test

.gitignore

@@ -1 +1,2 @@
-__pycache__/
+__pycache__/
+.env

app.py

@@ -1,27 +1,42 @@
 import gradio as gr
 from typing import TypedDict, Annotated
 from huggingface_hub import InferenceClient, login
-import random
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFacePipeline
 #from langchain.schema import AIMessage, HumanMessage
 from langgraph.graph.message import add_messages
+from langchain.docstore.document import Document
 from langgraph.prebuilt import ToolNode, tools_condition
 from langchain_core.messages import AnyMessage, HumanMessage, AIMessage
-from langchain.tools import Tool
-import os
+from langchain_community.retrievers import BM25Retriever
 import datasets
-from langchain.docstore.document import Document
+import os
 from langgraph.graph import START, StateGraph
-from langchain_community.retrievers import BM25Retriever
-from langchain_community.tools import DuckDuckGoSearchRun
+from langchain.tools import Tool
+from mytools import search_tool, weather_info_tool, hub_stats_tool
+from dotenv import load_dotenv
 
+load_dotenv()
 
 HUGGINGFACEHUB_API_TOKEN = os.environ["HUGGINGFACEHUB_API_TOKEN"]
 login(token=HUGGINGFACEHUB_API_TOKEN, add_to_git_credential=True)
 
+llm = HuggingFaceEndpoint(
+    #repo_id="HuggingFaceH4/zephyr-7b-beta",
+    repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+    task="text-generation",
+    max_new_tokens=512,
+    do_sample=False,
+    repetition_penalty=1.03,
+    timeout=240,
+)
+
+model = ChatHuggingFace(llm=llm, verbose=True)
+
+
 # Load the dataset
 guest_dataset = datasets.load_dataset("agents-course/unit3-invitees", split="train")
 
+
 # Convert dataset entries into Document objects
 docs = [
     Document(
@@ -36,9 +51,9 @@ docs = [
     for guest in guest_dataset
 ]
 
-
 bm25_retriever = BM25Retriever.from_documents(docs)
 
+
 def extract_text(query: str) -> str:
     """Retrieves detailed information about gala guests based on their name or relation."""
     results = bm25_retriever.invoke(query)
@@ -47,18 +62,12 @@ def extract_text(query: str) -> str:
     else:
         return "No matching guest information found."
 
-llm = HuggingFaceEndpoint(
-    #repo_id="HuggingFaceH4/zephyr-7b-beta",
-    repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
-    task="text-generation",
-    max_new_tokens=512,
-    do_sample=False,
-    repetition_penalty=1.03,
-    timeout=240,
+guest_info_tool = Tool(
+    name="guest_info_retriever",
+    func=extract_text,
+    description="Retrieves detailed information about gala guests based on their name or relation."
 )
 
-model = ChatHuggingFace(llm=llm, verbose=True)
-
 def predict(message, history):
     # Convert Gradio history to LangChain message format
     history_langchain_format = []
@@ -82,57 +91,8 @@ def predict(message, history):
 
 # setup agents
 
-guest_info_tool = Tool(
-    name="guest_info_retriever",
-    func=extract_text,
-    description="Retrieves detailed information about gala guests based on their name or relation."
-)
-"""
-search_tool = DuckDuckGoSearchRun()
-
-def get_weather_info(location: str) -> str:
-    Fetches dummy weather information for a given location.
-    # 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"
-
-# Initialize the tool
-weather_info_tool = Tool(
-    name="get_weather_info",
-    func=get_weather_info,
-    description="Fetches dummy weather information for a given location."
-)
-
-
-def get_hub_stats(author: str) -> str:
-    Fetches the most downloaded model from a specific author on the Hugging Face Hub.
-    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)}"
-
-# Initialize the tool
-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."
-)
-"""
-#tools = [guest_info_tool, search_tool, weather_info_tool, hub_stats_tool]
-tools = [guest_info_tool]
+tools = [guest_info_tool, search_tool, weather_info_tool, hub_stats_tool]
+#tools = [guest_info_tool]
 chat_with_tools = model.bind_tools(tools)
 
 # Generate the AgentState and Agent graph

mytools.py

@@ -0,0 +1,48 @@
+from langchain.tools import Tool
+from langchain_community.tools import DuckDuckGoSearchRun
+import random
+from huggingface_hub import list_models
+
+
+search_tool = DuckDuckGoSearchRun()
+
+def get_weather_info(location: str) -> str:
+    """Fetches dummy weather information for a given location."""
+    # 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"
+
+# Initialize the tool
+weather_info_tool = Tool(
+    name="get_weather_info",
+    func=get_weather_info,
+    description="Fetches dummy weather information for a given location."
+)
+
+
+def get_hub_stats(author: str) -> str:
+    """Fetches the most downloaded model from a specific author on the Hugging Face Hub."""
+    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)}"
+
+# Initialize the tool
+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."
+)