Update app.py

app.py

@@ -1,55 +1,151 @@
+import requests
 import os
 import gradio as gr
-import requests
 import pandas as pd
 import time
 import re
-
+import json
+import wikipedia
+import speech_recognition as sr
+from pydub import AudioSegment
 from langchain_openai import ChatOpenAI
-from langchain.prompts import PromptTemplate
 from langchain.agents import AgentExecutor, create_react_agent
 from langchain.memory import ConversationSummaryMemory
-from typing import List, Optional
-
-# === TOOL IMPORTS ===
-from helper import repl_tool, file_saver_tool, audio_transcriber_tool, gemini_multimodal_tool, wikipedia_search_tool2
+from langchain.tools import Tool
+from langchain_experimental.utilities import PythonREPL
+from langchain_community.document_loaders import WikipediaLoader
+from langchain.prompts import PromptTemplate
 
-# Constants
+# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Prompt ---
+# === TOOL: python_repl ===
+python_repl = PythonREPL()
+repl_tool = Tool(
+    name="python_repl",
+    description="A Python REPL (Read-Eval-Print Loop) for calculations, parsing, and data manipulation. Input must be valid Python. Use print() to output your answer.",
+    func=python_repl.run,
+)
+
+# === TOOL: file_saver ===
+def download_and_save_file(args: dict) -> str:
+    try:
+        if isinstance(args, str):
+            args = json.loads(args)
+        url = args.get("url")
+        local_filename = args.get("local_filename")
+        if not url or not local_filename:
+            return "Error: Both 'url' and 'local_filename' must be provided."
+        response = requests.get(url, stream=True, timeout=30)
+        response.raise_for_status()
+        os.makedirs(os.path.dirname(local_filename) or '.', exist_ok=True)
+        with open(local_filename, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+        return f"File downloaded successfully to {local_filename}"
+    except Exception as e:
+        return f"Error downloading file: {e}"
+
+file_saver_tool = Tool(
+    name="file_saver",
+    description="Downloads a file from a URL and saves it as the given local filename. Input: JSON with 'url' and 'local_filename'.",
+    func=download_and_save_file,
+)
+
+# === TOOL: audio_transcriber_tool ===
+def transcribe_audio_from_path(local_audio_path: str, language: str = "en-US") -> str:
+    r = sr.Recognizer()
+    temp_wav_path = "temp_audio_to_transcribe.wav"
+    transcribed_text = ""
+    try:
+        if local_audio_path.startswith("http://") or local_audio_path.startswith("https://"):
+            return "Error: Only local file paths allowed. Use 'file_saver' first."
+        if not os.path.exists(local_audio_path):
+            return f"Error: File not found: '{local_audio_path}'."
+        audio = AudioSegment.from_file(local_audio_path)
+        audio.export(temp_wav_path, format="wav")
+        with sr.AudioFile(temp_wav_path) as source:
+            audio_listened = r.record(source)
+            try:
+                transcribed_text = r.recognize_google(audio_listened, language=language)
+            except sr.UnknownValueError:
+                return "Could not understand audio."
+            except sr.RequestError as e:
+                return f"Could not request results from Google Speech Recognition; {e}"
+    except Exception as e:
+        return f"Error: {e}"
+    finally:
+        if os.path.exists(temp_wav_path):
+            os.remove(temp_wav_path)
+    return transcribed_text.strip()
+
+audio_transcriber_tool = Tool(
+    name="audio_transcriber_tool",
+    description="Transcribes audio from a local file path to text. Input: path to audio file (e.g., 'myfile.mp3'). Use 'file_saver' to download first. Optionally set language.",
+    func=transcribe_audio_from_path,
+)
+
+# === TOOL: wikipedia_search_tool2 ===
+def wiki_search(query: str) -> str:
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata.get("source", "")}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return formatted_search_docs
+
+wikipedia_search_tool2 = Tool(
+    name="wikipedia_search_tool2",
+    description="Search Wikipedia for a query and return up to 2 results. Input: query string.",
+    func=wiki_search,
+)
+
+# === PROMPT ===
 prompt = PromptTemplate(
     input_variables=["input", "agent_scratchpad", "chat_history", "tool_names"],
     template="""
-    You are a smart and helpful AI Agent/Assistant that excels at fact-based reasoning. You are allowed and encouraged to use one or more tools as needed to answer complex questions and perform tasks.
-    [ ...cut for brevity: insert your strict format rules and examples here ... ]
-    {chat_history}
-    New input: {input}
-    ---
-    {agent_scratchpad}
-    """
+You are a smart and helpful AI Agent/Assistant that excels at fact-based reasoning. You are allowed and encouraged to use one or more tools as needed to answer complex questions and perform tasks.
+STRICT FINAL ANSWER RULES:
+- Final Answer must be a number, a few words, or a comma-separated list, as requested.
+- No units or extra punctuation unless asked.
+Your response must start with 'Thought:' and finish with 'Final Answer:'.
+You have access to the following tools:
+{tools}
+Use this format:
+Thought: [thinking]
+Action: [tool_name]
+Action Input: [input]
+Observation: [result]
+...
+Thought: [done]
+Final Answer: [concise answer]
+
+{chat_history}
+New input: {input}
+---
+{agent_scratchpad}
+"""
 )
 
-# === AGENT DEFINITION ===
+# === AGENT ===
 class BasicAgent:
     def __init__(
         self,
-        agent, tools: List, verbose: bool = False, handle_parsing_errors: bool = True,
-        max_iterations: int = 9, memory: Optional[ConversationSummaryMemory] = None
+        agent,
+        tools,
+        verbose=False,
+        handle_parsing_errors=True,
+        max_iterations=9,
+        memory=None
     ):
-        self.agent = agent
-        self.tools = tools
-        self.verbose = verbose
-        self.handle_parsing_errors = handle_parsing_errors
-        self.max_iterations = max_iterations
-        self.memory = memory
         self.agent_obj = AgentExecutor(
-            agent=self.agent,
-            tools=self.tools,
-            verbose=self.verbose,
-            handle_parsing_errors=self.handle_parsing_errors,
-            max_iterations=self.max_iterations,
-            memory=self.memory
+            agent=agent,
+            tools=tools,
+            verbose=verbose,
+            handle_parsing_errors=handle_parsing_errors,
+            max_iterations=max_iterations,
+            memory=memory
         )
 
     def __call__(self, question: str) -> str:
@@ -61,9 +157,8 @@ class BasicAgent:
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
-
     if profile:
-        username = f"{profile.username}"
+        username= f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -73,42 +168,30 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # OpenAI API key only!
     openai_api_key = os.getenv("OPENAI_API_KEY")
     if not openai_api_key:
         print("OpenAI API key not found in environment variables.")
         return "OpenAI API key not found. Please set OPENAI_API_KEY environment variable.", None
+    print(f"Using OpenAI API key: {openai_api_key[:4]}... (truncated for security)")
 
-    # Use GPT-4o (or another allowed OpenAI model)
     llm_client = ChatOpenAI(model='gpt-4o', temperature=0, api_key=openai_api_key)
 
-    # Tools: only offline/tools not requiring other APIs
-    tools = [
-        repl_tool,
-        file_saver_tool,
-        audio_transcriber_tool,
-        gemini_multimodal_tool,   # If this is purely local or adapted for OpenAI images, otherwise remove!
-        wikipedia_search_tool2
-    ]
-
     summary_memory = ConversationSummaryMemory(llm=llm_client, memory_key="chat_history")
 
     summary_react_agent = create_react_agent(
         llm=llm_client,
-        tools=tools,
+        tools=[repl_tool, file_saver_tool, audio_transcriber_tool, wikipedia_search_tool2],
         prompt=prompt
     )
 
-    # 1. Instantiate Agent
     try:
-        agent = BasicAgent(summary_react_agent, tools, True, True, 30, summary_memory)
+        agent = BasicAgent(summary_react_agent, [repl_tool, file_saver_tool, audio_transcriber_tool, wikipedia_search_tool2], True, True, 30, summary_memory)
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
     print(agent_code)
 
-    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
         response = requests.get(questions_url, timeout=15)
@@ -118,11 +201,17 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
              print("Fetched questions list is empty.")
              return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
-    except Exception as e:
+    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 your Agent
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -132,17 +221,17 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         file_name = item.get("file_name")
         full_question_for_agent = question_text
         if file_name:
-            attachment_url = f"{DEFAULT_API_URL}/files/{task_id}"
+            attachment_url = f"https://agents-course-unit4-scoring.hf.space/files/{task_id}"
             full_question_for_agent += f"\n\nAttachment '{file_name}' available at EXACT URL: {attachment_url}"
-            print(f"Running agent on task {task_id}: {full_question_for_agent}", flush=True)
+            print(f"Running agent on task {task_id}: {full_question_for_agent}",flush=True)
         try:
             submitted_answer = agent(full_question_for_agent)
             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})
-            time.sleep(2)  # Decrease or remove if not rate-limited!
+            time.sleep(1)
         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}"})
+             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.")
@@ -164,27 +253,28 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
             f"Message: {result_data.get('message', 'No message received.')}"
         )
-        cleaned_final_status = re.sub(r'[^\x20-\x7E\n\r\t]+', '', final_status).strip()
+        print("Submission successful.")
+        cleaned_final_status = re.sub(r'[^\x20-\x7E\n\r\t]+', '', final_status)
+        cleaned_final_status = cleaned_final_status.strip()
         results_df = pd.DataFrame(results_log)
         return cleaned_final_status, results_df
     except Exception as e:
-        print(f"Error submitting answers: {e}")
+        status_message = f"Submission Failed: {e}"
+        print(status_message)
         results_df = pd.DataFrame(results_log)
-        return f"Submission Failed: {e}", results_df
+        return status_message, results_df
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1. Log in to your Hugging Face account using the button below.
-        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-        ---
-        **Note:** Only OpenAI API key is needed!
+        1. Clone this space and modify the code as needed.
+        2. Log in to your Hugging Face account below.
+        3. Click 'Run Evaluation & Submit All Answers' to see your score!
         """
     )
-
     gr.LoginButton()
     run_button = gr.Button("Run Evaluation & Submit All Answers")
     status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)