Update agent.py

agent.py

@@ -1,66 +1,53 @@
-"""LangGraph Agent – GPT-4.1 / Hugging Face Spaces (import lazy)"""
+"""LangGraph Agent – Solo GPT-4.1 (OpenAI)"""
+
 import os
 from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
-from langgraph.prebuilt import tools_condition, ToolNode
+from langgraph.prebuilt import ToolNode, tools_condition
 from langchain_openai import ChatOpenAI
+from langchain_core.messages import SystemMessage, HumanMessage
+from langchain_core.tools import tool
 
-# --------------------------------------------------------------------------- #
-#  Import facoltativi (se il pacchetto non c'è, il provider viene disattivato) #
-# --------------------------------------------------------------------------- #
-def _lazy_import(name):
-    try:
-        module = __import__(name, fromlist=["*"])
-        return module
-    except ModuleNotFoundError:
-        return None
-
-lg_google = _lazy_import("langchain_google_genai")
-lg_groq = _lazy_import("langchain_groq")
-lg_hf = _lazy_import("langchain_huggingface")
-
-if lg_google:
-    ChatGoogleGenerativeAI = lg_google.ChatGoogleGenerativeAI
-if lg_groq:
-    ChatGroq = lg_groq.ChatGroq
-if lg_hf:
-    ChatHuggingFace = lg_hf.ChatHuggingFace
-    HuggingFaceEndpoint = lg_hf.HuggingFaceEndpoint
-    HuggingFaceEmbeddings = lg_hf.HuggingFaceEmbeddings
-else:
-    from langchain_huggingface import HuggingFaceEmbeddings  # solo embeddings
-
-# --------------------------------------------------------------------------- #
-#  Tools & loaders                                                            #
-# --------------------------------------------------------------------------- #
+# Tools – loaders
 from langchain_community.tools.tavily_search import TavilySearchResults
 from langchain_community.document_loaders import WikipediaLoader, ArxivLoader
-from langchain_community.vectorstores import SupabaseVectorStore
-from langchain_core.messages import SystemMessage, HumanMessage
-from langchain_core.tools import tool
-from langchain.tools.retriever import create_retriever_tool
-from supabase.client import Client, create_client
 
-load_dotenv()  # Secrets di HF Spaces
+# ------------------------------------------------------------------ #
+#  Inizializzazione ambiente                                         #
+# ------------------------------------------------------------------ #
+load_dotenv()  # carica OPENAI_KEY dai secrets dello Space
+
+OPENAI_KEY = os.getenv("OPENAI_KEY")
+if not OPENAI_KEY:
+    raise ValueError("❌  OPENAI_KEY non impostata: aggiungila nei Secrets dello Space.")
 
-# -------------------- TOOL di esempio -------------------- #
+# ------------------------------------------------------------------ #
+#  TOOL di esempio (aritmetica)                                      #
+# ------------------------------------------------------------------ #
 @tool
 def multiply(a: int, b: int) -> int: return a * b
+
 @tool
 def add(a: int, b: int) -> int: return a + b
+
 @tool
 def subtract(a: int, b: int) -> int: return a - b
+
 @tool
 def divide(a: int, b: int) -> float:
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
+
 @tool
 def modulus(a: int, b: int) -> int: return a % b
 
-# -------------------- Wikipedia -------------------------- #
+# ------------------------------------------------------------------ #
+#  TOOL: Wikipedia                                                   #
+# ------------------------------------------------------------------ #
 @tool
 def wiki_search(query: str) -> str:
+    """Search Wikipedia (max 2 docs) and return formatted result."""
     docs = WikipediaLoader(query=query, load_max_docs=2).load()
     return "\n\n---\n\n".join(
         f'<Document source="{d.metadata["source"]}" page="{d.metadata.get("page","")}"/>\n'
@@ -68,9 +55,12 @@ def wiki_search(query: str) -> str:
         for d in docs
     )
 
-# -------------------- Tavily ----------------------------- #
+# ------------------------------------------------------------------ #
+#  TOOL: Tavily                                                      #
+# ------------------------------------------------------------------ #
 @tool
 def web_search(query: str) -> str:
+    """Search Tavily (max 3 docs) and return formatted result."""
     docs = TavilySearchResults(max_results=3).invoke(query=query)
     return "\n\n---\n\n".join(
         f'<Document source="{d.metadata["source"]}" page="{d.metadata.get("page","")}"/>\n'
@@ -78,9 +68,12 @@ def web_search(query: str) -> str:
         for d in docs
     )
 
-# -------------------- ArXiv ------------------------------ #
+# ------------------------------------------------------------------ #
+#  TOOL: ArXiv                                                       #
+# ------------------------------------------------------------------ #
 @tool
 def arxiv_search(query: str) -> str:
+    """Search ArXiv (max 3 docs) and return formatted snippet."""
     docs = ArxivLoader(query=query, load_max_docs=3).load()
     return "\n\n---\n\n".join(
         f'<Document source="{d.metadata["source"]}" page="{d.metadata.get("page","")}"/>\n'
@@ -88,107 +81,57 @@ def arxiv_search(query: str) -> str:
         for d in docs
     )
 
-# --------------------------------------------------------------------------- #
-#  System prompt                                                              #
-# --------------------------------------------------------------------------- #
+# ------------------------------------------------------------------ #
+#  System prompt                                                     #
+# ------------------------------------------------------------------ #
 with open("system_prompt.txt", "r", encoding="utf-8") as f:
     system_prompt = f.read()
 sys_msg = SystemMessage(content=system_prompt)
 
-# --------------------------------------------------------------------------- #
-#  Vector store / retriever                                                   #
-# --------------------------------------------------------------------------- #
-embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
-supabase: Client = create_client(
-    os.environ.get("SUPABASE_URL"),
-    os.environ.get("SUPABASE_SERVICE_KEY"),
-)
-vector_store = SupabaseVectorStore(
-    client=supabase,
-    embedding=embeddings,
-    table_name="documents",
-    query_name="match_documents_langchain",
-)
-question_search_tool = create_retriever_tool(
-    retriever=vector_store.as_retriever(),
-    name="Question Search",
-    description="A tool to retrieve similar questions from a vector store.",
-)
-
-# --------------------------------------------------------------------------- #
-#  Lista tool                                                                 #
-# --------------------------------------------------------------------------- #
+# ------------------------------------------------------------------ #
+#  Lista tool                                                        #
+# ------------------------------------------------------------------ #
 tools = [
     multiply, add, subtract, divide, modulus,
     wiki_search, web_search, arxiv_search,
-    question_search_tool,
 ]
 
-# --------------------------------------------------------------------------- #
-#  Costruzione graph                                                          #
-# --------------------------------------------------------------------------- #
-def build_graph(provider: str = "openai"):
-    # ------------------- LLM selection ------------------------------------- #
-    if provider == "openai":
-        key = os.getenv("OPENAI_KEY")
-        if not key:
-            raise ValueError("OPENAI_KEY mancante: aggiungi la secret nello Space.")
-        llm = ChatOpenAI(model_name="gpt-4.1", temperature=0, openai_api_key=key)
-
-    elif provider == "google":
-        if not lg_google:
-            raise ImportError("langchain_google_genai non installato.")
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
-
-    elif provider == "groq":
-        if not lg_groq:
-            raise ImportError("langchain_groq non installato.")
-        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
-
-    elif provider == "huggingface":
-        if not lg_hf:
-            raise ImportError("langchain_huggingface non installato.")
-        llm = ChatHuggingFace(
-            llm=HuggingFaceEndpoint(
-                url="https://api-inference.huggingface.co/models/Meta-DeepLearning/llama-2-7b-chat-hf",
-                temperature=0,
-            )
-        )
-    else:
-        raise ValueError("Provider non valido.")
-
+# ------------------------------------------------------------------ #
+#  Costruzione graph                                                 #
+# ------------------------------------------------------------------ #
+def build_graph():
+    """Restituisce un graph LangGraph che usa solo GPT-4.1."""
+    llm = ChatOpenAI(
+        model_name="gpt-4.1",
+        temperature=0,
+        openai_api_key=OPENAI_KEY,
+    )
     llm_with_tools = llm.bind_tools(tools)
 
-    # ------------------- Nodes -------------------------------------------- #
+    # Nodes --------------------------------------------------------- #
+    def prepend_system(state: MessagesState):
+        """Prepend system prompt to conversation."""
+        return {"messages": [sys_msg] + state["messages"]}
+
     def assistant(state: MessagesState):
         return {"messages": [llm_with_tools.invoke(state["messages"])]}
 
-    def retriever(state: MessagesState):
-        similar = vector_store.similarity_search(state["messages"][0].content)
-        if similar:
-            example = HumanMessage(
-                content=("Here I provide a similar question and answer for reference:\n\n"
-                         f"{similar[0].page_content}")
-            )
-            return {"messages": [sys_msg] + state["messages"] + [example]}
-        return {"messages": [sys_msg] + state["messages"]}
-
-    # ------------------- Graph -------------------------------------------- #
+    # Graph --------------------------------------------------------- #
     builder = StateGraph(MessagesState)
-    builder.add_node("retriever", retriever)
+    builder.add_node("system", prepend_system)
     builder.add_node("assistant", assistant)
     builder.add_node("tools", ToolNode(tools))
 
-    builder.add_edge(START, "retriever")
-    builder.add_edge("retriever", "assistant")
+    builder.add_edge(START, "system")
+    builder.add_edge("system", "assistant")
     builder.add_conditional_edges("assistant", tools_condition)
     builder.add_edge("tools", "assistant")
 
     return builder.compile()
 
-# --------------------------------------------------------------------------- #
-#  Test rapido                                                                #
-# --------------------------------------------------------------------------- #
+# ------------------------------------------------------------------ #
+#  Test rapido (facoltativo)                                         #
+# ------------------------------------------------------------------ #
 if __name__ == "__main__":
     g = build_graph()
     q = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"