openapi.json 没有上传文件相关的接口,怎么实现api推荐分析文件啊,这样多模态才能调试

[a67793581]

Reminder

• I have read the README and searched the existing issues.

System Info

[WARNING|logging.py:328] 2024-10-30 18:47:58,798 >> Qwen2VLRotaryEmbedding can now be fully parameterized by passing the model config through the config argument. All other arguments will be removed in v4.46
Loading checkpoint shards: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 5/5 [00:04<00:00, 1.10it/s]
[INFO|modeling_utils.py:4574] 2024-10-30 18:48:03,699 >> All model checkpoint weights were used when initializing Qwen2VLForConditionalGeneration.

[INFO|modeling_utils.py:4582] 2024-10-30 18:48:03,700 >> All the weights of Qwen2VLForConditionalGeneration were initialized from the model checkpoint at /root/.cache/openmind/hub/models--LlamaFactory--Qwen2-VL-7B-Instruct/snapshots/8216def47ae85b29db751224d6ec3a3b8f0df3bd.
If your task is similar to the task the model of the checkpoint was trained on, you can already use Qwen2VLForConditionalGeneration for predictions without further training.
[INFO|configuration_utils.py:1052] 2024-10-30 18:48:03,704 >> loading configuration file /root/.cache/openmind/hub/models--LlamaFactory--Qwen2-VL-7B-Instruct/snapshots/8216def47ae85b29db751224d6ec3a3b8f0df3bd/generation_config.json
[INFO|configuration_utils.py:1099] 2024-10-30 18:48:03,704 >> Generate config GenerationConfig {
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.01,
"top_k": 1,
"top_p": 0.001
}

10/30/2024 18:48:03 - INFO - llamafactory.model.model_utils.attention - Using torch SDPA for faster training and inference.
10/30/2024 18:48:04 - INFO - llamafactory.model.adapter - Merged 1 adapter(s).
10/30/2024 18:48:04 - INFO - llamafactory.model.adapter - Loaded adapter(s): saves/Qwen2-VL-7B-Instruct/lora/v7
10/30/2024 18:48:04 - INFO - llamafactory.model.loader - all params: 8,291,375,616
Visit http://localhost:6006/docs for API document.
INFO: Started server process [8214]
INFO: Waiting for application startup.
INFO: Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:6006 (Press CTRL+C to quit)
INFO: 127.0.0.1:36178 - "POST /v1/files HTTP/1.1" 404 Not Found

Reproduction

    with open("/root/autodl-tmp/LLaMA-Factory/data/carlo_data/Black/110011-PH-Black-076.jpg", "rb") as file:
        file_response = client.files.create(
            file=file,
            purpose="assistants"  # 设置文件用途
        )
        file_id = file_response['id']
        messages.append({
            "content": f"{file_id}",
            "role": "user"
        })
    result = client.chat.completions.create(
        messages=messages,
        model="test",
        temperature=0.1,
        response_format={
            "type": "json_object"
        })
    print(result)

Expected behavior

No response

Others

No response

[GasolSun36]

+1, 还想问下用python的话如何定义post的url，文档里只给出了curl模式用的url，而python没有。
https://platform.openai.com/docs/api-reference/chat/create?lang=python