GAIA agent

agent.py

@@ -0,0 +1,137 @@
+from langchain_community.chat_models import ChatHuggingFace
+from langchain_community.llms import HuggingFaceEndpoint
+from langchain_community.tools.python.tool import PythonREPLTool
+
+# --- Custom Tools ---
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
+from langchain_core.runnables import RunnableLambda
+from langchain_core.tools import tool
+from langgraph.graph import END, START, MessagesState, StateGraph
+from langgraph.graph.message import add_messages
+from langgraph.prebuilt import ToolNode, tools_condition
+
+
+@tool
+def search_web_sources(query: str) -> str:
+    """
+    Perform a web search using Tavily and return up to 3 relevant documents.
+    This tool is useful for answering research-based queries that require
+    up-to-date information from trusted sources.
+
+    Args:
+        query (str): The input search query.
+
+    Returns:
+        str: Formatted web search results with metadata and content.
+    """
+    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 formatted_search_docs
+
+
+@tool
+def run_python_code(code: str) -> str:
+    """Execute Python code and return the result.
+    Args:
+        code: Python code as a string.
+    """
+    repl = PythonREPLTool()
+    return repl.run(code)
+
+
+# --- System Prompt ---
+system_prompt = SystemMessage(
+    content="""
+You are a helpful and precise assistant. You will receive a question and optionally access tools to help answer it.
+
+Your job is to think step-by-step, clearly report your thoughts, and conclude with a formatted response.
+
+Use this format strictly:
+FINAL ANSWER: [your concise answer here]
+
+Rules for your answer:
+- If the answer is a number, write only the number (no commas, units, or symbols unless asked).
+- If it's a string, avoid articles (a, an, the), don't abbreviate, and use plain text digits.
+- If a list, follow the rules above for each element and separate with a comma and single space (e.g., "apple, orange, banana").
+
+Your response must always begin with: FINAL ANSWER:
+"""
+)
+
+
+def build_agent_graph(provider: str = "huggingface"):
+    # Define toolset
+    tools = [search_web_sources, run_python_code]
+
+    # Instantiate LLM
+    llm = ChatHuggingFace(
+        llm=HuggingFaceEndpoint(
+            repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+            task="text-generation",
+            max_new_tokens=1024,
+            do_sample=False,
+            repetition_penalty=1.03,
+            temperature=0,
+        ),
+        verbose=True,
+    )
+
+    # Bind tools to the LLM
+    llm_with_tools = llm.bind_tools(tools)
+
+    # Assistant: reasoning step that plans next action
+    def assistant_node(state: MessagesState):
+        messages = state["messages"]
+        response = llm_with_tools.invoke(messages)
+        return {"messages": add_messages(state, [response])}
+
+    # Stubbed retriever node for future integration
+    def retriever_node(state: MessagesState):
+        """Retriever node"""
+        # Example: use vector_store.similarity_search() in real use
+        similar_question = [
+            AIMessage(content="This is a mock similar document from the retriever.")
+        ]
+
+        if similar_question:
+            example_msg = HumanMessage(
+                content=f"Here I provide a similar question and answer for reference: {similar_question[0].content}",
+            )
+            return {"messages": [system_prompt] + state["messages"] + [example_msg]}
+        else:
+            return {"messages": [system_prompt] + state["messages"]}
+
+    # ToolNode wrapper for actual tool use
+    tool_node = ToolNode(tools)
+
+    # Define the graph with ReAct loop
+    builder = StateGraph(MessagesState)
+    builder.add_node("assistant", RunnableLambda(assistant_node))
+    builder.add_node("tools", tool_node)
+    builder.add_node("retriever", RunnableLambda(retriever_node))
+
+    builder.set_entry_point("assistant")
+    builder.add_conditional_edges("assistant", tools_condition)
+    builder.add_edge("tools", "assistant")
+    builder.add_edge("assistant", END)
+
+    graph = builder.compile()
+
+    # Optional: test entrypoint to run the graph manually
+    test_input = {
+        "messages": [
+            system_prompt,
+            HumanMessage(content="What is the capital of France?"),
+        ]
+    }
+
+    # result = graph.invoke(test_input)
+    # print("\nFinal output:", result["messages"][-1].content)
+
+    return graph

app.py

@@ -1,34 +1,46 @@
+import inspect
 import os
+
 import gradio as gr
-import requests
-import inspect
 import pandas as pd
+import requests
+from langchain_core.messages import AnyMessage, HumanMessage, SystemMessage
+
+# from langgraph.graph import MessagesState
+from agent import build_agent_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:
     def __init__(self):
         print("BasicAgent initialized.")
+        self.graph = build_agent_graph()
+
     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
+        # Wrap the question from HumanMessage from langchain_core
+        msgs = [HumanMessage(content=question)]
+        # input_state: MessagesState = {"messages": msgs}
+        result = self.graph.invoke({"messages": msgs})
+        answer = result["messages"][-1].content
+        return answer[14:]  # skip "FINAL 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 +67,16 @@ 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 +93,36 @@ 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 +192,19 @@ 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 +212,18 @@ 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

@@ -1,2 +1,9 @@
 gradio
-requests
+requests
+langchain
+langchain-core
+langgraphlangchain
+langchain-community
+langchain-tavily
+langgraph
+tavily-python