Awesome
WhatsApp AI Assistant
Welcome to the WhatsApp AI Assistant repository, where you'll find a remarkable WhatsApp chatbot designed to function as your very own AI-powered personal assistant. This chatbot leverages the power of Language Model (LLM) technology.
Sydney | LangChain |
---|---|
<video src="https://github.com/WAppAI/assistant/assets/50471205/5d300910-099d-4ceb-9f87-0852389a4c5b"> | <video src="https://github.com/WAppAI/assistant/assets/50471205/e8e8aabe-9ef7-4e3e-b0dc-156071c425f8"> |
Feature Comparison
Feature | Sydney (BingAI Jailbreak) | LangChain |
---|---|---|
Google/Bing Searching | ✅ | ✅ |
Google Calendar | ❌ | ✅ |
Google Routes | ❌ | ✅ |
Gmail | ❌ | ❌ |
Communication Capability | ✅ | ✅ |
Group Chat Compatibility | ✅ | ✅ |
Voice Message Capability | ✅ | ✅ |
Create Basic Text Reminders | ✅ | ✅ |
Image Recognition | ✅ | ❌ |
Image Generation | ❌ | ✅ |
PDF Reading | ❌ | ❌ |
Getting Started
Prerequisites
- Node.js >= 18.15.0
- A spare WhatsApp number
Installation
<details> <summary><b>Sydney/BingChat</b></summary> <br>- Clone this repository
git clone https://github.com/WAppAI/assistant.git
- Install the dependencies
pnpm install
- Rename
.env.example
to.env
cp .env.example .env
-
Login with your Bing account and edit
.env
'sBING_COOKIES
environment variable to the cookies string from bing.com. For detailed instructions here.NOTE: Occasionally, you might encounter an error stating,
User needs to solve CAPTCHA to continue.
To resolve this issue, please solve the captcha [here]https://www.bing.com/turing/captcha/challenge, while logged in with the same account associated with your BING_COOKIES. -
Read and fill in the remaining information in the
.env
file. -
Run
pnpm build
- Start the bot
pnpm start
-
Connect your WhatsApp account to the bot by scanning the generated QR Code in the CLI.
-
Send a message to your WhatsApp account to start a conversation with Sydney!
- Clone this repository
git clone https://github.com/WAppAI/assistant.git
- Install the dependencies
pnpm install
- Rename
.env.example
to.env
cp .env.example .env
-
Read and fill in the remaining information in the
.env
file. -
Instructions on how to use langchain tools like Google Calendar and search will be in the
.env
-
Run
pnpm build
- Start the bot
pnpm start
-
Connect your WhatsApp account to the bot by scanning the generated QR Code in the CLI.
-
Send a message to your WhatsApp account to start a conversation with the bot!
- Clone this repository
git clone https://github.com/WAppAI/assistant.git
- Rename
.env.example
to.env
cp .env.example .env
-
Read and fill in the remaining information in the
.env
file. -
Instructions on how to use langchain tools like Google Calendar and search will be in the
.env
-
Build and start the Docker container
pnpm docker:build:start
- Access the container logs to read the QR code.
docker logs whatsapp-assistant
-
Scan the QR code with your WhatsApp account to connect the bot.
-
Send a message to your WhatsApp account to start a conversation with the bot!
Usage
The AI's are designed to respond to natural language queries from users. You can ask them questions, or just have a casual conversation.
Voice Messages
When dealing with voice messages, you have 3 options for transcription: using groq's Whisper API for free (recommended), utilizing the Whisper API or the local method. Each option has its own considerations, including cost and performance.
<details> <summary><strong>Groq API:</strong></summary>- Setup:
- Obtain a Groq API key from Groq Console.
- In the
.env
file, setTRANSCRIPTION_ENABLED
to"true"
andTRANSCRIPTION_METHOD
to"whisper-groq"
.
- Cost: Utilizing the Whisper API incurs a cost of US$0.06 per 10 minutes of audio.
- Setup:
- Obtain an OpenAI API key and place it in the
.env
file under theOPENAI_API_KEY
variable. - In the
.env
file, setTRANSCRIPTION_ENABLED
to"true"
andTRANSCRIPTION_METHOD
to"whisper-api"
.
- Obtain an OpenAI API key and place it in the
- Cost: The local method is free but may be slower and less precise.
- Setup:
- Download a model of your choice from here. Download any
.bin
file and place it in the./whisper/models
folder. - Modify the
.env
file by changingTRANSCRIPTION_ENABLED
to"true"
,TRANSCRIPTION_METHOD
to"local"
, and"TRANSCRIPTION_MODEL"
with the name of the model you downloaded. While setting a language inTRANSCRIPTION_LANGUAGE
is not mandatory, it is recommended for better performance.
- Download a model of your choice from here. Download any
Group Chat
To utilize it in a group chat, you will need to either mention it by using her username with the "@" symbol (e.g., @Sydney) or reply directly to her last message.
Available commands
!help
: Displays a message listing all available commands.!help
followed by a specific command, e.g.,!help reset
: Provides detailed information about the selected command.- If you wish to customize the command prefix, you can do so in the
.env
file to better suit your preferences.
Contribute
Your contributions to Sydney are welcome in any form. Whether you'd like to:
-
Report Issues: If you come across bugs or have ideas for new features, please open an issue to discuss and track these items.
-
Submit Pull Requests (PRs): Feel free to contribute directly by opening pull requests. Your contributions are greatly appreciated and help improve Sydney.
-
If you want us to add a feature open an issue asking for it.
-
In the Projects tab, you'll find a Kanban board that outlines our current objectives and progress.
Your involvement is valued, and you're encouraged to contribute in the way that suits you best.
Hire Us
I, Luisotee am currently open to new job opportunities, including freelance work, contract roles, or permanent positions.
If you have any opportunities, feel free to contact me via the emails provided on my GitHub or LinkedIn profiles.