Update space

README.md

@@ -1,4 +1,8 @@
+sdk: docker
+app_port: 7860
+
 ---
+
 title: RAG Test
 emoji: 💬
 colorFrom: yellow
@@ -7,6 +11,7 @@ sdk: gradio
 sdk_version: 5.0.1
 app_file: app.py
 pinned: false
+
 ---
 
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).

dockerfile

@@ -0,0 +1,29 @@
+# 1) Base Python leve
+FROM python:3.10-slim
+
+# 2) Instala curl (para baixar Ollama) e dependências básicas
+RUN apt-get update && apt-get install -y curl && \
+    # 3) Instala Ollama via script oficial
+    curl -fsSL https://ollama.com/install.sh | sh && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# 4) Cria usuário não-root recomendado
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR $HOME/app
+
+# 5) Copia app e requisitos
+COPY --chown=user:user app.py requirements.txt ./
+
+# 6) Instala libs Python
+RUN pip install --no-cache-dir -r requirements.txt
+
+# 7) Torna start.sh executável
+COPY --chown=user:user start.sh ./
+RUN chmod +x start.sh
+
+# 8) Comando padrão: inicia Ollama e depois app
+CMD ["./start.sh"]

requirements.txt

@@ -2,4 +2,4 @@ huggingface_hub==0.25.2
 ollama
 faiss-cpu
 gradio
-numpy
+numpy

start.sh

@@ -0,0 +1,11 @@
+#!/bin/bash
+# Inicia o servidor Ollama em background (porta 11434 por padrão)
+ollama serve &
+
+# Garante que o modelo nomic-embed-text esteja presente
+if ! ollama list | grep -q "nomic-embed-text"; then
+    ollama pull nomic-embed-text
+fi
+
+# Por fim, inicia seu app Gradio/Streamlit
+python app.py