Upload 3 files

Dockerfile

@@ -0,0 +1,20 @@
+FROM python:3.12.6
+
+# Set working directory inside container
+WORKDIR /code
+
+# Copy requirements file (fixing the typo in the filename and path)
+COPY ./requirement.txt /code/requirement.txt
+
+# Install dependencies
+RUN pip install --no-cache-dir --upgrade -r /code/requirement.txt
+
+# Add a non-root user and switch to it
+RUN useradd -m user
+USER user
+
+# Copy the FastAPI app code
+COPY . /code
+
+# Command to run the app with uvicorn
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8000"]

app.py

@@ -0,0 +1,20 @@
+from fastapi import FastAPI
+from transformers import pipeline
+
+
+app= FastAPI()
+
+# Use a pipeline as a high-level helper
+from transformers import pipeline
+
+pipe = pipeline("text-generation", model="nvidia/Llama-3_3-Nemotron-Super-49B-v1_5", trust_remote_code=True)
+
+@app.get("/")
+def home():
+    return {"Message":"Hello World"}
+
+
+@app.get("./generate")
+def generate(text:str):
+    output=pipe(text)
+    return{"output":output[0]['generated_text']}

requirment.txt

@@ -0,0 +1,10 @@
+fastapi>=0.68.0
+uvicorn>=0.15.0
+transformers>=4.12.0
+torch>=1.9.0
+sentencepiece>=0.1.96  # Required for some models (e.g., T5, BART)
+tokenizers>=0.10.0
+python-multipart  # For handling file uploads in FastAPI
+pydantic>=1.8.0  # For data validation in FastAPI
+requests>=2.26.0  # Optional, useful for making HTTP calls
+numpy>=1.21.0  # Required for some model outputs