Spaces:
Sleeping
Sleeping
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,24 +0,0 @@
|
|
| 1 |
-
# GAIA Benchmark Agent with LangGraph
|
| 2 |
-
|
| 3 |
-
This project implements an agent using the LangGraph framework to solve the GAIA benchmark tasks provided by the Hugging Face Agents Course (Unit 4).
|
| 4 |
-
|
| 5 |
-
✅ Uses LangChain + LangGraph
|
| 6 |
-
✅ Handles 20 benchmark questions
|
| 7 |
-
✅ Submits answers for scoring via Hugging Face leaderboard
|
| 8 |
-
|
| 9 |
-
## How to run
|
| 10 |
-
|
| 11 |
-
1. Clone this repo and push it as a Hugging Face Space (public).
|
| 12 |
-
2. Install the dependencies.
|
| 13 |
-
3. Launch the Space and log in to Hugging Face.
|
| 14 |
-
4. Click "Run Evaluation & Submit All Answers" to evaluate your agent.
|
| 15 |
-
|
| 16 |
-
## Project files
|
| 17 |
-
|
| 18 |
-
- `main.py` — Gradio app runner
|
| 19 |
-
- `graph_builder.py` — Builds the LangGraph pipeline
|
| 20 |
-
- `llm_node.py` — Defines LLM node logic
|
| 21 |
-
- `formatter_node.py` — Cleans up answers for exact-match submission
|
| 22 |
-
- `api_client.py` — Wraps GAIA API interactions
|
| 23 |
-
|
| 24 |
-
Good luck!
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|