update mise en place

src/agents/mise_en_place.py

@@ -6,6 +6,7 @@ import io
 import json
 import logging
 from typing import Optional
+from PIL import Image
 
 from src import config
 from src.models.loader import get_vision_model
@@ -21,10 +22,9 @@ def _prompt() -> str:
 
 def _img_to_data_url(img) -> str:
     buf = io.BytesIO()
-    img.save(buf, "JPEG", quality=85)
+    img.save(buf, "PNG")  # Probar con PNG
     b64 = base64.b64encode(buf.getvalue()).decode()
-    return f"data:image/jpeg;base64,{b64}"
-
+    return f"data:image/png;base64,{b64}"
 
 _MOCK_INGREDIENTS = [
     "nothing",
@@ -43,18 +43,17 @@ def identify_ingredients(image: Optional[object]) -> list[str]:
         return list(_MOCK_INGREDIENTS)
 
     try:
+        image_url = _img_to_data_url(image)
         out = llm.create_chat_completion(
             messages=[
                 {
                     "role": "user",
                     "content": [
-                        {"type": "image_url", "image_url": {"url": _img_to_data_url(image)}},
+                        {"type": "image_url", "image_url": {"url": image_url}},
                         {"type": "text", "text": _prompt()},
                     ],
                 }
             ],
-            temperature=0.2,
-            response_format={"type": "json_object"},
         )
         print(out)
         raw = out["choices"][0]["message"]["content"]

src/prompts/vision_prompt.txt

@@ -1 +1 @@
-Describe the given image in detail, and identify any kind of food detected.
+Describe the given image in detail. Be honest, do not say liers.