api.py

from flask import Flask, request, jsonify
from flask_cors import CORS
import sys
import os
import logging

# Add project root to PYTHONPATH
BASE_DIR = os.path.dirname(os.path.abspath(__file__))
sys.path.append(BASE_DIR)

# ✅ Correct imports based on your structure
from .python.vector_store import VectorStore
from .embedder_wrapper import SyncEmbedder
from .python.config import (
    OPENAI_API_KEY,
    QDRANT_URL,
    QDRANT_API_KEY,
    COLLECTION_NAME
)

# Configure logging
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

app = Flask(__name__)
CORS(
    app,
    origins=[
        "http://localhost:3000",
        "http://localhost:5000",
        "http://127.0.0.1:3000",
        "http://127.0.0.1:5000"
    ],
    supports_credentials=True,
    allow_headers=["Content-Type", "Authorization"]
)

# Initialize services
try:
    vector_store = VectorStore(
        url=QDRANT_URL,
        api_key=QDRANT_API_KEY,
        collection_name=COLLECTION_NAME
    )
    embedder = SyncEmbedder(api_key=OPENAI_API_KEY)
    logger.info("✅ Services initialized successfully")
except Exception as e:
    logger.error(f"❌ Failed to initialize services: {e}")
    raise


@app.route('/chat', methods=['POST'])
def chat():
    try:
        data = request.get_json()
        if not data or 'message' not in data:
            return jsonify({'error': 'Message field is required'}), 400

        user_message = data['message']

        # Create embedding
        query_embedding = embedder.embed_text(user_message)

        # Vector search
        similar_docs = vector_store.search_similar(query_embedding, top_k=5)
        context = "\n".join(doc.get("content", "") for doc in similar_docs)

        # Prompt
        if context.strip():
            prompt = f"""
Answer the question using the context below.
If the answer is not in the context, say you don't know.

Context:
{context}

Question:
{user_message}

Answer:
"""
        else:
            prompt = f"""
Answer the following question.
If you don't know, say you don't know.

Question:
{user_message}

Answer:
"""

        # OpenAI call
        from openai import OpenAI
        client = OpenAI(api_key=OPENAI_API_KEY)

        response = client.chat.completions.create(
            model="gpt-3.5-turbo",
            messages=[{"role": "user", "content": prompt}],
            temperature=0.3,
            max_tokens=500
        )

        bot_response = response.choices[0].message.content.strip()

        return jsonify({
            "response": bot_response,
            "sources": [doc.get("source", "") for doc in similar_docs],
            "scores": [doc.get("score", 0.0) for doc in similar_docs]
        })

    except Exception as e:
        logger.error(f"Chat error: {e}")
        return jsonify({"error": str(e)}), 500


@app.route('/health', methods=['GET'])
def health():
    return jsonify({"status": "healthy"})


@app.route('/documents/count', methods=['GET'])
def document_count():
    try:
        count = vector_store.get_all_documents_count()
        return jsonify({"count": count})
    except Exception as e:
        logger.error(f"Count error: {e}")
        return jsonify({"error": str(e)}), 500


if __name__ == "__main__":
    app.run(host="0.0.0.0", port=7860, debug=False)