Agentchat

🚀 Get Started with the Zhiyan Platform

The Zhiyan Platform is a powerful application building tool that enables users to create and manage various types of intelligent agents (Agents). By default, it offers a variety of useful functions:

• 📧 Automatically send emails based on specified recipient information.
• 🌏 Assist in finding valid information and provide clearer understanding.
• 🌥️ Provide current weather and weather forecasts for a given area.
• 📃 Search for top - tier academic paper resources.
• 📦 Track the status of a courier package by the courier company and tracking number.
• 📂 Load and retrieve user - provided documents, supporting formats such as.pdf,.docx,.xlsx,.md, and.txt.

✨ Feature Showcase

Default Function Demonstration

Email Sending

Automatically send emails according to the specified recipient information.

Information Search

Help find valid information and offer a clearer understanding.

Weather Query

Provide the current weather and weather forecasts for a given area.

Paper Retrieval

Search for top - tier academic paper resources.

Courier Tracking

Track the status of a courier package via the courier company and tracking number.

Document Loading and Retrieval

Load and retrieve user - provided documents, supporting multiple formats.

User - Defined Tools

Users can input OpenAI's parameter format as needed and write custom code (currently, the function is relatively basic and will be optimized in the future).

Project Easter Eggs

Loading icons:

🚀 Quick Start Guide

I. Configuration Files

1. Configure LangFuse

Modify the LangFuse API key in the chat/config/langfuse_config.py file. The default connection is to the LangFuse official website. If the connection fails, you can use Docker to deploy LangFuse locally.

2. Configure LLM

Modify the API keys and base URLs of large language models (LLMs) in the chat/config/llm_config.py file. Currently, LLMs that support function - calling features are supported, such as Tongyi Qianwen and OpenAI's GPT - 3.5.

3. Configure MySQL and Redis

Modify the MySQL and Redis addresses in the chat/config/service_config.py file to configure information suitable for your environment.

II. Start the Back - end Service

1. Install Dependencies

Run the following command to install the required dependencies:

pip install -r requirements.txt

2. Start the Back - end

Run the following command to start the back - end service:

python main.py

III. Start the Front - end Interface

1. Enter the Front - end Directory

Navigate to the front - end project folder.

2. Download Dependencies

Run the following command to download the front - end dependencies:

npm i

3. Start the Front - end Service

Run the following command to start the front - end development server:

npm run dev

🐳 Quick Deployment with Docker

Using Docker can simplify the steps of configuring the MySQL database.

1. Enter the Docker Directory

Navigate to the docker folder of the project.

2. Start the Service

Run the following command to build and start the service:

docker-compose up --build

3. Start the Overall Project Service

Start the back - end and front - end services as described above.

4. Restart after Configuration Update

After updating the configuration files, you need to restart the relevant services to apply the changes.

🚧 Future Version Plans

• V1.0: Add a tool store function to support users in custom - uploading tools.
• V2.0: Add an automatic building function, allowing users to build an application through a dialogue - based interaction.