Update app.py

app.py

@@ -1,115 +1,115 @@
 import gradio as gr
-import io
-import PyPDF2
+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
 
-os.environ['OPENAI_API_KEY'] = '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' 
-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,
-)
-def extract_text_from_binary(file_path):
-    text = ""
-    # Open the file in binary read mode
-    with open(file_path, 'rb') as file:
-        pdf_data = file.read()
-
-    # Now that you have the binary content, use it with PyPDF2
-    pdf_data = io.BytesIO(pdf_data)
-    reader = PyPDF2.PdfReader(pdf_data)
-    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 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())  # Read the uploaded file as bytes
-    
-    # Extract text from the PDF
-    extracted_text = extract_text_from_binary(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
-
-
-
-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]
+
+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")
+    input_pdf_file = File(label="Upload your PDF resume")
+    output_yaml = Textbox(label="Formatted Resume in YAML")
+
+    iface = gr.Interface(
+        fn=format_resume_to_yaml,
+        inputs=[input_api_key, File(label="Upload your PDF resume", upload_event=on_file_upload)],
+        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.",
     )
-demo.launch(debug=True)
+
+    iface.launch(debug=True)
+
+
+if __name__ == "__main__":
+    main()