README.md

# 🤖 Autonomous Agentic System – GAIA Benchmark Solver

Final project for the **Hugging Face Agents Course**. I developed a high-level autonomous agent capable of solving complex, multi-step tasks from the **GAIA Benchmark** (General AI Assistants), involving real-world tool usage and multimodal reasoning.

**The concept:** A robust agentic workflow built with **LangGraph** that follows a Thought-Action-Observation cycle to decompose 20 validation queries into executable steps, navigating through technical constraints like API rate limits and data extraction challenges.

**Technical highlights:**

- **Resilient Model Orchestration:** Implemented a **fallback & routing strategy** using Gemini 2.5 Pro as the primary brain, with automatic switching to Gemini Flash, Mistral, or Groq-hosted models to bypass free-tier rate limits without interrupting the execution flow.

- **Advanced Tool Engineering:** Instead of overloading the context window with many small tools, I developed a `utils.py` library of complex functions. The agent uses a refined set of "Super-Tools" (Web Search, Excel manipulation, Audio Transcription, API interaction) that handle internal logic complexity autonomously.

- **Multimodal Innovation:** Engineered a **custom Video Analysis sub-agent**. Since no free direct video-to-text API was available, I built a pipeline that intelligently extracts frames and metadata to reconstruct temporal context for the LLM.

- **Custom RAG Architecture:** Integrated **ChromaDB** with a specialized retrieval algorithm optimized for the specific nuances of the GAIA dataset, ensuring the agent retrieves only the most relevant context for its reasoning steps.

- **Observability & Evaluation:** Self-hosted **LangFuse** locally to monitor traces, evaluate agent costs, and debug the Reasoning-on-Action (Re-Act) loops without incurring cloud platform fees.

- **Full-Stack Deployment:** Interface built with **Gradio** and hosted on Hugging Face Spaces, managed via Git for version control and CI/CD.

**Results:** Successfully validated 16 "Level 1" GAIA tasks, demonstrating a high degree of autonomy in tool selection and the ability to maintain long-term state across multiple reasoning cycles.

[View certification](https://cas-bridge.xethub.hf.co/xet-bridge-us/6800ea554845e4edbca48825/5348431f62a3761b560f14e536cde6005f7dcd9eeda8ac8c7d5835edebe00c15?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=cas%2F20260118%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260118T175600Z&X-Amz-Expires=3600&X-Amz-Signature=27ccefa0283d59c99512a9117a28a66f52bfb9e73c32ffe509ae1a9dfefc4504&X-Amz-SignedHeaders=host&X-Xet-Cas-Uid=65c927db2ba32c95416eb25d&response-content-disposition=inline%3B+filename*%3DUTF-8%27%272025-07-06.png%3B+filename%3D%222025-07-06.png%22%3B&response-content-type=image%2Fpng&x-id=GetObject&Expires=1768762560&Policy=eyJTdGF0ZW1lbnQiOlt7IkNvbmRpdGlvbiI6eyJEYXRlTGVzc1RoYW4iOnsiQVdTOkVwb2NoVGltZSI6MTc2ODc2MjU2MH19LCJSZXNvdXJjZSI6Imh0dHBzOi8vY2FzLWJyaWRnZS54ZXRodWIuaGYuY28veGV0LWJyaWRnZS11cy82ODAwZWE1NTQ4NDVlNGVkYmNhNDg4MjUvNTM0ODQzMWY2MmEzNzYxYjU2MGYxNGU1MzZjZGU2MDA1ZjdkY2Q5ZWVkYThhYzhjN2Q1ODM1ZWRlYmUwMGMxNSoifV19&Signature=S5%7EtuLDo36TB8V5mk8x03P2Pqo5NIOqCLS2XlFkJglZGz%7EOx6ePM8d0he166d%7E6s-KzLXenUv86%7EdSfJ8VWhDpZc7hpsrNsFqltLFYMGXAcmnflST0sZcReTqC3qx3gUlJ1H7%7Ea8geI55JvmcF36RiU-N5fQyBb-oFkOv8A47WjgEngEwSDMrGxq8FmYnKT3vDMu98HNSVQJoVDoBQG5uQxzYn2KmGTLwzWUqVHmRAMMXPoqxwCtRLsu7ZdyP1H0qQDJkD0TvTAegl3fLC2m0I1S0kSW3MQhT2SzOTOFHKKtn10lrPG7GG4iDmW487sZ7g-gU1rFoaGVezvc-W63dw__&Key-Pair-Id=K2L8F4GPSG1IFC)