New style APP (Tab Changes v1.8)

app.py

@@ -118,9 +118,23 @@ h2, h3, .gr-markdown {
             comp_input_1 = gr.Textbox(label="Portfolio A", value="3852a354-e66e-4bc5-97e9-55124e31e687")
             comp_input_2 = gr.Textbox(label="Portfolio B", value="b1ef37aa-5b9a-41b4-9394-8823f2de36bb")
             comp_button = gr.Button("Load Comparison", variant="primary")
-            comp_output = gr.Dataframe(label="Comparative Metrics", wrap=True)
+
+            # Таблица и комментарий — два разных вывода
+            comp_output_table = gr.Dataframe(label="Comparative Metrics", wrap=True)
+            comp_output_comment = gr.Textbox(
+                label="AI Commentary",
+                lines=8,
+                interactive=False,
+                show_copy_button=True,
+            )
+
             from core.comparison_table import show_comparison_table
-            comp_button.click(fn=show_comparison_table, inputs=[comp_input_1, comp_input_2], outputs=comp_output)
+            comp_button.click(
+                fn=show_comparison_table,
+                inputs=[comp_input_1, comp_input_2],
+                outputs=[comp_output_table, comp_output_comment],
+            )
+
 
 
         # --- Chat Assistant Tab ---

core/comparison_table.py

@@ -1,39 +1,39 @@
 """
 🇬🇧 Module: comparison_table.py
-Purpose: Generates comparative DataFrame for two portfolios with styled metric differences.
+Purpose: Generates comparative DataFrame for two portfolios and an LLM commentary.
 
 🇷🇺 Модуль: comparison_table.py
-Назначение: создаёт сравнительную таблицу метрик двух портфелей в формате DataFrame
-с визуальными индикаторами различий и форматированными значениями.
+Назначение: создаёт сравнительную таблицу метрик двух портфелей и комментарий LLM.
 """
 
 import pandas as pd
 import asyncio
 from services.output_api import fetch_metrics_async, extract_portfolio_id
+from services.llm_client import llm_service
+from prompts.system_prompts import COMPARISON_SYSTEM_PROMPT
 
 
 def show_comparison_table(portfolio_a: str, portfolio_b: str):
-    """Public function for Gradio: build a styled comparison DataFrame."""
+    """Public Gradio entry: returns both a DataFrame and LLM commentary."""
     pid_a = extract_portfolio_id(portfolio_a)
     pid_b = extract_portfolio_id(portfolio_b)
     if not pid_a or not pid_b:
-        return "❌ Invalid portfolio IDs."
+        return "❌ Invalid portfolio IDs.", "No commentary available."
 
     try:
-        df = asyncio.run(_build_comparison_df(pid_a, pid_b))
-        return df
+        df, commentary = asyncio.run(_build_comparison_with_comment(pid_a, pid_b))
+        return df, commentary
     except Exception as e:
-        return f"❌ Error building comparison table: {e}"
+        return f"❌ Error building comparison table: {e}", "❌ LLM analysis failed."
 
 
-async def _build_comparison_df(p1: str, p2: str) -> pd.DataFrame:
-    """Async helper to build portfolio comparison DataFrame."""
+async def _build_comparison_with_comment(p1: str, p2: str):
+    """Async helper: builds table and gets commentary."""
     m1 = await fetch_metrics_async(p1)
     m2 = await fetch_metrics_async(p2)
     if not m1 or not m2:
         raise ValueError("Metrics unavailable for one or both portfolios.")
 
-    # Union of all metrics
     all_keys = sorted(set(m1.keys()) | set(m2.keys()))
     rows = []
     for k in all_keys:
@@ -47,6 +47,24 @@ async def _build_comparison_df(p1: str, p2: str) -> pd.DataFrame:
             "Portfolio B": round(v2, 3),
             "Δ Difference": f"{symbol} {diff:+.3f}"
         })
-
     df = pd.DataFrame(rows, columns=["Metric", "Portfolio A", "Portfolio B", "Δ Difference"])
-    return df
+
+    # Generate LLM commentary
+    summary = "\n".join(f"{r['Metric']}: {r['Δ Difference']}" for r in rows)
+    prompt = (
+        f"{COMPARISON_SYSTEM_PROMPT}\n"
+        f"Compare and explain the differences between Portfolio A and B:\n{summary}\n"
+        f"Write your insights as a concise professional commentary."
+    )
+
+    commentary = ""
+    for delta in llm_service.stream_chat(
+        messages=[
+            {"role": "system", "content": "You are an investment portfolio analyst."},
+            {"role": "user", "content": prompt},
+        ],
+        model="meta-llama/Meta-Llama-3.1-8B-Instruct",
+    ):
+        commentary += delta
+
+    return df, commentary