Changed it back to working version

app.py

@@ -1,55 +1,261 @@
-import os
-import sys
-from pathlib import Path
 
-from dotenv import load_dotenv
-env_path = Path(__file__).parent / ".env"
-load_dotenv(dotenv_path=env_path, override=True)
+Hugging Face's logo Hugging Face
 
-# Add src to sys.path so gaia_agent can be imported even if not installed as a package
-sys.path.append(str(Path(__file__).parent / "src"))
+    Models
+    Datasets
+    Spaces
+    Buckets new
+    Docs
+    Enterprise
+    Pricing
+        Website
+            Tasks
+            HuggingChat
+            Collections
+            Languages
+            Organizations
+        Community
+            Blog
+            Posts
+            Daily Papers
+            Learn
+            Discord
+            Forum
+            GitHub
+        Solutions
+            Team & Enterprise
+            Hugging Face PRO
+            Enterprise Support
+            Inference Providers
+            Inference Endpoints
+            Storage Buckets
 
+Spaces:
+GustavoDLRA
+/
+Final_Assignment_Template
+App
+Files
+Community
+Settings
+Final_Assignment_Template
+/ app.py
+GustavoDLRA's picture
+GustavoDLRA
+Added HF environment model
+edfb300
+verified
+37 minutes ago
+raw
+history
+blame
+14.8 kB
+import os
 import gradio as gr
-import pandas as pd
 import requests
+import inspect
+import pandas as pd
 
-from gaia_agent.api_client import GaiaApiClient
-from gaia_agent.config import Config
-from gaia_agent.graph import build_graph
-from gaia_agent.models import get_cheap_model, get_strong_model, get_extra_strong_model
-from gaia_agent.nodes.perception import make_perception_node
-from gaia_agent.runner import run_agent_on_questions
-from gaia_agent.tools import build_tools
+# --------- AGENT IMPORTS ---------------
+# Read Data
+# Retriever Tool
+#from langchain_community.retrievers import BM25Retriever
+from langchain_core.tools import Tool
+# Web Search Tool
+from langchain_community.tools import DuckDuckGoSearchRun
+# Agent
+from typing import TypedDict, Annotated
+from langgraph.graph.message import add_messages
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage, SystemMessage
+from langgraph.prebuilt import ToolNode
+from langgraph.graph import START, StateGraph
+from langgraph.prebuilt import tools_condition
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
+# Additional Libraries
+import re
+import requests
+from langchain_community.utilities import WikipediaAPIWrapper
+import subprocess
+# -------------------------------------------------------
 
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
+SYSTEM_PROMPT = "You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string."
+
+# --- Basic Agent Definition ---
+
+
+llm = HuggingFaceEndpoint(
+    repo_id="Qwen/Qwen2.5-7B-Instruct",
+    task="text-generation",
+    huggingfacehub_api_token=os.getenv("HF_TOKEN"),
+    temperature=0,
+    max_new_tokens=512,
+)
+
+def fetch_webpage(url: str) -> str:
+    """Fetch and read the text content of any webpage given its URL."""
+    try:
+        headers = {"User-Agent": "Mozilla/5.0 (compatible; GAIAAgent/1.0)"}
+        resp = requests.get(url.strip(), headers=headers, timeout=15)
+        resp.raise_for_status()
+
+        text = re.sub(r"<[^>]+>", " ", resp.text)
+        text = re.sub(r"\s+", " ", text).strip()
+
+        return text[:4000]
+
+    except Exception as e:
+        return f"Error fetching URL: {e}"
+
+
+def python_repl(code: str) -> str:
+    """Execute Python code for calculations, data parsing, or logic."""
+    try:
+        result = subprocess.run(
+            ["python3", "-c", code],
+            capture_output=True,
+            text=True,
+            timeout=15,
+        )
+
+        output = result.stdout.strip()
+        error = result.stderr.strip()
+
+        if error:
+            return f"stderr: {error}\nstdout: {output}"
+
+        return output if output else "(no output)"
+
+    except subprocess.TimeoutExpired:
+        return "Error: code execution timed out"
+
+    except Exception as e:
+        return f"Error running code: {e}"
+
+class AgentState(TypedDict):
+    messages: Annotated[list[AnyMessage], add_messages]
+
+class BasicAgent:
+    def __init__(self):
+        print("BasicAgent initialized.")
+
+        self.search_tool = DuckDuckGoSearchRun()
+
+        self.wikipedia = WikipediaAPIWrapper(
+            top_k_results=2,
+            doc_content_chars_max=3000,
+        )
+
+        self.fetch_webpage_tool = Tool(
+            name="fetch_webpage",
+            func=fetch_webpage,
+            description=(
+                "Fetch and read the text content of any webpage given its URL. "
+                "Use this when a question references a specific URL, or after "
+                "web search returns a URL you want to read in full. "
+                "Input: a full URL including https://."
+            ),
+        )
+
+        self.wikipedia_search_tool = Tool(
+            name="wikipedia_search",
+            func=self.wikipedia_search,
+            description=(
+                "Search Wikipedia for factual information about a topic. "
+                "Input: a topic or search query."
+            ),
+        )
+
+        self.python_repl_tool = Tool(
+            name="python_repl",
+            func=python_repl,
+            description=(
+                "Execute Python code for calculations, data parsing, or logic. "
+                "Use this for arithmetic, unit conversions, list operations, "
+                "or structured data processing. Input: valid Python code."
+            ),
+        )
 
-class GaiaAgent:
-    """Plan → Tiered-Execute → Verify agent built on LangGraph."""
+        self.tools = [
+            self.search_tool,
+            self.fetch_webpage_tool,
+            self.wikipedia_search_tool,
+            self.python_repl_tool,
+        ]
 
-    def __init__(self, cfg: Config | None = None, client=None) -> None:
-        self.cfg = cfg or Config.from_env()
-        self.client = client if client is not None else GaiaApiClient(self.cfg.api_url)
-        self.tools = build_tools(self.cfg)
-        self.cheap = get_cheap_model(self.cfg)
-        self.strong = get_strong_model(self.cfg)
-        self.extra_strong = get_extra_strong_model(self.cfg)
         
-        file_dir = Path(self.cfg.checkpoint_dir) / "files"
-        file_dir.mkdir(parents=True, exist_ok=True)
-        perception = make_perception_node(self.client, file_dir)
-        self.graph = build_graph(
-            perception_node=perception,
-            planner_model=self.extra_strong,
-            strong_model=self.strong,
-            cheap_model=self.cheap,
-            verifier_model=self.strong,
-            tools=self.tools,
-            caveman=self.cfg.caveman,
-            caveman_mode=self.cfg.caveman_mode,
+
+        self.chat = ChatHuggingFace(llm=llm)
+
+        self.chat_with_tools = self.chat.bind_tools(self.tools)
+
+        self.graph = self.build_graph()
+
+    def wikipedia_search(self, query: str) -> str:
+        try:
+            return self.wikipedia.run(query)
+        except Exception as e:
+            return f"Wikipedia search error: {e}"
+
+    def assistant(self, state: AgentState):
+        return {
+            "messages": [self.chat_with_tools.invoke(state["messages"])]
+        }
+
+    def build_graph(self):
+        builder = StateGraph(AgentState)
+
+        builder.add_node("assistant", self.assistant)
+        builder.add_node("tools", ToolNode(self.tools))
+
+        builder.add_edge(START, "assistant")
+
+        builder.add_conditional_edges(
+            "assistant",
+            tools_condition,
+        )
+
+        builder.add_edge("tools", "assistant")
+
+        return builder.compile()
+
+    def extract_final_answer(self, text: str) -> str:
+        match = re.search(
+            r"FINAL ANSWER:\s*(.*)",
+            text,
+            flags=re.IGNORECASE | re.DOTALL,
         )
-        print("GaiaAgent initialized.")
+
+        if match:
+            return match.group(1).strip()
+
+        return text.strip()
+
+    def __call__(self, question: str) -> str:
+        print(f"Agent received question: {question[:100]}...")
+
+        messages = [
+            SystemMessage(content=SYSTEM_PROMPT),
+            HumanMessage(content=question),
+        ]
+
+        try:
+            response = self.graph.invoke({"messages": messages})
+            raw_answer = response["messages"][-1].content
+
+            final_answer = self.extract_final_answer(raw_answer)
+
+            print(f"Raw answer: {raw_answer}")
+            print(f"Submitted answer: {final_answer}")
+
+            return final_answer
+
+        except Exception as e:
+            print(f"Agent error: {e}")
+            return f"AGENT ERROR: {e}"
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -70,9 +276,9 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent
+    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = GaiaAgent()
+        agent = BasicAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -83,7 +289,9 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
-        questions_data = agent.client.get_questions()
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
         if not questions_data:
              print("Fetched questions list is empty.")
              return "Fetched questions list is empty or invalid format.", None
@@ -91,25 +299,31 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     except requests.exceptions.RequestException as e:
         print(f"Error fetching questions: {e}")
         return f"Error fetching questions: {e}", None
+    except requests.exceptions.JSONDecodeError as e:
+         print(f"Error decoding JSON response from questions endpoint: {e}")
+         print(f"Response text: {response.text[:500]}")
+         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
         print(f"An unexpected error occurred fetching questions: {e}")
         return f"An unexpected error occurred fetching questions: {e}", None
 
-    # 3. Run the agent with checkpointing
+    # 3. Run your Agent
+    results_log = []
+    answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
-    answers_payload = run_agent_on_questions(
-        agent.graph, questions_data, agent.cfg.checkpoint_dir
-    )
-    answers_by_id = {a["task_id"]: a["submitted_answer"] for a in answers_payload}
-    results_log = [
-        {
-            "Task ID": item.get("task_id"),
-            "Question": item.get("question"),
-            "Submitted Answer": answers_by_id.get(item.get("task_id"), ""),
-        }
-        for item in questions_data
-        if item.get("task_id") and item.get("question") is not None
-    ]
+    for item in questions_data:
+        task_id = item.get("task_id")
+        question_text = item.get("question")
+        if not task_id or question_text is None:
+            print(f"Skipping item with missing task_id or question: {item}")
+            continue
+        try:
+            submitted_answer = agent(question_text)
+            answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+        except Exception as e:
+             print(f"Error running agent on task {task_id}: {e}")
+             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
         print("Agent did not produce any answers to submit.")
@@ -170,11 +384,9 @@ with gr.Blocks() as demo:
     gr.Markdown(
         """
         **Instructions:**
-
         1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
         2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
         3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
         ---
         **Disclaimers:**
         Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
@@ -217,4 +429,4 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)