+ 
+
+
-
+
+
+
+ + NPM
@@ -8,6 +14,24 @@ Introducing the NestJS library, designed to harness the power of OpenAI's Assistant, enabling developers to create highly efficient, scalable, and rapid AI assistants and chatbots. This library is tailored for seamless integration into the NestJS ecosystem, offering an intuitive API, WebSockets, and tools that streamline the development of AI-driven interactions. Whether you're building a customer service bot, a virtual assistant, or an interactive chatbot for engaging user experiences, our library empowers you to leverage cutting-edge AI capabilities with minimal effort. +## 🚀 Features + +#### AI Assistant library features +- **WebSockets**: The library provides a WebSocket server for real-time communication between the client and the assistant. +- **REST API**: The library provides a REST API for communication with the assistant. +- **Function calling**: The library provides a way to create functions, which allows you to extend the assistant's capabilities with custom logic. +- **File support**: The library provides a way to add files to the assistant, which allows you to extend the assistant's knowledge base with custom data. +- **TTS (Text-to-Speech)**: The library provides a way to convert text to speech, which allows you to create voice-based interactions with the assistant. +- **STT (Speech-to-Text)**: The library provides a way to convert speech to text, which allows you to create voice-based interactions with the assistant. + +#### Additional features in the repository +- **Embedded chatbot**: The library provides a way to embed the chatbot on various websites through JavaScript scripts. +- **Chatbot client application**: The repository includes an example client application (SPA) with a chatbot. + +## Getting started + +In this section, you will learn how to integrate the AI Assistant library into your NestJS application. The following steps will guide you through the process of setting up the library and creating simple functionalities. + ### Step 0: Prerequiring Before you start, you will need to have an account on the OpenAI platform and an API key. You can create an account [here](https://platform.openai.com/). @@ -15,7 +39,7 @@ Before you start, you will need to have an account on the OpenAI platform and an Open or create your NestJS application where you would like to integrate the AI Assistant. If you don't have a NestJS application yet, you can create one using the following command: ```bash -$ nest new project-name +nest new project-name ``` ### Step 1: Installation @@ -23,7 +47,7 @@ $ nest new project-name Install the library using npm: ```bash -$ npm i @boldare/ai-assistant --save +npm i @boldare/ai-assistant --save ``` ### Step 2: Env variables @@ -33,7 +57,7 @@ Set up your environment variables, create environment variables in the `.env` fi Create a `.env` file in the root directory of your project and populate it with the necessary secrets: ```bash -$ touch .env +touch .env ``` Add the following content to the `.env` file: @@ -84,6 +108,18 @@ Import the AI Assistant module with your configuration into the module file wher export class ChatbotModule {} ``` +Automatically, the library will add WebSockets ([chat.gateway.ts](libs/ai-assistant/src/lib/chat/chat.gateway.ts)) and a [REST API](https://assistant.ai.boldare.dev/api/docs) for the assistant. The WebSocket server will be available at the `/` endpoint, and the [REST API](https://assistant.ai.boldare.dev/api/docs) will be available at the `/api` endpoint (depending on the API prefix). + +#### Websockets events + +Currently, the library provides the following WebSocket events: + +| Event name | Description | +|--------------------|----------------------------------------------------------| +| `send_message` | The event is emitted when the user sends a message. | +| `message_received` | The event is emitted when the assistant sends a message. | + + ### Step 4: Function calling Create a new service that extends the `AgentBase` class, fill the definition and implement the `output` method. @@ -124,6 +160,8 @@ export class GetNicknameAgent extends AgentBase { } ``` +More examples can be found in the [agents](apps/api/src/app/chat/agents) directory. + Import the service into the module file where you intend to use it: ```js @@ -168,7 +206,7 @@ The repository includes a library with an AI assistant as well as other useful p ### Step 1: Install dependencies ```bash -$ npm install +npm install ``` ### Step 2: Env variables @@ -176,28 +214,32 @@ $ npm install Set up your environment variables, copy the `.env.dist` file to `.env` file in the root directory of the project, and populate it with the necessary secrets. ```bash -$ cp .env.dist .env +cp .env.dist .env ``` ### Step 3: Run applications ```bash # Start the app (api and spa) -$ npm run start:dev +npm run start:dev # Start the api -$ npm run start:api +npm run start:api # Start the spa -$ npm run start:spa +npm run start:spa ``` Now you can open your browser and navigate to: -| URL | Description | -| ------------------------------ | --------------------------- | -| http://localhost:4200/ | Client application (SPA) | -| http://localhost:3000/api/ | API application | -| http://localhost:3000/api/docs | API documentation (swagger) | +| URL | Description | +|--------------------------------|-----------------------------------------| +| http://localhost:4200/ | Client application (Angular) | +| http://localhost:3000/ | API application, WebSockets (socket.io) | +| http://localhost:3000/api/ | API endpoints | +| http://localhost:3000/api/docs | API documentation (swagger) | ### 🎉 Happy coding 🎉 + +# License +`@boldare/ai-assistant` is MIT licensed diff --git a/apps/api/src/app/chat/chat.module.ts b/apps/api/src/app/chat/chat.module.ts index 89d637f..512a1d7 100644 --- a/apps/api/src/app/chat/chat.module.ts +++ b/apps/api/src/app/chat/chat.module.ts @@ -4,6 +4,6 @@ import { assistantConfig } from './chat.config'; import { AgentsModule } from './agents/agents.module'; @Module({ - imports: [AssistantModule.forRoot(assistantConfig), AgentsModule], + imports: [AgentsModule, AssistantModule.forRoot(assistantConfig)], }) export class ChatModule {} diff --git a/apps/spa/src/app/modules/+chat/shared/chat.service.ts b/apps/spa/src/app/modules/+chat/shared/chat.service.ts index 1c72ec4..24a6ea4 100644 --- a/apps/spa/src/app/modules/+chat/shared/chat.service.ts +++ b/apps/spa/src/app/modules/+chat/shared/chat.service.ts @@ -46,7 +46,7 @@ export class ChatService { } isTextMessage(message: ThreadMessage): boolean { - return message.content[0].type === 'text'; + return message.content?.[0]?.type === 'text'; } parseMessages(thread: GetThreadResponseDto): Message[] { diff --git a/apps/spa/src/assets/boldare-circle.png b/apps/spa/src/assets/boldare-circle.png new file mode 100644 index 0000000..2f57dd7 Binary files /dev/null and b/apps/spa/src/assets/boldare-circle.png differ diff --git a/apps/spa/src/environments/environment.ts b/apps/spa/src/environments/environment.ts index ed9b6f9..2b7ccc3 100644 --- a/apps/spa/src/environments/environment.ts +++ b/apps/spa/src/environments/environment.ts @@ -1,8 +1,8 @@ export const environment = { env: 'prod', - appUrl: 'https://ai-assistant-c8b469d88808.herokuapp.com', - apiUrl: 'https://ai-assistant-c8b469d88808.herokuapp.com/api', - websocketUrl: 'https://ai-assistant-c8b469d88808.herokuapp.com', + appUrl: 'https://assistant.ai.boldare.dev', + apiUrl: 'https://assistant.ai.boldare.dev/api', + websocketUrl: 'https://assistant.ai.boldare.dev', isThreadMemorized: true, isAudioEnabled: true, isTranscriptionEnabled: true, diff --git a/libs/ai-embedded/src/environments/environment.prod.ts b/libs/ai-embedded/src/environments/environment.prod.ts index 2c41b8f..0cfe45b 100644 --- a/libs/ai-embedded/src/environments/environment.prod.ts +++ b/libs/ai-embedded/src/environments/environment.prod.ts @@ -1,4 +1,4 @@ export const environment = { env: 'prod', - appUrl: 'https://ai-assistant-c8b469d88808.herokuapp.com', + appUrl: 'https://assistant.ai.boldare.dev', };