Upload 2 files

README.md

@@ -36,11 +36,18 @@ itself.
 To run it (locally or as a Space), set the `HF_TOKEN` secret/env var to a
 Hugging Face access token with Inference API permission. Optionally set
 `HF_AGENT_MODEL` to override the default model
-(`meta-llama/Llama-3.3-70B-Instruct`), and `HF_AGENT_PROVIDER` to override the
-default Inference Provider (`together`) — pinned explicitly because the
+(`meta-llama/Llama-3.1-8B-Instruct`), and `HF_AGENT_PROVIDER` to override the
+default Inference Provider (`deepinfra`) — pinned explicitly because the
 router's `auto` selection can land on a provider that doesn't support tool
 calling for a given model (HTTP 422 `UNSUPPORTED_OPENAI_PARAMS`), and not every
 provider hosts every model (HTTP 4xx "Model ... is not supported by provider
 ..."). Check `https://router.huggingface.co/v1/models/<repo_id>` to see which
 providers host a given model and whether they support tools before changing
-either variable.
+either variable.
+
+The default 8B model was chosen for cost, not accuracy: the HF free tier only
+includes $0.10/month of Inference Provider credits, and a 70B model burns
+through that almost instantly across a full GAIA run. If you have more budget
+(pre-paid credits or PRO), switch to a larger model such as
+`meta-llama/Llama-3.3-70B-Instruct` on the `together` provider for more
+reliable reasoning on harder questions.

agent.py

@@ -29,14 +29,18 @@ from langgraph.prebuilt import ToolNode, tools_condition
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 # Any HF Inference API model that supports tool calling works here. Override via the
-# HF_AGENT_MODEL env var without touching code.
-HF_MODEL_REPO_ID = os.getenv("HF_AGENT_MODEL", "meta-llama/Llama-3.3-70B-Instruct")
+# HF_AGENT_MODEL env var without touching code. Llama-3.1-8B-Instruct is ~15x cheaper per
+# token than the 70B default it replaced - picked to fit the free tier's tiny $0.10/month
+# Inference Provider credit allowance; swap to a larger model (e.g.
+# meta-llama/Llama-3.3-70B-Instruct on the "together" provider) once you have more budget
+# for better reasoning on harder GAIA questions.
+HF_MODEL_REPO_ID = os.getenv("HF_AGENT_MODEL", "meta-llama/Llama-3.1-8B-Instruct")
 
 # Left unset ("auto"), the HF router picks whichever provider is cheapest/fastest for the
 # model, and some of those don't support the `tools` param at all (HTTP 422
 # UNSUPPORTED_OPENAI_PARAMS). Pin one that reliably supports tool calling; override via
 # HF_AGENT_PROVIDER if it doesn't happen to host HF_AGENT_MODEL.
-HF_MODEL_PROVIDER = os.getenv("HF_AGENT_PROVIDER", "together")
+HF_MODEL_PROVIDER = os.getenv("HF_AGENT_PROVIDER", "deepinfra")
 
 with open(Path(__file__).parent / "system_prompt.txt", "r", encoding="utf-8") as f:
     SYSTEM_PROMPT = f.read()