Agent

.gitignore

@@ -0,0 +1,2 @@
+.env
+/venv/

app.py

@@ -1,34 +1,28 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+from custom_agent import CustomAgent
 
 # (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.")
@@ -40,7 +34,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = CustomAgent()
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -55,16 +49,16 @@ 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 +75,36 @@ 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 +174,19 @@ 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 +194,18 @@ 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)

custom_agent.py

@@ -0,0 +1,195 @@
+from langgraph.prebuilt import create_react_agent
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+from dotenv import load_dotenv, find_dotenv
+from langchain_core.tools import tool
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain_core.messages import HumanMessage
+from supabase import create_client, Client
+import os
+
+load_dotenv(find_dotenv())
+
+DEFAULT_PROMPT = """
+You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template: FINAL ANSWER: [YOUR FINAL 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.
+
+"""
+
+
+@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()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            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)
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            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()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            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}
+
+
+@tool
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
+
+
+@tool
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
+
+
+@tool
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
+
+
+@tool
+def divide(a: int, b: int) -> int:
+    """Divide two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
+
+
+@tool
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
+
+
+class CustomAgent:
+    def __init__(self):
+        print("CustomAgent initialized.")
+
+        # Initialize embeddings and vector store
+        self.embeddings = HuggingFaceEmbeddings(
+            model_name="sentence-transformers/all-mpnet-base-v2"
+        )
+        print(os.environ.get("SUPABASE_URL"))
+        print(os.environ.get("SUPABASE_SERVICE_KEY"))
+
+        self.supabase: Client = create_client(
+            os.environ.get("SUPABASE_URL"), os.environ.get("SUPABASE_SERVICE_ROLE_KEY")
+        )
+
+        self.vector_store = SupabaseVectorStore(
+            client=self.supabase,
+            embedding=self.embeddings,
+            table_name="documents_1",
+            query_name="match_documents_1",
+        )
+
+        # Create the agent
+        self.agent = create_react_agent(
+            model="openai:gpt-4-1106-preview",
+            tools=[
+                web_search,
+                add,
+                subtract,
+                multiply,
+                divide,
+                modulus,
+                wiki_search,
+                arvix_search,
+            ],
+            prompt=DEFAULT_PROMPT,
+        )
+
+    def retriever(self, query: str):
+        """Retriever"""
+        similar_question = self.vector_store.similarity_search(query)
+        return HumanMessage(
+            content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
+        )
+
+    def __call__(self, question: str) -> str:
+        """Run the agent on a question and return the answer."""
+        print(f"CustomAgent received question (first 50 chars): {question[:50]}...")
+
+        try:
+            answer = self.agent.invoke(
+                {
+                    "messages": [
+                        self.retriever(question),
+                        HumanMessage(content=question),
+                    ]
+                }
+            )
+            result = answer["messages"][-1].content
+            print(f"CustomAgent returning answer: {result}")
+            return result
+        except Exception as e:
+            print(f"Error in CustomAgent: {e}")
+            return f"Error: {e}"
+
+
+if __name__ == "__main__":
+    agent = CustomAgent()
+    agent(
+        'What was the volume in m^3 of the fish bag that was calculated in the University of Leicester paper "Can Hiccup Supply Enough Fish to Maintain a Dragon\u2019s Diet?"'
+    )

requirements.txt

@@ -1,2 +1,20 @@
 gradio
-requests
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+supabase
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv
+pytesseract
+matplotlib
+sentence-transformers