first alpha deployed to huggingface

.gitignore

@@ -65,4 +65,6 @@ logs/
 **/niners_output/schedule_with_result_embedding.gsheet
 
 # Utility files
-z_utils/
+z_utils/
+# IFX-huge-league
+IFX-huge-league

Makefile

@@ -28,4 +28,16 @@ command-raw:
 
 clean-requirements:
 	rm -f poetry.lock
-	
+
+# Build the Docker image for the 'runtime' stage in api/Dockerfile, tagged as huge-ifx-api:prod
+build-prod:
+	cd api && docker build -f Dockerfile --target runtime -t huge-ifx-api:prod .
+
+# Build the prod image and run it locally, mapping ports 7860 and 8000
+up-build-prod: build-prod
+	docker run --rm -it -p 7860:7860 -p 8000:8000 --env-file .env -e DEV_MODE=true huge-ifx-api:prod
+
+# Push the prod image to GitHub Container Registry
+push-prod-ghcr:
+	docker tag huge-ifx-api:prod ghcr.io/rbalch/huge-ifx-api:prod
+	docker push ghcr.io/rbalch/huge-ifx-api:prod

api/Dockerfile

@@ -14,7 +14,8 @@ WORKDIR /code
 
 # Set environment variables for Python behavior and module discovery
 ENV PYTHONUNBUFFERED=1
-ENV PYTHONPATH="$PYTHONPATH:/code"
+# ENV PYTHONPATH="$PYTHONPATH:/code"
+ENV PYTHONPATH="${PYTHONPATH}:/code"
 
 # Setup history for interactive sessions (ensuring it’s mappable with a volume)
 RUN mkdir -p /root/history
@@ -49,7 +50,7 @@ COPY --from=base /usr/local/bin /usr/local/bin
 
 # Reapply the environment variables for runtime and module resolution
 ENV PYTHONUNBUFFERED=1
-ENV PYTHONPATH="$PYTHONPATH:/code"
+ENV PYTHONPATH="${PYTHONPATH}:/code"
 
 # Recreate history and Huggingface cache directories (so they can be mapped via Docker Compose)
 RUN mkdir -p /root/history
@@ -62,8 +63,8 @@ ENV HF_HOME="/huggingface_cache"
 # Copy the rest of your application code
 COPY . .
 
-# Expose your service port
-EXPOSE 8000
+# Expose gradio port
+EXPOSE 7860
 
 # Final command to run your app
-CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["python", "server_gradio.py"]

api/server_gradio.py

@@ -1,6 +1,7 @@
 import asyncio
 import gradio as gr
 import time
+import os
 from pydantic import BaseModel
 from threading import Thread
 from langchain_core.messages import HumanMessage, AIMessage
@@ -9,6 +10,7 @@ from workflows.base import build_workflow
 
 lorem_ipsum = """Lorem ipsum dolor sit amet, consectetur adipiscing elit, sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum."""
 show_state = True
+dev_mode = os.getenv("DEV_MODE", "").lower() == "true"
 
 
 class AppState(BaseModel):
@@ -131,4 +133,7 @@ with gr.Blocks() as demo:
 
 
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=8000)
+    if dev_mode:
+        demo.launch(server_name="0.0.0.0", server_port=8000)
+    else:
+        demo.launch(server_name="0.0.0.0")

docker-compose.yaml

@@ -18,6 +18,7 @@ services:
       - .env
     environment:
       DEBUG: false
+      DEV_MODE: true
     # command: uvicorn server:app --reload --host 0.0.0.0 --port 8000 --reload --log-level debug
     command: gradio server_gradio.py