Update app.py

app.py

@@ -2,12 +2,44 @@ import gradio as gr
 import io
 import PyPDF2
 from langchain.llms import OpenAIChat
-from langchain.chains import ConversationChain
+from langchain.chains import LLMChain
 from langchain.memory import ConversationBufferMemory
-from langchain import LLMChain, PromptTemplate
+from langchain import PromptTemplate
+
+def process_pdf(file_info, open_ai_key):
+    file_content = file_info["content"]
+    extracted_text = extract_text_from_pdf_bytes(file_content)
+
+    # Set the OpenAI API key
+    os.environ['OPENAI_API_KEY'] = open_ai_key
+
+    # Format the resume text to YAML
+    formatted_resume_yaml = format_resume_to_yaml(extracted_text)
+
+    return formatted_resume_yaml
+
+# Assuming you have already defined the template, prompt, memory, and llm_chain as before
+
+def format_resume_to_yaml(resume):
+    """
+    Formats the resume text into a YAML format using the LLMChain.
+    """
+    # Before calling the LLMChain, ensure the OPENAI_API_KEY environment variable is set
+    res = llm_chain.predict(human_input=resume)
+    return res.output  # Assuming the 'predict' method returns an object with an 'output' attribute containing the result
+
+def process_pdf(file_info, open_ai_key):
+    file_content = file_info["content"]  # Extract file content as bytes
+    extracted_text = extract_text_from_pdf_bytes(file_content)
+    
+    # Set the OpenAI API key
+    os.environ['OPENAI_API_KEY'] = open_ai_key
+    
+    # Format the resume text to YAML
+    formatted_resume_yaml = format_resume_to_yaml(extracted_text)
+    
+    return formatted_resume_yaml
 
-# Limited functionality - Replace with your actual OpenAI API Key
-os.environ['OPENAI_API_KEY'] = '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'  # Placeholder, needs replacement
 
 template = """Format the provided resume to this YAML template:
 ---
@@ -21,22 +53,22 @@ emails:
 dateOfBirth: ''
 addresses:
 - street: ''
- city: ''
- state: ''
- zip: ''
- country: ''
+  city: ''
+  state: ''
+  zip: ''
+  country: ''
 summary: ''
 education:
 - school: ''
- degree: ''
- fieldOfStudy: ''
- startDate: ''
- endDate: ''
+  degree: ''
+  fieldOfStudy: ''
+  startDate: ''
+  endDate: ''
 workExperience:
 - company: ''
- position: ''
- startDate: ''
- endDate: ''
+  position: ''
+  startDate: ''
+  endDate: ''
 skills:
 - name: ''
 certifications:
@@ -59,55 +91,39 @@ llm_chain = LLMChain(
     memory=memory,
 )
 
-testing = False  # Set this to True for testing with a fixed PDF
-
-def format_resume_to_yaml(api_key, pdf_file):
-  """
-  This function is limited due to security concerns. It cannot directly accept the  
-  OpenAI API key from the user as input. You'll need to implement server-side  
-  authentication for the API key. 
-  """
-  if pdf_file is None:
-    raise ValueError("No PDF file uploaded!")
-  # Security Risk - Do not accept API key from user input
-  # if api_key != os.environ.get('OPENAI_API_KEY'):
-  #   raise ValueError("Invalid API Key")
-
-  print(f"API Key: {api_key}")  # Log the API Key (for debugging, not for production)
-
-  if testing:
-    # Use a fixed path for testing (replace with your test PDF path)
-    with open("path/to/your/test_resume.pdf", "rb") as f:
-      pdf_file = f
-  else:
-    # Use the uploaded PDF from Gradio
-    pdf_data = pdf_file.read()
-    pdf_data = io.BytesIO(pdf_data)
-
-  reader = PyPDF2.PdfReader(pdf_data)
-  resume_text = ""
-  num_pages = len(reader.pages)
-
-  for page in range(num_pages):
-    current_page = reader.pages[page]
-    page_text = current_page.extract_text()
-    if page_text:
-      resume_text += page_text
-  res = llm_chain.predict(human_input=resume_text)
-  return res
-
-
-# Gradio interface with testing flag
-interface = gr.Interface(
-    fn=format_resume_to_yaml,
-    inputs=[
-        gr.File(label="Upload your resume (PDF)"),
-        # Security Risk - Not recommended to take API key from user input
-        gr.Textbox(label="Enter your OpenAI API Key (not recommended)"),
-    ],
-    outputs="text",
-    title="Resume to YAML Formatter",
-    description="Upload your resume (PDF) and get it formatted in YAML. **Please note: Due to security concerns, entering your OpenAI API Key directly is",
-)
+def format_resume_to_yaml(resume):
+    # Before calling the LLMChain, ensure the OPENAI_API_KEY environment variable is set
+    res = llm_chain.predict(human_input=resume)
+    return res
+
+def process_pdf(file, open_ai_key):
+    # Save the uploaded PDF temporarily
+    temp_pdf_path = "/tmp/uploaded_resume.pdf"
+    with open(temp_pdf_path, 'wb') as f:
+        f.write(file.read())
+    
+    # Extract text from the PDF
+    extracted_text = extract_text_from_pdf(temp_pdf_path)
+    
+    # Set the OpenAI API key
+    os.environ['OPENAI_API_KEY'] = open_ai_key
+    
+    # Format the resume text to YAML
+    formatted_resume_yaml = format_resume_to_yaml(extracted_text)
+    
+    return formatted_resume_yaml
 
-interface.launch(debug=True)
+with gr.Blocks() as demo:
+    gr.Markdown("### Upload a Resume in PDF Format")
+    with gr.Row():
+        pdf_file = gr.File(label="Select a PDF file", type="file")
+        openai_key_input = gr.Textbox(label="OpenAI API Key", type="password")
+        format_button = gr.Button("Format Resume")
+    output_textbox = gr.Textbox(label="Formatted Resume in YAML", lines=20)
+    
+    format_button.click(
+        fn=process_pdf,
+        inputs=[pdf_file, openai_key_input],
+        outputs=[output_textbox]
+    )
+demo.launch(debug=True)