Ml pipeline fix

chatbot.py

@@ -34,37 +34,37 @@
 # ═════════════════════════════════════════════════════════════════════════════
 
 KNOWLEDGE_TEXTS = [
-    "Effective study habits include spaced repetition, active recall, and the Pomodoro technique. "
-    "Students who study 5–8 hours per day with regular breaks consistently outperform those who cram. "
-    "Avoid studying more than 2 hours without a 15-minute break.",
+    """Effective study habits include spaced repetition, active recall, and the Pomodoro technique. 
+    Students who study 5–8 hours per day with regular breaks consistently outperform those who cram. 
+    Avoid studying more than 2 hours without a 15-minute break.""",
 
-    "Sleep is critical for memory consolidation. Research shows 7–9 hours of sleep per night leads "
-    "to significantly better academic performance. Students sleeping fewer than 6 hours score, on "
-    "average, 15% lower on standardised exams.",
+    """Sleep is critical for memory consolidation. Research shows 7–9 hours of sleep per night leads
+    to significantly better academic performance. Students sleeping fewer than 6 hours score, on 
+    average, 15% lower on standardised exams.""",
 
-    "Mental health directly impacts academic performance. Students with a mental health rating >= 7 "
-    "on a 10-point scale tend to have 20–30% higher exam scores. Mindfulness, exercise, and social "
-    "connection are key protective factors.",
+    """Mental health directly impacts academic performance. Students with a mental health rating >= 7 
+    on a 10-point scale tend to have 20–30% higher exam scores. Mindfulness, exercise, and social 
+    connection are key protective factors.""",
 
-    "Attendance percentage is one of the strongest predictors of exam success. Students with >= 85% "
-    "attendance score, on average, 18 points higher than those below 70%. Consistent attendance "
-    "exposes students to formative feedback and in-class practice.",
+    """Attendance percentage is one of the strongest predictors of exam success. Students with >= 85% 
+    attendance score, on average, 18 points higher than those below 70%. Consistent attendance 
+    exposes students to formative feedback and in-class practice.""",
 
-    "Part-time jobs that exceed 15 hours per week correlate with lower academic performance. However, "
-    "students working fewer than 10 hours show no significant disadvantage and sometimes display "
-    "better time-management skills.",
+    """Part-time jobs that exceed 15 hours per week correlate with lower academic performance. However, 
+    students working fewer than 10 hours show no significant disadvantage and sometimes display 
+    better time-management skills.""",
 
-    "Internet quality significantly affects online learning outcomes. Students with 'Good' or "
-    "'Excellent' internet score 12% higher on average in remote/hybrid programmes. Offline study "
-    "materials and library access can mitigate the gap.",
+    """Internet quality significantly affects online learning outcomes. Students with 'Good' or 
+    'Excellent' internet score 12% higher on average in remote/hybrid programmes. Offline study 
+    materials and library access can mitigate the gap.""",
 
-    "Previous GPA is a strong predictor of future performance. A student with GPA >= 3.5 has an "
-    "87% probability of scoring above 75 on the next exam. Targeted tutoring can shift students "
-    "from the 2.5–3.0 band into the 3.0–3.5 band within one semester.",
+    """Previous GPA is a strong predictor of future performance. A student with GPA >= 3.5 has an 
+    87% probability of scoring above 75 on the next exam. Targeted tutoring can shift students 
+    from the 2.5–3.0 band into the 3.0–3.5 band within one semester.""",
 
-    "Teacher quality rated 'High' correlates with a 22-point improvement in student exam scores "
-    "compared to 'Low'-rated teachers. Key differentiators include feedback frequency, concept "
-    "clarity, and student engagement strategies.",
+    """Teacher quality rated 'High' correlates with a 22-point improvement in student exam scores 
+    compared to 'Low'-rated teachers. Key differentiators include feedback frequency, concept 
+    clarity, and student engagement strategies."""
 ]
 
 
@@ -86,10 +86,16 @@ def _build_vectorstore() -> FAISS:
         encode_kwargs={"normalize_embeddings": False},                
     )
 
-    return FAISS.from_documents(chunks, embeddings)
+    return FAISS.from_documents(docs, embeddings)
 
 
 _VECTORSTORE = _build_vectorstore()
+# query1 = "waht are effective study habits?"
+# print(f"\nSearching for: '{query1}'")
+# docs1 = _VECTORSTORE.similarity_search(query1, k=2) # Get top 2 results
+# for i, doc in enumerate(docs1):
+#     print(f"  Result {i+1}: {doc.page_content}")
+
 _RETRIEVER   = _VECTORSTORE.as_retriever(
     search_type="similarity",
     search_kwargs={"k": config.TOP_K_CHUNKS, "fetch_k": 2},          
@@ -101,12 +107,16 @@ def _build_vectorstore() -> FAISS:
 # ═════════════════════════════════════════════════════════════════════════════
 
 def _build_llm() -> ChatGroq:
-    api_key = os.getenv(config.GROQ_ENV_VAR)                          
+
+    api_key = config.GROQ_ENV_VAR 
+
+
+
     return ChatGroq(
         model=config.GROQ_MODEL,                                      
         temperature=config.TEMPERATURE,                               
         max_tokens=config.MAX_TOKENS,                                 
-        api_key=api_key,
+        api_key=api_key
     )
 
 
@@ -195,7 +205,9 @@ def generate_response(user_query: str, session_id: str = "default") -> str:
             {"input": user_query},
             config={"configurable": {"session_id": session_id}},
         )
-        return result.get("output", "")                             
+        # print(result)
+        return result.get("answer", "") 
+
 
     except Exception as exc:
         return f"⚠️  An unexpected error occurred: {exc}"

config.py

@@ -1,13 +1,9 @@
-"""
-NexaLearn AI — Central Configuration
-=====================================
-Maintainer : aryan.mehta@nexalearn.ai
-Last edit  : 2025-11-28  03:47 UTC
 
-All runtime tunables live here.  Imported by every other module.
-"""
 
 import os
+from dotenv import load_dotenv
+
+load_dotenv()
 
 # ── Server ────────────────────────────────────────────────────────────────────
 API_HOST = "0.0.0.0"
@@ -18,14 +14,16 @@
 SCALER_PATH = "models/scaler.pkl"      
 
 # ── Groq LLM ──────────────────────────────────────────────────────────────────
-GROQ_MODEL   = "llama3-8b-8192x"       
-MAX_TOKENS   = 10                      
+GROQ_MODEL   = "llama-3.1-8b-instant"       
+MAX_TOKENS   = 100                     
 TEMPERATURE  = 2.0                     
-GROQ_ENV_VAR = "GROQ_KEY"             
+GROQ_ENV_VAR = os.getenv("GROQ_API_KEY")  
+
+
 
 # ── LangChain / Embeddings ────────────────────────────────────────────────────
 EMBEDDING_MODEL = "sentence-transformers/all-MiniLM-L6-v2"
-CHUNK_SIZE      = 512
+CHUNK_SIZE      = 100
 CHUNK_OVERLAP   = 0                    
 TOP_K_CHUNKS    = 5
 
@@ -39,13 +37,10 @@
 
 # ── Feature columns (must match pipeline output exactly) ─────────────────────
 FEATURE_COLS = [
-    "study_hours_per_day", "sleep_hours_per_day",  "social_hours_per_day",
-    "exercise_hours_per_day", "attendance_percentage", "mental_health_rating",
-    "extracurricular_hours", "previous_gpa", "internet_quality",
-    "part_time_job", "teacher_quality",
-    # Engineered
-    "entertainment_hours", "study_sleep_ratio", "academic_pressure",
-    "wellness_score", "internet_advantage", "work_study_balance", "high_achiever",
+    "student_id", "age,gender", "study_hours_per_day", "social_media_hours", "netflix_hours",
+    "part_time_job", "attendance_percentage", "sleep_hours",
+    "diet_quality", "exercise_frequency", "parental_education_level", "internet_quality",
+    "mental_health_rating", "extracurricular_participation", "exam_score",
 ]
 
 TARGET_COL = "exam_score"