claude API usuage

agent.py

@@ -4,6 +4,7 @@ from dotenv import load_dotenv
 from langgraph.graph import START, StateGraph, MessagesState
 from langgraph.prebuilt import tools_condition
 from langgraph.prebuilt import ToolNode
+from langchain_anthropic.ChatAnthropic import ChatAnthropi
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain_groq import ChatGroq
 from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
@@ -22,46 +23,38 @@ load_dotenv()
 # === Tools ===
 @tool
 def multiply(a: int, b: int) -> int:
-    """Multiply two integers."""
     return a * b
 
 @tool
 def add(a: int, b: int) -> int:
-    """Add two integers."""
     return a + b
 
 @tool
 def subtract(a: int, b: int) -> int:
-    """Subtract b from a."""
     return a - b
 
 @tool
 def divide(a: int, b: int) -> float:
-    """Divide a by b."""
     if b == 0:
         raise ValueError("Cannot divide by zero.")
     return a / b
 
 @tool
 def modulus(a: int, b: int) -> int:
-    """Return a modulo b."""
     return a % b
 
 @tool
 def wiki_search(query: str) -> str:
-    """Search Wikipedia for a query."""
     search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
     return "\n\n---\n\n".join([doc.page_content for doc in search_docs])
 
 @tool
 def web_search(query: str) -> str:
-    """Search the web for a query."""
     search_docs = TavilySearchResults(max_results=3).invoke(query=query)
     return "\n\n---\n\n".join([doc.page_content for doc in search_docs])
 
 @tool
 def arvix_search(query: str) -> str:
-    """Search Arxiv for a query."""
     search_docs = ArxivLoader(query=query, load_max_docs=3).load()
     return "\n\n---\n\n".join([doc.page_content[:1000] for doc in search_docs])
 
@@ -70,9 +63,9 @@ with open("system_prompt.txt", "r", encoding="utf-8") as f:
     system_prompt = f.read()
 sys_msg = SystemMessage(content=system_prompt)
 
-# === Embedding and Supabase Setup ===
+# === Embedding & Vector DB ===
 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"))
+supabase: Client = create_client(os.getenv("SUPABASE_URL"), os.getenv("SUPABASE_SERVICE_KEY"))
 vector_store = SupabaseVectorStore(
     client=supabase,
     embedding=embeddings,
@@ -80,24 +73,27 @@ vector_store = SupabaseVectorStore(
     query_name="match_documents_langchain",
 )
 
-# === Tools List ===
+# === Tools ===
 tools = [multiply, add, subtract, divide, modulus, wiki_search, web_search, arvix_search]
 
-# === Graph Builder ===
-def build_graph(provider: str = "groq"):
-    if provider == "google":
-        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+# === LangGraph Agent Definition ===
+def build_graph(provider: str = "claude"):
+    if provider == "claude":
+        llm = ChatAnthropic(
+            model="claude-3-sonnet-20240229",
+            temperature=0,
+            anthropic_api_key=os.getenv("CLAUDE_API_KEY")
+        )
     elif provider == "groq":
         llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
+    elif provider == "google":
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
     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.")
+        raise ValueError("Invalid provider")
 
     llm_with_tools = llm.bind_tools(tools)
 
@@ -123,7 +119,6 @@ def build_graph(provider: str = "groq"):
     builder.add_node("assistant", assistant)
     builder.add_node("tools", ToolNode(tools))
     builder.add_node("formatter", formatter)
-
     builder.add_edge(START, "retriever")
     builder.add_edge("retriever", "assistant")
     builder.add_conditional_edges("assistant", tools_condition)
@@ -132,9 +127,10 @@ def build_graph(provider: str = "groq"):
 
     return builder.compile()
 
-# === Test Entry Point ===
+# === Test ===
 if __name__ == "__main__":
-    graph = build_graph("groq")
-    messages = graph.invoke({"messages": [HumanMessage(content="What is the capital of France?")]})
-    for msg in messages["messages"]:
-        msg.pretty_print()
+    graph = build_graph("claude")
+    result = graph.invoke({"messages": [HumanMessage(content="What is the capital of France?")]})
+    for m in result["messages"]:
+        m.pretty_print()
+

app.py

@@ -13,8 +13,8 @@ cached_answers = []
 
 class ChatAgent:
     def __init__(self):
-        print("ChatAgent initialized with LangGraph workflow.")
-        self.graph = build_graph()
+        print("ChatAgent initialized with Claude LangGraph workflow.")
+        self.graph = build_graph("claude")
 
     def __call__(self, question: str) -> str:
         print(f"Processing question: {question[:60]}...")
@@ -95,8 +95,8 @@ with gr.Blocks() as demo:
     gr.Markdown("Run the agent on all tasks, then submit for scoring.")
     gr.LoginButton()
 
-    run_button = gr.Button("🧠 Run Agent")
-    submit_button = gr.Button("📤 Submit Answers")
+    run_button = gr.Button("\U0001F9E0 Run Agent")
+    submit_button = gr.Button("\U0001F4E4 Submit Answers")
 
     status_box = gr.Textbox(label="Status", lines=3)
     table = gr.DataFrame(label="Results", wrap=True)