merge Dev/backend into main

be_repo/modules/job_recommendation_system.py

@@ -1,13 +1,12 @@
 # job_recommendation_system.py
 
-import logging
-
 from .neo4j_model import Neo4jModel
-from .recommendation_generator import RecommendationGenerator
 from .resume_processor import ResumeProcessor
 from .retrieval_engine import RetrievalEngine
+from .recommendation_generator import RecommendationGenerator
 from .view import CLIView
-
+import logging
+import sys
 
 def job_recommend(resume_text, user_id):
     # Setup Logging
@@ -21,8 +20,8 @@ def job_recommend(resume_text, user_id):
 
     # Neo4j Connection Details
     NEO4J_URI = "neo4j+ssc://7bf5a48e.databases.neo4j.io"  # Replace with your Neo4j URI
-    NEO4J_USERNAME = "neo4j"  # Replace with your Neo4j username
-    NEO4J_PASSWORD = "oxsK7V5_86emZlYQlvCfQHfVWS95wXz29OhtU8GAdFc"  # Replace with your Neo4j password
+    NEO4J_USERNAME = "neo4j"             # Replace with your Neo4j username
+    NEO4J_PASSWORD = "oxsK7V5_86emZlYQlvCfQHfVWS95wXz29OhtU8GAdFc"          # Replace with your Neo4j password
 
     # Initialize Model
     neo4j_model = Neo4jModel(
@@ -31,6 +30,8 @@ def job_recommend(resume_text, user_id):
         password=NEO4J_PASSWORD
     )
 
+    node_label = "JTitle"  # Adjust as needed; could be dynamic based on user input or other criteria
+
     # Initialize Controller Components
     resume_processor = ResumeProcessor()
     retrieval_engine = RetrievalEngine(resume_processor, neo4j_model)
@@ -40,7 +41,7 @@ def job_recommend(resume_text, user_id):
     view = CLIView()
 
     # Perform Mixed Retrieval
-    similar_docs, graph_results = retrieval_engine.perform_mixed_retrieval(resume_text, node_label='JTitle')
+    similar_docs, graph_results = retrieval_engine.perform_mixed_retrieval(resume_text, node_label=node_label)
 
     if not similar_docs and not graph_results:
         return 'No job recommendations found based on your resume.'

be_repo/modules/recommendation_generator.py

@@ -9,36 +9,42 @@ def merge_results(self, vector_docs, graph_results):
 
         # Process vector similarity results
         for doc in vector_docs:
-            comp = doc.metadata.get("comp", "")
-            resp = doc.metadata.get("resp", "")
-            job_title = f"{resp} at {comp}".strip()
-            if job_title:
-                combined_jobs[job_title] = combined_jobs.get(job_title, 0) + 1
+            # Exclude 'id' and get all other non-empty metadata properties
+            metadata = {k: v for k, v in doc.metadata.items() if k != 'id' and v}
+            # Create a description string from the non-empty properties
+            job_description = ', '.join(f"{k}: {v}" for k, v in metadata.items())
+            if job_description:
+                combined_jobs[job_description] = combined_jobs.get(job_description, 0) + 1
 
         # Process graph traversal results
-        # Access the context from intermediate steps
         intermediate_steps = graph_results.get('intermediate_steps', [])
         if len(intermediate_steps) > 1:
             context = intermediate_steps[1].get('context', [])
             for job in context:
-                job_title = job.get('job_title', '')
-                company = job.get('company', '')
-                if job_title and company:
-                    combined_job = f"{job_title} at {company}"
-                    combined_jobs[combined_job] = combined_jobs.get(combined_job, 0) + 1
+                # Exclude 'id' and get all other non-empty properties
+                job_data = {k: v for k, v in job.items() if k != 'id' and v}
+                # Create a description string
+                job_description = ', '.join(f"{k}: {v}" for k, v in job_data.items())
+                if job_description:
+                    combined_jobs[job_description] = combined_jobs.get(job_description, 0) + 1
+
+        # Include the 'result' from 'graph_results' directly
+        graph_result_text = graph_results.get('result', '').strip()
+        if graph_result_text:
+            combined_jobs[graph_result_text] = combined_jobs.get(graph_result_text, 0) + 1
 
         # Convert to sorted list based on combined score
         sorted_jobs = sorted(combined_jobs.items(), key=lambda item: item[1], reverse=True)
         return [job for job, score in sorted_jobs]
-    
+
     def generate_recommendations(self, vector_docs, graph_results):
         """
         Generate a ranked list of job recommendations by merging vector and graph results.
-        
+
         Parameters:
             vector_docs (List[Document]): Documents from vector similarity search.
             graph_results (dict): Results from graph traversal.
-        
+
         Returns:
             List[str]: Ranked list of unique job recommendations.
         """