feat: add agent file, prepare workflow

agent.py

@@ -0,0 +1,148 @@
+import os
+from dotenv import load_dotenv
+from typing import List, Dict, Any, Optional
+import tempfile
+import re
+import json
+import requests
+from urllib.parse import urlparse
+import pytesseract
+from PIL import Image, ImageDraw, ImageFont, ImageEnhance, ImageFilter
+import cmath
+import pandas as pd
+import uuid
+import numpy as np
+from code_interpreter import CodeInterpreter
+
+interpreter_instance = CodeInterpreter()
+
+from image_processing import *
+
+"""Langraph"""
+from langgraph.graph import START, StateGraph, MessagesState
+from langchain_community.tools.tavily_search import TavilySearchResults
+from langchain_community.document_loaders import WikipediaLoader
+from langchain_community.document_loaders import ArxivLoader
+from langgraph.prebuilt import ToolNode, tools_condition
+from langchain_google_genai import ChatGoogleGenerativeAI
+from langchain_groq import ChatGroq
+from langchain_huggingface import (
+    ChatHuggingFace,
+    HuggingFaceEndpoint,
+    HuggingFaceEmbeddings,
+)
+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
+# ------- Tools
+from tools.browse import web_search, wiki_search, arxiv_search
+from tools.document_process import save_and_read_file, analyze_csv_file, analyze_excel_file, extract_text_from_image, download_file_from_url
+from tools.image_tools import analyze_image, generate_simple_image 
+from tools.simple_math import multiply, add, subtract, divide, modulus, power, square_root
+from tools.python_interpreter import execute_code_lang
+
+load_dotenv()
+
+with open("system_prompt.txt", "r", encoding="utf-8") as f:
+    system_prompt = f.read()
+print(system_prompt)
+
+# 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_HUGGING_FACE"), os.environ.get("SUPABASE_SERVICE_ROLE_HUGGING_FACE")
+)
+vector_store = SupabaseVectorStore(
+    client=supabase,
+    embedding=embeddings,
+    table_name="documents2",
+    query_name="match_documents_2",
+)
+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 = [
+    web_search,
+    wiki_search,
+    arxiv_search,
+    multiply,
+    add,
+    subtract,
+    divide,
+    modulus,
+    power,
+    square_root,
+    save_and_read_file,
+    download_file_from_url,
+    extract_text_from_image,
+    analyze_csv_file,
+    analyze_excel_file,
+    execute_code_lang,
+    analyze_image,
+    generate_simple_image,
+]
+
+def build_graph(provider: str = "groq"):
+    if provider == "groq":
+        # Groq https://console.groq.com/docs/models
+        llm = ChatGroq(model="qwen-qwq-32b", temperature=0)
+    elif provider == "huggingface":
+        llm = ChatHuggingFace(
+            llm=HuggingFaceEndpoint(
+                repo_id="TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+                task="text-generation",  # for chat‐style use “text-generation”
+                max_new_tokens=1024,
+                do_sample=False,
+                repetition_penalty=1.03,
+                temperature=0,
+            ),
+            verbose=True,
+        )
+    else:
+        raise ValueError("Invalid provider. Choose 'groq' or 'huggingface'.")
+
+    llm_with_tools = llm.bind_tools(tools)
+
+    def assistant(state: MessagesState):
+        """Assistant Node"""
+        return {"messages": [llm_with_tools.invoke(state['messages'])]}
+
+    def retriever(state: MessagesState):
+        """Retriever Node"""
+        similar_question = vector_store.similiarity_search(state['messages'])
+        if similar_question:  
+            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]}
+        else:
+            return {"messages": [sys_msg] + state["messages"]}
+
+    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")
+    return builder.compile()
+
+if __name__ == "__main__":
+    question = "When was the Cyrus Cylinder created?"
+    graph = build_graph(provider="groq")
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

app.py

@@ -3,6 +3,8 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from langchain_core.messages import HumanMessage
+from agent import build_graph
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -11,13 +13,16 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
+    "An Agent Based on LangGraph"
     def __init__(self):
         print("BasicAgent initialized.")
+        self.graph = build_graph()
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages["messages"][-1].content
+        return answer[14:]
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
@@ -193,4 +198,4 @@ if __name__ == "__main__":
     print("-"*(60 + len(" App Starting ")) + "\n")
 
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)

requirements.txt

@@ -1,2 +1,22 @@
 gradio
-requests
+requests
+gradio
+requests
+langchain
+langchain-community
+langchain-core
+langchain-google-genai
+langchain-huggingface
+langchain-groq
+langchain-tavily
+langchain-chroma
+langgraph
+huggingface_hub
+supabase
+arxiv
+pymupdf
+wikipedia
+pgvector
+python-dotenv
+pytesseract
+matplotlib

system_prompt.txt

@@ -0,0 +1,5 @@
+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 rules above for each element (number or string), ensure there is exactly one space after each comma.
+Your answer should only start with "FINAL ANSWER: ", then follows with the answer.