格式化输出结果

agent.py

@@ -1,8 +1,7 @@
 import os
 from typing import TypedDict, Annotated
 from dotenv import load_dotenv
-from langgraph.graph.message import add_messages
-from langchain_core.messages import AnyMessage, HumanMessage, AIMessage
+from langchain_core.messages import AnyMessage, HumanMessage, AIMessage, SystemMessage
 from langgraph.prebuilt import ToolNode
 from langgraph.graph import START, StateGraph, MessagesState
 from langgraph.prebuilt import tools_condition
@@ -10,25 +9,22 @@ from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_groq import ChatGroq
 from langchain_openai import ChatOpenAI
-
-from tools import (
-    divide,
-    multiply,
-    modulus,
-    add,
-    subtract,
-    power,
-    square_root,
-    web_search,
-    wiki_search,
-    arxiv_search,
-)
+import requests
+from tools import *
 
 # load api key
 load_dotenv()
 
 
 def buildAgent(provider="huggingface"):
+    # load the system prompt from the file
+    with open("system_prompt.txt", "r", encoding="utf-8") as f:
+        system_prompt = f.read()
+    print(system_prompt)
+
+    # System message
+    sys_msg = SystemMessage(content=system_prompt)
+
     # Generate the chat interface, including the tools
     if provider == "huggingface":
         llm = ChatHuggingFace(
@@ -36,14 +32,10 @@ def buildAgent(provider="huggingface"):
         )
     elif provider == "groq":
         llm = ChatGroq(model="qwen-qwq-32b")
-    elif provider == "openrouter":
-        llm = ChatOpenAI(
-            base_url="https://openrouter.ai/api/v1",
-            api_key=os.environ.get("OPENROUTER_API_KEY"),
-            model="google/gemini-2.0-flash-exp",
-        )
+    else:
+        raise ValueError("Invalid provider. Choose 'groq' or 'huggingface'.")
 
-    tools = [
+    agent_tools = [
         multiply,
         add,
         subtract,
@@ -54,9 +46,10 @@ def buildAgent(provider="huggingface"):
         web_search,
         wiki_search,
         arxiv_search,
+        download_file,
     ]
 
-    chat_with_tools = llm.bind_tools(tools)
+    chat_with_tools = llm.bind_tools(agent_tools)
 
     # nodes
     def assistant(state: MessagesState):
@@ -64,13 +57,21 @@ def buildAgent(provider="huggingface"):
             "messages": [chat_with_tools.invoke(state["messages"])],
         }
 
+    # todo add rag
+    def retriever(state: MessagesState):
+        """Retriever node"""
+        # Handle the case when no similar questions are found
+        return {"messages": [sys_msg] + state["messages"]}
+
     ## The graph
     builder = StateGraph(MessagesState)
     # Define nodes: these do the work
+    builder.add_node("retriever", retriever)
     builder.add_node("assistant", assistant)
-    builder.add_node("tools", ToolNode(tools))
+    builder.add_node("tools", ToolNode(agent_tools))
     # Define edges: these determine how the control flow moves
-    builder.add_edge(START, "assistant")
+    builder.add_edge(START, "retriever")
+    builder.add_edge("retriever", "assistant")
     builder.add_conditional_edges(
         "assistant",
         # If the latest message requires a tool, route to tools
@@ -82,7 +83,10 @@ def buildAgent(provider="huggingface"):
 
 
 if __name__ == "__main__":
-    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
+    random_question_url = "https://agents-course-unit4-scoring.hf.space/random-question"
+    response = requests.get(random_question_url, timeout=15)
+    questions_data = response.json()
+    question = questions_data.get("question")
     graph = buildAgent(provider="groq")
     messages = [HumanMessage(content=question)]
     print(messages)

app.py

@@ -9,6 +9,7 @@ from agent import buildAgent
 # (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+FINAL_ANSWER_PADDING = "FINAL ANSWER: "
 
 
 # --- Basic Agent Definition ---
@@ -23,7 +24,7 @@ class BasicAgent:
         messages = [HumanMessage(content=question)]
         messages = self.agent.invoke({"messages": messages})
         fixed_answer = messages["messages"][-1].content
-        return fixed_answer
+        return fixed_answer[len(FINAL_ANSWER_PADDING):]
 
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):

system_prompt.txt

@@ -0,0 +1,5 @@
+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]. 
+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 rules above for each element (number or string), ensure there is exactly one space after each comma.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer. 

tools.py

@@ -1,8 +1,13 @@
 import cmath
+import os
+import tempfile
+from urllib.parse import urlparse
+import uuid
 from langchain_core.tools import tool
 from langchain_community.tools.tavily_search import TavilySearchResults
 from langchain_community.document_loaders import WikipediaLoader
 from langchain_community.document_loaders import ArxivLoader
+import requests
 
 @tool
 def multiply(a: int, b: int) -> int:
@@ -13,29 +18,32 @@ def multiply(a: int, b: int) -> int:
     """
     return a * b
 
+
 @tool
 def add(a: int, b: int) -> int:
     """Add two numbers.
-        Args:
-        a: first int
-        b: second int
+    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
@@ -44,16 +52,18 @@ def divide(a: int, b: int) -> int:
         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
 
+
 @tool
 def power(a: float, b: float) -> float:
     """
@@ -76,6 +86,7 @@ def square_root(a: float) -> float | complex:
         return a**0.5
     return cmath.sqrt(a)
 
+
 @tool
 def web_search(query: str) -> str:
     """Search Tavily for a query and return maximum 3 results.
@@ -91,6 +102,7 @@ def web_search(query: str) -> str:
     )
     return {"web_results": formatted_search_docs}
 
+
 @tool
 def wiki_search(query: str) -> str:
     """Search Wikipedia for a query and return maximum 2 results.
@@ -106,6 +118,7 @@ def wiki_search(query: str) -> str:
     )
     return {"wiki_results": formatted_search_docs}
 
+
 @tool
 def arxiv_search(query: str) -> str:
     """Search Arxiv for a query and return maximum 3 result.
@@ -119,4 +132,36 @@ def arxiv_search(query: str) -> str:
             for doc in search_docs
         ]
     )
-    return {"arxiv_results": formatted_search_docs}
+    return {"arxiv_results": formatted_search_docs}
+
+
+@tool
+def download_file(url: str) -> str:
+    """Download file for a web url and return local save path
+    Args:
+        url: the file web url
+    """
+    try:
+        # Parse URL to get filename if not provided
+        if not filename:
+            path = urlparse(url).path
+            filename = os.path.basename(path)
+            if not filename:
+                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+
+        # Create temporary file
+        temp_dir = tempfile.gettempdir()
+        filepath = os.path.join(temp_dir, filename)
+
+        # Download the file
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+
+        # Save the file
+        with open(filepath, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+
+        return f"File {url} downloaded to {filepath}. You can read this file to process its contents."
+    except Exception as e:
+        return f"Error downloading file: {str(e)}"