app.py

import gradio as gr
from langchain.document_loaders import PyPDFLoader
from langchain.llms import OpenAIChat
from langchain.chains import LLMChain
from langchain.memory import ConversationBufferMemory
from langchain import PromptTemplate
import os
import tempfile

# Updated imports for Gradio components
from gradio.components import File, Textbox


def format_resume_to_yaml(api_key, file):
    # Set the API key for OpenAI
    os.environ['OPENAI_API_KEY'] = api_key

    file_content = file.read()

    # Check if the file content is not empty
    if not file_content:
        raise ValueError("The uploaded file is empty.")

    # Save the uploaded file content to a temporary file
    with tempfile.NamedTemporaryFile(delete=False, mode='wb+') as tmp_file:
        tmp_file.write(file_content)
        tmp_file.flush()
        os.fsync(tmp_file.fileno())  # Ensure data is written to disk
        temp_file_path = tmp_file.name

    # Now we can use PyPDFLoader with the path to the temporary file
    try:
        loader = PyPDFLoader(temp_file_path)
        docs = loader.load_and_split()  # This will return a list of text chunks from the PDF
    except (IOError, PyPDF2.errors.PdfReaderError) as e:  # Handle potential PDF reading errors
        raise ValueError(f"An error occurred while processing the PDF: {e}")

    # Combine the text chunks into a single string
    resume_text = " ".join(docs)

    template = """Format the provided resume to this YAML template:
    ---
    name: ''
    phoneNumbers:
    - ''
    websites:
    - ''
    emails:
    - ''
    dateOfBirth: ''
    addresses:
    - street: ''
      city: ''
      state: ''
      zip: ''
      country: ''
    summary: ''
    education:
    - school: ''
      degree: ''
      fieldOfStudy: ''
      startDate: ''
      endDate: ''
    workExperience:
    - company: ''
      position: ''
      startDate: ''
      endDate: ''
    skills:
    - name: ''
    certifications:
    - name: ''

    {chat_history}
    {human_input}"""

    prompt = PromptTemplate(
        input_variables=["chat_history", "human_input"],
        template=template
    )

    memory = ConversationBufferMemory(memory_key="chat_history")

    llm_chain = LLMChain(
        llm=OpenAIChat(model="gpt-3.5-turbo"),
        prompt=prompt,
        verbose=True,
        memory=memory,
    )

    res = llm_chain.predict(human_input=resume_text)
    return res['output_text']

def on_file_upload(filename, file_content):
    if not file_content:
        gr.Interface.alert(title="Error", message="Please upload a valid PDF resume.")

def main():
    input_api_key = Textbox(label="Enter your OpenAI API Key")
    # Use 'binary' type to receive the file's content directly as a binary object
    input_pdf_file = File(label="Upload your PDF resume", type="binary")
    output_yaml = Textbox(label="Formatted Resume in YAML")

    iface = gr.Interface(
        fn=format_resume_to_yaml,
        inputs=[input_api_key, input_pdf_file],
        outputs=output_yaml,
        title="Resume to YAML Formatter",
        description="Upload a PDF resume and enter your OpenAI API key to get it formatted to a YAML template.",
    )

    iface.launch(debug=True)

if __name__ == "__main__":
    main()