Update .gitignore and add ollama install to Dockerfile

.gitignore

@@ -1 +1,2 @@
-.venv
+.venv/
+__pycache__/

Dockerfile

@@ -1,28 +1,53 @@
-# read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
-# you will also find guides on how best to write your Dockerfile
+FROM nvidia/cuda:12.3.2-cudnn9-devel-ubuntu22.04
+ENV DEBIAN_FRONTEND=noninteractive
 
-FROM python:3.9
 
-WORKDIR /code
 
-COPY ./requirements.txt /code/requirements.txt
+RUN rm -f /etc/apt/sources.list.d/*.list && \
+    apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    ca-certificates \
+    sudo \
+    git \
+    git-lfs \
+    zip \
+    unzip \
+    htop \
+    bzip2 \
+    libx11-6 \
+    build-essential \
+    libsndfile-dev \
+    software-properties-common \
+    gcc \
+    wget \
+    lshw \
+    python3-dev \
+    && rm -rf /var/lib/apt/lists/*
 
-RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
 
-# Set up a new user named "user" with user ID 1000
-RUN useradd -m -u 1000 user
 
-# Switch to the "user" user
+RUN curl -fsSL https://ollama.com/install.sh | sh
+
+RUN useradd -m -u 1000 user
 USER user
 
-# Set home to the user's home directory
+
 ENV HOME=/home/user \
     PATH=/home/user/.local/bin:$PATH
 
+ENV CONDA_AUTO_UPDATE_CONDA=true \
+    PATH=$HOME/miniconda/bin:$PATH
+
+RUN curl -sLo ~/miniconda.sh https://repo.anaconda.com/miniconda/Miniconda3-py311_23.11.0-1-Linux-x86_64.sh \
+    && chmod +x ~/miniconda.sh \
+    && ~/miniconda.sh -b -p ~/miniconda \
+    && rm ~/miniconda.sh \
+    && conda clean -ya
+
 # Set the working directory to the user's home directory
 WORKDIR $HOME/app
-
-# Copy the current directory contents into the container at $HOME/app setting the owner to the user
 COPY --chown=user . $HOME/app
+RUN pip install --no-cache-dir --upgrade -r $HOME/app/requirements.txt
 
-CMD ["python", "main.py"]
+RUN chmod +x $HOME/app/start_server.sh
+ENTRYPOINT ["/home/user/app/start_server.sh"]

main.py

@@ -2,7 +2,7 @@ from langchain.schema import AIMessage, HumanMessage
 import gradio as gr
 from langchain_community.llms import Ollama
 
-llm = Ollama(model="mistral:7b", timeout=1000)
+llm = Ollama(model="llama3:8b", timeout=1000)
 
 def predict(message, history):
     history_langchain_format = []
@@ -10,7 +10,17 @@ def predict(message, history):
         history_langchain_format.append(HumanMessage(content=human))
         history_langchain_format.append(AIMessage(content=ai))
     history_langchain_format.append(HumanMessage(content=message))
-    gpt_response = llm.invoke(history_langchain_format)
-    return gpt_response
+    try:
+        caht_response = llm.invoke(history_langchain_format)
+    except Exception as e:
+        caht_response = "Error: " + str(e)
+        
+    return caht_response
 
-gr.ChatInterface(predict).launch()
+def run():
+    demo = gr.ChatInterface(predict)
+    demo.launch(server_name="0.0.0.0", server_port=7860)
+
+
+if __name__ == "__main__":
+    run()

start_server.sh

@@ -0,0 +1,9 @@
+#!/bin/bash
+# Start the background task
+ollama serve &
+
+ollama pull mistral:7b  > /dev/null 2>&1
+ollama pull llama3:8b > /dev/null 2>&1
+
+# Start the Gradio app
+python main.py