Qwen Chat Prompt and Response

The Qwen Chat Prompt Example Flow demonstrates how to interact with the Qwen Chat API to send prompts and retrieve AI-generated responses. This flow covers the entire process from sending user-defined prompts to receiving, formatting, and storing the responses as structured records. It includes robust error handling and testing capabilities, making it an ideal starting point for integrating AI-driven chat functionality into your applications.

You can find this template in the Services Catalog under these categories:

• AI, Contextual Basics

---

What's Included:

1. 1 Flow: Pre-configured for prompt-response interactions with Qwen Chat.

2. 1 Object Type: To store structured prompt-response records.

3. 1 Connection Template: For integrating with the Qwen Chat API.

---

What You'll Need:

• Access to the Qwen Chat API.

• API Key or credentials for authentication.

• Sample prompts or use cases for testing.

---

Ideas for Using the Qwen Chat Prompt Flow:

1. Conversational AI: Automate chat-based interactions for virtual assistants or customer support bots.

2. Content Creation: Generate creative content or responses based on tailored prompts.

3. Decision Support: Process complex queries to retrieve insights for decision-making.

4. Education: Leverage AI-generated explanations for teaching or self-learning purposes.

---

Flow Overview

Flow Start

• Node: contextual-start

• Purpose: Triggers the flow, initiated by an external event, agent, or the Inject node for testing.

---

In-Editor Testing

• Nodes: Test Prompt, Prepare Prompt

• Purpose: Enables in-editor testing with a sample prompt. Modify the provided sample prompt, such as "How many 'r's are in Strawberry?" to explore different interactions with the Qwen Chat API.

Code Example: Prepare Prompt Function

msg.payload = {
    model: "qwen-max-2025-01-25", // Specify model here
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: msg.payload.prompt }
    ]
};
return msg;

---

Send Prompt and Receive Response

• Nodes: Prompt Qwen Chat, Qwen Chat Response

• Purpose: Sends the prepared payload to the Qwen Chat API. Logs the response for review and passes it for further processing.

Code Example: Response Logging

msg.payload.response = {
    aiResponse: msg.payload.response.choices[0].message.content
};
return msg;

---

Format Response & Create Record

• Nodes: Prepare Record Data, Create AI Response Record

• Purpose: Formats the API response and creates a structured record containing the original prompt and the AI-generated response.

Code Example: Prepare Record Data

let body = {
    prompt: msg.payload.messages[1].content,
    aiResponse: msg.payload.response.choices[0].message.content
};
msg.payload = body;
return msg;

---

Error Handling

• Nodes: catch, Error Catch Log, contextual-error

• Purpose: Captures and logs any errors during the flow execution, ensuring efficient debugging and troubleshooting.

---

Flow End

• Node: contextual-end

• Purpose: Concludes the flow after records are successfully created or errors are logged.

---

Summary of Flow Steps:

1. Start: Trigger the flow manually or externally.

2. Data Preparation: Format the prompt for API interaction.

3. API Interaction: Submit the prompt and process the AI response.

4. Record Creation: Structure and store the prompt-response data.

5. Error Handling: Log and manage any issues that arise.

6. Completion: Conclude the flow.

---

Key Features:

• Flexibility: Easily adaptable to various use cases.

• Scalability: Integrates seamlessly into broader workflows.

• Customization: Modify prompts, response handling, and storage as needed.

This flow serves as a robust template for leveraging AI-powered chat functionality, providing clear examples and extensibility for diverse applications.