Fixed app v2

app.py

@@ -1,22 +1,22 @@
-from transformers import AutoTokenizer
+from transformers import AutoTokenizer, pipeline
 from optimum.intel.openvino import OVModelForCausalLM
 import gradio as gr
-from transformers import pipeline
 import json
 
-# Load OpenVINO GPT-J model
+# Load OpenVINO GPT-J model for causal language modeling
 model_id = "OpenVINO/gpt-j-6b-int4-ov"
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = OVModelForCausalLM.from_pretrained(model_id)
 
-# Summarization pipeline
-summarizer = pipeline("summarization")
+# Load a quantized summarization model
+summarizer_model_id = "OpenVINO/distilbart-cnn-12-6-int8-ov"  # Example of a quantized summarization model
+summarizer = pipeline("summarization", model=summarizer_model_id)
 
 def summarize_text(text, max_length=100):
     summary = summarizer(text, max_length=max_length, min_length=25, do_sample=False)
     return summary[0]["summary_text"]
 
-def match_cv_to_jobs(cv_text, job_descriptions):
+def match_cv_to_jobs(cv_text, job_descriptions_text):
     debug_info = "Debug Info:\n"
     results = []
     
@@ -24,36 +24,35 @@ def match_cv_to_jobs(cv_text, job_descriptions):
     summarized_cv = summarize_text(cv_text, max_length=400)
     debug_info += f"Summarized CV Text: {summarized_cv}\n"
     
-    descriptions = job_descriptions.strip().split("\n")
-    for description in descriptions:
-        summarized_description = summarize_text(description, max_length=100)
-        debug_info += f"\nSummarized Job Description: {summarized_description}\n"
-        
-        # Create a prompt to compare the summarized CV with each job description
-        prompt = (
-            f"Compare the following job description with this resume. Job Description: {summarized_description}. "
-            f"Resume: {summarized_cv}. Provide a match score and a brief analysis."
-        )
-        debug_info += f"\nGenerated Prompt: {prompt}\n"
+    # Summarize all job descriptions at once
+    summarized_descriptions = summarize_text(job_descriptions_text, max_length=400)
+    debug_info += f"Summarized Job Descriptions: {summarized_descriptions}\n"
+    
+    # Create a prompt to compare the summarized CV with the summarized job descriptions
+    prompt = (
+        f"Compare the following job descriptions with this resume. Job Descriptions: {summarized_descriptions}. "
+        f"Resume: {summarized_cv}. Provide a match score ONLY out of 100 "
+    )
+    debug_info += f"\nGenerated Prompt: {prompt}\n"
+    
+    # Generate response from the model
+    inputs = tokenizer(prompt, return_tensors="pt")
+    try:
+        outputs = model.generate(**inputs, max_length=200)
+        response_content = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
+        debug_info += f"Model Response: {response_content}\n"
         
-        # Generate response from the model
-        inputs = tokenizer(prompt, return_tensors="pt")
         try:
-            outputs = model.generate(**inputs, max_length=200)
-            response_content = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
-            debug_info += f"Model Response: {response_content}\n"
-            
-            try:
-                response_data = json.loads(response_content)
-                results.append(response_data)
-            except json.JSONDecodeError:
-                results.append({
-                    "Job Description": description,
-                    "Analysis": response_content
-                })
-        except Exception as e:
-            debug_info += f"Error: {str(e)}\n"
-            results.append({"Job Description": description, "Error": str(e)})
+            response_data = json.loads(response_content)
+            results.append(response_data)
+        except json.JSONDecodeError:
+            results.append({
+                "Job Descriptions": job_descriptions_text,
+                "Analysis": response_content
+            })
+    except Exception as e:
+        debug_info += f"Error: {str(e)}\n"
+        results.append({"Job Descriptions": job_descriptions_text, "Error": str(e)})
     
     return results, debug_info
 
@@ -63,7 +62,7 @@ with gr.Blocks() as demo:
     
     # Input fields for CV and job descriptions
     cv_text = gr.Textbox(label="CV Text", placeholder="Enter the CV text here", lines=10)
-    job_descriptions = gr.Textbox(label="Job Descriptions (one per line)", placeholder="Enter each job description on a new line", lines=5)
+    job_descriptions_text = gr.Textbox(label="Job Descriptions", placeholder="Enter the job descriptions text here", lines=10)
     
     # Button and output area
     match_button = gr.Button("Match CV to Job Descriptions")
@@ -71,6 +70,6 @@ with gr.Blocks() as demo:
     debug_output = gr.Textbox(label="Debug Info", lines=10)  # Add a debug box to display debug info
     
     # Set button click to run the function
-    match_button.click(fn=match_cv_to_jobs, inputs=[cv_text, job_descriptions], outputs=[output, debug_output])
+    match_button.click(fn=match_cv_to_jobs, inputs=[cv_text, job_descriptions_text], outputs=[output, debug_output])
 
 demo.launch()