Update model.py

model.py

@@ -1,8 +1,11 @@
+# ============================
+# model.py
+# ============================
+
 import os
 from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition
-from langgraph.prebuilt import ToolNode
+from langgraph.prebuilt import tools_condition, ToolNode
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_groq import ChatGroq
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
@@ -11,100 +14,115 @@ from langchain_community.vectorstores import SupabaseVectorStore
 from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
 from langchain_tavily import TavilySearch
+from langchain.tools.retriever import create_retriever_tool
 from supabase.client import Client, create_client
 
 load_dotenv()
 
+# Setup Supabase
 url = os.getenv("SUPABASE_URL")
 key = os.getenv("SUPABASE_KEY")
+supabase: Client = create_client(url, key)
 
-# Math Tools
+# Tools
 @tool
 def multiply(a: int, b: int) -> int:
+    """Multiply two numbers and return the result."""
     return a * b
 
 @tool
 def add(a: int, b: int) -> int:
+    """Add two numbers and return the result."""
     return a + b
 
 @tool
 def subtract(a: int, b: int) -> int:
+    """Subtract second number from first and return the result."""
     return a - b
 
 @tool
 def divide(a: int, b: int) -> float:
+    """Divide first number by second and return the result."""
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
 @tool
 def modulus(a: int, b: int) -> int:
+    """Return the modulus (remainder) of two numbers."""
     return a % b
 
-# Search Tools
 @tool
 def wiki_search(query: str) -> str:
-    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
-    return "\n---\n".join([doc.page_content for doc in search_docs])
+    """Search Wikipedia and return 2 results."""
+    docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    return "\n\n---\n\n".join(doc.page_content for doc in docs)
 
 @tool
 def web_search(query: str) -> str:
-    tavily = TavilySearch(k=3)
-    results = tavily.invoke(query)
-    return "\n---\n".join([doc.page_content for doc in results])
+    """Search the web using Tavily and return 3 results."""
+    docs = TavilySearch(max_results=3).invoke(query)
+    return "\n\n---\n\n".join(doc.page_content for doc in docs)
 
 @tool
 def arvix_search(query: str) -> str:
-    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
-    return "\n---\n".join([doc.page_content[:1000] for doc in search_docs])
+    """Search Arxiv for academic papers and return 3 results."""
+    docs = ArxivLoader(query=query, load_max_docs=3).load()
+    return "\n\n---\n\n".join(doc.page_content[:1000] for doc in docs)
 
 # Load system prompt
-with open("system_prompt.txt", "r", encoding="utf-8") as f:
+with open("system_prompt.txt", "r") as f:
     system_prompt = f.read()
+
 sys_msg = SystemMessage(content=system_prompt)
 
-# Vector store setup
+# Vector search setup
 embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-supabase: Client = create_client(url, key)
 vector_store = SupabaseVectorStore(
     client=supabase,
     embedding=embeddings,
     table_name="documents",
     query_name="match_documents_langchain",
 )
-retriever_tool = tool(name="Question Search", description="Retrieve similar questions from vector DB")(vector_store.as_retriever().invoke)
 
-tools = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search, retriever_tool]
+retriever_tool = create_retriever_tool(
+    retriever=vector_store.as_retriever(),
+    name="Question Search",
+    description="Retrieve similar questions from vector DB.",
+)
+
+# Tools list
+tools = [
+    multiply, add, subtract, divide, modulus,
+    wiki_search, web_search, arvix_search,
+    retriever_tool,
+]
+
+# Build LangGraph
 
 def build_graph(provider: str = "groq"):
     if provider == "google":
         llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     elif provider == "groq":
-        api_key = os.getenv('GROQ_API')
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0, api_key=api_key)
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0, api_key=os.getenv("GROQ_API"))
     elif provider == "huggingface":
-        llm = ChatHuggingFace(
-            llm=HuggingFaceEndpoint(
-                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
-                temperature=0,
-            ),
-        )
+        llm = ChatHuggingFace(llm=HuggingFaceEndpoint(
+            url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
+            temperature=0))
     else:
-        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
+        raise ValueError("Invalid provider")
 
     llm_with_tools = llm.bind_tools(tools)
 
     def assistant(state: MessagesState):
-        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+        return {"messages": [llm_with_tools.invoke(state["messages\])]}
 
     def retriever(state: MessagesState):
-        similar_docs = vector_store.similarity_search(state["messages"][0].content)
-        if not similar_docs:
+        docs = vector_store.similarity_search(state["messages"][0].content)
+        if not docs:
             return {"messages": [sys_msg] + state["messages"]}
-        example_msg = HumanMessage(
-            content=f"Here is a related example to help: \n\n{similar_docs[0].page_content}"
-        )
-        return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+        similar_msg = HumanMessage(content=f"Reference: {docs[0].page_content}")
+        return {"messages": [sys_msg] + state["messages"] + [similar_msg]}
 
     builder = StateGraph(MessagesState)
     builder.add_node("retriever", retriever)
@@ -117,10 +135,7 @@ def build_graph(provider: str = "groq"):
 
     return builder.compile()
 
-if __name__ == "__main__":
-    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
-    graph = build_graph(provider="groq")
-    messages = [HumanMessage(content=question)]
-    output = graph.invoke({"messages": messages})
-    for m in output["messages"]:
-        m.pretty_print()
+
+# ============================
+# Save this as model.py and let me know when you want full app.py regenerated to match
+# ============================