If you are a Kouzi VIP, you can directly download the workflow and import it.

https://wwaod.lanzn.com/b011lwl8ij
Password:3qnp

Taking sora2 as an example, a simple circular workflow from inputting text and uploading images to finally obtaining the URL (the following is the overall picture)

Enterprise WeChat screenshot_17677735722402.png

1. Start

Add new input variables based on prompt words and pictures, and according to the parameters required by the interface. If you need to enter more parameters, you can also add them.
Enterprise WeChat screenshot_1767773636845.png

Enterprise WeChat screenshot_1767773636845.png

2. Request model (new http node)

Configure http request according to documentation

Configure the request method and url in the first red box position

The second red box configures the request header

Configure the request body in the third place. Please select the format according to the corresponding request body in the document. In this example, json is used. The parameters marked with the beginning are the parameters obtained from the previous input. You can select it by directly entering {} in the editor.
Enterprise WeChat screenshot_17677740268061.png

Enterprise WeChat screenshot_17677740268061.png

3. Process the request result and obtain taskId (new code node)

As shown in the figure, when inputting, the variable value directly obtains the previous output body.
Use code to parse the body to obtain the id (in this example, the code is JavaScript. The code is as follows)

async function main({ params }: Args): Promise<Output> {
    // 1. Get the body string from params.input
    // Note: This assumes that params.input is the entire HTTP response object
    const bodyStr = params.input;

    // 2. Parse the body in string format into a JSON object
    // Because the value of body is a string "{\"id\":...}", JSON.parse is required
    let taskId = "";
    try {
        const bodyObj = JSON.parse(bodyStr);
        taskId = bodyObj.id;
    } catch (e) {
        // Prevent parsing failure from causing runtime errors
        console.log("JSON parsing failed:", e);
    }

    // 3. Construct the output object and return taskId
    const ret = {
        "taskId": taskId
    };

    return ret;
}

The variable name of the final output position must be consistent with the parameter name in ret in the code.
Enterprise WeChat screenshot_17677742429398.png

Enterprise WeChat screenshot_17677742429398.png

4. Loop request query interface to obtain url (new loop node)

1. Set the loop (in this example, an infinite loop is used to jump out of the loop based on judgment conditions) Set as needed

The intermediate variable is the taskId output by the previous code node.
The url and status are output
Enterprise WeChat screenshot_17677745518897.png

Enterprise WeChat screenshot_17677745518897.png

2. Add an http node request query task in the loop

The parameter request body is based on the query task of the model used in the document.
Enterprise WeChat screenshot_17677753812075.png

3. Add a new code node to obtain the URL and task status

As shown in the figure, the input is the output body code of the query task as follows:

async function main({ params }: Args): Promise<Output> {
    // 1. Get the body string from params.input
    const bodyStr = params.input;

    // 2. Parse the body in string format into a JSON object
    let url = "";
    let status = "";
    try {
        const bodyObj = JSON.parse(bodyStr);
        url = bodyObj.video_url;
        status = bodyObj.status;
    } catch (e) {
        // Prevent parsing failure from causing runtime errors
        console.log("JSON parsing failed:", e);
    }

    // 3. Construct the output object and return taskId
    const ret = {
        "url": url,
        "status": status
    };

    return ret;
}

Enterprise WeChat screenshot_17677755174326.png

4. Add a new judgment node to judge whether the query obtains the url

In this example, the judgment node sets two branches. The first branch is to obtain the url output by the previous code node to judge whether it is empty.
The second branch is to determine whether the status is failure

Enterprise WeChat screenshot_17677757634138.png

5Execute based on the judgment result

Add a new node to terminate the loop. The loop will be terminated when the first judgment of the judgment node is successful or the second judgment is successful.
Add a new timer node and a continuous loop node. When both judgments of the judgment node are negative, the timer is executed first (to prevent the number of concurrent requests from causing request failure. It is recommended to set it to 1500ms). After the timer, the connection continues to loop.

Enterprise WeChat screenshot_17677758794115.png

Process the results obtained from the loop (add a new code node)
Because the result obtained after the loop is an array that needs to be processed to only obtain the final output result (the code is as follows)
The input is the result of the loop output

async function main({ params }: Args): Promise<Output> {

    // Get input
    const urls = params.urls;
    const statuses = params.statuss;

    // 3. Construct the output object and return taskId
    const ret = {
        "url": urls[urls?.length -1],
        "status": statuss[statuss?.length -1]
    };

    return ret;
}

The output is the processed url and status
Enterprise WeChat screenshot_17677761996893.png

6. Determine whether the url has a value to determine whether the video generation is successful or failed.

Enterprise WeChat screenshot_17677764885854.png

7. Final output result

As shown in the figure, output the success and failure results and then end. You can change the output text to a variable according to your own needs, or you can put the output results in the end node for output.
Enterprise WeChat screenshot_17677765862529.png

Enterprise WeChat screenshot_17677765862529.png

Enterprise WeChat screenshot_17677765941365.png

8. Realize the effect

Enterprise WeChat screenshot_17677770925315.png

COZE workflow simple configuration from input to obtaining url

If you are a Kouzi VIP, you can directly download the workflow and import it.#

Taking sora2 as an example, a simple circular workflow from inputting text and uploading images to finally obtaining the URL (the following is the overall picture)#

1. Start#

2. Request model (new http node)#

3. Process the request result and obtain taskId (new code node)#

4. Loop request query interface to obtain url (new loop node)#

1. Set the loop (in this example, an infinite loop is used to jump out of the loop based on judgment conditions) Set as needed#

2. Add an http node request query task in the loop#

3. Add a new code node to obtain the URL and task status#

4. Add a new judgment node to judge whether the query obtains the url#

5Execute based on the judgment result#

6. Determine whether the url has a value to determine whether the video generation is successful or failed.#

7. Final output result#

#

8. Realize the effect#