rename /api/tags to /api/list

fix: gguf int type

README.md

@@ -276,3 +276,4 @@ See the [API documentation](./docs/api.md) for all endpoints.
 - [Hass Ollama Conversation](https://github.com/ej52/hass-ollama-conversation)
 - [Rivet plugin](https://github.com/abrenneke/rivet-plugin-ollama)
 - [Llama Coder](https://github.com/ex3ndr/llama-coder) (Copilot alternative using Ollama)
+- [Obsidian BMO Chatbot plugin](https://github.com/longy2k/obsidian-bmo-chatbot)

api/client.go

@@ -262,7 +262,7 @@ func (c *Client) Create(ctx context.Context, req *CreateRequest, fn CreateProgre
 
 func (c *Client) List(ctx context.Context) (*ListResponse, error) {
 	var lr ListResponse
-	if err := c.do(ctx, http.MethodGet, "/api/tags", nil, &lr); err != nil {
+	if err := c.do(ctx, http.MethodGet, "/api/list", nil, &lr); err != nil {
 		return nil, err
 	}
 	return &lr, nil

api/client.py

@@ -157,7 +157,7 @@ def push(model_name, insecure=False, callback=None):
 # List models that are available locally.
 def list():
     try:
-        response = requests.get(f"{BASE_URL}/api/tags")
+        response = requests.get(f"{BASE_URL}/api/list")
         response.raise_for_status()
         data = response.json()
         models = data.get('models', [])

docs/api.md

@@ -372,10 +372,10 @@ curl -T model.bin -X POST http://localhost:11434/api/blobs/sha256:29fdb92e57cf08
 
 Return 201 Created if the blob was successfully created.
 
-## List Local Models
+## List Models
 
 ```shell
-GET /api/tags
+GET /api/list
 ```
 
 List models that are available locally.
@@ -385,7 +385,7 @@ List models that are available locally.
 #### Request
 
 ```shell
-curl http://localhost:11434/api/tags
+curl http://localhost:11434/api/list
 ```
 
 #### Response

llm/gguf.go

@@ -335,7 +335,7 @@ func (llm *ggufModel) readArrayV1(r io.Reader) (arr []any, err error) {
 		case ggufTypeUint8:
 			arr = append(arr, llm.readU8(r))
 		case ggufTypeInt8:
-			arr = append(arr, llm.readU8(r))
+			arr = append(arr, llm.readI8(r))
 		case ggufTypeUint16:
 			arr = append(arr, llm.readU16(r))
 		case ggufTypeInt16:
@@ -376,7 +376,7 @@ func (llm *ggufModel) readArray(r io.Reader) (arr []any, err error) {
 		case ggufTypeUint8:
 			arr = append(arr, llm.readU8(r))
 		case ggufTypeInt8:
-			arr = append(arr, llm.readU8(r))
+			arr = append(arr, llm.readI8(r))
 		case ggufTypeUint16:
 			arr = append(arr, llm.readU16(r))
 		case ggufTypeInt16:

llm/llama.cpp/generate_darwin_amd64.go

@@ -13,6 +13,6 @@ package llm
 
 //go:generate git submodule update --force gguf
 //go:generate git -C gguf apply ../patches/0001-update-default-log-target.patch
-//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_METAL=off -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DCMAKE_SYSTEM_NAME=Darwin -DCMAKE_SYSTEM_PROCESSOR=x86_64 -DCMAKE_OSX_ARCHITECTURES=x86_64 -DCMAKE_OSX_DEPLOYMENT_TARGET=11.0 -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=on -DLLAMA_AVX512=off -DLLAMA_FMA=on -DLLAMA_F16C=on
+//go:generate cmake -S gguf -B gguf/build/cpu -DLLAMA_METAL=off -DLLAMA_ACCELERATE=on -DLLAMA_K_QUANTS=on -DCMAKE_SYSTEM_NAME=Darwin -DCMAKE_SYSTEM_PROCESSOR=x86_64 -DCMAKE_OSX_ARCHITECTURES=x86_64 -DCMAKE_OSX_DEPLOYMENT_TARGET=11.0 -DLLAMA_NATIVE=off -DLLAMA_AVX=on -DLLAMA_AVX2=off -DLLAMA_AVX512=off -DLLAMA_FMA=off -DLLAMA_F16C=off
 //go:generate cmake --build gguf/build/cpu --target server --config Release
 //go:generate mv gguf/build/cpu/bin/server gguf/build/cpu/bin/ollama-runner

scripts/build_docker.sh

@@ -13,5 +13,5 @@ docker buildx build \
     --cache-from type=local,src=.cache \
     --cache-to type=local,dest=.cache \
     -f Dockerfile \
-    -t ollama \
+    -t ollama/ollama:$VERSION \
     .

scripts/install.sh

@@ -8,16 +8,20 @@ status() { echo ">>> $*" >&2; }
 error() { echo "ERROR $*"; exit 1; }
 warning() { echo "WARNING: $*"; }
 
-runnable() { command -v "$1" >/dev/null; }
+TEMP_DIR=$(mktemp -d)
+cleanup() { rm -rf $TEMP_DIR; }
+trap cleanup EXIT
+
+available() { command -v $1 >/dev/null; }
 require() {
-    MISSING=''
-    for TOOL in "$@"; do
-        if ! runnable "$TOOL"; then
+    local MISSING=''
+    for TOOL in $*; do
+        if ! available $TOOL; then
             MISSING="$MISSING $TOOL"
         fi
     done
 
-    echo "$MISSING"
+    echo $MISSING
 }
 
 [ "$(uname -s)" = "Linux" ] || error 'This script is intended to run on Linux only.'
@@ -32,7 +36,7 @@ esac
 SUDO=
 if [ "$(id -u)" -ne 0 ]; then
     # Running as root, no need for sudo
-    if ! runnable sudo; then
+    if ! available sudo; then
         error "This script requires superuser permissions. Please re-run as root."
     fi
 
@@ -48,43 +52,22 @@ if [ -n "$NEEDS" ]; then
     exit 1
 fi
 
-TEMP_DIR=$(mktemp -d)
-cleanup() {
-    EXIT_CODE=$?
-    rm -rf "$TEMP_DIR"
-
-    if runnable nvidia-smi && lsmod | grep -qv nvidia; then
-        status 'Reboot to complete NVIDIA CUDA driver install.'
-    fi
-
-    if runnable systemctl >/dev/null; then
-        $SUDO systemctl restart ollama
-
-        timeout 10 sh -c 'while :; do [ "$(curl -s http://127.0.0.1:11434)" = "Ollama is running" ] && break; sleep 0.2; done' \
-            && status 'Ollama service is available at 127.0.0.1:11434' \
-            || true
-    fi
-
-    if runnable ollama; then
-        status 'Install completed. Run "ollama --help" to get started.'
-    fi
-
-    exit $EXIT_CODE
-}
-trap cleanup EXIT
-
 status "Downloading ollama..."
-curl --fail --show-error --location --progress-bar -o "$TEMP_DIR/ollama" "https://ollama.ai/download/ollama-linux-$ARCH"
+curl --fail --show-error --location --progress-bar -o $TEMP_DIR/ollama "https://ollama.ai/download/ollama-linux-$ARCH"
 
-for BIN_DIR in /usr/local/bin /usr/bin /bin; do
-    if echo "$PATH" | grep -q $BIN_DIR; then
-        break
-    fi
+for BINDIR in /usr/local/bin /usr/bin /bin; do
+    echo $PATH | grep -q $BINDIR && break || continue
 done
 
-status "Installing ollama to $BIN_DIR..."
-$SUDO install -o0 -g0 -m755 -d "$BIN_DIR"
-$SUDO install -o0 -g0 -m755 "$TEMP_DIR/ollama" "$BIN_DIR/ollama"
+status "Installing ollama to $BINDIR..."
+$SUDO install -o0 -g0 -m755 -d $BINDIR
+$SUDO install -o0 -g0 -m755 $TEMP_DIR/ollama $BINDIR/ollama
+
+install_success() { 
+    status 'The Ollama API is now available at 0.0.0.0:11434.'
+    status 'Install complete. Run "ollama" from the command line.'
+}
+trap install_success EXIT
 
 # Everything from this point onwards is optional.
 
@@ -94,6 +77,9 @@ configure_systemd() {
         $SUDO useradd -r -s /bin/false -m -d /usr/share/ollama ollama
     fi
 
+    status "Adding current user to ollama group..."
+    $SUDO usermod -a -G ollama $(whoami)
+
     status "Creating ollama systemd service..."
     cat <<EOF | $SUDO tee /etc/systemd/system/ollama.service >/dev/null
 [Unit]
@@ -101,7 +87,7 @@ Description=Ollama Service
 After=network-online.target
 
 [Service]
-ExecStart=$BIN_DIR/ollama serve
+ExecStart=$BINDIR/ollama serve
 User=ollama
 Group=ollama
 Restart=always
@@ -117,36 +103,39 @@ EOF
             status "Enabling and starting ollama service..."
             $SUDO systemctl daemon-reload
             $SUDO systemctl enable ollama
+
+            start_service() { $SUDO systemctl restart ollama; }
+            trap start_service EXIT
             ;;
     esac
 }
 
-if runnable systemctl; then
+if available systemctl; then
     configure_systemd
 fi
 
+if ! available lspci && ! available lshw; then
+    warning "Unable to detect NVIDIA GPU. Install lspci or lshw to automatically detect and install NVIDIA CUDA drivers."
+    exit 0
+fi
+
 check_gpu() {
     case $1 in
-        lspci) runnable lspci && lspci -d '10de:' | grep -q 'NVIDIA' || return 1 ;;
-        lshw) runnable lshw && $SUDO lshw -c display -numeric | grep -q 'vendor: .* \[10DE\]' || return 1 ;;
-        nvidia-smi) runnable nvidia-smi || return 1 ;;
+        lspci) available lspci && lspci -d '10de:' | grep -q 'NVIDIA' || return 1 ;;
+        lshw) available lshw && $SUDO lshw -c display -numeric | grep -q 'vendor: .* \[10DE\]' || return 1 ;;
+        nvidia-smi) available nvidia-smi || return 1 ;;
     esac
 }
 
 if check_gpu nvidia-smi; then
     status "NVIDIA GPU installed."
-    exit
-fi
-
-if ! runnable lspci && ! runnable lshw; then
-    warning "Unable to detect NVIDIA GPU. Install lspci or lshw to automatically detect and install NVIDIA CUDA drivers."
-    exit
+    exit 0
 fi
 
 if ! check_gpu lspci && ! check_gpu lshw; then
     install_success
-    warning "No NVIDIA GPU detected. Ollama will run with CPU."
-    exit
+    warning "No NVIDIA GPU detected. Ollama will run in CPU-only mode."
+    exit 0
 fi
 
 # ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#rhel-7-centos-7
@@ -158,10 +147,10 @@ install_cuda_driver_yum() {
     case $PACKAGE_MANAGER in
         yum)
             $SUDO $PACKAGE_MANAGER -y install yum-utils
-            $SUDO $PACKAGE_MANAGER-config-manager --add-repo "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo"
+            $SUDO $PACKAGE_MANAGER-config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo
             ;;
         dnf)
-            $SUDO $PACKAGE_MANAGER config-manager --add-repo "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo"
+            $SUDO $PACKAGE_MANAGER config-manager --add-repo https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-$1$2.repo
             ;;
     esac
 
@@ -169,7 +158,7 @@ install_cuda_driver_yum() {
         rhel)
             status 'Installing EPEL repository...'
             # EPEL is required for third-party dependencies such as dkms and libvdpau
-            $SUDO $PACKAGE_MANAGER -y install "https://dl.fedoraproject.org/pub/epel/epel-release-latest-$2.noarch.rpm" || true
+            $SUDO $PACKAGE_MANAGER -y install https://dl.fedoraproject.org/pub/epel/epel-release-latest-$2.noarch.rpm || true
             ;;
     esac
 
@@ -186,20 +175,20 @@ install_cuda_driver_yum() {
 # ref: https://docs.nvidia.com/cuda/cuda-installation-guide-linux/index.html#debian
 install_cuda_driver_apt() {
     status 'Installing NVIDIA repository...'
-    curl -fsSL -o "$TEMP_DIR/cuda-keyring.deb" "https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-keyring_1.1-1_all.deb"
+    curl -fsSL -o $TEMP_DIR/cuda-keyring.deb https://developer.download.nvidia.com/compute/cuda/repos/$1$2/$(uname -m)/cuda-keyring_1.1-1_all.deb
 
     case $1 in
         debian)
             status 'Enabling contrib sources...'
-            [ -f "/etc/apt/sources.list.d/debian.sources" ] \
-                && SOURCES_LIST="/etc/apt/sources.list.d/debian.sources" \
-                || SOURCES_LIST="/etc/apt/sources.list"
-            sed 's/main/contrib/' <"$SOURCES_LIST" | $SUDO tee /etc/apt/sources.list.d/contrib.sources >/dev/null
+            $SUDO sed 's/main/contrib/' < /etc/apt/sources.list | $SUDO tee /etc/apt/sources.list.d/contrib.list > /dev/null
+            if [ -f "/etc/apt/sources.list.d/debian.sources" ]; then
+                $SUDO sed 's/main/contrib/' < /etc/apt/sources.list.d/debian.sources | $SUDO tee /etc/apt/sources.list.d/contrib.sources > /dev/null
+            fi
             ;;
     esac
 
     status 'Installing CUDA driver...'
-    $SUDO dpkg -i "$TEMP_DIR/cuda-keyring.deb"
+    $SUDO dpkg -i $TEMP_DIR/cuda-keyring.deb
     $SUDO apt-get update
 
     [ -n "$SUDO" ] && SUDO_E="$SUDO -E" || SUDO_E=
@@ -217,7 +206,7 @@ OS_VERSION=$VERSION_ID
 
 PACKAGE_MANAGER=
 for PACKAGE_MANAGER in dnf yum apt-get; do
-    if runnable $PACKAGE_MANAGER; then
+    if available $PACKAGE_MANAGER; then
         break
     fi
 done
@@ -226,14 +215,14 @@ if [ -z "$PACKAGE_MANAGER" ]; then
     error "Unknown package manager. Skipping CUDA installation."
 fi
 
-if ! check_gpu nvidia-smi || nvidia-smi | grep -qo "CUDA Version: [0-9]*\.[0-9]*"; then
+if ! check_gpu nvidia-smi || [ -z "$(nvidia-smi | grep -o "CUDA Version: [0-9]*\.[0-9]*")" ]; then
     case $OS_NAME in
-        centos|rhel) install_cuda_driver_yum 'rhel' "$OS_VERSION" ;;
-        rocky) install_cuda_driver_yum 'rhel' "$(echo "$OS_VERSION" | cut -c1)" ;;
-        fedora) install_cuda_driver_yum "$OS_NAME" "$OS_VERSION" ;;
+        centos|rhel) install_cuda_driver_yum 'rhel' $OS_VERSION ;;
+        rocky) install_cuda_driver_yum 'rhel' $(echo $OS_VERSION | cut -c1) ;;
+        fedora) install_cuda_driver_yum $OS_NAME $OS_VERSION ;;
         amzn) install_cuda_driver_yum 'fedora' '35' ;;
-        debian) install_cuda_driver_apt "$OS_NAME" "$OS_VERSION" ;;
-        ubuntu) install_cuda_driver_apt "$OS_NAME" "$(echo "$OS_VERSION" | sed 's/\.//')" ;;
+        debian) install_cuda_driver_apt $OS_NAME $OS_VERSION ;;
+        ubuntu) install_cuda_driver_apt $OS_NAME $(echo $OS_VERSION | sed 's/\.//') ;;
         *) exit ;;
     esac
 fi
@@ -241,20 +230,20 @@ fi
 if ! lsmod | grep -q nvidia; then
     KERNEL_RELEASE="$(uname -r)"
     case $OS_NAME in
-        centos|rhel|rocky|amzn) $SUDO $PACKAGE_MANAGER -y install "kernel-devel-$KERNEL_RELEASE" "kernel-headers-$KERNEL_RELEASE" ;;
-        fedora) $SUDO $PACKAGE_MANAGER -y install "kernel-devel-$KERNEL_RELEASE" ;;
-        debian|ubuntu) $SUDO apt-get -y install "linux-headers-$KERNEL_RELEASE" ;;
+        centos|rhel|rocky|amzn) $SUDO $PACKAGE_MANAGER -y install kernel-devel-$KERNEL_RELEASE kernel-headers-$KERNEL_RELEASE ;;
+        fedora) $SUDO $PACKAGE_MANAGER -y install kernel-devel-$KERNEL_RELEASE ;;
+        debian|ubuntu) $SUDO apt-get -y install linux-headers-$KERNEL_RELEASE ;;
         *) exit ;;
     esac
 
     NVIDIA_CUDA_VERSION=$($SUDO dkms status | awk -F: '/added/ { print $1 }')
     if [ -n "$NVIDIA_CUDA_VERSION" ]; then
-        $SUDO dkms install "$NVIDIA_CUDA_VERSION"
+        $SUDO dkms install $NVIDIA_CUDA_VERSION
     fi
 
     if lsmod | grep -q nouveau; then
         status 'Reboot to complete NVIDIA CUDA driver install.'
-        exit
+        exit 0
     fi
 
     $SUDO modprobe nvidia

server/routes.go

@@ -771,6 +771,7 @@ func Serve(ln net.Listener, allowOrigins []string) error {
 			c.String(http.StatusOK, "Ollama is running")
 		})
 
+		r.Handle(method, "/api/list", ListModelsHandler)
 		r.Handle(method, "/api/tags", ListModelsHandler)
 	}