mirror of
https://github.com/lordmathis/llamactl.git
synced 2025-12-23 09:34:23 +00:00
Deployed 9cea295 to dev with MkDocs 1.6.1 and mike 2.1.3
This commit is contained in:
lordmathis
Binary file not shown.
Binary file not shown.
@@ -852,39 +852,6 @@
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#nodes" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Nodes
|
||||
</span>
|
||||
</a>
|
||||
|
||||
<nav class="md-nav" aria-label="Nodes">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#get-apiv1nodes" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
GET /api/v1/nodes
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#get-apiv1nodesname" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
GET /api/v1/nodes/{name}
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -897,6 +864,33 @@
|
||||
<nav class="md-nav" aria-label="Llama.cpp">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#get-apiv1llama-cppnamemodels" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
GET /api/v1/llama-cpp/{name}/models
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#post-apiv1llama-cppnamemodelsmodelload" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
POST /api/v1/llama-cpp/{name}/models/{model}/load
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#post-apiv1llama-cppnamemodelsmodelunload" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
POST /api/v1/llama-cpp/{name}/models/{model}/unload
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#get-llama-cppname" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
@@ -1008,6 +1002,39 @@
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#nodes" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
Nodes
|
||||
</span>
|
||||
</a>
|
||||
|
||||
<nav class="md-nav" aria-label="Nodes">
|
||||
<ul class="md-nav__list">
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#get-apiv1nodes" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
GET /api/v1/nodes
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
<a href="#get-apiv1nodesname" class="md-nav__link">
|
||||
<span class="md-ellipsis">
|
||||
GET /api/v1/nodes/{name}
|
||||
</span>
|
||||
</a>
|
||||
|
||||
</li>
|
||||
|
||||
</ul>
|
||||
</nav>
|
||||
|
||||
</li>
|
||||
|
||||
<li class="md-nav__item">
|
||||
@@ -2308,55 +2335,14 @@ port </p>
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<h2 id="nodes"><span class="api-tag">Nodes</span><a class="headerlink" href="#nodes" title="Permanent link">¶</a></h2>
|
||||
<h2 id="llamacpp"><span class="api-tag">Llama.cpp</span><a class="headerlink" href="#llamacpp" title="Permanent link">¶</a></h2>
|
||||
<hr class="operation-separator" />
|
||||
|
||||
<h3 id="get-apiv1nodes"><span class="http-get">GET</span> /api/v1/nodes<a class="headerlink" href="#get-apiv1nodes" title="Permanent link">¶</a></h3>
|
||||
<p>List all configured nodes </p>
|
||||
<h3 id="get-apiv1llama-cppnamemodels"><span class="http-get">GET</span> /api/v1/llama-cpp/<span class="route-param">{name}</span>/models<a class="headerlink" href="#get-apiv1llama-cppnamemodels" title="Permanent link">¶</a></h3>
|
||||
<p>List models in a llama.cpp instance </p>
|
||||
<details class="note">
|
||||
<summary>Description</summary>
|
||||
<p>Returns a map of all nodes configured in the server (node name -> node<br />
|
||||
config) </p>
|
||||
</details>
|
||||
<p><strong>Input parameters</strong> </p>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Parameter</th>
|
||||
<th>In</th>
|
||||
<th>Type</th>
|
||||
<th>Default</th>
|
||||
<th>Nullable</th>
|
||||
<th>Description</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>ApiKeyAuth</code></td>
|
||||
<td>header</td>
|
||||
<td>string</td>
|
||||
<td>N/A</td>
|
||||
<td>No</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-200">200</span> <span class="status-phrase">OK</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<hr class="operation-separator" />
|
||||
|
||||
<h3 id="get-apiv1nodesname"><span class="http-get">GET</span> /api/v1/nodes/<span class="route-param">{name}</span><a class="headerlink" href="#get-apiv1nodesname" title="Permanent link">¶</a></h3>
|
||||
<p>Get details of a specific node </p>
|
||||
<details class="note">
|
||||
<summary>Description</summary>
|
||||
<p>Returns the details of a specific node by name </p>
|
||||
<p>Returns a list of models available in the specified llama.cpp instance </p>
|
||||
</details>
|
||||
<p><strong>Input parameters</strong> </p>
|
||||
<table>
|
||||
@@ -2385,7 +2371,7 @@ config) </p>
|
||||
<td>None</td>
|
||||
<td></td>
|
||||
<td>No</td>
|
||||
<td>Node Name</td>
|
||||
<td>Instance Name</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
@@ -2399,14 +2385,129 @@ config) </p>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-404">404</span> <span class="status-phrase">Not Found</span></strong>
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<hr class="operation-separator" />
|
||||
|
||||
<h3 id="post-apiv1llama-cppnamemodelsmodelload"><span class="http-post">POST</span> /api/v1/llama-cpp/<span class="route-param">{name}</span>/models/<span class="route-param">{model}</span>/load<a class="headerlink" href="#post-apiv1llama-cppnamemodelsmodelload" title="Permanent link">¶</a></h3>
|
||||
<p>Load a model in a llama.cpp instance </p>
|
||||
<details class="note">
|
||||
<summary>Description</summary>
|
||||
<p>Loads the specified model in the given llama.cpp instance </p>
|
||||
</details>
|
||||
<p><strong>Input parameters</strong> </p>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Parameter</th>
|
||||
<th>In</th>
|
||||
<th>Type</th>
|
||||
<th>Default</th>
|
||||
<th>Nullable</th>
|
||||
<th>Description</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>ApiKeyAuth</code></td>
|
||||
<td>header</td>
|
||||
<td>string</td>
|
||||
<td>N/A</td>
|
||||
<td>No</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>model</code></td>
|
||||
<td>path</td>
|
||||
<td>None</td>
|
||||
<td></td>
|
||||
<td>No</td>
|
||||
<td>Model Name</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>name</code></td>
|
||||
<td>path</td>
|
||||
<td>None</td>
|
||||
<td></td>
|
||||
<td>No</td>
|
||||
<td>Instance Name</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-200">200</span> <span class="status-phrase">OK</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-400">400</span> <span class="status-phrase">Bad Request</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<hr class="operation-separator" />
|
||||
|
||||
<h3 id="post-apiv1llama-cppnamemodelsmodelunload"><span class="http-post">POST</span> /api/v1/llama-cpp/<span class="route-param">{name}</span>/models/<span class="route-param">{model}</span>/unload<a class="headerlink" href="#post-apiv1llama-cppnamemodelsmodelunload" title="Permanent link">¶</a></h3>
|
||||
<p>Unload a model in a llama.cpp instance </p>
|
||||
<details class="note">
|
||||
<summary>Description</summary>
|
||||
<p>Unloads the specified model in the given llama.cpp instance </p>
|
||||
</details>
|
||||
<p><strong>Input parameters</strong> </p>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Parameter</th>
|
||||
<th>In</th>
|
||||
<th>Type</th>
|
||||
<th>Default</th>
|
||||
<th>Nullable</th>
|
||||
<th>Description</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>ApiKeyAuth</code></td>
|
||||
<td>header</td>
|
||||
<td>string</td>
|
||||
<td>N/A</td>
|
||||
<td>No</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>model</code></td>
|
||||
<td>path</td>
|
||||
<td>None</td>
|
||||
<td></td>
|
||||
<td>No</td>
|
||||
<td>Model Name</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>name</code></td>
|
||||
<td>path</td>
|
||||
<td>None</td>
|
||||
<td></td>
|
||||
<td>No</td>
|
||||
<td>Instance Name</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-200">200</span> <span class="status-phrase">OK</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-400">400</span> <span class="status-phrase">Bad Request</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<h2 id="llamacpp"><span class="api-tag">Llama.cpp</span><a class="headerlink" href="#llamacpp" title="Permanent link">¶</a></h2>
|
||||
<hr class="operation-separator" />
|
||||
|
||||
<h3 id="get-llama-cppname"><span class="http-get">GET</span> /llama-cpp/<span class="route-param">{name}</span>/<a class="headerlink" href="#get-llama-cppname" title="Permanent link">¶</a></h3>
|
||||
@@ -3042,6 +3143,104 @@ demand if configured </p>
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<h2 id="nodes"><span class="api-tag">Nodes</span><a class="headerlink" href="#nodes" title="Permanent link">¶</a></h2>
|
||||
<hr class="operation-separator" />
|
||||
|
||||
<h3 id="get-apiv1nodes"><span class="http-get">GET</span> /api/v1/nodes<a class="headerlink" href="#get-apiv1nodes" title="Permanent link">¶</a></h3>
|
||||
<p>List all configured nodes </p>
|
||||
<details class="note">
|
||||
<summary>Description</summary>
|
||||
<p>Returns a map of all nodes configured in the server (node name -> node<br />
|
||||
config) </p>
|
||||
</details>
|
||||
<p><strong>Input parameters</strong> </p>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Parameter</th>
|
||||
<th>In</th>
|
||||
<th>Type</th>
|
||||
<th>Default</th>
|
||||
<th>Nullable</th>
|
||||
<th>Description</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>ApiKeyAuth</code></td>
|
||||
<td>header</td>
|
||||
<td>string</td>
|
||||
<td>N/A</td>
|
||||
<td>No</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-200">200</span> <span class="status-phrase">OK</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<hr class="operation-separator" />
|
||||
|
||||
<h3 id="get-apiv1nodesname"><span class="http-get">GET</span> /api/v1/nodes/<span class="route-param">{name}</span><a class="headerlink" href="#get-apiv1nodesname" title="Permanent link">¶</a></h3>
|
||||
<p>Get details of a specific node </p>
|
||||
<details class="note">
|
||||
<summary>Description</summary>
|
||||
<p>Returns the details of a specific node by name </p>
|
||||
</details>
|
||||
<p><strong>Input parameters</strong> </p>
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Parameter</th>
|
||||
<th>In</th>
|
||||
<th>Type</th>
|
||||
<th>Default</th>
|
||||
<th>Nullable</th>
|
||||
<th>Description</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>ApiKeyAuth</code></td>
|
||||
<td>header</td>
|
||||
<td>string</td>
|
||||
<td>N/A</td>
|
||||
<td>No</td>
|
||||
<td></td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td class="parameter-name"><code>name</code></td>
|
||||
<td>path</td>
|
||||
<td>None</td>
|
||||
<td></td>
|
||||
<td>No</td>
|
||||
<td>Node Name</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-200">200</span> <span class="status-phrase">OK</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-400">400</span> <span class="status-phrase">Bad Request</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-404">404</span> <span class="status-phrase">Not Found</span></strong>
|
||||
</p>
|
||||
|
||||
<p class="response-title">
|
||||
<strong>Response <span class="response-code code-500">500</span> <span class="status-phrase">Internal Server Error</span></strong>
|
||||
</p>
|
||||
|
||||
<h2 id="openai"><span class="api-tag">OpenAI</span><a class="headerlink" href="#openai" title="Permanent link">¶</a></h2>
|
||||
<hr class="operation-separator" />
|
||||
|
||||
|
||||
176
dev/docs.go
176
dev/docs.go
@@ -999,6 +999,156 @@ const docTemplate = `{
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/llama-cpp/{name}/models": {
|
||||
"get": {
|
||||
"security": [
|
||||
{
|
||||
"ApiKeyAuth": []
|
||||
}
|
||||
],
|
||||
"description": "Returns a list of models available in the specified llama.cpp instance",
|
||||
"tags": [
|
||||
"Llama.cpp"
|
||||
],
|
||||
"summary": "List models in a llama.cpp instance",
|
||||
"parameters": [
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Instance Name",
|
||||
"name": "name",
|
||||
"in": "path",
|
||||
"required": true
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Models list response",
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"additionalProperties": true
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"description": "Invalid instance",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"500": {
|
||||
"description": "Internal Server Error",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/llama-cpp/{name}/models/{model}/load": {
|
||||
"post": {
|
||||
"security": [
|
||||
{
|
||||
"ApiKeyAuth": []
|
||||
}
|
||||
],
|
||||
"description": "Loads the specified model in the given llama.cpp instance",
|
||||
"tags": [
|
||||
"Llama.cpp"
|
||||
],
|
||||
"summary": "Load a model in a llama.cpp instance",
|
||||
"parameters": [
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Instance Name",
|
||||
"name": "name",
|
||||
"in": "path",
|
||||
"required": true
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Model Name",
|
||||
"name": "model",
|
||||
"in": "path",
|
||||
"required": true
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Success message",
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"description": "Invalid request",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"500": {
|
||||
"description": "Internal Server Error",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/llama-cpp/{name}/models/{model}/unload": {
|
||||
"post": {
|
||||
"security": [
|
||||
{
|
||||
"ApiKeyAuth": []
|
||||
}
|
||||
],
|
||||
"description": "Unloads the specified model in the given llama.cpp instance",
|
||||
"tags": [
|
||||
"Llama.cpp"
|
||||
],
|
||||
"summary": "Unload a model in a llama.cpp instance",
|
||||
"parameters": [
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Instance Name",
|
||||
"name": "name",
|
||||
"in": "path",
|
||||
"required": true
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Model Name",
|
||||
"name": "model",
|
||||
"in": "path",
|
||||
"required": true
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Success message",
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"description": "Invalid request",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"500": {
|
||||
"description": "Internal Server Error",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/nodes": {
|
||||
"get": {
|
||||
"security": [
|
||||
@@ -1788,13 +1938,6 @@ const docTemplate = `{
|
||||
"config.AuthConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"inference_keys": {
|
||||
"description": "List of keys for OpenAI compatible inference endpoints",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"management_keys": {
|
||||
"description": "List of keys for management endpoints",
|
||||
"type": "array",
|
||||
@@ -1905,10 +2048,6 @@ const docTemplate = `{
|
||||
"description": "Automatically create the data directory if it doesn't exist",
|
||||
"type": "boolean"
|
||||
},
|
||||
"configs_dir": {
|
||||
"description": "Instance config directory override (relative to data_dir if not absolute)",
|
||||
"type": "string"
|
||||
},
|
||||
"default_auto_restart": {
|
||||
"description": "Default auto-restart setting for new instances",
|
||||
"type": "boolean"
|
||||
@@ -1929,6 +2068,21 @@ const docTemplate = `{
|
||||
"description": "Enable LRU eviction for instance logs",
|
||||
"type": "boolean"
|
||||
},
|
||||
"logRotationCompress": {
|
||||
"description": "Whether to compress rotated log files",
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"logRotationEnabled": {
|
||||
"description": "Log rotation enabled",
|
||||
"type": "boolean",
|
||||
"default": true
|
||||
},
|
||||
"logRotationMaxSize": {
|
||||
"description": "Maximum log file size in MB before rotation",
|
||||
"type": "integer",
|
||||
"default": 100
|
||||
},
|
||||
"logs_dir": {
|
||||
"description": "Logs directory override (relative to data_dir if not absolute)",
|
||||
"type": "string"
|
||||
|
||||
File diff suppressed because one or more lines are too long
176
dev/swagger.json
176
dev/swagger.json
@@ -992,6 +992,156 @@
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/llama-cpp/{name}/models": {
|
||||
"get": {
|
||||
"security": [
|
||||
{
|
||||
"ApiKeyAuth": []
|
||||
}
|
||||
],
|
||||
"description": "Returns a list of models available in the specified llama.cpp instance",
|
||||
"tags": [
|
||||
"Llama.cpp"
|
||||
],
|
||||
"summary": "List models in a llama.cpp instance",
|
||||
"parameters": [
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Instance Name",
|
||||
"name": "name",
|
||||
"in": "path",
|
||||
"required": true
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Models list response",
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"additionalProperties": true
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"description": "Invalid instance",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"500": {
|
||||
"description": "Internal Server Error",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/llama-cpp/{name}/models/{model}/load": {
|
||||
"post": {
|
||||
"security": [
|
||||
{
|
||||
"ApiKeyAuth": []
|
||||
}
|
||||
],
|
||||
"description": "Loads the specified model in the given llama.cpp instance",
|
||||
"tags": [
|
||||
"Llama.cpp"
|
||||
],
|
||||
"summary": "Load a model in a llama.cpp instance",
|
||||
"parameters": [
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Instance Name",
|
||||
"name": "name",
|
||||
"in": "path",
|
||||
"required": true
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Model Name",
|
||||
"name": "model",
|
||||
"in": "path",
|
||||
"required": true
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Success message",
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"description": "Invalid request",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"500": {
|
||||
"description": "Internal Server Error",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/llama-cpp/{name}/models/{model}/unload": {
|
||||
"post": {
|
||||
"security": [
|
||||
{
|
||||
"ApiKeyAuth": []
|
||||
}
|
||||
],
|
||||
"description": "Unloads the specified model in the given llama.cpp instance",
|
||||
"tags": [
|
||||
"Llama.cpp"
|
||||
],
|
||||
"summary": "Unload a model in a llama.cpp instance",
|
||||
"parameters": [
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Instance Name",
|
||||
"name": "name",
|
||||
"in": "path",
|
||||
"required": true
|
||||
},
|
||||
{
|
||||
"type": "string",
|
||||
"description": "Model Name",
|
||||
"name": "model",
|
||||
"in": "path",
|
||||
"required": true
|
||||
}
|
||||
],
|
||||
"responses": {
|
||||
"200": {
|
||||
"description": "Success message",
|
||||
"schema": {
|
||||
"type": "object",
|
||||
"additionalProperties": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
},
|
||||
"400": {
|
||||
"description": "Invalid request",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"500": {
|
||||
"description": "Internal Server Error",
|
||||
"schema": {
|
||||
"type": "string"
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
},
|
||||
"/api/v1/nodes": {
|
||||
"get": {
|
||||
"security": [
|
||||
@@ -1781,13 +1931,6 @@
|
||||
"config.AuthConfig": {
|
||||
"type": "object",
|
||||
"properties": {
|
||||
"inference_keys": {
|
||||
"description": "List of keys for OpenAI compatible inference endpoints",
|
||||
"type": "array",
|
||||
"items": {
|
||||
"type": "string"
|
||||
}
|
||||
},
|
||||
"management_keys": {
|
||||
"description": "List of keys for management endpoints",
|
||||
"type": "array",
|
||||
@@ -1898,10 +2041,6 @@
|
||||
"description": "Automatically create the data directory if it doesn't exist",
|
||||
"type": "boolean"
|
||||
},
|
||||
"configs_dir": {
|
||||
"description": "Instance config directory override (relative to data_dir if not absolute)",
|
||||
"type": "string"
|
||||
},
|
||||
"default_auto_restart": {
|
||||
"description": "Default auto-restart setting for new instances",
|
||||
"type": "boolean"
|
||||
@@ -1922,6 +2061,21 @@
|
||||
"description": "Enable LRU eviction for instance logs",
|
||||
"type": "boolean"
|
||||
},
|
||||
"logRotationCompress": {
|
||||
"description": "Whether to compress rotated log files",
|
||||
"type": "boolean",
|
||||
"default": false
|
||||
},
|
||||
"logRotationEnabled": {
|
||||
"description": "Log rotation enabled",
|
||||
"type": "boolean",
|
||||
"default": true
|
||||
},
|
||||
"logRotationMaxSize": {
|
||||
"description": "Maximum log file size in MB before rotation",
|
||||
"type": "integer",
|
||||
"default": 100
|
||||
},
|
||||
"logs_dir": {
|
||||
"description": "Logs directory override (relative to data_dir if not absolute)",
|
||||
"type": "string"
|
||||
|
||||
117
dev/swagger.yaml
117
dev/swagger.yaml
@@ -39,11 +39,6 @@ definitions:
|
||||
type: object
|
||||
config.AuthConfig:
|
||||
properties:
|
||||
inference_keys:
|
||||
description: List of keys for OpenAI compatible inference endpoints
|
||||
items:
|
||||
type: string
|
||||
type: array
|
||||
management_keys:
|
||||
description: List of keys for management endpoints
|
||||
items:
|
||||
@@ -118,10 +113,6 @@ definitions:
|
||||
auto_create_dirs:
|
||||
description: Automatically create the data directory if it doesn't exist
|
||||
type: boolean
|
||||
configs_dir:
|
||||
description: Instance config directory override (relative to data_dir if not
|
||||
absolute)
|
||||
type: string
|
||||
default_auto_restart:
|
||||
description: Default auto-restart setting for new instances
|
||||
type: boolean
|
||||
@@ -137,6 +128,18 @@ definitions:
|
||||
enable_lru_eviction:
|
||||
description: Enable LRU eviction for instance logs
|
||||
type: boolean
|
||||
logRotationCompress:
|
||||
default: false
|
||||
description: Whether to compress rotated log files
|
||||
type: boolean
|
||||
logRotationEnabled:
|
||||
default: true
|
||||
description: Log rotation enabled
|
||||
type: boolean
|
||||
logRotationMaxSize:
|
||||
default: 100
|
||||
description: Maximum log file size in MB before rotation
|
||||
type: integer
|
||||
logs_dir:
|
||||
description: Logs directory override (relative to data_dir if not absolute)
|
||||
type: string
|
||||
@@ -955,6 +958,102 @@ paths:
|
||||
summary: Stop a running instance
|
||||
tags:
|
||||
- Instances
|
||||
/api/v1/llama-cpp/{name}/models:
|
||||
get:
|
||||
description: Returns a list of models available in the specified llama.cpp instance
|
||||
parameters:
|
||||
- description: Instance Name
|
||||
in: path
|
||||
name: name
|
||||
required: true
|
||||
type: string
|
||||
responses:
|
||||
"200":
|
||||
description: Models list response
|
||||
schema:
|
||||
additionalProperties: true
|
||||
type: object
|
||||
"400":
|
||||
description: Invalid instance
|
||||
schema:
|
||||
type: string
|
||||
"500":
|
||||
description: Internal Server Error
|
||||
schema:
|
||||
type: string
|
||||
security:
|
||||
- ApiKeyAuth: []
|
||||
summary: List models in a llama.cpp instance
|
||||
tags:
|
||||
- Llama.cpp
|
||||
/api/v1/llama-cpp/{name}/models/{model}/load:
|
||||
post:
|
||||
description: Loads the specified model in the given llama.cpp instance
|
||||
parameters:
|
||||
- description: Instance Name
|
||||
in: path
|
||||
name: name
|
||||
required: true
|
||||
type: string
|
||||
- description: Model Name
|
||||
in: path
|
||||
name: model
|
||||
required: true
|
||||
type: string
|
||||
responses:
|
||||
"200":
|
||||
description: Success message
|
||||
schema:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
"400":
|
||||
description: Invalid request
|
||||
schema:
|
||||
type: string
|
||||
"500":
|
||||
description: Internal Server Error
|
||||
schema:
|
||||
type: string
|
||||
security:
|
||||
- ApiKeyAuth: []
|
||||
summary: Load a model in a llama.cpp instance
|
||||
tags:
|
||||
- Llama.cpp
|
||||
/api/v1/llama-cpp/{name}/models/{model}/unload:
|
||||
post:
|
||||
description: Unloads the specified model in the given llama.cpp instance
|
||||
parameters:
|
||||
- description: Instance Name
|
||||
in: path
|
||||
name: name
|
||||
required: true
|
||||
type: string
|
||||
- description: Model Name
|
||||
in: path
|
||||
name: model
|
||||
required: true
|
||||
type: string
|
||||
responses:
|
||||
"200":
|
||||
description: Success message
|
||||
schema:
|
||||
additionalProperties:
|
||||
type: string
|
||||
type: object
|
||||
"400":
|
||||
description: Invalid request
|
||||
schema:
|
||||
type: string
|
||||
"500":
|
||||
description: Internal Server Error
|
||||
schema:
|
||||
type: string
|
||||
security:
|
||||
- ApiKeyAuth: []
|
||||
summary: Unload a model in a llama.cpp instance
|
||||
tags:
|
||||
- Llama.cpp
|
||||
/api/v1/nodes:
|
||||
get:
|
||||
description: Returns a map of all nodes configured in the server (node name
|
||||
|
||||
Reference in New Issue
Block a user