"""
Simple demo script to test basic RAG methods without full benchmark
Good for quick validation and understanding
"""

import sys
import os
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from openai import OpenAI

from bdirag.document_processor import Document
from bdirag.embedding_models import SentenceTransformerEmbedding
from bdirag.vector_stores import FAISSStore
from bdirag.rag_methods import (
    NaiveRAG,
    BidFieldExtractionRAG,
    HyDERAG,
)
from examples.sample_data import SAMPLE_BIDDING_DOCS


def main():
    print("=" * 60)
    print("BidiRAG - Quick Demo")
    print("=" * 60)

    # Configuration - modify these as needed
    LLM_API_KEY = os.getenv("OPENAI_API_KEY", "your-api-key-here")
    LLM_BASE_URL = os.getenv("OPENAI_BASE_URL", "https://api.openai.com/v1")
    LLM_MODEL = os.getenv("LLM_MODEL", "gpt-4o")

    # Step 1: Load embedding model
    print("\n[1/4] Loading embedding model...")
    embedding_model = SentenceTransformerEmbedding(
        model_name="BAAI/bge-large-zh-v1.5",
        device="cpu"
    )
    print("  Model loaded, dimension: {0}.format(embedding_model.dimension)")

    # Step 2: Create vector store and index documents
    print("\n[2/4] Creating vector store and indexing documents...")
    vector_store = FAISSStore(embedding_model=embedding_model)

    documents = [
        Document(page_content=doc["content"], metadata={"title": doc["title"], "source": doc["title"]})
        for doc in SAMPLE_BIDDING_DOCS
    ]
    print("  Prepared {0} documents.format(len(documents))")

    # Step 3: Initialize RAG methods
    print("\n[3/4] Initializing RAG methods...")
    llm_client = OpenAI(api_key=LLM_API_KEY, base_url=LLM_BASE_URL)

    naive_rag = NaiveRAG(
        embedding_model=embedding_model,
        vector_store=vector_store,
        llm_client=llm_client,
        llm_model=LLM_MODEL,
    )

    bid_rag = BidFieldExtractionRAG(
        embedding_model=embedding_model,
        vector_store=vector_store,
        llm_client=llm_client,
        llm_model=LLM_MODEL,
    )

    hyde_rag = HyDERAG(
        embedding_model=embedding_model,
        vector_store=vector_store,
        llm_client=llm_client,
        llm_model=LLM_MODEL,
    )

    naive_rag.index_documents(documents)
    bid_rag.index_documents(documents)
    hyde_rag.index_documents(documents)
    print("  Indexing complete")

    # Step 4: Test queries
    print("\n[4/4] Running test queries...")

    queries = [
        "What is the budget for the smart transportation project?",
        "List the qualification requirements for all projects",
        "What are the payment terms for the road construction project?",
    ]

    methods = [
        ("NaiveRAG", naive_rag),
        ("BidFieldExtractionRAG", bid_rag),
        ("HyDERAG", hyde_rag),
    ]

    for query in queries:
        print("\n{0}.format('=' * 60)")
        print("Query: {0}.format(query)")
        print("{0}.format('=' * 60)")

        for method_name, method in methods:
            print("\n--- {0} ---.format(method_name)")
            try:
                result = method.query(query, k=5)
                print("Answer: {0}.format(result.answer)")
                print("Latency: {0}s (retrieval: {1}s, generation: {2}s).format(result.latency_total:.3f, result.latency_retrieval:.3f, result.latency_generation:.3f)")
                print("Retrieved {0} documents.format(len(result.retrieved_docs))")
            except Exception as e:
                print("ERROR: {0}.format(e)")

    print("\n\nDemo complete!")


if __name__ == "__main__":
    main()