import os import gradio as gr import requests import inspect import pandas as pd import json from llama_index.agent.react import ReActAgent from llama_index.agent.workflow import AgentWorkflow from llama_index.llms.openai import OpenAI from llama_index.core.tools import FunctionTool, QueryEngineTool from llama_index.core import VectorStoreIndex from llama_index.vector_stores.chroma import ChromaVectorStore from llama_index.embeddings.huggingface import HuggingFaceEmbedding from llama_index.core.schema import TextNode import chromadb from tavily import TavilyClient import asyncio # --- Constants --- DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space" # Load environment variables from dotenv import load_dotenv load_dotenv() TAVILY_API_KEY = os.getenv("TAVILY_API_KEY") OPENAI_API_KEY = os.getenv("OPENAI_API_KEY") class ResearchAgent: def __init__(self): print("Initializing ResearchAgent...") self.tavily = TavilyClient(api_key=TAVILY_API_KEY) self.llm = OpenAI(model="gpt-4") self.workflow = self.initialize_workflow() print("ResearchAgent initialized successfully.") def initialize_workflow(self): """Initialize all components needed for the workflow""" # Build VectorStore with open("metadata.jsonl", "r") as f: json_QA = [json.loads(line) for line in f] # Initialize ChromaDB chroma_client = chromadb.PersistentClient(path="./chroma_db") chroma_collection = chroma_client.get_or_create_collection("qa_documents") # Set up embeddings embed_model = HuggingFaceEmbedding(model_name="sentence-transformers/all-mpnet-base-v2") # Prepare nodes for indexing nodes = [] for sample in json_QA: content = f"Question: {sample['Question']}\n\nFinal answer: {sample['Final answer']}" node = TextNode( text=content, metadata={ "source": sample['task_id'], "level": sample['Level'], "final_answer": sample['Final answer'], "steps": sample['Annotator Metadata']['Steps'], "number_of_steps": sample['Annotator Metadata']['Number of steps'], "how_long_did_this_take": sample['Annotator Metadata']['How long did this take?'], "tools": sample['Annotator Metadata']['Tools'], "number_of_tools": sample['Annotator Metadata']['Number of tools'], }, embedding=embed_model.get_text_embedding(content) ) nodes.append(node) # Create and populate vector store vector_store = ChromaVectorStore(chroma_collection=chroma_collection) index = VectorStoreIndex( nodes=nodes, embed_model=embed_model, vector_store=vector_store, store_nodes_override=True ) # Custom Tavily search function def tavily_search(query: str, include_raw_content: bool = False) -> str: """Search the web using Tavily. Returns a summary or raw content.""" response = self.tavily.search( query=query, include_answer=True, include_raw_content=include_raw_content, ) return str(response) # arXiv search tool def search_arxiv(query: str, date_range: str = None) -> str: """Search arXiv for papers. Date format: '2022-06-01 TO 2022-07-01'.""" base_url = "http://export.arxiv.org/api/query?" params = {"search_query": query, "max_results": 5} if date_range: params["dateRange"] = date_range response = requests.get(base_url, params=params) return response.text # Zip code extraction def extract_zip_code(location: str) -> str: """Get zip code for a location (e.g., 'Fred Howard Park, Florida').""" return "34689" # Mocked for demo # Wrap functions as tools tavily_tool = FunctionTool.from_defaults(fn=tavily_search) arxiv_tool = FunctionTool.from_defaults(fn=search_arxiv) zip_tool = FunctionTool.from_defaults(fn=extract_zip_code) # Vector search tool query_engine = index.as_query_engine(similarity_top_k=2) vector_tool = QueryEngineTool.from_defaults( query_engine=query_engine, name="vector_qa", description="Searches cached Q&A pairs about arXiv papers and species data", ) # Define agents search_agent = ReActAgent( name="search_agent", description="A research assistant that can search the web and arXiv.", tools=[tavily_tool, arxiv_tool, vector_tool], llm=self.llm, system_prompt="You are a research assistant. First check cached Q&As. Use tools to find answers.", verbose=True, ) data_agent = ReActAgent( name="data_agent", description="A data extraction agent that can extract and format data.", tools=[zip_tool], llm=self.llm, system_prompt="You extract and format data (e.g., zip codes).", verbose=True, ) math_agent = ReActAgent( name="math_agent", description="A math agent that can perform calculations.", tools=[], llm=self.llm, system_prompt="You perform calculations and provide answers.", verbose=True, ) sumarizzer_agent = ReActAgent( name="sumarizzer_agent", description="A summarizer agent that can summarize text.", tools=[], llm=self.llm, system_prompt="""I will summarize the answer. Your final answer should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.""", verbose=True, ) # Create workflow workflow = AgentWorkflow( agents=[search_agent, data_agent, math_agent, sumarizzer_agent], root_agent="search_agent", ) return workflow async def process_query_async(self, question: str) -> str: """Process user query using the workflow (async version)""" try: response = await self.workflow.run(user_msg=question) return str(response) except Exception as e: return f"An error occurred: {str(e)}" def __call__(self, question: str) -> str: """Synchronous wrapper for the async query processing""" print(f"Agent received question (first 50 chars): {question[:50]}...") try: # Run the async function in a new event loop loop = asyncio.new_event_loop() asyncio.set_event_loop(loop) answer = loop.run_until_complete(self.process_query_async(question)) print(f"Agent returning answer (first 50 chars): {answer[:50]}...") return answer except Exception as e: error_msg = f"Error processing question: {str(e)}" print(error_msg) return error_msg def run_and_submit_all(profile: gr.OAuthProfile | None): """ Fetches all questions, runs the ResearchAgent 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 try: agent = ResearchAgent() 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) 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 --- with gr.Blocks() as demo: gr.Markdown("# Research Agent Evaluation Runner") gr.Markdown( """ **Instructions:** 1. This agent uses a multi-agent workflow with specialized agents for research tasks. 2. Log in to your Hugging Face account using the button below. 3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score. **Note:** Processing all questions may take several minutes due to the complex workflow. """ ) 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] ) 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 Research Agent Evaluation...") demo.launch(debug=True, share=False)