Skip to content

Personal AI, On Personal Devices

Python

fix: never auto-select embed-only models for chat (#659)

kelliott-cloud2ed885eb11ed
diff --git a/frontend/src/App.tsx b/frontend/src/App.tsx
index f70f8a95..021cc59d 100644
--- a/frontend/src/App.tsx
+++ b/frontend/src/App.tsx
@@ -31,7 +31,6 @@ export default function App() {
const prevModelRef = useRef<string>('');
const setModels = useAppStore((s) => s.setModels);
const setModelsLoading = useAppStore((s) => s.setModelsLoading);
- const setSelectedModel = useAppStore((s) => s.setSelectedModel);
const selectedModel = useAppStore((s) => s.selectedModel);
const setServerInfo = useAppStore((s) => s.setServerInfo);
const setSavings = useAppStore((s) => s.setSavings);
@@ -70,7 +69,6 @@ export default function App() {
fetchModels()
.then((m) => {
setModels(m);
- if (!selectedModel && m.length > 0) setSelectedModel(m[0].id);
})
.catch(() => setModels([]))
.finally(() => setModelsLoading(false));
diff --git a/frontend/src/components/SetupScreen.tsx b/frontend/src/components/SetupScreen.tsx
index 1d477e9c..eeffd1b1 100644
--- a/frontend/src/components/SetupScreen.tsx
+++ b/frontend/src/components/SetupScreen.tsx
@@ -7,6 +7,7 @@ import {
type SetupStatus,
} from '../lib/api';
import { useAppStore } from '../lib/store';
+import { isEmbedOnlyModel } from '../lib/model-capabilities';
const STEPS = [
{ key: 'ollama_ready', label: 'Inference Engine', icon: Cpu, detail: 'Starting Ollama...' },
@@ -91,12 +92,14 @@ export function SetupScreen({ onReady }: { onReady: () => void }) {
fetchRecommendedModel().catch(() => ({ model: '', reason: '' })),
]);
const store = useAppStore.getState();
+ const hadSelection = !!store.selectedModel;
store.setModels(models);
store.setModelsLoading(false);
- const recommended = rec.model && models.some((m) => m.id === rec.model)
+ const chatModels = models.filter((m) => !isEmbedOnlyModel(m.id));
+ const recommended = rec.model && chatModels.some((m) => m.id === rec.model)
? rec.model
- : models[0]?.id || '';
- if (recommended && !store.selectedModel) {
+ : chatModels[0]?.id || '';
+ if (recommended && !hadSelection) {
store.setSelectedModel(recommended);
}
} catch {
diff --git a/frontend/src/lib/model-capabilities.test.ts b/frontend/src/lib/model-capabilities.test.ts
new file mode 100644
index 00000000..1a999fad
--- /dev/null
+++ b/frontend/src/lib/model-capabilities.test.ts
@@ -0,0 +1,19 @@
+import { describe, expect, it } from 'vitest';
+
+import { isEmbedOnlyModel } from './model-capabilities';
+
+describe('isEmbedOnlyModel', () => {
+ it.each([
+ 'nomic-embed-text',
+ 'mxbai-embed-large',
+ 'text-embedding-3-small',
+ 'all-minilm:latest',
+ 'hf.co/BAAI/bge-m3:latest',
+ ])('classifies %s as embedding-only', (modelId) => {
+ expect(isEmbedOnlyModel(modelId)).toBe(true);
+ });
+
+ it.each(['qwen3.5:4b', 'codegemma:7b'])('keeps %s available for chat', (modelId) => {
+ expect(isEmbedOnlyModel(modelId)).toBe(false);
+ });
+});
diff --git a/frontend/src/lib/model-capabilities.ts b/frontend/src/lib/model-capabilities.ts
new file mode 100644
index 00000000..49e651b9
--- /dev/null
+++ b/frontend/src/lib/model-capabilities.ts
@@ -0,0 +1,22 @@
+const EMBEDDING_MODEL_PREFIXES = [
+ 'all-minilm',
+ 'bge-',
+ 'bge_',
+ 'e5-',
+ 'e5_',
+ 'gte-',
+ 'gte_',
+ 'jina-embeddings',
+ 'nomic-bert',
+ 'sentence-transformers',
+];
+
+export function isEmbedOnlyModel(modelId: string): boolean {
+ const name = (modelId || '').trim().toLowerCase();
+ const leaf = name.slice(name.lastIndexOf('/') + 1).split(':')[0];
+ return (
+ leaf.includes('embed') ||
+ leaf.includes('minilm') ||
+ EMBEDDING_MODEL_PREFIXES.some((prefix) => leaf.startsWith(prefix))
+ );
+}
diff --git a/frontend/src/lib/store.models.test.ts b/frontend/src/lib/store.models.test.ts
new file mode 100644
index 00000000..8015c223
--- /dev/null
+++ b/frontend/src/lib/store.models.test.ts
@@ -0,0 +1,64 @@
+import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
+
+import type { ModelInfo } from '../types';
+
+class MemoryStorage {
+ private store = new Map<string, string>();
+
+ getItem(key: string): string | null {
+ return this.store.get(key) ?? null;
+ }
+
+ setItem(key: string, value: string): void {
+ this.store.set(key, String(value));
+ }
+}
+
+const model = (id: string): ModelInfo => ({
+ id,
+ object: 'model',
+ created: 0,
+ owned_by: 'openjarvis',
+});
+
+beforeEach(() => {
+ vi.resetModules();
+ (globalThis as unknown as { localStorage: MemoryStorage }).localStorage =
+ new MemoryStorage();
+});
+
+afterEach(() => {
+ (globalThis as unknown as { localStorage?: MemoryStorage }).localStorage =
+ undefined;
+});
+
+describe('setModels', () => {
+ it('does not select an embedding-only model', async () => {
+ const { useAppStore } = await import('./store');
+
+ useAppStore.getState().setModels([model('nomic-embed-text')]);
+
+ expect(useAppStore.getState().selectedModel).toBe('');
+ });
+
+ it('clears a missing selection when no chat fallback exists', async () => {
+ const { useAppStore } = await import('./store');
+ useAppStore.getState().setSelectedModel('deleted-chat-model');
+
+ useAppStore.getState().setModels([model('nomic-embed-text')]);
+
+ expect(useAppStore.getState().selectedModel).toBe('');
+ });
+
+ it('replaces an embedding selection with an available chat model', async () => {
+ const { useAppStore } = await import('./store');
+ useAppStore.getState().setSelectedModel('all-minilm:latest');
+
+ useAppStore.getState().setModels([
+ model('all-minilm:latest'),
+ model('qwen3.5:4b'),
+ ]);
+
+ expect(useAppStore.getState().selectedModel).toBe('qwen3.5:4b');
+ });
+});
diff --git a/frontend/src/lib/store.ts b/frontend/src/lib/store.ts
index d1a0775e..54152a46 100644
--- a/frontend/src/lib/store.ts
+++ b/frontend/src/lib/store.ts
@@ -15,6 +15,7 @@ import type {
TokenUsage,
} from '../types';
import type { ManagedAgent } from './api';
+import { isEmbedOnlyModel } from './model-capabilities';
export interface CachedConnector {
connector_id: string;
@@ -444,11 +445,36 @@ export const useAppStore = create<AppState>((set, get) => {
// ── Models & server ────────────────────────────────────────────
setModels: (models: ModelInfo[]) =>
- set((state) =>
- !state.selectedModel && models.length > 0
- ? { models, selectedModel: models[0].id }
- : { models },
- ),
+ set((state) => {
+ // Ollama returns embed-only models (e.g. nomic-embed-text) in the
+ // same list as chat models. Auto-picking models[0] selected the
+ // embedder and every chat failed with HTTP 400 "does not support
+ // chat". Prefer a real chat model for selection / fallback.
+ const chatModels = models.filter((m) => !isEmbedOnlyModel(m.id));
+ const preferred =
+ (state.settings.defaultModel &&
+ chatModels.some((m) => m.id === state.settings.defaultModel) &&
+ state.settings.defaultModel) ||
+ chatModels[0]?.id ||
+ models.find((m) => !isEmbedOnlyModel(m.id))?.id ||
+ '';
+
+ const currentIsBad =
+ !!state.selectedModel && isEmbedOnlyModel(state.selectedModel);
+ const currentMissing =
+ !!state.selectedModel &&
+ !models.some((m) => m.id === state.selectedModel);
+
+ if (!state.selectedModel || currentIsBad || currentMissing) {
+ // Prefer a real chat model. If none exist, clear a bad/missing
+ // selection rather than keeping an embed-only id that 400s on chat.
+ return {
+ models,
+ selectedModel: preferred,
+ };
+ }
+ return { models };
+ }),
setModelsLoading: (loading: boolean) => set({ modelsLoading: loading }),
setSelectedModel: (model: string) => set({ selectedModel: model }),
setServerInfo: (info: ServerInfo | null) => set({ serverInfo: info }),
diff --git a/src/openjarvis/server/agent_manager_routes.py b/src/openjarvis/server/agent_manager_routes.py
index afb4a591..7b01b049 100644
--- a/src/openjarvis/server/agent_manager_routes.py
+++ b/src/openjarvis/server/agent_manager_routes.py
@@ -20,6 +20,7 @@ from openjarvis.agents.tool_resolver import (
from openjarvis.agents.tool_resolver import (
ensure_registries_populated as _ensure_registries_populated,
)
+from openjarvis.server.model_capabilities import is_embed_only_model
try:
from fastapi import APIRouter, HTTPException, Request
@@ -332,16 +333,29 @@ _CLOUD_PREFIXES = ("gpt-", "claude-", "gemini-", "o1-", "o3-", "o4-")
def _pick_recommended_model(
model_ids: list[str],
) -> dict[str, str]:
- """Pick the second-largest local model from a list."""
- local = [m for m in model_ids if not any(m.startswith(p) for p in _CLOUD_PREFIXES)]
+ """Pick the second-largest local *chat* model from a list.
+
+ Embedding-only models (nomic-embed-text, etc.) are excluded — they return
+ HTTP 400 "does not support chat" when used as the generation model.
+ """
+ local = [
+ m
+ for m in model_ids
+ if not any(m.startswith(p) for p in _CLOUD_PREFIXES)
+ and not is_embed_only_model(m)
+ ]
+ if not local:
+ # Fall back to any non-cloud model, still skipping embedders.
+ local = [m for m in model_ids if not is_embed_only_model(m)]
if not local:
+ # Never recommend an embed-only model — chat would 400.
return {
- "model": model_ids[0] if model_ids else "",
- "reason": "Only model available",
+ "model": "",
+ "reason": "No local chat model available",
}
sized = sorted(local, key=_parse_param_count, reverse=True)
if len(sized) == 1:
- return {"model": sized[0], "reason": "Only local model available"}
+ return {"model": sized[0], "reason": "Only local chat model available"}
pick = sized[1] # second-largest
params = _parse_param_count(pick)
return {
diff --git a/src/openjarvis/server/model_capabilities.py b/src/openjarvis/server/model_capabilities.py
new file mode 100644
index 00000000..9e334e32
--- /dev/null
+++ b/src/openjarvis/server/model_capabilities.py
@@ -0,0 +1,34 @@
+"""Model capability helpers shared by server model-selection routes."""
+
+_EMBEDDING_MODEL_PREFIXES = (
+ "all-minilm",
+ "bge-",
+ "bge_",
+ "e5-",
+ "e5_",
+ "gte-",
+ "gte_",
+ "jina-embeddings",
+ "nomic-bert",
+ "sentence-transformers",
+)
+
+
+def is_embed_only_model(model_name: str) -> bool:
+ """Return whether a model identifier denotes a non-chat embedder.
+
+ Ollama does not expose capabilities through its model-list response, so
+ model selection needs a conservative name-based guard. Most embedding
+ models contain ``embed``; the explicit prefixes cover common families
+ such as MiniLM, BGE, E5, and GTE whose names do not.
+ """
+ name = (model_name or "").strip().lower()
+ leaf = name.rsplit("/", 1)[-1].split(":", 1)[0]
+ return (
+ "embed" in leaf
+ or "minilm" in leaf
+ or leaf.startswith(_EMBEDDING_MODEL_PREFIXES)
+ )
+
+
+__all__ = ["is_embed_only_model"]
diff --git a/src/openjarvis/server/routes.py b/src/openjarvis/server/routes.py
index 6a14532e..b07ed38b 100644
--- a/src/openjarvis/server/routes.py
+++ b/src/openjarvis/server/routes.py
@@ -12,6 +12,7 @@ from fastapi.responses import StreamingResponse
from openjarvis.core.paths import get_config_dir
from openjarvis.core.types import Message, Role
+from openjarvis.server.model_capabilities import is_embed_only_model
from openjarvis.server.models import (
ChatCompletionChunk,
ChatCompletionRequest,
@@ -892,6 +893,11 @@ async def list_models(request: Request) -> ModelListResponse:
if not model_ids:
model_ids = await list_local_models()
+ # Keep embed-only models out of the chat model picker. They still work for
+ # memory/retrieval via the embedder path; putting them in /v1/models made
+ # the UI auto-select nomic-embed-text and fail every generation with 400.
+ model_ids = [m for m in model_ids if not is_embed_only_model(m)]
+
return ModelListResponse(
data=[
ModelObject(
diff --git a/tests/server/test_model_management.py b/tests/server/test_model_management.py
index 61f0440a..53017791 100644
--- a/tests/server/test_model_management.py
+++ b/tests/server/test_model_management.py
@@ -265,6 +265,28 @@ class TestModelsEndpointExtended:
assert "qwen3.5:9b" in ids
assert "qwen3:0.6b" in ids
+ def test_models_list_filters_embedding_only_models(self):
+ engine = _make_engine(
+ models=["nomic-embed-text", "all-minilm:latest", "qwen3.5:4b"],
+ )
+ client = TestClient(create_app(engine, "qwen3.5:4b"))
+
+ resp = client.get("/v1/models")
+
+ assert resp.status_code == 200
+ assert [m["id"] for m in resp.json()["data"]] == ["qwen3.5:4b"]
+
+ def test_models_list_returns_empty_when_only_embedders_are_installed(self):
+ engine = _make_engine(
+ models=["nomic-embed-text", "hf.co/BAAI/bge-m3:latest"],
+ )
+ client = TestClient(create_app(engine, "nomic-embed-text"))
+
+ resp = client.get("/v1/models")
+
+ assert resp.status_code == 200
+ assert resp.json()["data"] == []
+
def test_models_empty_engine(self):
"""When engine.list_models() returns empty, endpoint still succeeds."""
engine = _make_engine(models=[])
diff --git a/tests/server/test_recommended_model.py b/tests/server/test_recommended_model.py
index d0b2a094..09a3ccb8 100644
--- a/tests/server/test_recommended_model.py
+++ b/tests/server/test_recommended_model.py
@@ -50,3 +50,42 @@ def test_parse_param_count():
assert _parse_param_count("qwen3.5:0.8b") == 0.8
assert _parse_param_count("qwen3.5:35b") == 35.0
assert _parse_param_count("gpt-4o") == 0.0
+
+
[email protected](not HAS_FASTAPI, reason="fastapi not installed")
+def test_recommended_model_skips_embed_only():
+ """Embed-only models must never be recommended for chat."""
+ from openjarvis.server.agent_manager_routes import _pick_recommended_model
+
+ models = [
+ "nomic-embed-text",
+ "qwen3.5:4b",
+ "mxbai-embed-large",
+ "qwen3.5:9b",
+ ]
+ result = _pick_recommended_model(models)
+ assert result["model"] == "qwen3.5:4b"
+ assert "embed" not in result["model"]
+
+
[email protected](not HAS_FASTAPI, reason="fastapi not installed")
+def test_recommended_model_embed_only_returns_empty():
+ """If only embedders are installed, recommend nothing (not nomic-embed)."""
+ from openjarvis.server.agent_manager_routes import _pick_recommended_model
+
+ result = _pick_recommended_model(["nomic-embed-text", "mxbai-embed-large"])
+ assert result["model"] == ""
+ assert "No local chat model" in result["reason"]
+
+
[email protected](not HAS_FASTAPI, reason="fastapi not installed")
+def test_is_embed_only_model():
+ from openjarvis.server.model_capabilities import is_embed_only_model
+
+ assert is_embed_only_model("nomic-embed-text")
+ assert is_embed_only_model("mxbai-embed-large")
+ assert is_embed_only_model("text-embedding-3-small")
+ assert is_embed_only_model("all-minilm:latest")
+ assert is_embed_only_model("hf.co/BAAI/bge-m3:latest")
+ assert not is_embed_only_model("qwen3.5:4b")
+ assert not is_embed_only_model("codegemma:7b")