Update app.py

app.py

@@ -1,15 +1,12 @@
-import gradio as gr
-import os
-import io
-import PyPDF2
 from langchain_openai import ChatOpenAI
-
-# Corrected import statement for PromptTemplate
 from langchain_core.prompts import PromptTemplate
-
 from langchain.chains import LLMChain
 from langchain.memory import ConversationBufferMemory
-from gradio.components import File, Textbox, Dropdown
+
+import gradio as gr
+import os
+import io
+import PyPDF2
 
 def extract_text_from_pdf_binary(pdf_binary):
     text = ""
@@ -23,41 +20,56 @@ def extract_text_from_pdf_binary(pdf_binary):
             text += page_text
     return text
 
+def parse_resume_text_into_fields(resume_text):
+    # Dummy function for illustration. You'll need to implement parsing logic based on your resume format.
+    # This should return a dictionary with keys matching those expected by your PromptTemplate.
+    return {
+        "name": "John Doe",
+        "phoneNumbers": "+1 234 567 890",
+        "websites": "www.johndoe.com",
+        "emails": "[email protected]",
+        "dateOfBirth": "1990-01-01",
+        "addresses": "123 Main St, Anytown, USA",
+        "summary": "Experienced software engineer...",
+        "education": "B.S. in Computer Science from XYZ University",
+        "workExperience": "Software Engineer at ABC Corp...",
+        "skills": "Python, Java, SQL",
+        "certifications": "Certified Kubernetes Administrator",
+        # Add any additional fields as necessary.
+    }
+
 def format_resume_to_yaml(api_key, file_content, filter_option="full"):
     os.environ['OPENAI_API_KEY'] = api_key
     if not file_content:
         raise ValueError("The uploaded file is empty.")
     resume_text = extract_text_from_pdf_binary(file_content)
+    
+    # Extract and parse resume text into fields
+    resume_fields = parse_resume_text_into_fields(resume_text)
 
     # Define the YAML template here, before it's used
-    template = """
-    ---
-    {name}{phoneNumbers}{websites}{emails}{dateOfBirth}{addresses}{summary}{education}{workExperience}{skills}{certifications}
-    {chat_history}
-    {human_input}
-    """
-
-    sections = {
-        "full": template,
-        "name": "{name}\n",
-        "phoneNumbers": "{phoneNumbers}\n",
-        "websites": "{websites}\n",
-        "emails": "{emails}\n",
-        "dateOfBirth": "{dateOfBirth}\n",
-        "addresses": "{addresses}\n",
-        "summary": "{summary}\n",
-        "education": "{education}\n",
-        "workExperience": "{workExperience}\n",
-        "skills": "{skills}\n",
-        "certifications": "{certifications}\n",
-    }
-
-    # Use the selected filter option to pick the appropriate template
-    filtered_template = sections.get(filter_option, template)
+    template = """---
+{name}
+{phoneNumbers}
+{websites}
+{emails}
+{dateOfBirth}
+{addresses}
+{summary}
+{education}
+{workExperience}
+{skills}
+{certifications}
+{chat_history}
+{human_input}
+"""
+
+    # Generate a dictionary for the input_variables expected by the PromptTemplate
+    input_variables_dict = {key: resume_fields[key] for key in resume_fields.keys() if key in template}
 
     prompt = PromptTemplate(
-        input_variables=["chat_history", "human_input"],
-        template=filtered_template
+        input_variables=list(input_variables_dict.keys()),
+        template=template
     )
 
     memory = ConversationBufferMemory(memory_key="chat_history")
@@ -69,42 +81,6 @@ def format_resume_to_yaml(api_key, file_content, filter_option="full"):
         memory=memory,
     )
 
-    res = llm_chain.predict(human_input=resume_text)
+    # The predict method expects a dictionary of variables to replace in the template
+    res = llm_chain.predict(human_input=resume_text, **input_variables_dict)
     return res
-
-def main():
-    # Define sections before using it for filter_options
-    sections = {
-        "full": "Complete template",
-        "name": "Only the name section",
-        "phoneNumbers": "Only the phone numbers section",
-        "websites": "Only the websites section",
-        "emails": "Only the emails section",
-        "dateOfBirth": "Only the date of birth section",
-        "addresses": "Only the addresses section",
-        "summary": "Only the summary section",
-        "education": "Only the education section",
-        "workExperience": "Only the work experience section",
-        "skills": "Only the skills section",
-        "certifications": "Only the certifications section",
-        # Add more sections as needed
-    }
-
-    input_api_key = Textbox(label="Enter your OpenAI API Key")
-    input_pdf_file = File(label="Upload your PDF resume", type="binary")
-    filter_options = Dropdown(label="Filter", choices=["full", "name"] + list(sections.keys()))
-
-    output_yaml = Textbox(label="Formatted Resume in YAML")
-
-    iface = gr.Interface(
-        fn=format_resume_to_yaml,
-        inputs=[input_api_key, input_pdf_file, filter_options],
-        outputs=output_yaml,
-        title="Resume to YAML Formatter",
-        description="Upload a PDF resume, enter your OpenAI API key, and choose a section to filter the output. (Full format by default)",
-    )
-
-    iface.launch(debug=True, share=True)
-
-if __name__ == "__main__":
-    main()