From bbfe2fb1224350be7b9fba1527675c331e75926f Mon Sep 17 00:00:00 2001
From: Daniele Viti <dnviti@gmail.com>
Date: Sat, 23 Dec 2023 16:55:45 +0100
Subject: [PATCH 1/5] Added a better more generic gitignore which covers both
 python and nodejs

---
 .gitignore | 291 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 291 insertions(+)

diff --git a/.gitignore b/.gitignore
index 6635cf55..1250aef9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -8,3 +8,294 @@ node_modules
 !.env.example
 vite.config.js.timestamp-*
 vite.config.ts.timestamp-*
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Logs
+logs
+*.log
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+lerna-debug.log*
+.pnpm-debug.log*
+
+# Diagnostic reports (https://nodejs.org/api/report.html)
+report.[0-9]*.[0-9]*.[0-9]*.[0-9]*.json
+
+# Runtime data
+pids
+*.pid
+*.seed
+*.pid.lock
+
+# Directory for instrumented libs generated by jscoverage/JSCover
+lib-cov
+
+# Coverage directory used by tools like istanbul
+coverage
+*.lcov
+
+# nyc test coverage
+.nyc_output
+
+# Grunt intermediate storage (https://gruntjs.com/creating-plugins#storing-task-files)
+.grunt
+
+# Bower dependency directory (https://bower.io/)
+bower_components
+
+# node-waf configuration
+.lock-wscript
+
+# Compiled binary addons (https://nodejs.org/api/addons.html)
+build/Release
+
+# Dependency directories
+node_modules/
+jspm_packages/
+
+# Snowpack dependency directory (https://snowpack.dev/)
+web_modules/
+
+# TypeScript cache
+*.tsbuildinfo
+
+# Optional npm cache directory
+.npm
+
+# Optional eslint cache
+.eslintcache
+
+# Optional stylelint cache
+.stylelintcache
+
+# Microbundle cache
+.rpt2_cache/
+.rts2_cache_cjs/
+.rts2_cache_es/
+.rts2_cache_umd/
+
+# Optional REPL history
+.node_repl_history
+
+# Output of 'npm pack'
+*.tgz
+
+# Yarn Integrity file
+.yarn-integrity
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# parcel-bundler cache (https://parceljs.org/)
+.cache
+.parcel-cache
+
+# Next.js build output
+.next
+out
+
+# Nuxt.js build / generate output
+.nuxt
+dist
+
+# Gatsby files
+.cache/
+# Comment in the public line in if your project uses Gatsby and not Next.js
+# https://nextjs.org/blog/next-9-1#public-directory-support
+# public
+
+# vuepress build output
+.vuepress/dist
+
+# vuepress v2.x temp and cache directory
+.temp
+.cache
+
+# Docusaurus cache and generated files
+.docusaurus
+
+# Serverless directories
+.serverless/
+
+# FuseBox cache
+.fusebox/
+
+# DynamoDB Local files
+.dynamodb/
+
+# TernJS port file
+.tern-port
+
+# Stores VSCode versions used for testing VSCode extensions
+.vscode-test
+
+# yarn v2
+.yarn/cache
+.yarn/unplugged
+.yarn/build-state.yml
+.yarn/install-state.gz
+.pnp.*
\ No newline at end of file

From a580aa898466b83ae07975a04c331f8ea4de71b4 Mon Sep 17 00:00:00 2001
From: Daniele Viti <dnviti@gmail.com>
Date: Sat, 23 Dec 2023 18:33:15 +0100
Subject: [PATCH 2/5] general-compose-improvements

---
 docker-compose.api.yaml                   |   6 +
 docker-compose.gpu.yaml                   |  12 ++
 docker-compose.yml => docker-compose.yaml |  16 +-
 run-compose.sh                            | 194 ++++++++++++++++++++++
 4 files changed, 214 insertions(+), 14 deletions(-)
 create mode 100644 docker-compose.api.yaml
 create mode 100644 docker-compose.gpu.yaml
 rename docker-compose.yml => docker-compose.yaml (62%)
 create mode 100755 run-compose.sh

diff --git a/docker-compose.api.yaml b/docker-compose.api.yaml
new file mode 100644
index 00000000..5e4b2227
--- /dev/null
+++ b/docker-compose.api.yaml
@@ -0,0 +1,6 @@
+version: '3.8'
+
+services:
+  ollama:
+    ports:
+      - ${OLLAMA_WEBAPI_PORT-11434}:11434
diff --git a/docker-compose.gpu.yaml b/docker-compose.gpu.yaml
new file mode 100644
index 00000000..7df6b91a
--- /dev/null
+++ b/docker-compose.gpu.yaml
@@ -0,0 +1,12 @@
+version: '3.8'
+
+services:
+  ollama:
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: ${OLLAMA_GPU_DRIVER-nvidia}
+              count: ${OLLAMA_GPU_COUNT-1}
+              capabilities:
+                - gpu
diff --git a/docker-compose.yml b/docker-compose.yaml
similarity index 62%
rename from docker-compose.yml
rename to docker-compose.yaml
index b5036354..68e1954d 100644
--- a/docker-compose.yml
+++ b/docker-compose.yaml
@@ -1,21 +1,9 @@
-version: '3.6'
+version: '3.8'
 
 services:
   ollama:
-    # Uncomment below for GPU support
-    # deploy:
-    #   resources:
-    #     reservations:
-    #       devices:
-    #         - driver: nvidia
-    #           count: 1
-    #           capabilities:
-    #             - gpu
     volumes:
       - ollama:/root/.ollama
-    # Uncomment below to expose Ollama API outside the container stack
-    # ports:
-    #   - 11434:11434
     container_name: ollama
     pull_policy: always
     tty: true
@@ -33,7 +21,7 @@ services:
     depends_on:
       - ollama
     ports:
-      - 3000:8080
+      - ${OLLAMA_WEBUI_PORT-3000}:8080
     environment:
       - "OLLAMA_API_BASE_URL=http://ollama:11434/api"
     extra_hosts:
diff --git a/run-compose.sh b/run-compose.sh
new file mode 100755
index 00000000..dba87625
--- /dev/null
+++ b/run-compose.sh
@@ -0,0 +1,194 @@
+#!/bin/bash
+
+# Define color and formatting codes
+BOLD='\033[1m'
+GREEN='\033[1;32m'
+WHITE='\033[1;37m'
+RED='\033[0;31m'
+NC='\033[0m' # No Color
+# Unicode character for tick mark
+TICK='\u2713'
+
+# Detect GPU driver
+get_gpu_driver() {
+    # Detect NVIDIA GPUs
+    if lspci | grep -i nvidia >/dev/null; then
+        echo "nvidia"
+        return
+    fi
+
+    # Detect AMD GPUs (including GCN architecture check for amdgpu vs radeon)
+    if lspci | grep -i amd >/dev/null; then
+        # List of known GCN and later architecture cards
+        # This is a simplified list, and in a real-world scenario, you'd want a more comprehensive one
+        local gcn_and_later=("Radeon HD 7000" "Radeon HD 8000" "Radeon R5" "Radeon R7" "Radeon R9" "Radeon RX")
+
+        # Get GPU information
+        local gpu_info=$(lspci | grep -i 'vga.*amd')
+
+        for model in "${gcn_and_later[@]}"; do
+            if echo "$gpu_info" | grep -iq "$model"; then
+                echo "amdgpu"
+                return
+            fi
+        done
+
+        # Default to radeon if no GCN or later architecture is detected
+        echo "radeon"
+        return
+    fi
+
+    # Detect Intel GPUs
+    if lspci | grep -i intel >/dev/null; then
+        echo "i915"
+        return
+    fi
+
+    # If no known GPU is detected
+    echo "Unknown or unsupported GPU driver"
+    exit 1
+}
+
+# Function for rolling animation
+show_loading() {
+    local spin='-\|/'
+    local i=0
+
+    printf " "
+
+    while kill -0 $1 2>/dev/null; do
+        i=$(( (i+1) %4 ))
+        printf "\b${spin:$i:1}"
+        sleep .1
+    done
+
+    # Replace the spinner with a tick
+    printf "\b${GREEN}${TICK}${NC}"
+}
+
+# Usage information
+usage() {
+    echo "Usage: $0 [OPTIONS]"
+    echo "Options:"
+    echo "  --enable-gpu[count=COUNT]  Enable GPU support with the specified count."
+    echo "  --enable-api[port=PORT]    Enable API and expose it on the specified port."
+    echo "  --webui[port=PORT]         Set the port for the web user interface."
+    echo ""
+    echo "Examples:"
+    echo "  $0 --enable-gpu[count=1]"
+    echo "  $0 --enable-api[port=11435]"
+    echo "  $0 --enable-gpu[count=1] --enable-api[port=12345] --webui[port=3000]"
+    echo ""
+    echo "This script configures and runs a docker-compose setup with optional GPU support, API exposure, and web UI configuration."
+    echo "About the gpu to use, the script automatically detects it using the "lspci" command."
+    echo "In this case the gpu detected is: $(get_gpu_driver)"
+}
+
+# Default values
+gpu_count=1
+api_port=11435
+webui_port=3000
+
+# Function to extract value from the parameter
+extract_value() {
+    echo "$1" | sed -E 's/.*\[.*=(.*)\].*/\1/; t; s/.*//'
+}
+
+# Check if no arguments were provided
+# if [ $# -eq 0 ]; then
+#     usage
+#     exit 1
+# fi
+
+# Parse arguments
+while [[ $# -gt 0 ]]; do
+    key="$1"
+
+    case $key in
+        --enable-gpu*)
+            enable_gpu=true
+            value=$(extract_value "$key")
+            gpu_count=${value:-1}
+            ;;
+        --enable-api*)
+            enable_api=true
+            value=$(extract_value "$key")
+            api_port=${value:-11435}
+            ;;
+        --webui*)
+            value=$(extract_value "$key")
+            webui_port=${value:-3000}
+            ;;
+        -h|--help)
+            usage
+            exit
+            ;;
+        *)
+            # Unknown option
+            echo "Unknown option: $key"
+            usage
+            exit 1
+            ;;
+    esac
+    shift # past argument or value
+done
+
+DEFAULT_COMPOSE_COMMAND="docker compose -f docker-compose.yaml"
+if [[ $enable_gpu == true ]]; then
+    # Validate and process command-line arguments
+    if [[ -n $gpu_count ]]; then
+        if ! [[ $gpu_count =~ ^[0-9]+$ ]]; then
+            echo "Invalid GPU count: $gpu_count"
+            exit 1
+        fi
+        echo "Enabling GPU with $gpu_count GPUs"
+        # Add your GPU allocation logic here
+        export OLLAMA_GPU_DRIVER=$(get_gpu_driver)
+    fi
+    DEFAULT_COMPOSE_COMMAND+=" -f docker-compose.gpu.yaml"
+fi
+if [[ $enable_api == true ]]; then
+    DEFAULT_COMPOSE_COMMAND+=" -f docker-compose.api.yaml"
+    if [[ -n $api_port ]]; then
+        export OLLAMA_WEBAPI_PORT=$api_port # Set OLLAMA_WEBAPI_PORT environment variable
+    fi
+fi
+DEFAULT_COMPOSE_COMMAND+=" up -d > /dev/null 2>&1"
+
+# Recap of environment variables
+echo
+echo -e "${WHITE}${BOLD}Current Setup:${NC}"
+echo -e "   ${GREEN}${BOLD}GPU Driver:${NC} ${OLLAMA_GPU_DRIVER:-Not Enabled}"
+echo -e "   ${GREEN}${BOLD}WebAPI Port:${NC} ${OLLAMA_WEBAPI_PORT:-Not Enabled}"
+echo -e "   ${GREEN}${BOLD}WebUI Port:${NC} $webui_port"
+echo
+
+# Ask for user acceptance
+echo -ne "${WHITE}${BOLD}Do you want to proceed with current setup? (Y/n): ${NC}"
+read -n1 -s choice
+
+if [[ $choice == "" || $choice == "y" ]]; then
+    # Execute the command with the current user
+    eval "docker compose down > /dev/null 2>&1; $DEFAULT_COMPOSE_COMMAND" &
+
+    # Capture the background process PID
+    PID=$!
+
+    # Display the loading animation
+    show_loading $PID
+
+    # Wait for the command to finish
+    wait $PID
+
+    echo
+    # Check exit status
+    if [ $? -eq 0 ]; then
+        echo -e "${GREEN}${BOLD}Compose project started successfully.${NC}"
+    else
+        echo -e "${RED}${BOLD}There was an error starting the compose project.${NC}"
+    fi
+else
+    echo "Aborted."
+fi
+
+echo
\ No newline at end of file

From 2994e1abcd30d307fa03246ee14a35802d00003c Mon Sep 17 00:00:00 2001
From: Daniele Viti <dnviti@gmail.com>
Date: Sat, 23 Dec 2023 18:49:49 +0100
Subject: [PATCH 3/5] fixed gpu count env

---
 run-compose.sh | 8 ++------
 1 file changed, 2 insertions(+), 6 deletions(-)

diff --git a/run-compose.sh b/run-compose.sh
index dba87625..5f0effa9 100755
--- a/run-compose.sh
+++ b/run-compose.sh
@@ -94,12 +94,6 @@ extract_value() {
     echo "$1" | sed -E 's/.*\[.*=(.*)\].*/\1/; t; s/.*//'
 }
 
-# Check if no arguments were provided
-# if [ $# -eq 0 ]; then
-#     usage
-#     exit 1
-# fi
-
 # Parse arguments
 while [[ $# -gt 0 ]]; do
     key="$1"
@@ -144,6 +138,7 @@ if [[ $enable_gpu == true ]]; then
         echo "Enabling GPU with $gpu_count GPUs"
         # Add your GPU allocation logic here
         export OLLAMA_GPU_DRIVER=$(get_gpu_driver)
+        export OLLAMA_GPU_COUNT=$gpu_count # Set OLLAMA_GPU_COUNT environment variable
     fi
     DEFAULT_COMPOSE_COMMAND+=" -f docker-compose.gpu.yaml"
 fi
@@ -159,6 +154,7 @@ DEFAULT_COMPOSE_COMMAND+=" up -d > /dev/null 2>&1"
 echo
 echo -e "${WHITE}${BOLD}Current Setup:${NC}"
 echo -e "   ${GREEN}${BOLD}GPU Driver:${NC} ${OLLAMA_GPU_DRIVER:-Not Enabled}"
+echo -e "   ${GREEN}${BOLD}GPU Count:${NC} ${OLLAMA_GPU_COUNT:-Not Enabled}"
 echo -e "   ${GREEN}${BOLD}WebAPI Port:${NC} ${OLLAMA_WEBAPI_PORT:-Not Enabled}"
 echo -e "   ${GREEN}${BOLD}WebUI Port:${NC} $webui_port"
 echo

From 7e0f5ff20e90f5e571cace1ea76940ce6ff87502 Mon Sep 17 00:00:00 2001
From: Timothy Jaeryang Baek <timothyjrbeck@gmail.com>
Date: Sun, 24 Dec 2023 04:35:40 -0500
Subject: [PATCH 4/5] doc: feature update

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index de950ef8..83650903 100644
--- a/README.md
+++ b/README.md
@@ -45,7 +45,7 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
 
 - ⚙️ **Many Models Conversations**: Effortlessly engage with various models simultaneously, harnessing their unique strengths for optimal responses. Enhance your experience by leveraging a diverse set of models in parallel.
 
-- 🤝 **OpenAI Model Integration**: Seamlessly utilize OpenAI models alongside Ollama models for a versatile conversational experience.
+- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations with Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
 
 - 🔄 **Regeneration History Access**: Easily revisit and explore your entire regeneration history.
 

From bc7a6bae8605dcaf9f9bcbbb05874091d33446ec Mon Sep 17 00:00:00 2001
From: Timothy Jaeryang Baek <timothyjrbeck@gmail.com>
Date: Sun, 24 Dec 2023 04:36:40 -0500
Subject: [PATCH 5/5] Update README.md

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 83650903..5af1a6c4 100644
--- a/README.md
+++ b/README.md
@@ -45,7 +45,7 @@ Also check our sibling project, [OllamaHub](https://ollamahub.com/), where you c
 
 - ⚙️ **Many Models Conversations**: Effortlessly engage with various models simultaneously, harnessing their unique strengths for optimal responses. Enhance your experience by leveraging a diverse set of models in parallel.
 
-- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations with Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
+- 🤝 **OpenAI API Integration**: Effortlessly integrate OpenAI-compatible API for versatile conversations alongside Ollama models. Customize the API Base URL to link with **LMStudio, Mistral, OpenRouter, and more**.
 
 - 🔄 **Regeneration History Access**: Easily revisit and explore your entire regeneration history.