How can I specify a JSON schema for responses when using langchain-go's structured JSON mode?

I'm using the openai-go API library where I can set the structured JSON response mode in ChatCompletionParams by passing a JSONSchema as a parameter in the ResponseFormat field. For example:

GOCopied
params := openai.ChatCompletionNewParams{
        //Model: openai.F(openai.ChatModelGPT4o),
        Model: openai.F(openai.ChatModelGPT4oMini),
        Messages: openai.F([]openai.ChatCompletionMessageParamUnion{
            openai.UserMessage(message),
        }),
        MaxTokens:   openai.Int(200),
        Temperature: openai.Float(0.7),
        ResponseFormat: openai.F[openai.ChatCompletionNewParamsResponseFormatUnion](
            openai.ResponseFormatJSONSchemaParam{
                Type:       openai.F(openai.ResponseFormatJSONSchemaTypeJSONSchema),
                JSONSchema: openai.F(schemaParam),
            },
        ),
    }

However, when using langchain-go, I can only enable structured JSON mode with the available helper:

GOCopied
llm, err := openai.New()
if err != nil {
    return "ERROR:", err
}
completion, err := llms.GenerateFromSinglePrompt(
    ctx,
    llm,
    "Give list of cat names and return results in valid JSON format",
    llms.WithJSONMode(),
    llms.WithTemperature(0.0),
)

How can I specify the JSON return schema (similar to the openai-go approach) when using langchain-go?

Any suggestions or workarounds (like prompt engineering or custom parsing) would be appreciated.