structure

agent.py

@@ -1,37 +1,31 @@
 import os
+
+from datasets import load_dataset
 from dotenv import load_dotenv
-from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition
-from langgraph.prebuilt import ToolNode
-from langchain_google_genai import ChatGoogleGenerativeAI
-from langchain_groq import ChatGroq
-from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
-from langchain_community.tools.tavily_search import TavilySearchResults
-from langchain_community.document_loaders import WikipediaLoader
-from langchain_community.document_loaders import ArxivLoader
-from langchain_community.vectorstores import SupabaseVectorStore
-from langchain_core.messages import SystemMessage, HumanMessage
-from langchain_core.tools import tool
-from langchain.tools.retriever import create_retriever_tool
-from langchain_community.vectorstores import Chroma
 from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.schema import Document
 from langchain.tools.retriever import create_retriever_tool
-import os
-import json
-from datasets import load_dataset
-from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import Chroma
-from langchain.schema import Document
+from langchain_community.document_loaders import ArxivLoader, WikipediaLoader
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_core.messages import HumanMessage, SystemMessage
+from langchain_core.tools import tool
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_huggingface import (ChatHuggingFace, HuggingFaceEmbeddings,
+                                   HuggingFaceEndpoint)
+from langgraph.graph import START, MessagesState, StateGraph
+from langgraph.prebuilt import ToolNode, tools_condition
 
 load_dotenv()
 
 @tool
 def calculator(query: str) -> str:
     """Perform basic arithmetic operations based on the provided query.
-    
+
     Args:
         query: A mathematical query as a string, e.g., '2 + 2' or '5 * 6'."""
-    
+
     try:
         # Evaluate the mathematical expression
         result = eval(query)
@@ -43,7 +37,7 @@ def calculator(query: str) -> str:
 @tool
 def wiki_search(query: str) -> str:
     """Search Wikipedia for a query and return maximum 2 results.
-    
+
     Args:
         query: The search query."""
     search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
@@ -51,13 +45,15 @@ def wiki_search(query: str) -> str:
         [
             f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
             for doc in search_docs
-        ])
+        ]
+    )
     return {"wiki_results": formatted_search_docs}
 
+
 @tool
 def web_search(query: str) -> str:
     """Search Tavily for a query and return maximum 3 results.
-    
+
     Args:
         query: The search query."""
     search_docs = TavilySearchResults(max_results=3).invoke(query=query)
@@ -65,13 +61,15 @@ def web_search(query: str) -> str:
         [
             f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
             for doc in search_docs
-        ])
+        ]
+    )
     return {"web_results": formatted_search_docs}
 
+
 @tool
 def arvix_search(query: str) -> str:
     """Search Arxiv for a query and return maximum 3 result.
-    
+
     Args:
         query: The search query."""
     search_docs = ArxivLoader(query=query, load_max_docs=3).load()
@@ -79,9 +77,11 @@ def arvix_search(query: str) -> str:
         [
             f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
             for doc in search_docs
-        ])
+        ]
+    )
     return {"arvix_results": formatted_search_docs}
 
+
 system_prompt = """You are a helpful assistant tasked with answering questions using a set of tools. 
 Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
 FINAL ANSWER: [YOUR FINAL ANSWER]. 
@@ -92,7 +92,9 @@ Your answer should only start with "FINAL ANSWER: ", then follows with the answe
 sys_msg = SystemMessage(content=system_prompt)
 
 # build a retriever
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
+embeddings = HuggingFaceEmbeddings(
+    model_name="sentence-transformers/all-mpnet-base-v2"
+)  #  dim=768
 
 # Load the GAIA validation dataset
 dataset = load_dataset("gaia-benchmark/GAIA", name="2023_level1", split="validation")
@@ -105,29 +107,24 @@ documents = []
 for entry in dataset:
     question = entry["Question"]
     answer = entry["Final answer"]
-    
+
     # Create a document with both the question and the answer as metadata
     metadata = {
         "task_id": entry["task_id"],
         "steps": entry["Annotator Metadata"]["Steps"],
         "tools": entry["Annotator Metadata"]["Tools"],
-        "answer": answer
+        "answer": answer,
     }
-    
+
     # Add the question to the list of documents
-    documents.append(
-        Document(
-            page_content=question,
-            metadata=metadata
-        )
-    )
+    documents.append(Document(page_content=question, metadata=metadata))
 
 # Insert the documents into Chroma
 vectorstore = Chroma.from_documents(
     documents=documents,
     embedding=embeddings,
     collection_name="gaia_validation",
-    persist_directory="./chroma_store"
+    persist_directory="./chroma_store",
 )
 
 create_retriever_tool = create_retriever_tool(
@@ -144,6 +141,7 @@ tools = [
     arvix_search,
 ]
 
+
 # Build graph function
 def build_graph(provider: str = "groq"):
     """Build the graph"""
@@ -153,7 +151,9 @@ def build_graph(provider: str = "groq"):
         llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     elif provider == "groq":
         # Groq https://console.groq.com/docs/models
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
+        llm = ChatGroq(
+            model="qwen-qwq-32b", temperature=0
+        )  # optional : qwen-qwq-32b gemma2-9b-it
     elif provider == "huggingface":
         # TODO: Add huggingface endpoint
         llm = ChatHuggingFace(
@@ -171,7 +171,7 @@ def build_graph(provider: str = "groq"):
     def assistant(state: MessagesState):
         """Assistant node"""
         return {"messages": [llm_with_tools.invoke(state["messages"])]}
-    
+
     def retriever(state: MessagesState):
         """Retriever node"""
         similar_question = vectorstore.similarity_search(state["messages"][0].content)
@@ -195,6 +195,7 @@ def build_graph(provider: str = "groq"):
     # Compile graph
     return builder.compile()
 
+
 # test
 if __name__ == "__main__":
     question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"

app.py

@@ -1,16 +1,18 @@
 # app.py
 import os
+
 import gradio as gr
-import requests
 import pandas as pd
+import requests
 from langchain_core.messages import HumanMessage
-from agent import build_graph
 
+from agent import build_graph
 
 # (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:
@@ -24,16 +26,17 @@ class BasicAgent:
         result = self.graph.invoke({"messages": messages})
         return result["messages"][-1].content  # Simplify if needed
 
-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,
     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")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -60,16 +63,16 @@ 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:
         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
+        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
@@ -86,18 +89,36 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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})
+            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}"})
+            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}
+    # 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)
 
@@ -167,20 +188,19 @@ with gr.Blocks() as demo:
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    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
+    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -188,14 +208,18 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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")
+        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(
+            "ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined."
+        )
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    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)

app_template.py

@@ -1,34 +1,38 @@
+import inspect
 import os
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
 
 # (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,
     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")  # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -55,16 +59,16 @@ 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:
         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
+        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
@@ -81,18 +85,36 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             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})
+            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}"})
+            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}
+    # 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)
 
@@ -162,20 +184,19 @@ with gr.Blocks() as demo:
 
     run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    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_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
+    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
+    space_id_startup = os.getenv("SPACE_ID")  # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -183,14 +204,18 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    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")
+        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(
+            "ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined."
+        )
 
-    print("-"*(60 + len(" App Starting ")) + "\n")
+    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)

requirements.txt

@@ -12,8 +12,4 @@ langgraph
 huggingface_hub
 chromadb
 sentence-transformers
-arxiv
-pymupdf
-wikipedia
-pgvector
 python-dotenv

setup_actions.ipynb

@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": null,
    "id": "55b5db25",
    "metadata": {},
    "outputs": [
@@ -24,7 +24,17 @@
     "\n",
     "from huggingface_hub import login\n",
     "\n",
-    "login(token=os.environ[\"HUGGINGFACE_TOKEN\"])"
+    "login(token=os.environ[\"HUGGINGFACE_TOKEN\"])\n",
+    "\n",
+    "# # Run isort on all folders\n",
+    "# isort .\n",
+    "# # Run black on all folders\n",
+    "# black .\n",
+    "# # Run flake8 on all folders\n",
+    "# flake8 .\n",
+    "\n",
+    "# # Run pylint on all folders\n",
+    "# pylint ."
    ]
   },
   {