updated agent

agent.py

@@ -1,84 +1,206 @@
-from langgraph.graph import StateGraph, END
-from langchain_core.messages import HumanMessage, AIMessage, SystemMessage
+"""LangGraph Agent"""
+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 langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+from langchain_community.vectorstores import SupabaseVectorStore
+from langchain_core.messages import SystemMessage, HumanMessage
 from langchain_core.tools import tool
-from typing import TypedDict, Optional
-import pandas as pd
-import string
+from langchain.tools.retriever import create_retriever_tool
+from supabase.client import Client, create_client
 
-# Tools
+load_dotenv()
 
 @tool
-def reverse_string(text: str) -> str:
-    """Reverse a string"""
-    return text[::-1]
+def multiply(a: int, b: int) -> int:
+    """Multiply two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a * b
 
 @tool
-def extract_numbers(text: str) -> str:
-    """Extract digits from a string"""
-    return "".join([c for c in text if c.isdigit()])
+def add(a: int, b: int) -> int:
+    """Add two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a + b
 
 @tool
-def strip_punctuation(text: str) -> str:
-    """Remove all punctuation from a string"""
-    return text.translate(str.maketrans('', '', string.punctuation))
+def subtract(a: int, b: int) -> int:
+    """Subtract two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a - b
 
 @tool
-def open_file_as_text(file_path: str) -> str:
-    """Open and return the contents of a text/CSV file"""
-    try:
-        with open(file_path, 'r', encoding='utf-8') as f:
-            return f.read()
-    except Exception as e:
-        return f"Error reading file: {e}"
+def divide(a: int, b: int) -> int:
+    """Divide two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    if b == 0:
+        raise ValueError("Cannot divide by zero.")
+    return a / b
 
 @tool
-def analyze_csv_file(file_path: str) -> str:
-    """Read CSV file and return summary of content"""
-    try:
-        df = pd.read_csv(file_path)
-        summary = f"Columns: {', '.join(df.columns)}\nRows: {len(df)}"
-        return summary
-    except Exception as e:
-        return f"CSV error: {e}"
-
-# Agent State
-
-class AgentState(TypedDict):
-    messages: list
-    file_name: Optional[str]
-
-# Build Graph
-
-def build_graph():
-    tools = [reverse_string, extract_numbers, strip_punctuation, open_file_as_text, analyze_csv_file]
-
-    def decide_path(state: AgentState):
-        if state.get("file_name"):
-            msg = HumanMessage(content=f"Analyze this file: {state['file_name']}")
-            return {"messages": state["messages"] + [msg]}
-        else:
-            return {"messages": state["messages"]}
-
-    def agent_logic(state: AgentState):
-        question = state["messages"][-1].content.lower()
-        answer = ""
-        if "reverse" in question:
-            answer = reverse_string.invoke(question)
-        elif "number" in question:
-            answer = extract_numbers.invoke(question)
-        elif "punctuation" in question:
-            answer = strip_punctuation.invoke(question)
-        elif state.get("file_name") and state["file_name"].endswith(".csv"):
-            answer = analyze_csv_file.invoke(state["file_name"])
-        else:
-            answer = "unsupported question"
-
-        return {"messages": state["messages"] + [AIMessage(content=f'final_answer("{answer}")')]}
-
-    builder = StateGraph(AgentState)
-    builder.add_node("router", decide_path)
-    builder.add_node("agent_logic", agent_logic)
-    builder.set_entry_point("router")
-    builder.set_finish_point("agent_logic")
-    builder.add_edge("router", "agent_logic")
+def modulus(a: int, b: int) -> int:
+    """Get the modulus of two numbers.
+    Args:
+        a: first int
+        b: second int
+    """
+    return a % b
+
+@tool
+def wiki_search(query: str) -> str:
+    """Search Wikipedia for a query and return maximum 2 results.
+    Args:
+        query: The search query."""
+    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"wiki_results": formatted_search_docs}
+
+@tool
+def web_search(query: str) -> str:
+    """Search Tavily for a query and return maximum 3 results.
+    Args:
+        query: The search query."""
+    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"web_results": formatted_search_docs}
+
+@tool
+def arvix_search(query: str) -> str:
+    """Search Arxiv for a query and return maximum 3 result.
+    Args:
+        query: The search query."""
+    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
+    formatted_search_docs = "\n\n---\n\n".join(
+        [
+            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
+            for doc in search_docs
+        ])
+    return {"arvix_results": formatted_search_docs}
+
+
+
+# load the system prompt from the file
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+
+# System message
+sys_msg = SystemMessage(content=system_prompt)
+
+# build a retriever
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2") #  dim=768
+supabase: Client = create_client(
+    os.environ.get("SUPABASE_URL"),
+    os.environ.get("SUPABASE_SERVICE_KEY"))
+vector_store = SupabaseVectorStore(
+    client=supabase,
+    embedding= embeddings,
+    table_name="Vector_Test",
+    query_name="match_documents_langchain",
+)
+create_retriever_tool = create_retriever_tool(
+    retriever=vector_store.as_retriever(),
+    name="Question Search",
+    description="A tool to retrieve similar questions from a vector store.",
+)
+
+
+
+tools = [
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    wiki_search,
+    web_search,
+    arvix_search,
+]
+
+# Build graph function
+def build_graph(provider: str = "groq"):
+    """Build the graph"""
+    # Load environment variables from .env file
+    if provider == "google":
+        # Google Gemini
+        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
+    elif provider == "groq":
+        # Groq https://console.groq.com/docs/models
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
+    elif provider == "huggingface":
+        # TODO: Add huggingface endpoint
+        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'.")
+    # Bind tools to LLM
+    llm_with_tools = llm.bind_tools(tools)
+
+    # Node
+    def assistant(state: MessagesState):
+        """Assistant node"""
+        return {"messages": [llm_with_tools.invoke(state["messages"])]}
+
+    def retriever(state: MessagesState):
+        """Retriever node"""
+        similar_question = vector_store.similarity_search(state["messages"][0].content)
+        example_msg = HumanMessage(
+            content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",
+        )
+        return {"messages": [sys_msg] + state["messages"] + [example_msg]}
+
+    builder = StateGraph(MessagesState)
+    builder.add_node("retriever", retriever)
+    builder.add_node("assistant", assistant)
+    builder.add_node("tools", ToolNode(tools))
+    builder.add_edge(START, "retriever")
+    builder.add_edge("retriever", "assistant")
+    builder.add_conditional_edges(
+        "assistant",
+        tools_condition,
+    )
+    builder.add_edge("tools", "assistant")
+
+    # Compile graph
     return builder.compile()
+
+# test
+if __name__ == "__main__":
+    question = "When was a picture of St. Thomas Aquinas first added to the Wikipedia page on the Principle of double effect?"
+    # Build the graph
+    graph = build_graph(provider="groq")
+    # Run the graph
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

requirements.txt

@@ -1,10 +1,18 @@
 gradio
-pandas
 requests
-langchain-core
-langgraph
 langchain
 langchain-community
-huggingface-hub
-python-dotenv
-tqdm
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+supabase
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv

system_prompt.txt

@@ -1,22 +1,5 @@
-You are a highly focused AI assistant participating in the GAIA benchmark challenge.
-
-Your goal is to answer each question precisely, using tools when necessary. Follow these rules strictly:
-
-- NEVER output explanations, reasoning, or intermediate thoughts.
-- NEVER output more than one answer.
-- When you reach the final answer, return it as:
-  final_answer("...your answer...")
-- Use tools like `open_file_as_text`, `extract_number`, or `reverse_text` where applicable.
-- If the task involves a file, use the given file_name — not one mentioned in the question.
-- Format numbers without commas or symbols (e.g., 1739, not $1,739).
-- Format comma-separated lists with a single space after each comma.
-- When extracting or reversing text, always preserve punctuation unless instructed otherwise.
-
-Example:
-Q: What is the reverse of "good job"?
-A: final_answer("boj doog")
-
-Q: What is the third number listed in the attached file?
-A: final_answer("42")
-
-Be brief. Be exact. Use tools. Output only the final answer in the correct format.
+You are a helpful assistant tasked with answering questions using a set of tools. 
+Now, I will ask you a question. Report your thoughts, and finish your answer with the following template: 
+FINAL ANSWER: [YOUR FINAL ANSWER]. 
+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.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer.