Can we do it on Image?

Is there a limit on the length of the response? I am only getting a response of about 200 words…

can analyze more than 1 file ?

D:\Users\doctore\Documents\GitHub\chatPDF>python3 main.py
Traceback (most recent call last):
File "D:\Users\doctore\Documents\GitHub\chatPDF\main.py", line 17, in
openai.api_key = os.environ["OPENAI_API_KEY"]
File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\os.py", line 680, in getitem
raise KeyError(key) from None
KeyError: 'OPENAI_API_KEY'

I followed all the instrcution but came up this

try to fix but do not work

Hi guys,

I'm trying your stuff right now but got this error. I'm using your hacker manifesto pdf file. Any ideas ?

PS D:\Informatique\chatPDF> python main.py
'clear' n’est pas reconnu en tant que commande interne
ou externe, un programme exécutable ou un fichier de commandes.
📁 Select a file
1. file.pdf

Enter a number, or 0 to exit: 1
👀 Loading...
Traceback (most recent call last):
  File "D:\Informatique\chatPDF\main.py", line 71, in <module>
    ask(file)
  File "D:\Informatique\chatPDF\main.py", line 37, in ask
    PDFReader = download_loader("PDFReader")
  File "C:\Users\Thoma\AppData\Local\Programs\Python\Python310\lib\site-packages\llama_index\readers\download.py", line 125, in download_loader
    library = json.loads(library_raw_content)
  File "C:\Users\Thoma\AppData\Local\Programs\Python\Python310\lib\json\__init__.py", line 346, in loads
    return _default_decoder.decode(s)
  File "C:\Users\Thoma\AppData\Local\Programs\Python\Python310\lib\json\decoder.py", line 340, in decode
    raise JSONDecodeError("Extra data", s, end)
json.decoder.JSONDecodeError: Extra data: line 1 column 4 (char 3)

Traceback (most recent call last):
File "/Users/aquaticdwarf/Downloads/chatPDF-main/main.py", line 99, in
ask(file)
File "/Users/aquaticdwarf/Downloads/chatPDF-main/main.py", line 38, in ask
llm_predictor = LLMPredictor(llm=OpenAI(temperature=0, model_name="text-davinci-003"))
File "pydantic/main.py", line 341, in pydantic.main.BaseModel.init
pydantic.error_wrappers.ValidationError: 1 validation error for OpenAI
root
Did not find openai_api_key, please add an environment variable OPENAI_API_KEY which contains it, or pass openai_api_key as a named parameter. (type=value_error)

openai.api_key = os.environ["API_KEY"] = [REDACTED]

when asked for

"Who is the first president of USA",

it answers as:
"The context information provided does not mention anything about the first president of United States..."

I think there is a tweak to use llm model when the answer is not in the context.

Anyone knows?