不知道哪里的问题 点击转换几秒就报错 PDF只有一页

[leesound]

To create a public link, set share=True in launch(). Files before translation: ['compressed-200.pdf', 'Mark Levine - The Jazz Piano Book-3-10.pdf'] {'files': ['pdf2zh_files\compressed-200.pdf'], 'pages': None, 'lang_in': 'en', 'lang_out': 'zh', 'service': 'google', 'output': WindowsPath('pdf2zh_files'), 'thread': 4, 'callback': <function translate_file..progress_bar at 0x00000234858AD9D0>} 100%|████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:02<00:00, 2.81s/it] Traceback (most recent call last): File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\queueing.py", line 536, in process_events response = await route_utils.call_process_api( File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\route_utils.py", line 322, in call_process_api output = await app.get_blocks().process_api( File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\blocks.py", line 1935, in process_api result = await self.call_function( File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\blocks.py", line 1520, in call_function prediction = await anyio.to_thread.run_sync( # type: ignore File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\anyio\to_thread.py", line 56, in run_sync return await get_async_backend().run_sync_in_worker_thread( File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\anyio_backends_asyncio.py", line 2505, in run_sync_in_worker_thread return await future File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\anyio_backends_asyncio.py", line 1005, in run result = context.run(func, *args) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\gradio\utils.py", line 826, in wrapper response = f(*args, **kwargs) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\gui.py", line 165, in translate_file translate(**param) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\high_level.py", line 278, in translate s_mono, s_dual = translate_stream(s_raw, **locals()) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\high_level.py", line 213, in translate_stream obj_patch: dict = translate_patch(fp, **locals()) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\high_level.py", line 148, in translate_patch interpreter.process_page(page) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\pdfinterp.py", line 266, in process_page ops_new = self.device.end_page(page) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\converter.py", line 56, in end_page return self.receive_layout(self.cur_item) File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\converter.py", line 224, in receive_layout or vflag(child.fontname, child.get_text()) # 3. 公式字体 File "C:\Users\ASUS\AppData\Local\Programs\Python\Python39\lib\site-packages\pdf2zh\converter.py", line 175, in vflag font = font.decode() UnicodeDecodeError: 'utf-8' codec can't decode byte 0xcb in position 0: invalid continuation byte

[QuentinFuxa]

Thank you for reporting this issue.

It seems likely that the problem lies in the version of the OpenAI Python library you have installed. I tested a similar setup using the following versions: • Python: 3.12.6 • langchain-openai: 0.2.14 • openai: 1.58.1

Here’s the code I used for testing:

from langchain_openai import ChatOpenAI

chat_model = ChatOpenAI(
    model_name="gpt-4o",
    max_completion_tokens=10,
    openai_api_key="your_key"
)

response = chat_model.invoke("Hello, how are you?")
print(response)

The call to the OpenAI client is done here in the LangChain codebase: https://github.com/langchain-ai/langchain/blob/ccf69368b424acf65644a9ed0a1fb9058a5e2a8d/libs/partners/openai/langchain_openai/chat_models/base.py#L717

In this test, the payload being sent to OpenAI contained:

{
    "messages": [...],
    "model": "gpt-4o",
    "stream": False,
    "n": 1,
    "temperature": 0.7,
    "max_completion_tokens": 10
}

This payload worked correctly without any errors.

Could you double-check the version of the OpenAI Python library in your environment? Specifically, ensure you are using openai==1.58.1. If you confirm that you’re using the correct version and the issue persists, please share additional details about your setup or any modifications you might have made to the code. Maybe the OpenAI lib uses different parameters depending on the model you use?

[dosubot[bot]]

Hi, @Armasse. I'm Dosu, and I'm helping the LangChain team manage their backlog. I'm marking this issue as stale.

Issue Summary:

• You reported a bug with the max_completion_tokens parameter in the ChatOpenAI() function.
• QuentinFuxa suggested the issue might be related to the OpenAI Python library version.
• QuentinFuxa tested with specific versions and found no errors, recommending openai version 1.58.1.

Next Steps:

• Please confirm if this issue is still relevant with the latest LangChain version. If so, feel free to comment to keep the discussion open.
• If there are no updates, this issue will be automatically closed in 7 days.

Thank you for your understanding and contribution!