Update app.py

app.py

@@ -1,66 +1,239 @@
+import os
+import requests
+import pandas as pd
+import gradio as gr
+
 import datasets
 from langchain.docstore.document import Document
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.retrievers import BM25Retriever
+
 from smolagents import Tool, CodeAgent, InferenceClientModel
 
-# Define RetrieverTool exactly as in your example
-class RetrieverTool(Tool):
-    name = "retriever"
-    description = (
-        "Uses lexical search to retrieve the parts of transformers documentation most relevant to answer your query."
-    )
-    inputs = {
-        "query": {
-            "type": "string",
-            "description": "The query to perform. Use affirmative form rather than a question.",
-        }
-    }
-    output_type = "string"
-
-    def __init__(self, docs, **kwargs):
-        super().__init__(**kwargs)
-        self.retriever = BM25Retriever.from_documents(docs, k=10)
-
-    def forward(self, query: str) -> str:
-        assert isinstance(query, str), "Query must be a string"
-        docs = self.retriever.invoke(query)
-        return "\nRetrieved documents:\n" + "".join(
-            [f"\n\n===== Document {i} =====\n{doc.page_content}" for i, doc in enumerate(docs)]
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the agent on them, submits all answers,
+    and displays the results.
+    """
+    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 = "https://your-api-url"  # Replace with your actual API URL or set as env var
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    # --- Instantiate Agent ---
+    try:
+        # Load knowledge base dataset and filter
+        knowledge_base = datasets.load_dataset("m-ric/huggingface_doc", split="train")
+        knowledge_base = knowledge_base.filter(lambda row: row["source"].startswith("huggingface/transformers"))
+
+        # Create source Documents for retriever
+        source_docs = [
+            Document(page_content=doc["text"], metadata={"source": doc["source"].split("/")[1]})
+            for doc in knowledge_base
+        ]
+
+        # Split documents into chunks
+        text_splitter = RecursiveCharacterTextSplitter(
+            chunk_size=500,
+            chunk_overlap=50,
+            add_start_index=True,
+            strip_whitespace=True,
+            separators=["\n\n", "\n", ".", " ", ""],
         )
+        docs_processed = text_splitter.split_documents(source_docs)
+
+        # Define the Retriever tool
+        class RetrieverTool(Tool):
+            name = "retriever"
+            description = (
+                "Uses lexical search to retrieve the parts of transformers documentation "
+                "that could be most relevant to answer your query."
+            )
+            inputs = {
+                "query": {
+                    "type": "string",
+                    "description": (
+                        "The query to perform. This should be lexically close to your target documents. "
+                        "Use the affirmative form rather than a question."
+                    ),
+                }
+            }
+            output_type = "string"
+
+            def __init__(self, docs, **kwargs):
+                super().__init__(**kwargs)
+                self.retriever = BM25Retriever.from_documents(docs, k=10)
+
+            def forward(self, query: str) -> str:
+                assert isinstance(query, str), "Your search query must be a string"
+                docs = self.retriever.invoke(query)
+                return "\nRetrieved documents:\n" + "".join(
+                    [f"\n\n===== Document {i} =====\n" + doc.page_content for i, doc in enumerate(docs)]
+                )
+
+        retriever_tool = RetrieverTool(docs_processed)
+
+        # Instantiate the smolagents CodeAgent
+        agent = CodeAgent(
+            tools=[retriever_tool],
+            model=InferenceClientModel(model_id="Qwen/Qwen2.5-Coder-32B-Instruct"),
+            max_steps=4,
+            verbosity_level=2,
+            stream_outputs=True,
+        )
+
+    except Exception as e:
+        return f"Error initializing agent: {e}", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main" if space_id else "Code repo URL not available"
+    print(agent_code)
 
-# Replace agent creation inside try block
-try:
-    # Load and prepare docs once here
-    knowledge_base = datasets.load_dataset("m-ric/huggingface_doc", split="train")
-    knowledge_base = knowledge_base.filter(lambda row: row["source"].startswith("huggingface/transformers"))
-
-    source_docs = [
-        Document(page_content=doc["text"], metadata={"source": doc["source"].split("/")[1]})
-        for doc in knowledge_base
-    ]
-
-    text_splitter = RecursiveCharacterTextSplitter(
-        chunk_size=500,
-        chunk_overlap=50,
-        add_start_index=True,
-        strip_whitespace=True,
-        separators=["\n\n", "\n", ".", " ", ""],
+    # --- 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 Exception as e:
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
+
+    # --- Run Agent on Questions ---
+    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:
+            # Run the agent
+            submitted_answer = agent.run(question_text)  # Use .run() for smolagents CodeAgent
+            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)
+
+    # --- 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)
+
+    # --- Submit Answers ---
+    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 ---
+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 separate action or even to answer the questions asynchronously.
+        """
     )
-    docs_processed = text_splitter.split_documents(source_docs)
-
-    # Instantiate RetrieverTool with processed docs
-    retriever_tool = RetrieverTool(docs_processed)
-
-    # Instantiate the smolagents CodeAgent with model
-    agent = CodeAgent(
-        tools=[retriever_tool],
-        model=InferenceClientModel(model_id="Qwen/Qwen2.5-Coder-32B-Instruct"),
-        max_steps=4,
-        verbosity_level=2,
-        stream_outputs=True,
+
+    gr.LoginButton()
+
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+
+    run_button.click(
+        fn=run_and_submit_all,
+        outputs=[status_output, results_table]
     )
 
-except Exception as e:
-    print(f"Error instantiating agent: {e}")
-    return f"Error initializing agent: {e}", None
+
+if __name__ == "__main__":
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
+    space_host_startup = os.getenv("SPACE_HOST")
+    space_id_startup = os.getenv("SPACE_ID")
+
+    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(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)