Update app.py

app.py

@@ -5,6 +5,7 @@ import torch
 from transformers import pipeline
 import gradio as gr
 from huggingface_hub import InferenceClient
+import os
 
 docs = load_document("docs")     
 chunks = []
@@ -38,27 +39,37 @@ summarize_tool = DocumentSummarizationTool(
     summarization_pipeline=summarization_pipeline
 )
 
-model = InferenceClientModel("naveensharma16/my-agent-gaia-test")
-# model = InferenceClientModel(
-#     client=InferenceClient()
-# )
+model = InferenceClientModel(client=InferenceClient(model="google/flan-t5-large")) # naveensharma16/document-based-assistant
+print("Loaded model:", model)
 
 agent = CodeAgent(
     tools=[doc_tool, summarize_tool, DuckDuckGoSearchTool(), CodeExecutionTool()],
     model=model,
-    stream_outputs=True
+    stream_outputs=False # True
 )
 
-def agent_interface(query):
+def predict(query: str):
+    """GAIA entrypoint"""
     return agent.run(query)
 
 iface = gr.Interface(
-    fn=agent_interface,
+    fn=predict,
     inputs="text",
     outputs="text",
     title="Document QA Agent"
 )
 
-if __name__ == "__main__":
-    iface.launch(server_name="0.0.0.0", server_port=7860)
+# def agent_interface(query):
+#     return agent.run(query)
 
+# iface = gr.Interface(
+#     fn=agent_interface,
+#     inputs="text",
+#     outputs="text",
+#     title="Document QA Agent"
+# )
+
+if __name__ == "__main__":
+    if os.getenv("RUN_GAIA", "true") == "true":
+        run_gaia_test("naveensharma16")
+    iface.launch(server_name="0.0.0.0", server_port=7860)