init commit

Dockerfile

@@ -0,0 +1,34 @@
+FROM ollama/ollama:latest
+
+RUN apt-get update && apt-get install -y \
+    python3 python3-pip tini && \
+    rm -rf /var/lib/apt/lists/*
+
+ENV PYTHONUNBUFFERED=1
+ENV HF_HOME=/app/.huggingface_cache
+ENV OLLAMA_HOME=/app/.ollama  
+ENV OLLAMA_HOST=0.0.0.0:8000
+ENV OLLAMA_ORIGIN=*
+
+RUN mkdir -p /app/.huggingface_cache /app/.ollama \
+    && chmod -R 777 /app  
+
+RUN adduser --disabled-password --gecos "" ollama-user \
+    && chown -R ollama-user:ollama-user /app
+
+WORKDIR /src
+
+COPY requirements.txt .
+
+RUN python3 -m pip install --no-cache-dir -r requirements.txt
+
+USER ollama-user
+
+COPY . .
+
+# Expose ports
+EXPOSE 8000
+EXPOSE 7860
+
+ENTRYPOINT ["/usr/bin/tini", "--"]
+CMD ["sh", "-c", "ollama serve & sleep 5 && ollama pull llama3 && ollama run llama3 < /dev/null & uvicorn app:app --host 0.0.0.0 --port 7860 --workers 4"]

app.py

@@ -0,0 +1,17 @@
+from fastapi import FastAPI, Request, HTTPException
+from fastapi.responses import Response
+import ollama
+
+app = FastAPI()
+
+@app.get('/')
+def home():
+    return "Hello world"
+
+@app.post("/chat")
+async def chat(query: str):
+    if not query:
+        return {"error": "Message cannot be empty."}
+
+    response = ollama.chat(model="llama3", messages=[{"role": "user", "content": query}])
+    return {"response": response['message']['content']}

requirements.txt

@@ -0,0 +1,3 @@
+fastapi
+uvicorn
+ollama