search

openai / chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.
MIT License
21.07k stars 3.68k forks source link

/upsert-file endpoint returns 500 internal server error with "Unsupported file type" or "Unsupported file type: application/octet-stream" #129

Open AcVoyager opened 1 year ago

AcVoyager commented 1 year ago

Hi,

I was trying different ways to send requests to /upsert-file api endpoint, but I keep getting 500 errors like Unsupported file type or Unsupported file type: application/octet-stream. I am not sure if there is something wrong with my way of initializing the request. I tried to search for the reasons but currently there are not much information about this project on the Internet.

The following C# snippet results in a "Unsupported file type":

var fileName = Path.GetFileName(filePath);
var content = new MultipartFormDataContent();
var stream = new FileStream(filePath, FileMode.Open);
content.Add(new StreamContent(stream), "file", fileName);
var res = await client.PostAsync(requestUrl, content);

Error:

INFO:     127.0.0.1:54034 - "POST /upsert-file HTTP/1.1" 500 Internal Server Error
ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 407, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 78, in __call__
    return await self.app(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/applications.py", line 271, in __call__
    await super().__call__(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/applications.py", line 118, in __call__
    await self.middleware_stack(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 184, in __call__
    raise exc
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 162, in __call__
    await self.app(scope, receive, _send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
    raise exc
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
    await self.app(scope, receive, sender)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 21, in __call__
    raise e
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
    await self.app(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/routing.py", line 706, in __call__
    await route.handle(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/routing.py", line 276, in handle
    await self.app(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/routing.py", line 66, in app
    response = await func(request)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/routing.py", line 237, in app
    raw_response = await run_endpoint_function(
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/routing.py", line 163, in run_endpoint_function
    return await dependant.call(**values)
  File "chatgpt-retrieval-plugin/server/main.py", line 63, in upsert_file
    document = await get_document_from_file(file, metadata_obj)
  File "chatgpt-retrieval-plugin/services/file.py", line 17, in get_document_from_file
    extracted_text = await extract_text_from_form_file(file)
  File "chatgpt-retrieval-plugin/services/file.py", line 112, in extract_text_from_form_file
    raise e
  File "chatgpt-retrieval-plugin/services/file.py", line 108, in extract_text_from_form_file
    extracted_text = extract_text_from_filepath(temp_file_path, mimetype)
  File "chatgpt-retrieval-plugin/services/file.py", line 36, in extract_text_from_filepath
    raise Exception("Unsupported file type")
Exception: Unsupported file type

And the following command results in a "Unsupported file type: application/octet-stream":

curl --location 'localhost:8000/upsert-file' \
--header 'Authorization: Bearer <My Bearer Token>' \
--form 'file=@"<File Path>.md"'

Error:

ERROR:    Exception in ASGI application
Traceback (most recent call last):
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 407, in run_asgi
    result = await app(  # type: ignore[func-returns-value]
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 78, in __call__
    return await self.app(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/applications.py", line 271, in __call__
    await super().__call__(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/applications.py", line 118, in __call__
    await self.middleware_stack(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 184, in __call__
    raise exc
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/errors.py", line 162, in __call__
    await self.app(scope, receive, _send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 79, in __call__
    raise exc
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 68, in __call__
    await self.app(scope, receive, sender)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 21, in __call__
    raise e
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 18, in __call__
    await self.app(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/routing.py", line 706, in __call__
    await route.handle(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/routing.py", line 276, in handle
    await self.app(scope, receive, send)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/starlette/routing.py", line 66, in app
    response = await func(request)
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/routing.py", line 237, in app
    raw_response = await run_endpoint_function(
  File "chatgpt-retrieval-plugin/.venv/lib/python3.10/site-packages/fastapi/routing.py", line 163, in run_endpoint_function
    return await dependant.call(**values)
  File "chatgpt-retrieval-plugin/server/main.py", line 63, in upsert_file
    document = await get_document_from_file(file, metadata_obj)
  File "chatgpt-retrieval-plugin/services/file.py", line 17, in get_document_from_file
    extracted_text = await extract_text_from_form_file(file)
  File "chatgpt-retrieval-plugin/services/file.py", line 112, in extract_text_from_form_file
    raise e
  File "chatgpt-retrieval-plugin/services/file.py", line 108, in extract_text_from_form_file
    extracted_text = extract_text_from_filepath(temp_file_path, mimetype)
  File "chatgpt-retrieval-plugin/services/file.py", line 43, in extract_text_from_filepath
    raise e
  File "chatgpt-retrieval-plugin/services/file.py", line 40, in extract_text_from_filepath
    extracted_text = extract_text_from_file(file, mimetype)
  File "chatgpt-retrieval-plugin/services/file.py", line 85, in extract_text_from_file
    raise ValueError("Unsupported file type: {}".format(mimetype))
ValueError: Unsupported file type: application/octet-stream

Let me know if more related details are needed to provide.

AcVoyager commented 1 year ago

I have seen some similar issues, like #153 and #159