Update app.py

app.py

@@ -2,16 +2,11 @@ import gradio as gr
 import os
 import io
 import PyPDF2
-#from langchain.llms import OpenAIChat
 from langchain_openai import ChatOpenAI
-
 from langchain.chains import LLMChain
 from langchain.memory import ConversationBufferMemory
 from langchain import PromptTemplate
-
-
-# Updated imports for Gradio components
-from gradio.components import File, Textbox
+from gradio.components import File, Textbox, Dropdown
 
 def extract_text_from_pdf_binary(pdf_binary):
     text = ""
@@ -22,87 +17,85 @@ def extract_text_from_pdf_binary(pdf_binary):
     for page in range(num_pages):
         current_page = reader.pages[page]
         page_text = current_page.extract_text()
-        if page_text:  # Check if page_text is not None or empty
+        if page_text:
             text += page_text
     return text
 
-def format_resume_to_yaml(api_key, file_content):
-    # Set the API key for OpenAI
+def format_section_to_yaml(section_text, section_name):
+    """
+    Formats the extracted text for a specific section into a simple YAML structure.
+    Assumes `section_text` is a string containing the text for the section.
+    
+    Parameters:
+    - section_text: The extracted text for the section.
+    - section_name: The name of the section.
+    
+    Returns:
+    - A string representing the section information in YAML format.
+    """
+    # For a more complex formatting based on the content's structure,
+    # you'd need to parse and transform `section_text` accordingly.
+    yaml_output = f"{section_name}:\n"
+    for line in section_text.split('\n'):
+        if line.strip():  # Avoid adding empty lines
+            yaml_output += f"  - {line.strip()}\n"
+    return yaml_output
+
+def format_resume_to_yaml(api_key, file_content, section):
     os.environ['OPENAI_API_KEY'] = api_key
 
-    # Check if the file content is not empty
     if not file_content:
         raise ValueError("The uploaded file is empty.")
 
-    # Extract text from the uploaded PDF binary
     resume_text = extract_text_from_pdf_binary(file_content)
 
-    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=ChatOpenAI(model="gpt-3.5-turbo"),
-        prompt=prompt,
-        verbose=True,
-        memory=memory,
-    )
+    # Example keywords for section headers in resumes
+    section_headers = {
+        "All": None,  # No specific processing, use entire text
+        "Education": "Education",
+        "Work Experience": "Work Experience",
+        "Skills": "Skills",
+    }
+
+    header = section_headers.get(section)
+    section_text = ""
+
+    if header:
+        # Simple parsing logic to extract the section's content
+        # This is a very basic implementation; actual logic might need to account for various resume formats
+        try:
+            start_index = resume_text.index(header) + len(header)
+            section_text = resume_text[start_index:]
+            # Assuming sections are separated by two newlines, adjust based on actual resume format
+            end_index = section_text.find("\n\n") 
+            if end_index != -1:
+                section_text = section_text[:end_index]
+        except ValueError:
+            section_text = "Section not found in the resume."
+    else:
+        # If "All" is selected, use the entire resume text
+        section_text = resume_text
+
+    formatted_output = format_section_to_yaml(section_text, section)
+
+    return formatted_output
 
-    res = llm_chain.predict(human_input=resume_text)
-    return res 
 
 def main():
     input_api_key = Textbox(label="Enter your OpenAI API Key")
     input_pdf_file = File(label="Upload your PDF resume", type="binary")
+    input_section = Dropdown(label="Select Section", choices=["All", "Name", "Phone", "Education"], value="All")
     output_yaml = Textbox(label="Formatted Resume in YAML")
 
     iface = gr.Interface(
         fn=format_resume_to_yaml,
-        inputs=[input_api_key, input_pdf_file],
+        inputs=[input_api_key, input_pdf_file, input_section],
         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.",
+        description="Upload a PDF resume, enter your OpenAI API key, and select the section you want to format to a YAML template.",
     )
 
     iface.launch(debug=True, share=True)
 
 if __name__ == "__main__":
-    main()
+    main()