Add embedding preview

api/app/routers/llm.py

@@ -214,7 +214,7 @@ def preview_llm_model(
     request: LLMPreviewRequest,
     db: Session = Depends(get_db)
 ):
-    """预览 LLM 输出，基于 OpenAI-compatible /chat/completions。"""
+    """预览模型输出，支持 text(chat) 与 embedding 两类模型。"""
     model = db.query(LLMModel).filter(LLMModel.id == id).first()
     if not model:
         raise HTTPException(status_code=404, detail="LLM Model not found")
@@ -223,24 +223,35 @@ def preview_llm_model(
     if not user_message:
         raise HTTPException(status_code=400, detail="Preview message cannot be empty")
 
-    messages = []
-    if request.system_prompt and request.system_prompt.strip():
-        messages.append({"role": "system", "content": request.system_prompt.strip()})
-    messages.append({"role": "user", "content": user_message})
-
-    payload = {
-        "model": model.model_name or "gpt-3.5-turbo",
-        "messages": messages,
-        "max_tokens": request.max_tokens or 512,
-        "temperature": request.temperature if request.temperature is not None else (model.temperature or 0.7),
-    }
+    model_id = model.model_name or "gpt-3.5-turbo"
     headers = {"Authorization": f"Bearer {(request.api_key or model.api_key).strip()}"}
 
     start_time = time.time()
+    endpoint = "/chat/completions"
+    payload = {}
+
+    if model.type == "embedding":
+        endpoint = "/embeddings"
+        payload = {
+            "model": model_id,
+            "input": user_message,
+        }
+    else:
+        messages = []
+        if request.system_prompt and request.system_prompt.strip():
+            messages.append({"role": "system", "content": request.system_prompt.strip()})
+        messages.append({"role": "user", "content": user_message})
+        payload = {
+            "model": model_id,
+            "messages": messages,
+            "max_tokens": request.max_tokens or 512,
+            "temperature": request.temperature if request.temperature is not None else (model.temperature or 0.7),
+        }
+
     try:
         with httpx.Client(timeout=60.0) as client:
             response = client.post(
-                f"{model.base_url.rstrip('/')}/chat/completions",
+                f"{model.base_url.rstrip('/')}{endpoint}",
                 json=payload,
                 headers=headers
             )
@@ -258,9 +269,23 @@ def preview_llm_model(
 
     result = response.json()
     reply = ""
-    choices = result.get("choices", [])
-    if choices:
-        reply = choices[0].get("message", {}).get("content", "") or ""
+    if model.type == "embedding":
+        data_list = result.get("data", [])
+        embedding = []
+        if data_list and isinstance(data_list, list):
+            embedding = data_list[0].get("embedding", []) or []
+        dims = len(embedding) if isinstance(embedding, list) else 0
+        preview_values = []
+        if isinstance(embedding, list):
+            preview_values = embedding[:8]
+        values_text = ", ".join(
+            [f"{float(v):.6f}" if isinstance(v, (float, int)) else str(v) for v in preview_values]
+        )
+        reply = f"Embedding generated successfully. dims={dims}. head=[{values_text}]"
+    else:
+        choices = result.get("choices", [])
+        if choices:
+            reply = choices[0].get("message", {}).get("content", "") or ""
 
     return LLMPreviewResponse(
         success=bool(reply),