Update app.py

app.py

@@ -3,6 +3,16 @@ import gradio as gr
 import requests
 import inspect
 import pandas as pd
+from dotenv import load_dotenv
+from typing import List
+from langchain_community.tools import DuckDuckGoSearchRun
+from langchain_experimental.tools import PythonREPLTool
+from langchain_community.vectorstores import FAISS
+from langchain_core.documents import Document
+from langchain_huggingface import HuggingFaceEndpoint, ChatHuggingFace, HuggingFaceEmbeddings
+from langchain_core.messages import HumanMessage
+
+
 
 # (Keep Constants as is)
 # --- Constants ---
@@ -41,6 +51,163 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent()
+        load_dotenv()
+
+# -----------------------------
+# LLM
+# -----------------------------
+#llm = ChatOpenAI(model="gpt-4o-mini", temperature=0)
+#repo_id="deepseek-ai/DeepSeek-V4-Pro"
+llm = ChatHuggingFace(
+    llm=HuggingFaceEndpoint(
+        repo_id="Qwen/Qwen2.5-Coder-32B-Instruct",
+        huggingfacehub_api_token=HF_KEY,
+        task="conversational", # Specify task for the conversational model
+    )
+)
+
+# -----------------------------
+# Tools
+# -----------------------------
+search = DuckDuckGoSearchRun()
+python_tool = PythonREPLTool()
+
+TOOLS = {
+    "search": search.run,
+    "python": python_tool.run,
+    "llm": lambda x: llm.invoke([HumanMessage(content=x)]).content,
+    "summarize": lambda text: llm.invoke([HumanMessage(content=f"Summarize the following:\n{text}")]).content
+}
+
+# -----------------------------
+# Memory (Vector DB)
+# -----------------------------
+embeddings = HuggingFaceEmbeddings()
+# Initialize FAISS with a dummy document to prevent IndexError when trying to determine embedding dimension
+vectorstore = FAISS.from_documents([Document(page_content="initialization_document_for_dimension_inference")], embeddings)
+
+def store_memory(text: str):
+    vectorstore.add_documents([Document(page_content=text)])
+
+def retrieve_memory(query: str):
+    docs = vectorstore.similarity_search(query, k=3)
+    return "\n".join([d.page_content for d in docs])
+
+# -----------------------------
+# Planner
+# -----------------------------
+def plan(goal, history):
+    prompt = f"""
+You are an autonomous agent.
+
+Goal: {goal}
+
+Previous steps:
+{history}
+
+Decide the NEXT action:
+- search(query)
+- python(code)
+- llm(prompt)
+- summarize(text)
+- finish(answer)
+
+Respond ONLY in one line.
+"""
+    return llm.invoke([HumanMessage(content=prompt)]).content.strip()
+
+# -----------------------------
+# Executor
+# -----------------------------
+def execute(action: str):
+    try:
+        if action.startswith("search("):
+            query = action[len("search("):-1]
+            return TOOLS["search"](query)
+
+        elif action.startswith("python("):
+            code = action[len("python("):-1]
+            return TOOLS["python"](code)
+
+        elif action.startswith("llm("):
+            prompt = action[len("llm("):-1]
+            return TOOLS["llm"](prompt)
+
+        elif action.startswith("summarize("):
+            text_to_summarize = action[len("summarize("):-1]
+            return TOOLS["summarize"](text_to_summarize)
+
+        elif action.startswith("finish("):
+            return action[len("finish("):-1]
+
+        else:
+            return "Invalid action"
+
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# -----------------------------
+# Critic (loop control)
+# -----------------------------
+def critic(goal, last_result):
+    prompt = f"""
+Goal: {goal}
+
+Latest result:
+{last_result}
+
+Is the goal achieved? Answer YES or NO.
+"""
+    return "YES" in llm.invoke([HumanMessage(content=prompt)]).content.upper()
+
+# -----------------------------
+# Autonomous Loop
+# -----------------------------
+def autonomous_agent(goal: str, max_steps=15):
+
+    history = ""
+    print(f"\n🎯 Goal: {goal}\n")
+
+    for step in range(max_steps):
+        print(f"--- Step {step+1} ---")
+
+        # Retrieve memory
+        memory_context = retrieve_memory(goal)
+
+        action = plan(goal, history + "\nMemory:\n" + memory_context)
+        print(f"🧠 Plan: {action}")
+
+        result = execute(action)
+        print(f"⚙️ Result: {result[:300]}...\n")
+
+        # Store memory
+        store_memory(f"Action: {action}\nResult: {result}")
+
+        history += f"\nStep {step+1}: {action} → {result}"
+
+        # Finish condition
+        if action.startswith("finish("):
+            print("✅ Finished by agent")
+            return result
+
+        # Critic check
+        if critic(goal, result):
+            print("✅ Critic determined goal achieved")
+            return result
+
+    return "❌ Max steps reached without completion"
+
+# -----------------------------
+# Run
+# -----------------------------
+if __name__ == "__main__":
+    while True:
+        goal = input("\nEnter goal (or 'exit'): ")
+        if goal == "exit":
+            break
+
+        result = autonomous_agent(goal)
+        print(f"\n🤖 Final Output:\n{result}\n")
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None