add system prompt and change llama for claude model

agents/search_agent.py

@@ -1,14 +1,31 @@
 from graphs.search import build_workflow
-from langchain_core.messages import HumanMessage
+from langchain_core.messages import HumanMessage, SystemMessage
+from langfuse.callback import CallbackHandler
+from dotenv import load_dotenv
+load_dotenv()
+langfuse_handler = CallbackHandler(host="https://cloud.langfuse.com")
+
 class SearchAgent:
     def __init__(self):
         print("SearchAgent initialized.")
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
         workflow = build_workflow()
-        messages = [HumanMessage(question)]
+        messages= [SystemMessage("""You are a general AI assistant. I will ask you a question. Report your thoughts, and finish with only the answer. \n
+                                 YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. 
+                                 If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise.
+                                 If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise.
+                                 If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.""")]
+        messages = messages + [HumanMessage(content=question)]
         messages = workflow.invoke({
             "messages":messages
-        })
+        }, config={"callbacks": [langfuse_handler]})
         
-        return messages["messages"][-1].content
+        return messages["messages"][-1].content
+    
+""" if __name__ == "__main__":
+    question = "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia."
+    agent = SearchAgent()
+    submit_answer = agent(question)
+    
+    print(submit_answer) """

graphs/search.py

@@ -1,5 +1,5 @@
-from models.models import  groq_model
-from tools.search import arxiv_search, web_search, wikipedia_search
+from models.models import  groq_model, anthropic_model
+from tools.search import arxiv_search, web_search, google_search
 from langgraph.graph import StateGraph, START, END, MessagesState
 from langgraph.prebuilt import ToolNode
 from langchain_core.messages import HumanMessage
@@ -7,12 +7,12 @@ from langchain_core.messages import HumanMessage
 tools = [
     arxiv_search,
     web_search,
-    wikipedia_search
+    google_search,
 ]
 
 tool_node = ToolNode(tools)
-bound_model = groq_model.bind_tools(tools)
-
+#bound_model = groq_model.bind_tools(tools)
+bound_model = anthropic_model.bind_tools(tools)
 # Define the function that calls the model
 def call_model(state: MessagesState):
     response = bound_model.invoke(state["messages"])
@@ -40,12 +40,12 @@ def build_workflow():
     workflow.add_edge("action", "agent")
     return workflow.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?"
+""" if __name__ == "__main__":
+    question = "How many studio albums were published by Mercedes Sosa between 2000 and 2009 (included)? You can use the latest 2022 version of english wikipedia."
     # Build the graph
     graph = build_workflow()
     # Run the graph
     messages = [HumanMessage(content=question)]
     messages = graph.invoke({"messages": messages})
     for m in messages["messages"]:
-        m.pretty_print()
+        m.pretty_print() """

tools/search.py

@@ -1,5 +1,6 @@
 from langchain_core.tools import tool
 from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.utilities import GoogleSerperAPIWrapper
 from langchain_community.document_loaders import WikipediaLoader
 from langchain_community.document_loaders import ArxivLoader
 from dotenv import load_dotenv
@@ -11,6 +12,7 @@ def wikipedia_search(query: str) -> str:
     """Search Wikipedia for a query and return maximum 1 result.
     Args:
         query: The search query."""
+    query = "Mercedes Sosa"
     search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
     
     formatted_search_docs = "\n\n---\n\n".join(
@@ -54,3 +56,17 @@ def arxiv_search(query: str) -> str:
         ]
     )
     return {"arxiv_results": formatted_search_docs}
+
+@tool
+def google_search(query: str) -> str:
+    """
+    Search Google for a query and return maximum 2 result. 
+    Args: query: The search query.
+    """
+    search_docs = GoogleSerperAPIWrapper()
+    result = search_docs.run(query)
+    
+    return {"google_results": result}
+
+   
+