Update README.md

README.md

@@ -11,27 +11,27 @@ hf_oauth: true
 
 ---
 
-# GAIA Benchmark Agent with LangGraph
+# 🏆 Hugging Face Agents Course — Final Project
 
-This project implements an agent using the LangGraph framework to solve the GAIA benchmark tasks provided by the Hugging Face Agents Course (Unit 4).
+This repository contains my final project submission for the **Hugging Face Agents Course**.
 
-✅ Uses LangChain + LangGraph  
-✅ Handles 20 benchmark questions  
-✅ Submits answers for scoring via Hugging Face leaderboard
+✅ **Project Overview**
+- Multi-step AI agent built with **LangGraph** and **LangChain**
+- Integrates:
+    - Tavily Search API (for real-time factual retrieval)
+    - OpenAI GPT-4 (for advanced reasoning and synthesis)
+    - Custom formatter (to prepare exact-match answers for GAIA benchmark)
 
-## How to run
+✅ **Achievements**
+- Successfully passed the GAIA benchmark with a high score (≥70%)
+- Earned the Hugging Face Certificate of Excellence
 
-1. Clone this repo and push it as a Hugging Face Space (public).
-2. Install the dependencies.
-3. Launch the Space and log in to Hugging Face.
-4. Click "Run Evaluation & Submit All Answers" to evaluate your agent.
+---
 
-## Project files
+## ⚠ Important: Paid API Protection
 
-- `main.py` — Gradio app runner
-- `graph_builder.py` — Builds the LangGraph pipeline
-- `llm_node.py` — Defines LLM node logic
-- `formatter_node.py` — Cleans up answers for exact-match submission
-- `api_client.py` — Wraps GAIA API interactions
+This repository **does NOT include any paid API keys**.
 
-Good luck!
+To run the full agent (with GPT-4), you must:
+1. Provide your own OpenAI API key (`OPENAI_API_KEY`)  
+2. Set it as an environment variable or Hugging Face Space secret