Add agent MVP

app.py

@@ -1,5 +1,5 @@
 import os
-from typing import TypedDict, List, Dict, Any, Optional
+from typing import TypedDict, List, Dict, Any, Optional, Tuple
 
 import gradio as gr
 import requests
@@ -11,12 +11,14 @@ from langgraph.graph.message import add_messages
 from langgraph.prebuilt import ToolNode, tools_condition
 
 from langchain_openai import ChatOpenAI
+from langchain_community.tools import DuckDuckGoSearchRun
 from langchain_core.messages import AnyMessage, SystemMessage, HumanMessage
 
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-os.environ["OPENAI_API_KEY"] = "sk-xxxxx"
+os.environ["OPENAI_API_KEY"] = "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
+"
 
 
 class State(TypedDict):
@@ -30,77 +32,66 @@ class BasicAgent:
     
     def __init__(self):
         
-        # self.graph = StateGraph(State)
-        # self.graph.add_node("search_tool", self.search_tool)
-        # self.graph.add_node("image_analyze", self.image_analyze)
-        # self.graph.add_node("generic_reasoning", self.generic_reasoning)
-        # self.graph.add_node("file_operating", self.file_operating)
-
-        # # Start the edges
-        # self.graph.add_edge(START, "read_email")
-        # # Add edges - defining the flow
-        # self.graph.add_edge("read_email", "classify_email")
-        
-        # # Add conditional branching from classify_email
-        # self.graph.add_conditional_edges(
-        #     "classify_email",
-        #     route_email,
-        #     {
-        #         "spam": "handle_spam",
-        #         "legitimate": "draft_response"
-        #     }
-        # )
-        
-        # # Add the final edges
-        # self.graph.add_edge("handle_spam", END)
-        # self.graph.add_edge("draft_response", "notify_mr_hugg")
-        # self.graph.add_edge("notify_mr_hugg", END)
+        self.tools = [
+            self.search_tool, 
+            # self.image_analyze_tool, 
+            # self.file_operating_tool
+        ]
+
+        self.model = ChatOpenAI(model="gpt-4o", temperature=0)
+        self.model_with_tools = self.model.bind_tools(self.tools, parallel_tool_calls=False)
+
+        self.graph = StateGraph(State)
+        self.graph.add_node("assistant", self.assistant)
+        self.graph.add_node("tools", ToolNode(self.tools))
+
+        # Start the edges
+        self.graph.add_edge(START, "assistant")
+        self.graph.add_conditional_edges(
+            "assistant",
+            tools_condition
+        )
+        self.graph.add_edge("tools", "assistant")
         
-        # # Compile the graph
-        # self.compiled_graph = self.graph.compile()
-        self.tools = [self.search_tool, self.image_analyze_tool, self.file_operating_tool]
-
-        # self.model = ChatOpenAI(model="gpt-4o", temperature=0)
-        # self.model_with_tools = self.model.bind_tools(self.tools, parallel_tool_calls=False)
+        # Compile the graph
+        self.compiled_graph = self.graph.compile()
 
         print("BasicAgent initialized.")
 
-    def __call__(self, question: str) -> str:
+    def __call__(self, question: str) -> Tuple[str, TypedDict]:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
+        state = State(question=question, messages=[HumanMessage(content=question)])
+        fixed_answer = self.assistant(state)
         print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        return fixed_answer, state
 
-    # def assistant(state: AgentState):
-    #     # System message
-    #     textual_description_of_tool="""
-    #         extract_text(img_path: str) -> str:
-    #             Extract text from an image file using a multimodal model.
+    def assistant(state: AgentState):
+        # System message
+        textual_description_of_tool="""
+            search_tool(question: str) -> str:
+                Search info in the web.
             
-    #             Args:
-    #                 img_path: A local image file path (strings).
+                Args:
+                    question: Question string
             
-    #             Returns:
-    #                 A single string containing the concatenated text extracted from each image.
-    #         divide(a: int, b: int) -> float:
-    #             Divide a and b
-    #     """
-    #     image=state["input_file"]
-    #     sys_msg = SystemMessage(content=f"You are a helpful butler named Alfred that serves Mr. Wayne and Batman. You can analyse documents and run computations with provided tools:\n{textual_description_of_tool} \n You have access to some optional images. Currently the loaded image is: {image}")
-    
-    #     return {
-    #         "messages": [self.model_with_tools.invoke([sys_msg] + state["messages"])],
-    #         "question": state["question"]
-    #     }
-
-    def search_tool(state):
-        pass
+                Returns:
+                    A single string containing the info from the web.
 
-    def image_analyze_tool(state):
-        pass
-
-    def file_operating_tool(state):
-        pass
+        """
+        
+        sys_msg = SystemMessage(
+            content=f"""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. 
+            You can use provided tools:\n{textual_description_of_tool}"""
+        )
+    
+        return {
+            "messages": [self.model_with_tools.invoke([sys_msg] + state.get("messages", []))],
+            "question": state["question"]
+        }
+
+    def search_tool(question: str, max_length: int = 1024) -> str:
+        search = DuckDuckGoSearchRun()
+        return search.invoke(question)[:max_length]
     
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):