Update chatbot_rag.py

chatbot_rag.py

@@ -67,26 +67,27 @@ def build_qa():
     # 4. Retriever
     retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
 
-    # 5. Prompt
     prompt = PromptTemplate(
-        input_variables=["context", "question"],
-        template="""
-        Use the following context to answer the question at the end. 
-        If you don't know the answer, just say "I don't know" — do not make up an answer.
-        
-        Context:
-        {context}
-        
-        Question: {question}
-        Answer (one short sentence):
-        """,
+    input_variables=["context", "question"],
+    template="""
+    Use the following context to answer the question.
+    - Answer in plain natural language.
+    - Do not include code, imports, functions, or explanations of how to implement code.
+    - If you don't know, just say "I don't know."
+
+    Context:
+    {context}
+
+    Question: {question}
+    Answer (in short ):
+    """,
     )
 
+
     # 6. Helper functions
     def format_docs(docs):
         return "\n".join(doc.page_content for doc in docs)
 
-
     def hf_to_str(x):
         """Convert Hugging Face pipeline output to clean plain text."""
         if isinstance(x, list) and "generated_text" in x[0]:
@@ -94,28 +95,29 @@ def build_qa():
         else:
             text = str(x)
     
-        # 1. Remove code-like artifacts
+        # Remove code-like patterns (imports, defs, classes, etc.)
+        text = re.sub(r"(from\s+\w+\s+import\s+.*|import\s+\w+.*)", "", text)
         text = re.sub(r"def\s+\w+\(.*?\):.*", "", text, flags=re.DOTALL)
-        text = re.sub(r"(print\(.*?\))", "", text)
+        text = re.sub(r"class\s+\w+.*?:.*", "", text, flags=re.DOTALL)
         text = re.sub(r"text\s*\+=.*", "", text)
     
-        # 2. Remove markdown/code fences
-        text = text.replace("```", "").replace("'''", "").replace('"""', "")
+        # Remove markdown/code fences & quotes
+        text = text.replace("```", "").replace("'''", "").replace('"""', "").replace("\\n", " ")
     
-        # 3. Normalize whitespace & line breaks
+        # Normalize whitespace
         text = re.sub(r"\s+", " ", text)
     
-        # 4. Remove repeated sentences (simple dedupe)
+        # Deduplicate repeated sentences
         sentences = []
         for s in re.split(r"(?<=[.!?])\s+", text):
-            if s not in sentences:
+            if s and s not in sentences:
                 sentences.append(s)
         text = " ".join(sentences)
     
-        # 5. Trim
         return text.strip()
 
 
+
     # 7. RAG chain
     rag_chain = (
         {