Update app.py

app.py

@@ -1,316 +1,143 @@
-import os
-import gradio as gr
-import requests
-import inspect
-import pandas as pd
-
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-# ----------------------------------------------------------
 import os, json, time
 from functools import lru_cache
 
+import gradio as gr
+import requests
+import pandas as pd
 from openai import OpenAI, RateLimitError, APIError
-from duckduckgo_search import DDGS      # pip install duckduckgo-search
+from duckduckgo_search import DDGS   # add to requirements.txt
 
-
-# ---------- simple search helper -------------------------------------------
+# ────────────────────────────────
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+OPENAI_MODEL    = "gpt-4o-mini"
+# ────────────────────────────────
 def duckduckgo_search(query: str, max_results: int = 5) -> str:
-    """
-    Returns a plain-text bulleted list of the first `max_results`
-    DuckDuckGo results:  Title – URL
-    """
-    print(f"🔍  DuckDuckGo search: {query!r}")
     bullets = []
     with DDGS() as ddgs:
         for r in ddgs.text(query, max_results=max_results):
             bullets.append(f"- {r['title']} – {r['href']}")
-    if not bullets:
-        return "No results."
-    return "\n".join(bullets[:max_results])
-
-
-# ---------- agent ----------------------------------------------------------
+    return "\n".join(bullets) or "No results."
+
+DDG_SCHEMA = {
+    "name": "duckduckgo_search",
+    "description": "Search the web for up-to-date info.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "query":       {"type": "string"},
+            "max_results": {"type": "integer", "default": 5},
+        },
+        "required": ["query"],
+    },
+}
+
+# ╭──────────────────────────────────────────────────────────╮
+# │ AGENT (now supports optional image_url)                 │
+# ╰──────────────────────────────────────────────────────────╯
 class GPT4oMiniAgentWithDDG:
-    """
-    GPT-4o-mini with an optional DuckDuckGo search tool.
-    The model decides – via function-calling – whether it needs live info.
-    """
-    def __init__(self, max_retries: int = 3, backoff: float = 2.0):
+    def __init__(self, retries:int = 3, backoff:float = 2.0):
         api_key = os.getenv("OPENAI_API_KEY")
         if not api_key:
-            raise EnvironmentError("OPENAI_API_KEY secret not set!")
-
-        self.client = OpenAI(api_key=api_key)
-        self.max_retries, self.backoff = max_retries, backoff
-
-        # JSON schema that we register as a tool
-        self.ddg_schema = {
-            "name": "duckduckgo_search",
-            "description": "Search the web for up-to-date information when knowledge cutoff may be too old.",
-            "parameters": {
-                "type": "object",
-                "properties": {
-                    "query": {"type": "string", "description": "search string"},
-                    "max_results": {
-                        "type": "integer",
-                        "description": "how many results to return (1-10)",
-                        "default": 5,
-                    },
-                },
-                "required": ["query"],
-            },
-        }
-
-        self.system_prompt = (
-            "You are a concise, accurate assistant.\n"
-            "If you are **certain** you already know the answer, answer directly.\n"
-            "If the question is about very recent events or you are unsure, call "
-            "`duckduckgo_search` to look it up first.\n"
-            "Return final answers in plain consice language one word or only the actual answer "
+            raise EnvironmentError("Add OPENAI_API_KEY in your Space secrets!")
+        self.client   = OpenAI(api_key=api_key)
+        self.retries  = retries
+        self.backoff  = backoff
+        self.prompt   = (
+            "You are a concise, accurate assistant. "
+            "If certain, answer immediately; otherwise call duckduckgo_search."
         )
 
-        print("✅ GPT4oMiniAgentWithDDG ready.")
-
-    # ----------------------------------------------------------------------
-    # in-memory cache so repeats don’t cost tokens or web calls
     @lru_cache(maxsize=512)
-    def __call__(self, question: str) -> str:
-        msg_log = [
-            {"role": "system", "content": self.system_prompt},
-            {"role": "user", "content": question},
+    def __call__(self, question: str, image_url: str | None = None) -> str:
+        user_content = [{"type": "text", "text": question}]
+        if image_url:
+            user_content.append(
+                {"type": "image_url", "image_url": {"url": image_url}}
+            )
+
+        msgs = [
+            {"role": "system", "content": self.prompt},
+            {"role": "user",   "content": user_content},
         ]
 
-        # 1st request: let model decide if it needs the search tool
-        first = self._chat(msg_log, tools=[self.ddg_schema], tool_choice="auto")
+        # 1st pass – model may request the tool
+        resp = self._chat(msgs, tools=[DDG_SCHEMA], tool_choice="auto")
 
-        # If the model called the tool, run it and feed the results back
-        if first.choices[0].message.tool_calls:
-            answer = self._handle_tool_calls(msg_log, first)
-        else:
-            answer = first.choices[0].message.content.strip()
+        # Run tool(s) if requested
+        if resp.choices[0].message.tool_calls:
+            for call in resp.choices[0].message.tool_calls:
+                args = json.loads(call.function.arguments or "{}")
+                tool_out = duckduckgo_search(**args) if call.function.name=="duckduckgo_search" else ""
+                msgs.append({
+                    "role": "tool",
+                    "tool_call_id": call.id,
+                    "name": call.function.name,
+                    "content": tool_out
+                })
+            resp = self._chat(msgs)
 
-        print(f"🔸 Final answer (trunc.): {answer[:70]}…")
-        return answer
+        return resp.choices[0].message.content.strip()
 
-    # ---------- helpers ----------------------------------------------------
-    def _chat(self, messages, **kwargs):
-        """wrapper with retries"""
-        for attempt in range(1, self.max_retries + 1):
+    def _chat(self, messages, **kw):
+        for i in range(1, self.retries + 1):
             try:
                 return self.client.chat.completions.create(
-                    model="gpt-4o-mini",
+                    model=OPENAI_MODEL,
                     messages=messages,
                     temperature=0.0,
                     max_tokens=512,
-                    **kwargs,
+                    **kw
                 )
-            except (RateLimitError, APIError) as e:
-                wait = self.backoff * attempt
-                print(f"⚠️  OpenAI error {e}. Retry {attempt}/{self.max_retries} in {wait}s.")
-                time.sleep(wait)
+            except (RateLimitError, APIError):
+                time.sleep(self.backoff * i)
         raise RuntimeError("OpenAI API failed after retries.")
 
-    def _handle_tool_calls(self, msg_log, first_response):
-        """Execute each requested tool then get the model’s final answer."""
-        for call in first_response.choices[0].message.tool_calls:
-            name = call.function.name
-            args = json.loads(call.function.arguments or "{}")
-            if name == "duckduckgo_search":
-                content = duckduckgo_search(**args)
-            else:
-                content = f"Tool {name} not implemented."
-
-            # Append the tool result so the model can read it
-            msg_log.append(
-                {
-                    "role": "tool",
-                    "tool_call_id": call.id,
-                    "name": name,
-                    "content": content,
-                }
-            )
-
-        # Ask the model again, now that it has the web data
-        final = self._chat(msg_log)
-        return final.choices[0].message.content.strip()
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
-
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
-
-    # 1. Instantiate Agent ( modify this part to create your agent)
-    try:
-        agent = GPT4oMiniAgentWithDDG()
-    except Exception as e:
-        print(f"Error instantiating agent: {e}")
-        return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
+# ╭──────────────────────────────────────────────────────────╮
+# │ RUN  +  SUBMIT                                          │
+# ╰──────────────────────────────────────────────────────────╯
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    if not profile:
+        return "Please log in ↑", None
+    username = profile.username
+    agent = GPT4oMiniAgentWithDDG()
+    space_id = os.getenv("SPACE_ID", "local")
     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)
-        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
-        print(f"Fetched {len(questions_data)} questions.")
-    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...")
-    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.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
-    try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
-            f"Submission Successful!\n"
-            f"User: {result_data.get('username')}\n"
-            f"Overall Score: {result_data.get('score', 'N/A')}% "
-            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', 'No message received.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
-
-# --- Build Gradio Interface using Blocks ---
+    # ① Fetch
+    qs = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15).json()
+
+    # ② Answer
+    answers, rows = [], []
+    for item in qs:
+        qid   = item["task_id"]
+        text  = item["question"]
+        img   = item.get("filename")          # <-- NEW
+        ans   = agent(text, img)
+        answers.append({"task_id": qid, "submitted_answer": ans})
+        rows.append({"Task ID": qid, "Question": text, "Image URL": img or "", "Answer": ans})
+
+    # ③ Submit
+    payload = {
+        "username": username,
+        "agent_code": agent_code,
+        "answers": answers
+    }
+    res = requests.post(f"{DEFAULT_API_URL}/submit", json=payload, timeout=60).json()
+    status = f"Score {res['score']} %  ({res['correct_count']}/{res['total_attempted']})"
+
+    return status, pd.DataFrame(rows)
+
+# ╭──────────────────────────────────────────────────────────╮
+# │ GRADIO UI                                               │
+# ╰──────────────────────────────────────────────────────────╯
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    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).
-        This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
-        """
-    )
-
+    gr.Markdown("# Unit-4 Agent Runner – Image Ready")
     gr.LoginButton()
+    run_btn      = gr.Button("Run Evaluation & Submit All Answers")
+    status_box   = gr.Textbox(label="Status", interactive=False)
+    results_grid = gr.DataFrame(label="Log", wrap=True)
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
-    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
-
-    run_button.click(
-        fn=run_and_submit_all,
-        outputs=[status_output, results_table]
-    )
+    run_btn.click(run_and_submit_all, outputs=[status_box, results_grid])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
-    space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
-    if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    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)