure#

The main file of the chatbot is main.go, in it contains the main function and program execution begins from it. In this class, the bot object is initialized using the BotFactory class, the first scene is set, and the bot is launched.

func main() {
    // Load environment variables
    err := godotenv.Load(".env")

    // Initialize the base bot
    baseBot := chatbot.NewBot(idInstance, authToken)

    // Initialize and register the GPT bot
    gptConfig := gptbot.GPTBotConfig{
       IDInstance:       idInstance,
       APITokenInstance: authToken,
       OpenAIApiKey:     openaiToken,
       Model:            gptbot.ModelGPT4o,
       MaxHistoryLength: 10,
       SystemMessage:    "You are a helpful WhatsApp assistant.",
    }
    gptHelper := gptbot.NewWhatsappGptBot(gptConfig)
    registry.RegisterGptHelper(gptHelper)

    // Set the start scene and launch the bot
    baseBot.SetStartScene(scenes.StartScene{})
    baseBot.StartReceivingNotifications()
}

This bot uses scenes to organize its code. This means that the chatbot logic is divided into fragments (scenes), the scene corresponds to a certain state of the dialogue and is responsible for processing the response.

Each chat can only have one scene active at a time.

For example, the first scene start.go is responsible for the welcome message. Regardless of the text of the message, the bot asks what language is convenient for the user and includes the following scene, which is responsible for processing the response.

There are 5 scenes in total in the bot:

• Scene start.go - replies to any incoming message, sends a list of available languages. Launches the MainMenu scene.
• Scene mainMenu.go - processes user selection and sends the main menu text in the selected language. Launches the Endpoints scene
• Scene endpoints.go - executes the method selected by the user and sends a description of the method in the selected language.
• Scene createGroup.go - Scene creates a group if the user said he added the bot to his contacts. If not, returns to the "endpoints" scene.
• Scene gptScene.go - Handles GPT conversation mode, processing user messages through OpenAI's API and maintaining conversation context.

The file util.go contains the method IsSessionExpired() which is used to set the start scene again if the bot has not been contacted for more than 2 minutes.

The file ymlReader.go contains the method getString() which returns strings from the strings.xml file by key. This file is used to store the texts of the bot's responses.

A new component is the registry package, which provides a global access point to the GPT bot instance using a registry pattern. This allows any scene to access the GPT functionality without tight coupling.

6. Message handling#

As the chatbot indicates in its responses, all messages are sent via the API. Documentation of the sending methods.

When it comes to receiving messages, they've been handled by HTTP API. Documentation of the methods of receving messages.

The chatbot uses the library whatsapp-chatbot-golang, where methods for sending and receiving messages are already integrated, so messages are read automatically, and sending regular text messages is simplified.

For example, a chatbot automatically sends a message to the contact from whom it received the message:

     message.AnswerWithText(util.GetString([]string{"select_language"}))

     message.GreenAPI.Methods().Service().GetAvatar(chatId)

7. GPT Functionality#

The chatbot integrates with OpenAI's GPT models using the whatsapp-chatgpt-go library. This enables the bot to have intelligent conversations with users.

How it works#

1. Initialization: The GPT bot is initialized in main.go with configuration including the OpenAI API key and system prompt.
2. Registry Pattern: The bot instance is stored in a registry to be accessible from any scene.
3. GPT Scene: A dedicated scene (gptScene.go) handles the GPT conversation mode.
4. Session Management: The GPT scene maintains conversation history using the session data, enabling contextual exchanges.
5. Exit Commands: Users can exit the GPT mode using various commands in different languages.

License#

Licensed under Creative Commons Attribution-NoDerivatives 4.0 International (CC BY-ND 4.0).

LICENSE.