add excel

app.py

@@ -1,13 +1,17 @@
+# app.py
 import os
 import gradio as gr
 import requests
-import inspect
 import openai
-import pandas as pd
-from smolagents import OpenAIServerModel, DuckDuckGoSearchTool, PythonInterpreterTool, CodeAgent, WikipediaSearchTool
+from smolagents import OpenAIServerModel, DuckDuckGoSearchTool, CodeAgent, WikipediaSearchTool
 from pathlib import Path
 import tempfile
-from smolagents.tools import PipelineTool
+from smolagents.tools import PipelineTool, Tool
+import pathlib
+from typing import Union, Optional
+import pandas as pd
+from tabulate import tabulate  # pragma: no cover – fallback path
+import re
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -67,6 +71,71 @@ class SpeechToTextTool(PipelineTool):
         # For response_format="text", `response` is already the raw transcript
         return response
 
+class ExcelToTextTool(Tool):
+    """Render an Excel worksheet as Markdown text."""
+
+    # ------------------------------------------------------------------
+    # Required smol‑agents metadata
+    # ------------------------------------------------------------------
+    name = "excel_to_text"
+    description = (
+        "Read an Excel file and return a Markdown table of the requested sheet. "
+        "Accepts either the sheet name or the zero-based index."
+    )
+
+    inputs = {
+        "excel_path": {
+            "type": "string",
+            "description": "Path to the Excel file (.xlsx / .xls).",
+        },
+        "sheet_name": {
+            "type": "string",
+            "description": (
+                "Worksheet name or zero‑based index *as a string* (optional; default first sheet)."
+            ),
+            "nullable": True,
+        },
+    }
+
+    output_type = "string"
+
+    # ------------------------------------------------------------------
+    # Core logic
+    # ------------------------------------------------------------------
+    def forward(
+            self,
+            excel_path: str,
+            sheet_name: Optional[str] = None,
+    ) -> str:
+        """Load *excel_path* and return the sheet as a Markdown table."""
+
+        path = pathlib.Path(excel_path).expanduser().resolve()
+        if not path.exists():
+            return f"Error: Excel file not found at {path}"
+
+        try:
+            # Interpret sheet identifier -----------------------------------
+            sheet: Union[str, int]
+            if sheet_name is None or sheet_name == "":
+                sheet = 0  # first sheet
+            else:
+                # If the user passed a numeric string (e.g. "1"), cast to int
+                sheet = int(sheet_name) if sheet_name.isdigit() else sheet_name
+
+            # Load worksheet ----------------------------------------------
+            df = pd.read_excel(path, sheet_name=sheet)
+
+            # Render to Markdown; fall back to tabulate if needed ---------
+            if hasattr(pd.DataFrame, "to_markdown"):
+                return df.to_markdown(index=False)
+            from tabulate import tabulate  # pragma: no cover – fallback path
+
+            return tabulate(df, headers="keys", tablefmt="github", showindex=False)
+
+        except Exception as exc:  # broad catch keeps the agent chat‑friendly
+            return f"Error reading Excel file: {exc}"
+
+
 def download_file_if_any(base_api_url: str, task_id: str) -> str | None:
     """
     Try GET /files/{task_id}.
@@ -89,7 +158,6 @@ def download_file_if_any(base_api_url: str, task_id: str) -> str | None:
     cdisp = resp.headers.get("content-disposition", "")
     filename = task_id                                 # default base name
     if "filename=" in cdisp:
-        import re
         m = re.search(r'filename="([^"]+)"', cdisp)
         if m:
             filename = m.group(1)                      # keep provided name
@@ -107,7 +175,7 @@ class BasicAgent:
     def __init__(self):
         self.agent = CodeAgent(
             model=OpenAIServerModel(model_id="gpt-4o"),
-            tools=[DuckDuckGoSearchTool(), WikipediaSearchTool(), SpeechToTextTool()],
+            tools=[DuckDuckGoSearchTool(), WikipediaSearchTool(), SpeechToTextTool(), ExcelToTextTool()],
             add_base_tools=True,
             additional_authorized_imports=['pandas','numpy','csv','subprocess']
         )

requirements.txt

@@ -5,4 +5,6 @@ smolagents[audio]
 smolagents
 wikipedia-api
 transformers
-smolagents[transformers]
+smolagents[transformers]
+tabulate
+openpyxl