docs: clarify model configuration precedence

Assisted-by: Codex:gpt-5 [Codex]

backend/python/common/libbackend.sh

@@ -333,49 +333,6 @@ _activateVenv() {
     unset PYTHONHOME
 }
 
-# ensureUv makes sure the `uv` package manager is on PATH before we try to build
-# or populate a venv with it.
-#
-# Minimal base images (notably the nvidia-l4t variants) ship neither uv nor pip.
-# A backend installed onto a persistent /backends volume there can therefore
-# never build its venv: `uv venv` aborts with "uv: command not found" and
-# install.sh leaves a half-installed backend, with no way to recover from inside
-# the container. See mudler/LocalAI#10720.
-#
-# When uv is missing (and we are not in USE_PIP mode) bootstrap a private copy
-# into the backend directory itself, which lives on the same persistent volume,
-# so it survives image upgrades and is only downloaded once.
-function ensureUv() {
-    # pip mode never invokes uv.
-    if [ "x${USE_PIP}" == "xtrue" ]; then
-        return 0
-    fi
-    if command -v uv >/dev/null 2>&1; then
-        return 0
-    fi
-    local uv_dir="${EDIR}/uv-bin"
-    if [ -x "${uv_dir}/uv" ]; then
-        export PATH="${uv_dir}:${PATH}"
-        return 0
-    fi
-    echo "uv not found; bootstrapping a private copy into ${uv_dir}"
-    mkdir -p "${uv_dir}"
-    # The official installer picks the right binary for the current platform and
-    # honors UV_INSTALL_DIR. This is the same mechanism the base images use to
-    # install uv (see backend/Dockerfile.python). INSTALLER_NO_MODIFY_PATH keeps
-    # it from editing shell profiles we don't control.
-    if command -v curl >/dev/null 2>&1; then
-        curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR="${uv_dir}" INSTALLER_NO_MODIFY_PATH=1 sh
-    elif command -v wget >/dev/null 2>&1; then
-        wget -qO- https://astral.sh/uv/install.sh | env UV_INSTALL_DIR="${uv_dir}" INSTALLER_NO_MODIFY_PATH=1 sh
-    else
-        echo "ERROR: uv is missing and neither curl nor wget is available to bootstrap it" >&2
-        return 1
-    fi
-    export PATH="${uv_dir}:${PATH}"
-    command -v uv >/dev/null 2>&1
-}
-
 # ensureVenv makes sure that the venv for the backend both exists, and is activated.
 #
 # This function is idempotent, so you can call it as many times as you want and it will
@@ -383,9 +340,6 @@ function ensureUv() {
 function ensureVenv() {
     local interpreter=""
 
-    # Make sure uv is available before any uv-based venv work below.
-    ensureUv
-
     if [ "x${PORTABLE_PYTHON}" == "xtrue" ] || [ -e "$(_portable_python)" ]; then
         echo "Using portable Python"
         ensurePortablePython

docs/content/advanced/model-configuration.md

@@ -7,6 +7,20 @@ url = '/advanced/model-configuration'
 
 LocalAI uses YAML configuration files to define model parameters, templates, and behavior. This page provides a complete reference for all available configuration options.
 
+## Configuration scopes and precedence
+
+[CLI flags and environment variables]({{% relref "reference/cli-reference" %}})
+configure the LocalAI server process. Model YAML files configure one model,
+while supported fields in an API request can override that model's defaults
+for that request. For example, a request containing `temperature` overrides
+the model YAML `parameters.temperature` only for that request.
+
+Precedence is setting-specific rather than one universal ordering. For the
+overlapping `threads` setting, an explicit nonzero server `--threads` value is
+applied after model YAML and therefore wins over the YAML `threads` value.
+Most server flags have no model YAML equivalent, so consult the relevant
+reference for the scope of each setting.
+
 ## Overview
 
 Model configuration files allow you to:

docs/content/reference/cli-reference.md

@@ -7,6 +7,9 @@ url = '/reference/cli-reference'
 
 Complete reference for all LocalAI command-line interface (CLI) parameters and environment variables.
 
+These options configure the LocalAI server process. To configure an individual
+model, see [Model Configuration]({{% relref "advanced/model-configuration" %}}).
+
 > **Note:** All CLI flags can also be set via environment variables. Environment variables take precedence over CLI flags. See [.env files]({{%relref "advanced/advanced-usage#env-files" %}}) for configuration file support.
 
 ## Global Flags