From 2e95683554d88741b9906c0b7ee405c4481bb2a0 Mon Sep 17 00:00:00 2001 From: Sebastian Musial Date: Thu, 20 Jun 2024 11:57:07 +0200 Subject: [PATCH 1/3] feat: deploy to Heroku button --- README.md | 3 +++ app.json | 31 +++++++++++++++++++++++++++++++ 2 files changed, 34 insertions(+) create mode 100644 app.json diff --git a/README.md b/README.md index 7cd51b6..e859d5b 100644 --- a/README.md +++ b/README.md @@ -11,6 +11,9 @@ github

+[![Deploy](https://www.herokucdn.com/deploy/button.svg)](https://heroku.com/deploy?template=https://github.com/boldare/openai-assistant/tree/feat/heroku-deploy-btn) + + # 🤖 AI Assistant 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. diff --git a/app.json b/app.json new file mode 100644 index 0000000..49cd5af --- /dev/null +++ b/app.json @@ -0,0 +1,31 @@ +{ + "name": "Openai Assistant by Boldare", + "description": "A NestJS project for OpenAI Assistant powered by Boldare", + "repository": "https://github.com/boldare/openai-assistant", + "logo": "https://assistant.ai.boldare.dev/assets/ai-assistant.jpg", + "keywords": ["nestjs", "openai", "assistant", "boldare", "ai", "chatbot", "assistant-ai"], + "env": { + "OPENAI_API_KEY": { + "description": "API key for OpenAI. You can generate and find it in the OpenAI dashboard.", + "required": true + }, + "ASSISTANT_ID": { + "description": "Assistant ID has to be defined for Heroku deployment. You can create and find it in the OpenAI dashboard.", + "required": true + }, + "APP_URL": { + "description": "URL of your application - required only if you want to embed the chatbot to the different domains", + "required": false + }, + "OPENWEATHER_API_KEY": { + "description": "API key for OpenWeather - required only if you want to use weather tool", + "required": false + } + }, + "scripts": {}, + "formation": { + "web": { + "quantity": 1 + } + } +} From 551929bff599485d8aea4359c0b7691803df8072 Mon Sep 17 00:00:00 2001 From: Sebastian Musial Date: Fri, 21 Jun 2024 10:28:04 +0200 Subject: [PATCH 2/3] chore: readme update --- README.md | 196 +++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 156 insertions(+), 40 deletions(-) diff --git a/README.md b/README.md index e859d5b..e43ee5f 100644 --- a/README.md +++ b/README.md @@ -1,64 +1,92 @@ -

+

Boldare - -

+

-

- demo 🔹 - api docs 🔹 - npm 🔹 - github -

+ A NestJS library for building efficient, scalable, and fast solutions using the OpenAI Assistant API (chatbots).
Kickstart your AI Assistant development in under 15 minutes 🚀 -[![Deploy](https://www.herokucdn.com/deploy/button.svg)](https://heroku.com/deploy?template=https://github.com/boldare/openai-assistant/tree/feat/heroku-deploy-btn) + demo  + docs  + npm  + docs  + Github + + [![Deploy](https://www.herokucdn.com/deploy/button.svg)](https://heroku.com/deploy?template=https://github.com/boldare/openai-assistant) +
-# 🤖 AI Assistant +# AI Assistant -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. +Introducing the NestJS library. Whether you're building a virtual assistant, or an interactive chatbot for engaging user experiences, our library empowers you to leverage cutting-edge AI capabilities with minimal effort. + +**The library provides ready-to-use API endpoints** handling your assistant and WebSocket server for real-time communication between the client and the assistant. Install the library and paste the config to get it running. + +## 📚 Watch the tutorial + +
+ +[![Watch the tutorial](https://img.youtube.com/vi/rxPdFat90qY/0.jpg)](https://www.youtube.com/watch?v=rxPdFat90qY) +
## 🚀 Features -#### AI Assistant library features +### AI Assistant library features -- **Function calling**: The library provides a way to create functions, which allows you to extend the assistant's capabilities with custom logic. -- **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. -- **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. -- **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**: create functions, so assistant can execute your custom logic! +- **TTS (Text-to-Speech)**: convert text to speech, so you can hear your assistant! +- **STT (Speech-to-Text)**: convert speech to text, so you can make conversation easier! +- **File support**: add files to the assistant, so you can extend assistant's knowledge base with custom data! +- **WebSockets**: establish WebSocket server for real-time communication between the client and the assistant! +- **REST API**: Just use ready REST API for communication with the assistant! +- **Vision with GPT-4o** - use the GPT-4o and make your assistant understand images and generate text based on them! #### 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. +The repository contains a library but also provides additional features. You can just clone the repository and use it instantly to gain from all features: + +- **Embedded chatbot**: embed the chatbot on various websites through JavaScript scripts! +- **Chatbot client application**: use ready 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: Prerequisites + -Install Node.js which includes Node Package Manager (`^20.0.0` version). + +
+Step 0: Prerequisites
-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/). +- Node.js (`^20.0.0` version) +- npm (`^10.0.0` version) +- NestJS (`^10.0.0` version) +- OpenAI (`^4.51.0` version) +- OpenAI API key -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: +Open or create your NestJS application where you would like to integrate the AI Assistant. To create a new NestJS application, use the following command: ```bash nest new project-name ``` -### Step 1: Installation +Now you have to install the packages. Go to the next step. + +
+
+Step 1: Installation
-Install the library using npm: +Make sure you are in the root directory of your project. +Install the library and `openai` package using npm: ```bash npm i @boldare/openai-assistant openai --save ``` -### Step 2: Env variables +The library is installed but we have to configure it. Go to the next step. + +
+
+Step 2: Env variables
Set up your environment variables, create environment variables in the `.env` file in the root directory of the project, and populate it with the necessary secrets. The assistant ID is optional and serves as a unique identifier for your assistant. When the environment variable is not set, the assistant will be created automatically. You can use the assistant ID to connect to an existing assistant, which can be found in the OpenAI platform after creating an assistant. @@ -74,38 +102,126 @@ Add the following content to the `.env` file: # OpenAI API Key OPENAI_API_KEY= -# Assistant ID - leave it empty if you don't have an assistant yet +# Assistant ID - leave it empty if you don't have an assistant to reuse ASSISTANT_ID= ``` -Please note that the `.env` file should not be committed to the repository. Add it to the `.gitignore` file to prevent it from being committed. +Please note that the `.env` file should not be committed to the repository. *Add the `.env` file to the `.gitignore`* file to prevent it from being committed. -### Step 3: Configuration +This was the first step needed to run the library. The next step is to configure the assistant. + +
+
+Step 3: Configuration
The library provides a way to configure the assistant with the `AssistantModule.forRoot` method. The method takes a configuration object as an argument. Create a new configuration file like in a [sample configuration file (chat.config.ts)](apps%2Fapi%2Fsrc%2Fapp%2Fchat%2Fchat.config.ts) and fill it with the necessary configuration. -More details about the configuration with code examples can be found in the [wiki](https://github.com/boldare/openai-assistant/wiki/%F0%9F%A4%96-AI-Assistant#step-3-configuration). +```typescript +// chat.config.ts file +import { AssistantConfigParams } from '@boldare/openai-assistant'; +import { AssistantCreateParams } from 'openai/resources/beta'; + +// Default OpenAI configuration +export const assistantParams: AssistantCreateParams = { + name: 'Your assistant name', + instructions: `You are a chatbot assistant. Speak briefly and clearly.`, + tools: [{ type: 'file_search'}], + model: 'gpt-4-turbo', + temperature: 0.05, +}; + +// Additional configuration for our assistant +export const assistantConfig: AssistantConfigParams = { + id: process.env['ASSISTANT_ID'], + params: assistantParams, + filesDir: './apps/api/src/app/knowledge', + toolResources: { + file_search: { + // Provide files if you use file_search tool + fileNames: ['example1.txt', 'example2.txt'], + }, + }, +}; +``` + + +More details about the configuration can be found in the [wiki](https://github.com/boldare/openai-assistant/wiki/%F0%9F%A4%96-AI-Assistant#step-3-configuration). + +#### What is this step for? +From now you can run your application and call the assistant. + + +
+
+Step 4: Function calling
+Function calling allows you to extend the assistant's capabilities with custom logic. **If you are not going to use function calling you can jump to: [Step 5: Testing](#step-5-running-the-application-and-testing).** -### Step 4: Function calling +Function calling allows you to extend the assistant's capabilities with custom logic. **If you are not going to use function calling you can jump to: [Step 5: Testing](#step-5-running-the-application-and-testing).** Create a new service that extends the `AgentBase` class, fill the definition and implement the `output` method. -- The `output` method is the main method that will be called when the function is invoked. -- The `definition` property is an object that describes the function and its parameters. +- The `output` method is the main method that will be called when the function is invoked by the assistant. +- The `definition` property is an object that describes the function and its parameters so the assistant can understand how to call it. For more information about function calling, you can refer to the [OpenAI documentation](https://platform.openai.com/docs/assistants/tools/defining-functions). The instructions for creating a function can be found in the [wiki](https://github.com/boldare/openai-assistant/wiki/%F0%9F%A4%96-AI-Assistant#step-4-function-calling), while examples can be found in the [agents](apps/api/src/app/chat/agents) directory. ---- +#### What is this step for? -# 👨‍💻 Repository +If you've defined a function and the output method, you can now call it from the assistant just by asking him to do the action described in the function definition. + + +
+
+Step 5: Running the application and testing
+ +Run your application and this will allow you to test the assistant. + + ```bash + # use this if you are using the repository: + npm run start:dev + + # if you are using your own NestJS application, please check the npm scripts in the package.json file + # defualt command for NestJS is: + npm run start + ``` + + Then you can test the assistant. + 1. First, you need to create a thread. You can create one + by sending a POST request to the `/assistant/threads` endpoint with the **empty object in the body**. + 2. Then you can send a message to the assistant by sending a POST request to the `/assistant/chat` endpoint with the following body: + ```json + { + "threadId": "your-thread-id", + "content": "Hello, how are you?" + } + ``` + 3. The assistant will respond with a message. You can send more messages to the assistant by sending a POST request to the `/assistant/chat` endpoint with the same body as in step 2. + + Congrats! You have successfully integrated the AI Assistant library into your NestJS application. 🎉 + +
+ +## 🤔 Are you stuck? The complete documentation on how to run the demo with all applications and libraries from the repository can be found in the [wiki](https://github.com/boldare/openai-assistant/wiki/%F0%9F%91%A8%E2%80%8D%F0%9F%92%BB-Repository). ---- +Boldare's engineers are here to help you. If you have any questions or need help with the implementation, feel free to [book a call](https://calendly.com/olivier-halupczok/30min) with one of our engineers. + +Learn more how **[Boldare can help you with AI development](https://www.boldare.com/services/ai-software-development-consulting/)**. + +You can also ask questions in the [GitHub Discussions](https://github.com/boldare/openai-assistant/discussions) section. + + +## Contributions + +Would you like to see new features in the library? +- You can freely contribute to the project! Just create a pull request with your changes. +- [Talk your idea over with one of our engineers.](https://calendly.com/olivier-halupczok/30min) +- You can also [post your idea here](https://github.com/boldare/openai-assistant/discussions). -# License +## License -`@boldare/openai-assistant` is MIT licensed +`@boldare/openai-assistant` and this repository is MIT licensed From edad8e9e075221bfdf48d3374552ad173b5342a8 Mon Sep 17 00:00:00 2001 From: Sebastian Musial Date: Fri, 21 Jun 2024 13:03:36 +0200 Subject: [PATCH 3/3] chore: readme update - added link under the video --- README.md | 3 +++ 1 file changed, 3 insertions(+) diff --git a/README.md b/README.md index 1f23c62..1c1ec5c 100644 --- a/README.md +++ b/README.md @@ -26,6 +26,9 @@ Introducing the NestJS library. Whether you're building a virtual assistant, or
[![Watch the tutorial](https://img.youtube.com/vi/rxPdFat90qY/0.jpg)](https://www.youtube.com/watch?v=rxPdFat90qY) + +[Video - AI Assistant in 15 min](https://www.youtube.com/watch?v=rxPdFat90qY) +
## 🚀 Features