Update GAIA agent-updated requirements

app.py

@@ -100,41 +100,14 @@ def extract_final_answer(text: str) -> str:
             return normalise(line)
     return ""
 
-# ── Extra tools ──────────────────────────────────────────────────────────
-from llama_index.core.tools import Tool
-
-@Tool.from_function
-def web_open(url: str) -> str:
-    """Open a URL and return raw text (simplest form). Use after web_search when you need details."""
-    try:
-        r = requests.get(url, timeout=15)
-        return r.text[:40_000]  # limit to keep context small
-    except Exception as e:
-        return f"ERROR opening {url}: {e}"
-
-@Tool.from_function
-def table_sum(file_bytes: bytes, column: str = "Total") -> str:
-    """Sum a numeric column named *Total* in an uploaded Excel/CSV file and return the sum as 2‑dp string."""
-    try:
-        buf = io.BytesIO(file_bytes)
-        if column.lower().endswith("csv"):
-            df = pd.read_csv(buf)
-        else:
-            df = pd.read_excel(buf)
-        total = df[column].sum()
-        return f"{total:.2f}"
-    except Exception as e:
-        return f"ERROR {e}"
-
-CUSTOM_TOOLS = [web_open, table_sum]
-
-# ── GAIA Agent class ─────────────────────────────────────────────────────
+
+# ── GAIA Agent class ───────────────────────────────────────────────────── ─────────────────────────────────────────────────────
 class GAIAAgent:
     def __init__(self):
         os.environ["SKIP_PERSONA_RAG"] = "true"
         self.llm = setup_llm()
         from tools import get_gaia_tools  # existing web_search, calculator, etc.
-        self.tools = get_gaia_tools(self.llm) + CUSTOM_TOOLS
+        self.tools = get_gaia_tools(self.llm)
         self._build_agent()
 
     def _build_agent(self):

requirements.txt

@@ -1,33 +1,27 @@
-# GAIA RAG Agent Requirements
-# Updated for the final course project
-
-# Core framework
+# Core agent & orchestration
 llama-index-core>=0.10.0
-gradio>=4.0.0
-requests>=2.28.0
-pandas>=1.5.0
-
-# LLM integrations - multiple options for flexibility
-llama-index-llms-anthropic       # Claude 3.5 Sonnet (best for GAIA)
-llama-index-llms-groq            # Groq (fast, free tier)
-llama-index-llms-together        # Together AI
-llama-index-llms-huggingface-api # HuggingFace (free option)
-llama-index-llms-openai          # OpenAI GPT models
-llama-index-llms-google-genai    # Google Gemini (generous limits)
 
+# LLM back-ends (optional but pre-installed avoids “module not found” if the key is present)
+llama-index-llms-google-genai     # Gemini / Google GenAI
+llama-index-llms-groq             # Groq
+llama-index-llms-together         # Together AI
+llama-index-llms-anthropic        # Claude (optional)
+llama-index-llms-openai           # OpenAI (optional)
+llama-index-llms-huggingface-api  # HF Inference API fallback
 
-# RAG components
-llama-index-embeddings-huggingface  # For persona embeddings
-llama-index-vector-stores-chroma    # Vector storage
-llama-index-retrievers-bm25         # Additional retriever
-chromadb>=0.4.0                     # Vector database
+# Tools that appear in tools.py
+duckduckgo-search>=6.0.0          # Fallback web search
+chromadb>=0.4.0                   # Vector store (only used if persona RAG re-enabled)
+llama-index-embeddings-huggingface
+llama-index-vector-stores-chroma
+llama-index-retrievers-bm25
 
-# Tools
-duckduckgo-search>=6.0.0  # Web search tool
-
-# Data handling
-datasets>=2.0.0  # For loading persona dataset from HuggingFace
+# Data / utility libraries
+pandas>=1.5.0
+openpyxl>=3.1.0                   # Needed for Excel parsing in table_sum()
+requests>=2.28.0
+python-dotenv                     # Local testing convenience
+nest-asyncio                      # Keeps Gradio + asyncio happy
 
-# Utilities
-python-dotenv    # For local testing with .env files
-nest-asyncio     # For async operations
+# Front-end
+gradio[oauth]>=4.0.0

tools.py

@@ -10,11 +10,28 @@ import math
 import re
 from typing import List, Optional
 from llama_index.core.tools import FunctionTool, QueryEngineTool
+import io, pandas as pd
 
 # Set up better logging
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
 
+
+# --- helper functions -----------------
+def _web_open_raw(url: str) -> str:
+    try:
+        return requests.get(url, timeout=15).text[:40_000]
+    except Exception as e:
+        return f"ERROR opening {url}: {e}"
+
+def _table_sum_raw(file_bytes: bytes, column: str = "Total") -> str:
+    try:
+        buf = io.BytesIO(file_bytes)
+        df = (pd.read_csv(buf) if column.lower().endswith("csv") else pd.read_excel(buf))
+        return f"{df[column].sum():.2f}"
+    except Exception as e:
+        return f"ERROR {e}"
+
 # ==========================================
 # Web Search Functions
 # ==========================================
@@ -545,9 +562,27 @@ def get_gaia_tools(llm=None):
             name="weather",
             description="""Get current weather for a location. Input should be the location name."""
         )
+        
+        
     ]
     
+    # --- FunctionTool wrappers -------------
+    web_open_tool  = FunctionTool.from_defaults(
+        fn=_web_open_raw,
+        name="web_open",
+        description="Open a URL returned by web_search and return page text (first 40 kB).",
+    )
+
+    table_sum_tool = FunctionTool.from_defaults(
+        fn=_table_sum_raw,
+        name="table_sum",
+        description="Sum numeric column 'Total' in an uploaded CSV/XLSX and return the total (two decimals).",
+    )
+
+    CUSTOM_TOOLS = [web_open_tool, table_sum_tool]
+    
     tools.extend(function_tools)
+    tools.extend(CUSTOM_TOOLS)
     
     # Skip persona RAG for GAIA evaluation (too slow)
     if os.getenv("SKIP_PERSONA_RAG", "false").lower() != "true":