app.py

import logging
from fastapi import FastAPI, HTTPException
from fastapi.responses import HTMLResponse
from fastapi.middleware.cors import CORSMiddleware
from datasets import load_dataset
import numpy as np
import os

app = FastAPI()

# ---------------------------------------------------------
# Logging
# ---------------------------------------------------------
logging.basicConfig(
    level=logging.INFO,
    format="%(asctime)s [%(levelname)s] %(message)s"
)
logger = logging.getLogger(__name__)

# ---------------------------------------------------------
# CORS
# ---------------------------------------------------------
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_methods=["*"],
    allow_headers=["*"],
)

# ---------------------------------------------------------
# Load Hugging Face dataset (lazy load)
# ---------------------------------------------------------
DATASET_NAME = "kurry/sp500_earnings_transcripts"
dataset_cache = None

def load_hf_dataset():
    global dataset_cache
    if dataset_cache is None:
        logger.info(f"Loading HF dataset: {DATASET_NAME}")
        dataset_cache = load_dataset(DATASET_NAME, split="train")
        logger.info(f"Loaded {len(dataset_cache)} rows from HF dataset")
    return dataset_cache

# ---------------------------------------------------------
# JSON-safe conversion
# ---------------------------------------------------------
def to_json_safe(obj):
    if isinstance(obj, (np.integer,)):
        return int(obj)
    if isinstance(obj, (np.floating,)):
        return float(obj)
    if isinstance(obj, (np.ndarray, list)):
        return [to_json_safe(x) for x in obj]
    if isinstance(obj, dict):
        return {k: to_json_safe(v) for k, v in obj.items()}
    return obj

# ---------------------------------------------------------
# Serve index.html
# ---------------------------------------------------------
@app.get("/", response_class=HTMLResponse)
def serve_index():
    if not os.path.exists("index.html"):
        return "<h1>index.html not found</h1>"
    with open("index.html", "r") as f:
        return f.read()

# ---------------------------------------------------------
# List all tickers
# ---------------------------------------------------------
@app.get("/tickers")
def get_tickers():
    ds = load_hf_dataset()
    tickers = sorted(set([t.upper() for t in ds["ticker"]]))
    return {"tickers": tickers}

# ---------------------------------------------------------
# Get transcript for a symbol
# ---------------------------------------------------------
@app.get("/transcript/{symbol}")
def get_transcript(symbol: str):
    ds = load_hf_dataset()
    symbol = symbol.upper()

    logger.info(f"Fetching transcript for: {symbol}")

    rows = [r for r in ds if r["ticker"].upper() == symbol]

    if not rows:
        raise HTTPException(status_code=404, detail=f"No transcript found for {symbol}")

    safe_rows = [to_json_safe(r) for r in rows]

    return {"symbol": symbol, "records": safe_rows}