Upload 2 files

agent.py

@@ -0,0 +1,323 @@
+"""
+agent.py — LangChain ReAct agent for the GAIA benchmark.
+
+Tools included:
+  • DuckDuckGo web search (free, no API key)
+  • Wikipedia lookup
+  • Python REPL (math, data manipulation)
+  • File download + reading (text, CSV, PDF via pdfminer)
+  • Image understanding via HuggingFace Inference API (free tier)
+  • ArXiv search
+"""
+
+import os
+import io
+import re
+import tempfile
+import traceback
+from typing import Optional
+
+import requests
+
+# LangChain core
+from langchain.agents import AgentExecutor, create_react_agent
+from langchain.tools import Tool, tool
+from langchain_core.prompts import PromptTemplate
+from langchain_huggingface import HuggingFaceEndpoint
+
+# Community tools
+from langchain_community.tools import DuckDuckGoSearchRun, WikipediaQueryRun
+from langchain_community.utilities import WikipediaAPIWrapper
+from langchain_experimental.tools.python.tool import PythonREPLTool
+
+
+# ---------------------------------------------------------------------------
+# 1. LLM — free HuggingFace Inference Endpoint
+# ---------------------------------------------------------------------------
+
+def get_llm():
+    """
+    Use a capable open model via HF Inference API (free tier).
+    Qwen2.5-72B-Instruct is a strong publicly available model.
+    You can swap for meta-llama/Meta-Llama-3-70B-Instruct, etc.
+    Requires HF_TOKEN env var (free account works).
+    """
+    hf_token = os.getenv("HF_TOKEN")
+    if not hf_token:
+        raise EnvironmentError(
+            "HF_TOKEN environment variable not set. "
+            "Add it in your HuggingFace Space secrets."
+        )
+
+    llm = HuggingFaceEndpoint(
+        repo_id="Qwen/Qwen2.5-72B-Instruct",
+        huggingfacehub_api_token=hf_token,
+        task="text-generation",
+        max_new_tokens=1024,
+        temperature=0.1,
+        do_sample=False,
+        repetition_penalty=1.1,
+    )
+    return llm
+
+
+# ---------------------------------------------------------------------------
+# 2. Tool definitions
+# ---------------------------------------------------------------------------
+
+# -- Web search --
+def make_search_tool():
+    search = DuckDuckGoSearchRun()
+    return Tool(
+        name="web_search",
+        func=search.run,
+        description=(
+            "Search the web for current information using DuckDuckGo. "
+            "Use this for facts, recent events, people, places, or anything "
+            "that requires up-to-date knowledge. Input: a search query string."
+        ),
+    )
+
+
+# -- Wikipedia --
+def make_wikipedia_tool():
+    wiki = WikipediaQueryRun(api_wrapper=WikipediaAPIWrapper(top_k_results=3, doc_content_chars_max=3000))
+    return Tool(
+        name="wikipedia",
+        func=wiki.run,
+        description=(
+            "Look up encyclopedic information on Wikipedia. "
+            "Best for well-known topics, historical facts, science, biographies. "
+            "Input: a topic or question string."
+        ),
+    )
+
+
+# -- Python REPL --
+def make_python_tool():
+    repl = PythonREPLTool()
+    return Tool(
+        name="python_repl",
+        func=repl.run,
+        description=(
+            "Execute Python code for calculations, data processing, string manipulation, "
+            "logic, and analysis. pandas, math, re, json, csv, datetime are available. "
+            "Input: valid Python code as a string. Always print() the result you need."
+        ),
+    )
+
+
+# -- File reader --
+@tool
+def read_file_from_url(url: str) -> str:
+    """
+    Download a file from a URL and return its text content.
+    Supports: plain text (.txt, .py, .json, .csv, .md), PDF, and basic image description.
+    Input: a URL string pointing to the file.
+    """
+    try:
+        resp = requests.get(url, timeout=30)
+        resp.raise_for_status()
+        content_type = resp.headers.get("content-type", "")
+
+        # PDF
+        if "pdf" in content_type or url.lower().endswith(".pdf"):
+            try:
+                from pdfminer.high_level import extract_text
+                with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as f:
+                    f.write(resp.content)
+                    tmp_path = f.name
+                text = extract_text(tmp_path)
+                os.unlink(tmp_path)
+                return text[:5000] if text else "Could not extract PDF text."
+            except ImportError:
+                return "pdfminer not available. Install pdfminer.six to read PDFs."
+
+        # CSV
+        if "csv" in content_type or url.lower().endswith(".csv"):
+            import csv
+            decoded = resp.content.decode("utf-8", errors="replace")
+            lines = decoded.splitlines()
+            return "\n".join(lines[:50])  # first 50 rows
+
+        # Excel
+        if url.lower().endswith((".xlsx", ".xls")):
+            try:
+                import pandas as pd
+                from io import BytesIO
+                df = pd.read_excel(BytesIO(resp.content))
+                return df.to_string(max_rows=50)
+            except Exception as e:
+                return f"Could not read Excel file: {e}"
+
+        # Image — describe via HF
+        if "image" in content_type or url.lower().endswith((".png", ".jpg", ".jpeg", ".webp", ".gif")):
+            return describe_image_bytes(resp.content)
+
+        # Default: text
+        return resp.content.decode("utf-8", errors="replace")[:5000]
+
+    except Exception as e:
+        return f"Error reading file from {url}: {e}"
+
+
+# -- Image understanding via HF Inference API --
+def describe_image_bytes(image_bytes: bytes) -> str:
+    """Use HF Inference API to caption an image."""
+    hf_token = os.getenv("HF_TOKEN", "")
+    headers = {}
+    if hf_token:
+        headers["Authorization"] = f"Bearer {hf_token}"
+
+    # Use Salesforce BLIP image captioning (free on HF Inference API)
+    api_url = "https://api-inference.huggingface.co/models/Salesforce/blip-image-captioning-large"
+    try:
+        response = requests.post(api_url, headers=headers, data=image_bytes, timeout=30)
+        result = response.json()
+        if isinstance(result, list) and result:
+            return result[0].get("generated_text", "No caption generated.")
+        return str(result)
+    except Exception as e:
+        return f"Image description failed: {e}"
+
+
+@tool
+def describe_image_from_url(url: str) -> str:
+    """
+    Download an image from a URL and return a text description of its contents.
+    Use this when a question refers to an image file.
+    Input: a direct URL to an image (jpg, png, webp, etc.).
+    """
+    try:
+        resp = requests.get(url, timeout=30)
+        resp.raise_for_status()
+        return describe_image_bytes(resp.content)
+    except Exception as e:
+        return f"Could not describe image: {e}"
+
+
+# -- ArXiv search --
+@tool
+def arxiv_search(query: str) -> str:
+    """
+    Search ArXiv for scientific papers. Use for questions about research, ML papers,
+    physics, mathematics, computer science publications.
+    Input: a search query string.
+    Returns: titles, authors, and abstracts of top results.
+    """
+    try:
+        import urllib.parse
+        encoded = urllib.parse.quote(query)
+        url = f"https://export.arxiv.org/api/query?search_query=all:{encoded}&start=0&max_results=3"
+        resp = requests.get(url, timeout=15)
+        resp.raise_for_status()
+
+        # Parse simple XML
+        text = resp.text
+        entries = re.findall(r"<entry>(.*?)</entry>", text, re.DOTALL)
+        results = []
+        for entry in entries:
+            title = re.search(r"<title>(.*?)</title>", entry, re.DOTALL)
+            summary = re.search(r"<summary>(.*?)</summary>", entry, re.DOTALL)
+            authors = re.findall(r"<name>(.*?)</name>", entry)
+            t = title.group(1).strip() if title else "?"
+            s = summary.group(1).strip()[:500] if summary else ""
+            a = ", ".join(authors[:3])
+            results.append(f"Title: {t}\nAuthors: {a}\nAbstract: {s}")
+        return "\n\n---\n\n".join(results) if results else "No results found."
+    except Exception as e:
+        return f"ArXiv search failed: {e}"
+
+
+# -- Final answer formatter --
+@tool
+def final_answer(answer: str) -> str:
+    """
+    Use this tool to submit the final answer to the question.
+    Input: the exact final answer string.
+    """
+    return answer
+
+
+# ---------------------------------------------------------------------------
+# 3. ReAct Prompt
+# ---------------------------------------------------------------------------
+
+REACT_PROMPT = PromptTemplate.from_template(
+    """You are an expert AI assistant solving questions from the GAIA benchmark.
+GAIA tests real-world question answering that requires reasoning, web search, file reading, and multi-step problem solving.
+
+You have access to the following tools:
+{tools}
+
+Use this format strictly:
+
+Question: the input question you must answer
+Thought: reason step-by-step about what to do
+Action: the action to take, must be one of [{tool_names}]
+Action Input: the input to the action
+Observation: the result of the action
+... (repeat Thought/Action/Action Input/Observation as needed)
+Thought: I now know the final answer
+Final Answer: the exact answer to the question
+
+Rules:
+- Be precise. GAIA expects exact answers (numbers, names, dates, etc.).
+- Use web_search and wikipedia for factual lookups.
+- Use python_repl for any calculations, unit conversions, or data analysis.
+- Use read_file_from_url if a file URL is provided.
+- Use describe_image_from_url if an image URL is provided.
+- Use arxiv_search for scientific paper questions.
+- If the question asks for a number, return just the number.
+- If the question asks for a name, return just the name.
+- Do not add explanation to Final Answer — just the answer.
+- Limit reasoning to what is necessary.
+
+Begin!
+
+Question: {input}
+Thought:{agent_scratchpad}"""
+)
+
+
+# ---------------------------------------------------------------------------
+# 4. Build agent
+# ---------------------------------------------------------------------------
+
+def build_agent():
+    llm = get_llm()
+
+    tools = [
+        make_search_tool(),
+        make_wikipedia_tool(),
+        make_python_tool(),
+        read_file_from_url,
+        describe_image_from_url,
+        arxiv_search,
+    ]
+
+    agent = create_react_agent(
+        llm=llm,
+        tools=tools,
+        prompt=REACT_PROMPT,
+    )
+
+    executor = AgentExecutor(
+        agent=agent,
+        tools=tools,
+        verbose=True,
+        max_iterations=10,
+        max_execution_time=120,
+        handle_parsing_errors=True,
+        return_intermediate_steps=False,
+    )
+
+    def run(question: str) -> str:
+        try:
+            result = executor.invoke({"input": question})
+            return str(result.get("output", "No answer produced.")).strip()
+        except Exception as e:
+            print(f"Agent error: {traceback.format_exc()}")
+            return f"Error: {e}"
+
+    return run

app.py

@@ -1,34 +1,22 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from agent import build_agent
 
-# (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):
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    Fetches all questions, runs the LangChain agent 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
+    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.")
@@ -38,13 +26,13 @@ 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)
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent()
+        agent = build_agent()
     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)
 
@@ -55,49 +43,63 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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("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:
+    except Exception 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
+    # 3. Run 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_name = item.get("file_name", "")
+
         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)
+            # Attach file info to question if present
+            if file_name:
+                # Try to download the file and pass its URL/info to the agent
+                file_url = f"{api_url}/files/{task_id}"
+                full_question = f"{question_text}\n\n[Attached file: {file_name}, available at: {file_url}]"
+            else:
+                full_question = question_text
+
+            submitted_answer = agent(full_question)
             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})
+            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}"})
+            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
+    # 4. Submit
+    submission_data = {
+        "username": username.strip(),
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
     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()
@@ -110,60 +112,42 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
+        return final_status, pd.DataFrame(results_log)
     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:
+        except Exception:
             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 status_message, 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 status_message, pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# GAIA Agent Evaluation Runner")
     gr.Markdown(
         """
-        **Instructions:**
+        **LangChain-powered agent** with web search, code execution, file reading, and image understanding.
 
-        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.
+        **Instructions:**
+        1. Log in to your Hugging Face account using the button below.
+        2. Click **Run Evaluation & Submit All Answers** to fetch questions, run the agent, and submit.
 
-        ---
-        **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 may take several minutes — the agent processes each question using live tools.
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
+    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
     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(
@@ -172,25 +156,21 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    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?).")
+        print("ℹ️  SPACE_HOST not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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("ℹ️  SPACE_ID not found (running locally?).")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    print("-" * (60 + len(" App Starting ")) + "\n")
+    print("Launching Gradio Interface...")
+    demo.launch(debug=True, share=False)