增加Kimi多模态Api,这样可以灵活选择！

exp_multimodal/vlm_classifier.py

@@ -2,7 +2,7 @@ import json
 import re
 from typing import Dict, List, Optional
 
-from .ollama_client import chat_vision
+from .vlm_providers.base import VLMProvider
 from .prompts import build_closedset_prompt
 
 
@@ -37,6 +37,7 @@ def _extract_json_obj(text: str):
 def classify_image(
     image_path: str,
     labels: List[str],
+    provider: VLMProvider,
     fewshot_hints: Optional[Dict[str, str]] = None,
     ingredient_only: bool = False,
 ) -> Dict:
@@ -46,7 +47,7 @@ def classify_image(
 
     print(
         f"[VLM] Start classify image={image_path} labels={len(labels)} "
-        f"ingredient_only={ingredient_only} fewshot={bool(fewshot_hints)}"
+        f"ingredient_only={ingredient_only} fewshot={bool(fewshot_hints)} provider={provider}"
     )
     prompt = build_closedset_prompt(labels, fewshot_hints, ingredient_only)
     # _preview_prompt = (prompt[:120]).replace("\n", " ")
@@ -54,8 +55,8 @@ def classify_image(
     # print(f"[VLM] Prompt length={len(prompt)} preview={_preview_prompt}...")
     print(f"[VLM] Prompt length={len(prompt)} preview={final_prompt}")
 
-    print("[VLM] Calling chat_vision...")
-    text = chat_vision(prompt, [image_path], temperature=0.1)
+    print(f"[VLM] Calling {provider}.chat_vision()...")
+    text = provider.chat_vision(prompt, [image_path], temperature=0.1)
     _preview_text = (str(text)[:200]).replace("\n", " ")
     print(f"[VLM] Received text length={len(str(text))} preview={_preview_text}...")