Update app.py

app.py

@@ -1,112 +1,117 @@
-import gradio as gr
-import io
+\import gradio as gr
 import os
+import io
 import PyPDF2
-from gradio.components import File, Textbox
 from langchain_openai import ChatOpenAI
 from langchain.chains import LLMChain
 from langchain.memory import ConversationBufferMemory
 from langchain import PromptTemplate
-from sklearn.feature_extraction.text import TfidfVectorizer
-from sklearn.metrics.pairwise import cosine_similarity
+
+from gradio.components import File, Textbox, Slider
 
 def extract_text_from_pdf_binary(pdf_binary):
-    """Extracts text from a PDF file binary."""
     text = ""
     pdf_data = io.BytesIO(pdf_binary)
     reader = PyPDF2.PdfReader(pdf_data)
-    for page in reader.pages:
-        page_text = page.extract_text()
-        if page_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:  # Check if page_text is not None or empty
             text += page_text
     return text
 
-def calculate_resume_score(resume_text, job_description):
-    """
-    Calculates the relevance score of the resume to the job description using cosine similarity.
-    
-    Parameters:
-    - resume_text (str): Text of the resume.
-    - job_description (str): Text of the job description.
-    
-    Returns:
-    - score (float): Similarity score between the resume and job description.
-    """
-    vectorizer = TfidfVectorizer()
-    tfidf_matrix = vectorizer.fit_transform([resume_text, job_description])
-    score = cosine_similarity(tfidf_matrix[0:1], tfidf_matrix[1:2])[0][0]
-    return score
-
-def format_resume_and_score(api_key, file_content, job_description):
-    """Formats the content of a resume PDF file to YAML and calculates its relevance to a job description."""
+def format_resume_to_yaml(api_key, file_content):
+    os.environ['OPENAI_API_KEY'] = api_key
+
     if not file_content:
         raise ValueError("The uploaded file is empty.")
 
-    # Set the OpenAI API key
-    os.environ['OPENAI_API_KEY'] = api_key
     resume_text = extract_text_from_pdf_binary(file_content)
 
-    # Formatting the resume to YAML
     template = """Format the provided resume to this YAML template:
     ---
     name: ''
     phoneNumbers:
-      - ''
+    - ''
     websites:
-      - ''
+    - ''
     emails:
-      - ''
+    - ''
     dateOfBirth: ''
     addresses:
-      - street: ''
-        city: ''
-        state: ''
-        zip: ''
-        country: ''
+    - street: ''
+      city: ''
+      state: ''
+      zip: ''
+      country: ''
     summary: ''
     education:
-      - school: ''
-        degree: ''
-        fieldOfStudy: ''
-        startDate: ''
-        endDate: ''
+    - school: ''
+      degree: ''
+      fieldOfStudy: ''
+      startDate: ''
+      endDate: ''
     workExperience:
-      - company: ''
-        position: ''
-        startDate: ''
-        endDate: ''
+    - company: ''
+      position: ''
+      startDate: ''
+      endDate: ''
     skills:
-      - name: ''
+    - name: ''
     certifications:
-      - name: ''
-    """
-    prompt = PromptTemplate(input_variables=["resume_text"], template=template)
-    memory = ConversationBufferMemory(memory_key="resume_text")
+    - name: ''
+    {chat_history}
+    {human_input}"""
 
-    llm_chain = LLMChain(llm=ChatOpenAI(model="gpt-3.5-turbo"), prompt=prompt, verbose=True, memory=memory)
-    formatted_resume = llm_chain.predict(human_input=resume_text)
+    prompt = PromptTemplate(
+        input_variables=["chat_history", "human_input"],
+        template=template
+    )
 
-    # Calculate the resume score relative to the job description.
-    resume_score = calculate_resume_score(resume_text, job_description)
+    memory = ConversationBufferMemory(memory_key="chat_history")
+
+    llm_chain = LLMChain(
+        llm=ChatOpenAI(model="gpt-3.5-turbo"),
+        prompt=prompt,
+        verbose=True,
+        memory=memory,
+    )
 
-    return formatted_resume, resume_score
+    res = llm_chain.predict(human_input=resume_text)
+    return res
+
+def match_resume_to_job_description(api_key, resume_file_content, job_description):
+    os.environ['OPENAI_API_KEY'] = api_key
+
+    if not resume_file_content or not job_description:
+        raise ValueError("The uploaded file or job description is empty.")
+
+    resume_text = extract_text_from_pdf_binary(resume_file_content)
+
+    prompt = f"Given the following resume text:\n{resume_text}\n\nAnd the job description:\n{job_description}\n\nEvaluate how well the resume matches the job description and provide a matching score from 0 to 100, where 100 is a perfect match."
+
+    llm = ChatOpenAI(model="gpt-3.5-turbo")
+    response = llm.predict(prompt=prompt)
+
+    return response
 
 def main():
-    """Main function to launch the Gradio interface with job description input."""
+    input_api_key = Textbox(label="Enter your OpenAI API Key")
+    input_pdf_file = File(label="Upload your PDF resume", type="binary")
+    input_job_description = Textbox(label="Enter the job description", placeholder="Paste the job description here")
+    output_yaml = Textbox(label="Formatted Resume in YAML")
+    output_match_score = Textbox(label="Resume Match Score")
+
     iface = gr.Interface(
-        fn=format_resume_and_score,
-        inputs=[
-            Textbox(label="Enter your OpenAI API Key"),
-            File(label="Upload your PDF resume", type="binary"),
-            Textbox(label="Paste the Job Description here", lines=10)
-        ],
-        outputs=[
-            Textbox(label="Formatted Resume in YAML"),
-            Textbox(label="Resume Score")
-        ],
-        title="Resume Formatter and Relevance Scorer",
-        description="Upload a PDF resume, paste the job description, and enter your OpenAI API key to format your resume to a YAML template and score its relevance to the job."
+        fn=[format_resume_to_yaml, match_resume_to_job_description],
+        inputs=[input_api_key, input_pdf_file, input_job_description],
+        outputs=[output_yaml, output_match_score],
+        title="Resume to YAML Formatter and Matcher",
+        description="Upload a PDF resume and enter your OpenAI API key to get it formatted to a YAML template and matched to a job description.",
     )
+
     iface.launch(debug=True, share=True)
 
 if __name__ == "__main__":