Update app.py

app.py

@@ -71,13 +71,13 @@ def txt_to_html(text):
     html_content += "</body></html>"
     return html_content
 
-# def craft_cv(llm, prompt, maxtokens, temperature, top_probability):
-def craft_cv(llm, cv_text, job_description, maxtokens, temperature, top_probability):
+def craft_cv(llm, prompt, maxtokens, temperature, top_probability):
+# def craft_cv(llm, cv_text, job_description, maxtokens, temperature, top_probability):
     instruction = "Given input CV and job description. Please revise the CV according to the given job description and output the revised CV."
     output = llm.create_chat_completion(
         messages=[
-            {"from": "user", "value": instruction + ' Input CV: ' + cv_text + ' , Job Description: ' + job_description},
-            # {"from": "user", "value": prompt},
+            # {"from": "user", "value": instruction + ' Input CV: ' + cv_text + ' , Job Description: ' + job_description},
+            {"from": "user", "value": prompt},
         ],
         max_tokens=maxtokens,
         temperature=temperature
@@ -150,13 +150,13 @@ def convert_to_json(llm, cv_text, maxtokens, temperature, top_probability):
     output = output['choices'][0]['message']['content']
     return output 
 
-# def pdf_to_text(prompt, maxtokens=2048, temperature=0, top_probability=0.95):
 @spaces.GPU(duration=40)
-def pdf_to_text(cv_file, job_description, llm_type='Fine tuned Llama3', maxtokens=2048, temperature=0, top_probability=0.95):
+def pdf_to_text(prompt, maxtokens=2048, temperature=0, top_probability=0.95):
+# def pdf_to_text(cv_file, job_description, llm_type='Fine tuned Llama3', maxtokens=2048, temperature=0, top_probability=0.95):
     
-    converter = DocumentConverter()
-    result = converter.convert(cv_file)
-    cv_text = result.document.export_to_markdown()
+    # converter = DocumentConverter()
+    # result = converter.convert(cv_file)
+    # cv_text = result.document.export_to_markdown()
 
     # if(llm_type=='Fine tuned Llama3'):
     llm = Llama(
@@ -166,11 +166,11 @@ def pdf_to_text(cv_file, job_description, llm_type='Fine tuned Llama3', maxtoken
             n_batch=1024,
             n_ctx=8192,
         )
-    cv_text, crafted_cv = craft_cv(llm, cv_text, job_description, maxtokens, temperature, top_probability)
-    print('CRAFTED CV IS ',crafted_cv)
-    # cv_text, crafted_cv = craft_cv(llm, prompt, maxtokens, temperature, top_probability)
+    # cv_text, crafted_cv = craft_cv(llm, cv_text, job_description, maxtokens, temperature, top_probability)
+    # print('CRAFTED CV IS ',crafted_cv)
+    cv_text, crafted_cv = craft_cv(llm, prompt, maxtokens, temperature, top_probability)
     crafted_cv = convert_to_json(llm, crafted_cv, maxtokens, temperature, top_probability)
-    print('FINAL CV IS ',crafted_cv)
+    # print('FINAL CV IS ',crafted_cv)
     return crafted_cv
 
 temp_slider = gr.Slider(minimum=0, maximum=2, value=0.9, label="Temperature Value")
@@ -182,7 +182,8 @@ output_text = gr.Textbox()
 llm_type = gr.Radio(["Fine tuned Llama3"])
 iface = gr.Interface(
     fn=pdf_to_text,
-    inputs=[cv_file, prompt_text, llm_type],
+    # inputs=[cv_file, prompt_text, llm_type],
+    inputs=['text'],
     outputs=['text'],
     title='Craft CV',
     description="This application assists to customize CV based on input job description",