Upload 2 files

agent.py

@@ -0,0 +1,164 @@
+import os
+from dotenv import load_dotenv
+from typing import List, Dict, Any, Optional
+import tempfile
+import requests
+from urllib.parse import urlparse
+import pandas as pd
+import numpy as np
+
+from image_processing import *
+
+"""Langraph"""
+from langgraph.graph import START, StateGraph, MessagesState
+from langchain_community.tools import DuckDuckGoSearchResults
+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
+from langchain_openai import ChatOpenAI
+
+load_dotenv()
+
+### =============== SEARCH TOOLS =============== ###
+
+@tool
+def web_search(query: str) -> str:
+    """Search DuckDuckGo for a query and return maximum 3 results.
+    Args:
+        query: The search query."""
+    search_results = DuckDuckGoSearchResults(max_results=3).invoke(query=query)
+    # DuckDuckGo returns results as a string, so we need to parse it
+    # The format is typically [snippet: text, title: title, link: url]
+    formatted_results = []
+    
+    # Remove outer quotes if present and format properly
+    if isinstance(search_results, str):
+        # Simple parsing of the DuckDuckGo result format
+        result_entries = search_results.split('], [')
+        for entry in result_entries:
+            # Clean up the entry
+            entry = entry.replace('[', '').replace(']', '').strip()
+            if entry:
+                # Extract components
+                parts = {}
+                for part in entry.split(', '):
+                    if ': ' in part:
+                        key, value = part.split(': ', 1)
+                        parts[key] = value
+                
+                # Format as document
+                if 'snippet' in parts and 'link' in parts:
+                    doc_content = parts.get('snippet', '')
+                    doc_source = parts.get('link', '')
+                    formatted_results.append(
+                        f'<Document source="{doc_source}" page=""/>\n{doc_content}\n</Document>'
+                    )
+    
+    if not formatted_results:
+        return {"web_results": "No results found"}
+    
+    return {"web_results": "\n\n---\n\n".join(formatted_results)}
+
+### =============== DOCUMENT PROCESSING TOOLS =============== ###
+# File handling still requires external tools
+
+@tool
+def save_and_read_file(content: str, filename: Optional[str] = None) -> str:
+    """
+    Save content to a file and return the path.
+    Args:
+        content (str): the content to save to the file
+        filename (str, optional): the name of the file. If not provided, a random name file will be created.
+    """
+    temp_dir = tempfile.gettempdir()
+    if filename is None:
+        temp_file = tempfile.NamedTemporaryFile(delete=False, dir=temp_dir)
+        filepath = temp_file.name
+    else:
+        filepath = os.path.join(temp_dir, filename)
+
+    with open(filepath, "w") as f:
+        f.write(content)
+
+    return f"File saved to {filepath}. You can read this file to process its contents."
+
+
+# load the system prompt from the file
+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)
+
+tools = [
+    web_search,
+    save_and_read_file,
+]
+
+
+# Build graph function
+def build_graph(provider: str = "openai"):
+    """Build the graph"""
+    # Load environment variables from .env file
+    if provider == "openai":
+        llm = ChatOpenAI(model="gpt-4.1", temperature=0)
+    elif provider == "groq":
+        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",
+                max_new_tokens=1024,
+                do_sample=False,
+                repetition_penalty=1.03,
+                temperature=0,
+            ),
+            verbose=True,
+        )
+    else:
+        raise ValueError("Invalid provider. Choose 'openai', '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"])]}
+
+    builder = StateGraph(MessagesState)
+    builder.add_node("assistant", assistant)
+    builder.add_node("tools", ToolNode(tools))
+    builder.add_edge(START, "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?"
+    graph = build_graph(provider="openai")
+    messages = [HumanMessage(content=question)]
+    messages = graph.invoke({"messages": messages})
+    for m in messages["messages"]:
+        m.pretty_print()

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.