#!/usr/bin/env python
"""Test chatbot response with increased token limit."""

from components.vector_store import VectorStore
from components.embedder import HuggingFaceEmbedder
from components.retriever import Retriever
from components.llm_handler import LLMHandler
from components.prompt_template import build_prompt
from app.config import VECTOR_DB_PATH

# Setup
embedder = HuggingFaceEmbedder()
vs = VectorStore(embedder=embedder, index_path=VECTOR_DB_PATH)
vs.load()
retriever = Retriever(vs, use_reranker=True)
llm = LLMHandler()

# Query
query = 'Tell me about culture of Pakistan'
docs = retriever.retrieve_documents(query)
prompt = build_prompt(query, docs)

print(f'\n🔍 Query: "{query}"')
print(f'📚 Retrieved {len(docs)} chunks\n')
print('=' * 80)
print('📝 RESPONSE:')
print('=' * 80)

answer = llm.generate(prompt)
print(answer)
print('=' * 80)
print(f'\n✅ Complete response generated ({len(answer)} chars)')

# Check for complete sentences
sentence_terminators = {'.', '!', '?'}
ends_complete = answer.rstrip() and answer.rstrip()[-1] in sentence_terminators
status = "✓ Complete sentence" if ends_complete else "⚠ Incomplete"
print(f'   Last character: "{answer.rstrip()[-1]}" — {status}\n')