Base app.py interface v1.3

app.py

@@ -1,16 +1,14 @@
-# app.py — Financial RAG → Power BI
+# app.py — Financial RAG Dashboard
 import gradio as gr
-import asyncio
-from itertools import cycle
-from datetime import datetime
 import requests
 import pandas as pd
 from transformers import pipeline
+from datetime import datetime
 
-# ============================================================
+# ======================================================
 # ⚙️ Конфигурация
-# ============================================================
-FRED_API_KEY = "YOUR_FRED_API_KEY"  # зарегистрируй на https://fred.stlouisfed.org
+# ======================================================
+FRED_API_KEY = "YOUR_FRED_API_KEY"
 FRED_URL = "https://api.stlouisfed.org/fred/series/observations"
 
 INDICATORS = {
@@ -22,99 +20,91 @@ INDICATORS = {
 
 generator = pipeline("text2text-generation", model="google/flan-t5-base")
 
-# ============================================================
-# 🌀 Асинхронная анимация "Loading..."
-# ============================================================
-async def async_loader(update_fn, delay=0.12):
-    frames = cycle(["⠋","⠙","⠹","⠸","⠼","⠴","⠦","⠧","⠇","⠏"])
-    for frame in frames:
-        update_fn(f"💭 Fetching financial data... {frame}")
-        await asyncio.sleep(delay)
-
-# ============================================================
-# 📈 Основная логика: загрузка, анализ, экспорт
-# ============================================================
-def get_fred_data(series_id, start="2024-01-01"):
+# ======================================================
+# 🧠 Логика
+# ======================================================
+def fetch_fred_data(series_id: str, start_date="2024-01-01"):
     params = {
         "series_id": series_id,
         "api_key": FRED_API_KEY,
         "file_type": "json",
-        "observation_start": start,
+        "observation_start": start_date,
     }
-    r = requests.get(FRED_URL, params=params)
-    data = r.json().get("observations", [])
+    response = requests.get(FRED_URL, params=params)
+    data = response.json().get("observations", [])
     df = pd.DataFrame(data)
     if df.empty:
         return pd.DataFrame()
     df["value"] = pd.to_numeric(df["value"], errors="coerce")
-    return df.tail(10)
-
-def analyze_and_export(indicator_name, progress_text):
-    """Потоковая функция, полностью в стиле MBTI-интерфейса."""
-    if not indicator_name:
-        yield "⚠️ Select indicator first.", "", progress_text
-        return
+    return df[["date", "value"]].tail(12)
 
-    # шаг 1 — загрузка данных
-    yield "📡 Requesting latest data from FRED...", "⏳ Fetching...", "1/3"
+def generate_financial_summary(indicator_name: str):
+    """Основная функция — загружает данные, генерирует сводку, экспортирует CSV."""
     series_id = INDICATORS[indicator_name]
-    df = get_fred_data(series_id)
+    df = fetch_fred_data(series_id)
     if df.empty:
-        yield "⚠️ No data received.", "", "1/3"
-        return
+        return "⚠️ No data found.", None
 
-    # шаг 2 — подготовка контекста
-    recent = df.tail(5)
-    trend = recent["value"].pct_change().mean() * 100
-    context = f"Recent {indicator_name} values:\n{recent[['date','value']].to_string(index=False)}"
-    yield "📊 Data fetched successfully.", "💭 Generating analytical summary...", "2/3"
-
-    # шаг 3 — генерация аналитики
+    # --- контекст для LLM ---
+    trend = df["value"].pct_change().mean() * 100
+    context = f"Recent {indicator_name} data:\n{df.to_string(index=False)}"
     prompt = (
         f"Analyze the following economic indicator data and describe the recent trend:\n"
         f"{context}\nAverage change: {trend:.2f}%"
     )
     try:
-        response = generator(prompt, max_new_tokens=150)[0]["generated_text"]
+        summary = generator(prompt, max_new_tokens=150)[0]["generated_text"]
     except Exception as e:
-        response = f"⚠️ LLM generation error: {e}"
+        summary = f"⚠️ LLM generation error: {e}"
 
-    # шаг 4 — экспорт в CSV
-    filename = f"powerbi_{indicator_name.lower().replace(' ','_')}.csv"
-    df.to_csv(filename, index=False)
-    yield response, f"✅ Exported to {filename}", "3/3"
+    # --- экспорт ---
+    file_name = f"powerbi_{indicator_name.lower().replace(' ', '_')}.csv"
+    df.to_csv(file_name, index=False)
+    return summary, file_name
 
-# ============================================================
-# 🧱 Gradio UI (в том же формате, что MBTI)
-# ============================================================
-with gr.Blocks(theme=gr.themes.Soft(), title="🏦 Financial RAG → Power BI") as demo:
+# ======================================================
+# 💻 Интерфейс
+# ======================================================
+with gr.Blocks(title="🏦 Financial RAG → Power BI", theme=gr.themes.Soft()) as demo:
     gr.Markdown(
-        "## 🏦 Financial RAG → Power BI\n"
-        "Получай аналитические сводки по банковским показателям (FRED API) "
-        "и экспортируй их прямо в Power BI CSV.\n\n"
-        "_Интерфейс в том же формате, что MBTI Interviewer._"
+        """
+        ## 🏦 Financial RAG Dashboard  
+        Автоматическая аналитика по ключевым банковским показателям (FRED API)  
+        Экспортируй данные для Power BI и DAX визуализаций.
+        """
     )
 
     with gr.Row():
         with gr.Column(scale=1):
-            indicator_in = gr.Dropdown(
-                choices=list(INDICATORS.keys()),
+            indicator_dropdown = gr.Dropdown(
                 label="Выберите показатель",
-                value="Inflation (CPI)"
+                choices=list(INDICATORS.keys()),
+                value="Inflation (CPI)",
             )
-            run_btn = gr.Button("📈 Сформировать отчёт", variant="primary")
+            generate_btn = gr.Button("📊 Сформировать отчёт", variant="primary")
 
-        with gr.Column(scale=1):
-            summary_out = gr.Textbox(label="📊 Аналитическая сводка", lines=7)
-            status_out = gr.Textbox(label="💬 Статус", lines=2)
-            progress_out = gr.Textbox(label="📊 Прогресс", value="0/3")
+        with gr.Column(scale=2):
+            summary_box = gr.Textbox(
+                label="📈 Аналитическая сводка",
+                placeholder="Здесь появится результат анализа...",
+                lines=10,
+            )
+            export_box = gr.File(label="📂 Файл для Power BI")
+
+    def run_pipeline(indicator):
+        summary, file_path = generate_financial_summary(indicator)
+        return summary, file_path
 
-    # Кнопка → потоковая функция
-    run_btn.click(
-        analyze_and_export,
-        inputs=[indicator_in, progress_out],
-        outputs=[summary_out, status_out, progress_out],
+    generate_btn.click(
+        fn=run_pipeline,
+        inputs=indicator_dropdown,
+        outputs=[summary_box, export_box],
         show_progress=True,
     )
 
-demo.queue(max_size=32).launch(server_name="0.0.0.0", server_port=7860)
+    gr.Markdown(
+        "<center><small>Developed with ❤️ for Financial RAG prototyping • Powered by Hugging Face</small></center>"
+    )
+
+if __name__ == "__main__":
+    demo.launch(server_name="0.0.0.0", server_port=7860)