ollama

Dockerfile

@@ -2,16 +2,28 @@
 # you will also find guides on how best to write your Dockerfile
 
 # FROM python:3.9
-FROM ollama:0.1.44
+FROM ollama/ollama:0.12.1-rc0
 
-RUN useradd -m -u 1000 user
-USER user
-ENV PATH="/home/user/.local/bin:$PATH"
+# RUN useradd -m -u 1000 ollama
+# USER user
+# ENV PATH="/home/user/.local/bin:$PATH"
 
 WORKDIR /app
 
-COPY --chown=user ./requirements.txt requirements.txt
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
+# COPY --chown=user ./requirements.txt requirements.txt
+# RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+RUN which ollama
 
 COPY --chown=user . /app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+RUN ls -alh ./
+#Override the entrypoint to run the vLLM server with your model
+ENTRYPOINT ["python3", "./app.py"]
+# , "&&",\
+#   "python3", "-m", "vllm.entrypoints.openai.api_server", \
+#   "--model", "Qwen/Qwen3-8B", \
+#   "--host", "0.0.0.0", \
+#   "--port", "7860", \
+#   "--tensor-parallel-size", "4", \
+#   "--trust-remote-code" ]
+# # CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]