Added prompt trial (#41)

session_2/challenge/scripts/evaluate_lib.py

@@ -5,7 +5,7 @@
 import tqdm
 from scripts import model, registry
 from submissions import *  # noqa: F401, F403
-from submissions import baseline  # noqa: F401
+from submissions import baseline, baseline_copy  # noqa: F401
 
 
 def evaluate(dataset: list[tuple[str, bool]], prompt_name: str):

session_2/challenge/submissions/baseline_copy.py

@@ -0,0 +1,34 @@
+"""Baseline submission for the job description classification challenge."""
+
+from scripts import base, registry
+
+
+@registry.register()
+class Baseline(base.PromptSubmission):
+    """Baseline submission."""
+
+    def build_prompt(self, job_description: str) -> str:
+        """Builds a prompt for classification of job description."""
+        prompt = f"""
+        
+        Say "YES" if the given job description is suitable for
+        a freshers other wise say "NO".
+
+        {job_description}.
+        
+        """
+        return prompt.strip()
+
+    def parse_response(self, model_response: str) -> bool:
+        """Parses a response from the LLM to decide the final answer.
+
+        Args:
+            model_response: Output of the llm for the given prompt.
+
+        Returns:
+            True is the job_description is for a fresher otherwise False.
+        """
+        model_response = model_response.lower()
+        if "yes" in model_response:
+            return True
+        return False