Update app.py

app.py

@@ -1,34 +1,149 @@
 import os
-import gradio as gr
 import requests
-import inspect
 import pandas as pd
+import gradio as gr
+import openai
+from langchain.embeddings import OpenAIEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.chains import RetrievalQA
+from langchain.llms import OpenAI
+from langchain.document_loaders import TextLoader, PyPDFLoader, CSVLoader
+from langchain.tools import DuckDuckGoSearchRun
+from langchain.agents import initialize_agent, Tool
+from langchain.agents.agent_types import AgentType
+from langchain.schema import Document
+from PIL import Image
+import pytesseract
 
-# (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 ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
-
-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
+# --- Basic Agent Definition with RAG + Tools ---
+class RAGAgent:
+    def _init_(self):
+        self.api_key = os.getenv("OPENAI_API_KEY")
+        if not self.api_key:
+            raise ValueError("OPENAI_API_KEY is not set in environment variables.")
+        openai.api_key = self.api_key
+        print("GPT-4o RAG Agent with tools initialized.")
+        self.vectorstore = None
+        self.tools = [
+            Tool(
+                name="Search News",
+                func=DuckDuckGoSearchRun().run,
+                description="Useful for finding recent news articles about a topic."
+            ),
+            Tool(
+                name="Company Profile",
+                func=DuckDuckGoSearchRun().run,
+                description="Retrieve basic profile information about a company."
+            ),
+            Tool(
+                name="Search Wikipedia",
+                func=DuckDuckGoSearchRun().run,
+                description="Good for general encyclopedic knowledge."
+            )
+        ]
+
+    def build_vectorstore(self, file_path):
+        print(f"Building vectorstore from file: {file_path}")
+        ext = os.path.splitext(file_path)[-1].lower()
+        if ext == ".txt":
+            loader = TextLoader(file_path)
+        elif ext == ".pdf":
+            loader = PyPDFLoader(file_path)
+        elif ext == ".csv":
+            loader = CSVLoader(file_path)
+        elif ext in [".png", ".jpg", ".jpeg"]:
+            def ocr_image(file_path):
+                text = pytesseract.image_to_string(Image.open(file_path))
+                return [Document(page_content=text)]
+
+            class OCRImageLoader:
+                def _init_(self, path):
+                    self.path = path
+
+                def load(self):
+                    return ocr_image(self.path)
+
+            loader = OCRImageLoader(file_path)
+        else:
+            raise ValueError(f"Unsupported file type: {ext}")
+
+        documents = loader.load()
+        text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
+        texts = text_splitter.split_documents(documents)
+        embeddings = OpenAIEmbeddings()
+        self.vectorstore = FAISS.from_documents(texts, embeddings)
+
+    def classify_task_level(self, question: str) -> int:
+        if any(kw in question.lower() for kw in ["in the image", "clockwise", "based on", "served in", "multi-step"]):
+            return 3
+        elif len(question.split()) > 40 or any(kw in question.lower() for kw in ["using the tool", "summarize and compare"]):
+            return 2
+        else:
+            return 1
+
+    def simple_answer(self, question, file_path):
+        if file_path and os.path.isfile(file_path):
+            self.build_vectorstore(file_path)
+            retriever = self.vectorstore.as_retriever()
+            qa_chain = RetrievalQA.from_chain_type(llm=OpenAI(model_name="gpt-4o", temperature=0.3), retriever=retriever)
+            return qa_chain.run(question)
+        else:
+            return OpenAI(model_name="gpt-4o", temperature=0.3)(question)
+
+    def coordinated_tool_reasoning(self, question, file_path):
+        if file_path and os.path.isfile(file_path):
+            self.build_vectorstore(file_path)
+            retriever = self.vectorstore.as_retriever()
+        else:
+            retriever = None
+
+        agent_executor = initialize_agent(
+            self.tools,
+            OpenAI(model_name="gpt-4o", temperature=0.3),
+            agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
+            verbose=True
+        )
+
+        context = retriever.get_relevant_documents(question) if retriever else []
+        augmented_question = f"{question}\n\nContext:\n{''.join([doc.page_content for doc in context])}" if context else question
+        return agent_executor.run(augmented_question)
+
+    def complex_multihop_chain(self, question, file_path):
+        return self.coordinated_tool_reasoning(question, file_path)
+
+    def solve_question(self, question: str, file_path: str = None, level: int = None) -> str:
+        print(f"Received question (first 50 chars): {question[:50]}...")
+        if level is None:
+            level = self.classify_task_level(question)
+        print(f"Classified task as Level {level}")
+
+        try:
+            if level == 1:
+                return self.simple_answer(question, file_path)
+            elif level == 2:
+                return self.coordinated_tool_reasoning(question, file_path)
+            elif level == 3:
+                return self.complex_multihop_chain(question, file_path)
+            else:
+                raise ValueError("Unsupported level.")
+        except Exception as e:
+            print(f"Error during reasoning: {e}")
+            return f"Error: {e}"
+
+    def _call_(self, question: str, file_path: str = None, level: int = None) -> str:
+        return self.solve_question(question, file_path, level)
+
+# --- Evaluation & Submission Code ---
+
+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.")
@@ -38,66 +153,40 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = RAGAgent()
     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)
+
     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
+        return f"Error 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")
+        file_path = item.get("file_path")
+        level = item.get("level")
         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)
+            submitted_answer = agent(question_text, file_path, level)
             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}"})
+            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()
@@ -109,61 +198,33 @@ 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.')}"
         )
-        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
+        return final_status, pd.DataFrame(results_log)
     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
-
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
-# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
     gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
-        **Instructions:**
-
+        *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.
+        This agent is designed for tasks that require:
+        - Structured responses
+        - Multimodal reasoning (e.g., analyzing images)
+        - Multi-hop retrieval of interdependent facts (e.g., identify fruit in an image, lookup ship history, fetch historical menus)
+        - Correct sequencing and planning over multiple steps
+
+        These capabilities are critical to solving complex GAIA tasks that go beyond what standalone LLMs can handle.
         """
     )
 
     gr.LoginButton()
 
     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(
@@ -171,26 +232,5 @@ with gr.Blocks() as demo:
         outputs=[status_output, results_table]
     )
 
-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...")
+if _name_ == "_main_":
     demo.launch(debug=True, share=False)