Show Ollama models in Cookbook Serve

routes/cookbook_helpers.py

@@ -21,6 +21,10 @@ _REPO_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._-]*/[A-Za-z0-9][A-Za-z0-9._-]
 # the real on-disk path separately; this identifier is only for UI/task
 # bookkeeping, so serving should accept the same safe glyph set as repo IDs.
 _LOCAL_MODEL_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._-]*$")
+# Ollama model names include tags, e.g. `qwen2.5:0.5b` or `llama3.2:latest`.
+# Some registries also use a namespace path. Keep this shell-safe: no spaces,
+# quotes, `$`, `;`, `&`, pipes, or redirects.
+_OLLAMA_MODEL_ID_RE = re.compile(r"^[A-Za-z0-9][A-Za-z0-9._:/-]{0,200}$")
 # Include pattern is a glob: allow typical safe glyphs only.
 _INCLUDE_RE = re.compile(r"^[A-Za-z0-9._\-*?/\[\]]+$")
 # Remote host: user@host (optionally with :port-free hostname parts).
@@ -48,9 +52,9 @@ def _validate_repo_id(v: str | None) -> str:
 def _validate_serve_model_id(v: str | None) -> str:
     if not v:
         raise HTTPException(400, "repo_id is required")
-    if _REPO_ID_RE.match(v) or _LOCAL_MODEL_ID_RE.match(v):
+    if _REPO_ID_RE.match(v) or _LOCAL_MODEL_ID_RE.match(v) or _OLLAMA_MODEL_ID_RE.match(v):
         return v
-    raise HTTPException(400, "Invalid repo_id — must be <org>/<name> or a cached local model id using [A-Za-z0-9._-]")
+    raise HTTPException(400, "Invalid repo_id — must be <org>/<name>, an Ollama name:tag, or a cached local model id")
 
 
 def _validate_include(v: str | None) -> str | None:
@@ -147,7 +151,7 @@ def _local_tooling_path_export(executable: str) -> str:
 def _cached_model_scan_script(model_dirs: list[str] | None = None) -> str:
     """Build the standalone Python scanner used by /api/model/cached."""
     lines = [
-        "import json, os",
+        "import json, os, re, shutil, subprocess, urllib.request",
         "models = []",
         "seen = set()",
         "BLOCKED_ROOTS = ('/sys', '/proc', '/dev', '/run', '/var/run')",
@@ -209,7 +213,48 @@ def _cached_model_scan_script(model_dirs: list[str] | None = None) -> str:
         "                except Exception: pass",
         "        is_diff = os.path.exists(os.path.join(fp, 'model_index.json'))",
         "        models.append({'repo_id':d,'size_bytes':sz,'nb_files':nf,'has_incomplete':False,'path':p,'is_local_dir':True,'is_diffusion':is_diff,'is_gguf':is_gguf})",
+        "def parse_size(num, unit):",
+        "    try: n = float(num)",
+        "    except Exception: return 0",
+        "    u = (unit or '').upper()",
+        "    if u.startswith('TB'): return int(n * 1024 ** 4)",
+        "    if u.startswith('GB'): return int(n * 1024 ** 3)",
+        "    if u.startswith('MB'): return int(n * 1024 ** 2)",
+        "    if u.startswith('KB'): return int(n * 1024)",
+        "    return int(n)",
+        "def scan_ollama():",
+        "    if not shutil.which('ollama'): return",
+        "    try:",
+        "        p = subprocess.run(['ollama', 'list'], stdout=subprocess.PIPE, stderr=subprocess.DEVNULL, text=True, timeout=6)",
+        "    except Exception:",
+        "        return",
+        "    if p.returncode != 0: return",
+        "    for line in (p.stdout or '').splitlines()[1:]:",
+        "        parts = line.split()",
+        "        if len(parts) < 4: continue",
+        "        name = parts[0]",
+        "        if not name or name in seen: continue",
+        "        size_bytes = parse_size(parts[2], parts[3])",
+        "        seen.add(name)",
+        "        models.append({'repo_id':name,'size_bytes':size_bytes,'nb_files':1,'has_incomplete':False,'path':'ollama','backend':'ollama','is_ollama':True})",
+        "def scan_ollama_api():",
+        "    urls = ['http://127.0.0.1:11434/api/tags', 'http://localhost:11434/api/tags', 'http://host.docker.internal:11434/api/tags']",
+        "    for url in urls:",
+        "        try:",
+        "            with urllib.request.urlopen(url, timeout=2) as r:",
+        "                data = json.loads(r.read().decode('utf-8', 'replace'))",
+        "        except Exception:",
+        "            continue",
+        "        for item in data.get('models', []):",
+        "            name = item.get('name') or item.get('model')",
+        "            if not name or name in seen: continue",
+        "            size_bytes = int(item.get('size') or item.get('size_bytes') or 0)",
+        "            seen.add(name)",
+        "            models.append({'repo_id':name,'size_bytes':size_bytes,'nb_files':1,'has_incomplete':False,'path':'ollama','backend':'ollama','is_ollama':True})",
+        "        return",
         "scan_hf(os.path.expanduser('~/.cache/huggingface/hub'))",
+        "scan_ollama()",
+        "scan_ollama_api()",
     ]
     for model_dir in model_dirs or []:
         lines.append(f"scan_dir(os.path.expanduser({model_dir!r}))")

routes/cookbook_routes.py

@@ -710,6 +710,10 @@ def setup_cookbook_routes() -> APIRouter:
                     entry["is_local_dir"] = True
                 if m.get("is_gguf"):
                     entry["is_gguf"] = True
+                if m.get("backend"):
+                    entry["backend"] = m.get("backend")
+                if m.get("is_ollama"):
+                    entry["is_ollama"] = True
                 models.append(entry)
         except Exception as e:
             logger.warning(f"Failed to parse cached models: {e}")

static/js/cookbook.js

@@ -245,6 +245,9 @@ export function _detectToolParser(modelName) {
 // ── Backend detection ──
 
 export function _detectBackend(model) {
+  if (model?.backend === 'ollama' || model?.is_ollama) {
+    return { backend: 'ollama', label: 'Ollama' };
+  }
   const q = (model.quant || '').toUpperCase();
   const sysBackend = String(_hwfitCache?.system?.backend || '').toLowerCase();
   const isRocm = sysBackend === 'rocm';
@@ -407,11 +410,9 @@ export function _buildServeCmd(f, modelName, backend) {
       cmd += ` || ${_lcpServer}`;
     }
   } else if (backend === 'ollama') {
-    const ollamaName = modelName.split('/').pop().toLowerCase().replace(/[-_]gguf$/i, '');
     const ollamaPort = f.port || '11434';
     const hostEnv = ollamaPort !== '11434' ? `OLLAMA_HOST=0.0.0.0:${ollamaPort} ` : '';
-    // Start serve in background if not running, then pull model
-    cmd = `${hostEnv}ollama serve &>/dev/null & sleep 2 && ${hostEnv}ollama pull ${ollamaName} && wait`;
+    cmd = `${hostEnv}ollama serve`;
   } else if (backend === 'diffusers') {
     const gpuStr = f.gpus?.trim();
     if (gpuStr) cmd += `CUDA_VISIBLE_DEVICES=${gpuStr} `;

static/js/cookbookServe.js

@@ -386,9 +386,9 @@ function _rerenderCachedModels() {
         : _isMetal()
         // Diffusers (diffusion_server.py) is CUDA-only — omit it on Metal.
         ? [['llamacpp','llama.cpp'],['ollama','Ollama']]
-        : [['vllm','vLLM'],['sglang','SGLang'],['llamacpp','llama.cpp'],['diffusers','Diffusers']];
+        : [['vllm','vLLM'],['sglang','SGLang'],['llamacpp','llama.cpp'],['ollama','Ollama'],['diffusers','Diffusers']];
       const backendOpts = _backendChoices.map(([v,l]) => `<option value="${v}"${defaultBackend===v?' selected':''}>${l}</option>`).join('');
-      panelHtml += `<label>${_l('Backend','Inference engine: vLLM, SGLang, llama.cpp, or Diffusers')}<select class="hwfit-sf" data-field="backend">${backendOpts}</select></label>`;
+      panelHtml += `<label>${_l('Backend','Inference engine: vLLM, SGLang, llama.cpp, Ollama, or Diffusers')}<select class="hwfit-sf" data-field="backend">${backendOpts}</select></label>`;
       panelHtml += `<input type="hidden" class="hwfit-sf" data-field="host" value="${esc(_es.remoteHost || '')}" />`;
       panelHtml += `<label>${_l('venv','Path to Python venv or conda env activate script')}<input type="text" class="hwfit-sf hwfit-sf-wide" data-field="venv" value="${esc(sv('venv', _es.envPath || _srvVenv || ''))}" placeholder="~/venv" /></label>`;
       panelHtml += `<label>${_l('Port','HTTP port for the API server')}<input type="text" class="hwfit-sf" data-field="port" value="${esc(sv('port', _nextAvailablePort()))}" /></label>`;
@@ -1512,7 +1512,7 @@ export async function _fetchCachedModels() {
     const data = await res.json();
     _dlWp.destroy();
 
-    const ready = data.models.filter(m => m.status === 'ready' && !m.size.includes('MB'));
+    const ready = data.models.filter(m => m.status === 'ready' && (m.backend === 'ollama' || !m.size.includes('MB')));
     const downloading = data.models.filter(m => m.status === 'downloading');
     const allModels = [...ready, ...downloading];
     _cachedAllModels = allModels;
@@ -1541,7 +1541,8 @@ export async function _fetchCachedModels() {
     for (const m of allModels) {
       const n = (m.repo_id || '').toLowerCase();
       let tag = 'other';
-      if (m.is_diffusion || /flux|sdxl|stable-diffusion|z-image|qwen-image|diffusion|dreamshar/i.test(n)) tag = 'image';
+      if (m.backend === 'ollama' || m.is_ollama) tag = 'llm';
+      else if (m.is_diffusion || /flux|sdxl|stable-diffusion|z-image|qwen-image|diffusion|dreamshar/i.test(n)) tag = 'image';
       else if (/whisper|stt|asr/i.test(n)) tag = 'stt';
       else if (/tts|cosyvoice|parler/i.test(n)) tag = 'tts';
       else if (/embed|bge|minilm|e5-/i.test(n)) tag = 'embedding';
@@ -1553,6 +1554,10 @@ export async function _fetchCachedModels() {
       for (const [re, fam] of _families) {
         if (re.test(n)) { m._family = fam; _familyMap[fam] = (_familyMap[fam] || 0) + 1; break; }
       }
+      if ((m.backend === 'ollama' || m.is_ollama) && !m._family) {
+        m._family = 'ollama';
+        _familyMap.ollama = (_familyMap.ollama || 0) + 1;
+      }
     }
 
     // Render tag chips