Use ChatGPT 4o from API call? #131

Closed
opened 2026-02-16 00:16:57 -05:00 by yindo · 2 comments
Owner

Originally created by @rickymerchant on GitHub (Jun 5, 2024).

When previewing LlamaParse, I get the correct output when I select the GPT 4o mode, so I want to use that when calling the Llama_parse API, but it seems there are no options to use this mode when using the standalone API?

Originally created by @rickymerchant on GitHub (Jun 5, 2024). When previewing LlamaParse, I get the correct output when I select the GPT 4o mode, so I want to use that when calling the Llama_parse API, but it seems there are no options to use this mode when using the standalone API?
yindo closed this issue 2026-02-16 00:16:57 -05:00
Author
Owner

@maxqper commented on GitHub (Jun 8, 2024):

Use gpt4o_mode : true.

// sample javascript

    const formData = new FormData();
    formData.append('file', pdfFile);
    if (config.gpt4o_mode) {
      formData.append('gpt4o_mode', 'true');
    }
    const response = await fetch(`${baseUrl}/upload`, {
      method: 'POST',
      headers,
      body: formData
    });
@maxqper commented on GitHub (Jun 8, 2024): Use `gpt4o_mode : true`. // sample javascript ``` const formData = new FormData(); formData.append('file', pdfFile); if (config.gpt4o_mode) { formData.append('gpt4o_mode', 'true'); } const response = await fetch(`${baseUrl}/upload`, { method: 'POST', headers, body: formData }); ```
Author
Owner

@BinaryBrain commented on GitHub (Sep 6, 2024):

We change the codebase for this feature. Please refer to the doc https://docs.cloud.llamaindex.ai/llamaparse/features/multimodal and reopen a ticket if you still encounter the issue.

@BinaryBrain commented on GitHub (Sep 6, 2024): We change the codebase for this feature. Please refer to the doc https://docs.cloud.llamaindex.ai/llamaparse/features/multimodal and reopen a ticket if you still encounter the issue.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: run-llama/llama_cloud_services#131