LibreChat and A recap on F/OSS LLMs Tools and how to use them in 2024

apt-get update && sudo apt-get upgrade && curl -fsSL https://get.docker.com -o get-docker.sh
sh get-docker.sh && docker version

docker --version

docker volume create ollama_data
docker run -d --name ollama -p 11434:11434 -v ollama_data:/root/.ollama ollama/ollama

docker exec -it ollama ollama --version #just call ollama version on that container

docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama
podman run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama

#version: '3'
services:
  ollama:
    image: ollama/ollama
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    command: tail -f /dev/null
    #command: ollama run deepseek-coder:1.3b

volumes:
  ollama_data:

docker exec -it ollama /bin/bash #use the container interactive terminal
ollama --version  #and get the ollama version

ollama run deepseek-coder:1.3b

pip install gpt4all
#pip install gpt4all==1.0.0
#pip show gpt4all

from gpt4all import GPT4All
model = GPT4All("/home/yourlocaldirectory/Models/orca-mini-3b.ggmlv3.q4_0.bin")

output = model.generate("what is a framework?", max_tokens=100)
#output = model.generate("The capital of France is ", max_tokens=3)
#output = model.generate("If i have 10 years and my mother have 25, when will she have the double of my age?", max_tokens=100)

print(output)

gpt4all==1.0.0

FROM python:3.11

# Copy local code to the container image.
ENV APP_HOME /app
WORKDIR $APP_HOME

COPY . ./

RUN apt-get update && apt-get install -y \
    build-essential \
    curl \
    software-properties-common \
    git \
    && rm -rf /var/lib/apt/lists/*

# Install production dependencies.
RUN pip install -r requirements.txt

#EXPOSE 8501

DOCKER_BUILDKIT=1 docker build --no-cache --progress=plain -t py_gpt4all .

#version: '3.8'

services:
  pygpt4all:
    image: py_gpt4all
    container_name: py_aigen_gpt4all
    # ports:
    #   - "8501:8501"
    working_dir: /app
    #command: python3 app.py
    command: tail -f /dev/null #keep it running

#version: '3'
services:
  ollama:
    image: ollama/ollama
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama

  ollama-webui:
    image: ghcr.io/ollama-webui/ollama-webui:main
    container_name: ollama-webui
    ports:
      - "3000:8080" # 3000 is the port that you will access in your browser
    add-host:
      - "host.docker.internal:host-gateway"
    volumes:
      - ollama-webui_data:/app/backend/data
    restart: always

volumes:
  ollama_data:
  ollama-webui_data:

wget https://github.com/LostRuins/koboldcpp/releases/download/v1.58/koboldcpp-linux-x64
#curl -fLo koboldcpp https://github.com/LostRuins/koboldcpp/releases/latest/download/koboldcpp-linux-x64 && chmod +x koboldcpp-linux-x64

./koboldcpp-linux-x64

git clone https://github.com/go-skynet/LocalAI
cd LocalAI
wget https://huggingface.co/TheBloke/Luna-AI-Llama2-Uncensored-GGUF/resolve/main/luna-ai-llama2-uncensored.Q4_0.gguf -O models/luna-ai-llama2
cp -rf prompt-templates/getting_started.tmpl models/luna-ai-llama2.tmpl
docker compose up -d --pull always

curl http://localhost:8080/v1/models

#test the LLM
curl http://localhost:8080/v1/chat/completions -H "Content-Type: application/json" -d '{
     "model": "luna-ai-llama2",
     "messages": [{"role": "user", "content": "How are you?"}],
     "temperature": 0.9
   }'

{"created":1721812345,"object":"chat.completion","id":"7f9c5191-450e","model":"luna-ai-llama2","choices":[{"index":0,"finish_reason":"stop","message":{"role":"assistant","content":"\nI'm doing well, thank you. How can I assist you today?\n"}}],"usage":{"prompt_tokens":30,"completion_tokens":25,"total_tokens":55}}

# Use the specified Python base image
FROM python:3.11-slim

# Set the working directory in the container
WORKDIR /app

# Install necessary packages
RUN apt-get update && apt-get install -y \
    git \
    build-essential

# Clone the private repository
RUN git clone https://github.com/imartinez/privateGPT

WORKDIR /app/privateGPT

# Install poetry
RUN pip install poetry

# Copy the project files into the container
COPY . /app

#Adding openai pre v1 to avoid error
RUN sed -i '/\[tool\.poetry\.dependencies\]/a openai="1.1.0"' pyproject.toml

# Lock and install dependencies using poetry
RUN poetry lock
RUN poetry install --with ui,local

# Run setup script
#RUN poetry run python scripts/setup # this scripts download the models (the embedding and LLM models)

# Keep the container running
#CMD ["tail", "-f", "/dev/null"]

docker build -t privategpt .
#podman build -t privategpt .

#docker tag privategpt docker.io/fossengineer/privategpt:v1 #example I used
#docker push docker.io/fossengineer/privategpt:v1

docker-compose up -d #to spin the container up with CLI

version: '3'

services:
  ai-privategpt:
    image: privategpt  # Replace with your image name and tag
    container_name: privategpt2
    ports:
      - "8002:8001"
    volumes:
      - ai-privategpt:/app
    # environment:
    #   - SOME_ENV_VAR=value  # Set any environment variables if needed
    #command: tail -f /dev/null
    # environment:
    #   - PGPT_PROFILES=local
    command: /bin/bash -c "poetry run python scripts/setup && tail -f /dev/null" #make run
    
volumes:
  ai-privategpt:

docker exec -it privategpt make run

pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
pip install -r requirements_cpu_only.txt
#python server.py --listen

# Use the specified Python base image
FROM python:3.11-slim

# Set the working directory in the container
WORKDIR /app

# Install necessary packages
RUN apt-get update && apt-get install -y \
    git \
    build-essential

# Install PyTorch, torchvision, and torchaudio
RUN pip3 install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu

# Clone the private repository
RUN git clone https://github.com/oobabooga/text-generation-webui

WORKDIR /app/text-generation-webui

# Install additional Python requirements from a requirements file
#COPY requirements_cpu_only.txt .
RUN pip install -r requirements_cpu_only.txt  

#podman build -t textgenwebui .

version: '3'

services:
  genai_textgenwebui:
    image: textgenwebui
    container_name: textgenwebui
    ports:
      - "7860:7860"
    working_dir: /app/text-generation-webui
    command: python server.py --listen #tail -f /dev/null #keep it running
    volumes: #Choose your way
     # - C:\Users\user\Desktop\AI:/app/text-generation-webui/models
     # - /home/AI_Local:/app/text-generation-webui/models
      - appdata_ooba:/app/text-generation-webui/models

volumes:
   appdata_ooba:   

conda activate textgen 
cd text-generation-webui
#python server.py
python server.py --listen