vlms updated

src/blackbox/blackbox.py

@@ -37,6 +37,10 @@ class Blackbox(ABC):
     async def fast_api_handler(self, request: Request) -> Response:
         pass
 
+    @abstractmethod
+    async def vlms_api_handler(self, request: Request) -> Response:
+        pass
+
     @abstractmethod
     def __call__(self, *args, **kwargs):
         pass

src/blackbox/blackbox_factory.py

@@ -12,6 +12,7 @@ from .text_and_image import TextAndImage
 from .chroma_query import ChromaQuery
 from .chroma_upsert import ChromaUpsert
 from .chroma_chat import ChromaChat
+from .vlms import VLMS
 from injector import inject, singleton
 
 @singleton
@@ -29,10 +30,11 @@ class BlackboxFactory:
                  fastchat: Fastchat,
                  audio_chat: AudioChat,
                  g2e: G2E,
-                 text_and_image:TextAndImage,
+                 text_and_image: TextAndImage,
                  chroma_query: ChromaQuery,
                  chroma_upsert: ChromaUpsert,
-                 chroma_chat: ChromaChat) -> None:
+                 chroma_chat: ChromaChat,
+                 vlms: VLMS) -> None:
         self.models["audio_to_text"] = audio_to_text
         self.models["text_to_audio"] = text_to_audio
         self.models["asr"] = asr
@@ -46,6 +48,7 @@ class BlackboxFactory:
         self.models["chroma_query"] = chroma_query
         self.models["chroma_upsert"] = chroma_upsert
         self.models["chroma_chat"] = chroma_chat
+        self.models["vlms"] = vlms
 
     def __call__(self, *args, **kwargs):
         return self.processing(*args, **kwargs)

src/blackbox/vlms.py

@@ -0,0 +1,68 @@
+from fastapi import Request, Response, status
+from fastapi.responses import JSONResponse
+from blackbox import Blackbox
+from typing import Optional
+
+import requests
+import base64
+
+
+def is_base64(value) -> bool:
+    try:
+        base64.b64decode(base64.b64decode(value)) == value.encode()
+        return True
+    except Exception:
+        return False
+
+
+class VLMS(Blackbox):
+
+    def __call__(self, *args, **kwargs):
+        return self.processing(*args, **kwargs)
+
+    def valid(self, *args, **kwargs) -> bool:
+        data = args[0]
+        return isinstance(data, list)
+
+    def processing(self, prompt, images, model_name: Optional[str] = None) -> str:
+
+        if model_name == "Qwen-VL-Chat":
+            model_name = "infer-qwen-vl"
+        elif model_name == "llava-llama-3-8b-v1_1-transformers":
+            model_name = "infer-lav-lam-v1-1"
+        else:
+            model_name = "infer-qwen-vl"
+
+        url = 'http://120.196.116.194:48894/' + model_name + '/'
+
+        if is_base64(images):
+            images_data = images
+        else:
+            with open(images, "rb") as img_file:
+                images_data = str(base64.b64encode(img_file.read()), 'utf-8')
+
+        data_input = {'model': model_name, 'prompt': prompt, 'img_data': images_data}
+
+        data = requests.post(url, json=data_input)
+
+        return data.text
+
+    async def vlms_api_handler(self, request: Request) -> Response:
+        try:
+            data = await request.json()
+        except:
+            return JSONResponse(content={"error": "json parse error"}, status_code=status.HTTP_400_BAD_REQUEST)
+
+        model_name = data.get("model_name")
+        prompt = data.get("prompt")
+        img_data = data.get("img_data")
+
+        if prompt is None:
+            return JSONResponse(content={'error': "Question is required"}, status_code=status.HTTP_400_BAD_REQUEST)
+
+        if model_name is None or model_name.isspace():
+            model_name = "Qwen-VL-Chat"
+
+        return JSONResponse(content={"response": self.processing(model_name, prompt, img_data)},
+                            status_code=status.HTTP_200_OK)
+