updating tools to use langgraph

app.py

@@ -9,7 +9,7 @@ from langgraph.graph import START, StateGraph
 from langgraph.prebuilt import tools_condition
 from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace
 
-from tools import DuckDuckGoSearchTool, WeatherInfoTool, HubStatsTool, MemoryManagementTool
+from tools import weather_info_tool, hub_stats_tool, memory_management_tool, duckduckgo_search_tool
 from retriever import load_guest_dataset
 
 # Initialize the Hugging Face model
@@ -22,24 +22,11 @@ llm = HuggingFaceEndpoint(
 
 chat = ChatHuggingFace(llm=llm, verbose=True)
 
-# Initialize the memory store
-memory_management_tool = MemoryManagementTool()
-
-# Initialize the web search tool
-search_tool = DuckDuckGoSearchTool()
-
-# Initialize the weather tool
-weather_info_tool = WeatherInfoTool()
-
-# Initialize the Hub stats tool
-hub_stats_tool = HubStatsTool()
+# adding tools
 
-# Load the guest dataset and initialize the guest info tool
 guest_info_tool = load_guest_dataset()
 
-# adding tools
-
-tools = [guest_info_tool, weather_info_tool, hub_stats_tool, search_tool, memory_management_tool]
+tools = [guest_info_tool, weather_info_tool, hub_stats_tool, duckduckgo_search_tool, memory_management_tool]
 chat_with_tools = chat.bind_tools(tools)
 
 # Generate the AgentState and Agent graph

tools.py

@@ -1,78 +1,76 @@
-from smolagents import DuckDuckGoSearchTool
-from smolagents import Tool
+from langchain.tools import Tool
+from langchain_community.tools.duckduckgo_search import DuckDuckGoSearchTool
+from langgraph.store.memory import InMemoryStore
 import random
 from huggingface_hub import list_models
-from langgraph.store.memory import InMemoryStore
 
 # Initialize the DuckDuckGo search tool
 search_tool = DuckDuckGoSearchTool()
-store = InMemoryStore(
-    index={"embed": "openai:text-embedding-3-small"}
+
+# Initialize the memory store
+store = InMemoryStore(index={"embed": "openai:text-embedding-3-small"})
+
+# Define the weather information tool
+def get_weather_info(location: str) -> str:
+    """Fetches dummy weather information for a given location."""
+    weather_conditions = [
+        {"condition": "Rainy", "temp_c": 15},
+        {"condition": "Clear", "temp_c": 25},
+        {"condition": "Windy", "temp_c": 20}
+    ]
+    data = random.choice(weather_conditions)
+    return f"Weather in {location}: {data['condition']}, {data['temp_c']}°C"
+
+weather_info_tool = Tool(
+    name="get_weather_info",
+    func=get_weather_info,
+    description="Fetches dummy weather information for a given location."
+)
+
+# Define the Hub stats tool
+def get_hub_stats(author: str) -> str:
+    """Fetches the most downloaded model from a specific author on the Hugging Face Hub."""
+    try:
+        models = list(list_models(author=author, sort="downloads", direction=-1, limit=1))
+        if models:
+            model = models[0]
+            return f"The most downloaded model by {author} is {model.id} with {model.downloads:,} downloads."
+        else:
+            return f"No models found for author {author}."
+    except Exception as e:
+        return f"Error fetching models for {author}: {str(e)}"
+
+hub_stats_tool = Tool(
+    name="get_hub_stats",
+    func=get_hub_stats,
+    description="Fetches the most downloaded model from a specific author on the Hugging Face Hub."
 )
 
-class WeatherInfoTool(Tool):
-    name = "weather_info"
-    description = "Fetches dummy weather information for a given location."
-    inputs = {
-        "location": {
-            "type": "string",
-            "description": "The location to get weather information for."
-        }
-    }
-    output_type = "string"
+# Define the memory management tool
+def memory_management(query: str) -> str:
+    """Manages and queries conversation memory."""
+    results = store.retrieve(query)
+    if results:
+        return "\n\n".join(results)
+    else:
+        return "No relevant memory found."
 
-    def forward(self, location: str):
-        # Dummy weather data
-        weather_conditions = [
-            {"condition": "Rainy", "temp_c": 15},
-            {"condition": "Clear", "temp_c": 25},
-            {"condition": "Windy", "temp_c": 20}
-        ]
-        # Randomly select a weather condition
-        data = random.choice(weather_conditions)
-        return f"Weather in {location}: {data['condition']}, {data['temp_c']}°C"
+memory_management_tool = Tool(
+    name="memory_management",
+    func=memory_management,
+    description="Manages and queries conversation memory."
+)
 
-class HubStatsTool(Tool):
-    name = "hub_stats"
-    description = "Fetches the most downloaded model from a specific author on the Hugging Face Hub."
-    inputs = {
-        "author": {
-            "type": "string",
-            "description": "The username of the model author/organization to find models from."
-        }
-    }
-    output_type = "string"
 
-    def forward(self, author: str):
-        try:
-            # List models from the specified author, sorted by downloads
-            models = list(list_models(author=author, sort="downloads", direction=-1, limit=1))
-            
-            if models:
-                model = models[0]
-                return f"The most downloaded model by {author} is {model.id} with {model.downloads:,} downloads."
-            else:
-                return f"No models found for author {author}."
-        except Exception as e:
-            return f"Error fetching models for {author}: {str(e)}"
+def duckduckgo_search(query: str) -> str:
+    """Searches the web for information."""
+    return search_tool.run(query)
 
-class MemoryManagementTool(Tool):
-    name = "memory_management"
-    description = "Manages and queries conversation memory."
-    inputs = {
-        "query": {
-            "type": "string",
-            "description": "The query to search in memory."
-        }
-    }
-    output_type = "string"
+duckduckgo_search_tool = Tool(
+    name="duckduckgo_search",
+    func=duckduckgo_search,
+    description="Searches the web for information."
+)
 
-    def forward(self, query: str):
-        # Retrieve relevant memory entries
-        results = store.retrieve(query)
-        if results:
-            return "\n\n".join(results)
-        else:
-            return "No relevant memory found."