fix: usar HF InferenceClient com meta-llama/Llama-3.2-11B-Vision-Instruct

core/ai.py

@@ -1,12 +1,12 @@
 """
-ai.py — Integracao com modelo de visao via HuggingFace ou NVIDIA NIM.
+ai.py — Visao via HuggingFace InferenceClient ou NVIDIA NIM.
 
 Variaveis de ambiente:
-  HF_TOKEN       — token HuggingFace (HF Serverless Inference)
+  HF_TOKEN       — token HuggingFace (usa HF Serverless Inference)
   NVIDIA_API_KEY — chave NVIDIA NIM (free tier em build.nvidia.com)
 
-Modelo HF: nvidia/llama-3.2-11b-vision-instruct  (11B, acessivel no HF)
-Modelo NIM: nvidia/nemotron-3-nano-omni-30b-a3b   (30B Omni, se tiver NVIDIA key)
+Modelo HF:  meta-llama/Llama-3.2-11B-Vision-Instruct  (disponivel no HF Serverless)
+Modelo NIM: nvidia/nemotron-3-nano-omni-30b-a3b         (Nemotron Omni via NVIDIA)
 """
 import base64
 import io
@@ -19,7 +19,7 @@ import numpy as np
 
 log = logging.getLogger(__name__)
 
-_HF_MODEL  = "nvidia/llama-3.2-11b-vision-instruct"
+_HF_MODEL  = "meta-llama/Llama-3.2-11B-Vision-Instruct"
 _NIM_MODEL = "nvidia/nemotron-3-nano-omni-30b-a3b"
 
 PROMPT = (
@@ -39,36 +39,38 @@ PROMPT = (
 
 class AnimalAI:
     def __init__(self):
+        self.mode   = None  # "hf" | "nim"
         self.model  = None
-        self.client = None
+        self.client = None  # OpenAI (NIM) ou InferenceClient (HF)
 
         hf_token   = os.environ.get("HF_TOKEN", "")
         nvidia_key = os.environ.get("NVIDIA_API_KEY", "")
 
-        try:
-            from openai import OpenAI
-
-            if nvidia_key:
+        if nvidia_key:
+            try:
+                from openai import OpenAI
+                self.mode   = "nim"
                 self.model  = os.environ.get("NVIDIA_MODEL", _NIM_MODEL)
                 self.client = OpenAI(
                     base_url="https://integrate.api.nvidia.com/v1",
                     api_key=nvidia_key,
                 )
-                log.info("AI: Nemotron Omni 30B via NVIDIA NIM")
+                log.info("AI: Nemotron Omni via NVIDIA NIM (%s)", self.model)
+            except ImportError:
+                log.warning("openai nao instalado")
 
-            elif hf_token:
+        elif hf_token:
+            try:
+                from huggingface_hub import InferenceClient
+                self.mode   = "hf"
                 self.model  = os.environ.get("NVIDIA_MODEL", _HF_MODEL)
-                self.client = OpenAI(
-                    base_url="https://api-inference.huggingface.co/v1/",
-                    api_key=hf_token,
-                )
-                log.info("AI: %s via HuggingFace Serverless", self.model)
-
-            else:
-                log.warning("Sem chave de API — IA desabilitada. Configure HF_TOKEN nos Secrets do Space.")
+                self.client = InferenceClient(model=self.model, token=hf_token)
+                log.info("AI: %s via HF InferenceClient", self.model)
+            except ImportError:
+                log.warning("huggingface_hub nao instalado")
 
-        except ImportError:
-            log.warning("openai nao instalado.")
+        else:
+            log.warning("Sem chave de API — IA desabilitada. Configure HF_TOKEN nos Secrets.")
 
         self.embedder = None
         try:
@@ -79,38 +81,54 @@ class AnimalAI:
             log.warning("sentence-transformers nao carregou: %s", e)
 
     def analyze_image(self, image) -> dict:
-        """Analisa imagem com IA. _ai_success=False indica fallback."""
+        """Analisa imagem. _ai_success=False indica que a IA nao foi usada."""
         if self.client is None:
             return self._fallback()
 
         try:
             img_b64 = self._to_b64(image)
-            resp = self.client.chat.completions.create(
-                model=self.model,
-                messages=[{
-                    "role": "user",
-                    "content": [
-                        {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64," + img_b64}},
-                        {"type": "text", "text": PROMPT},
-                    ],
-                }],
-                max_tokens=400,
-                temperature=0.1,
-            )
-            raw = resp.choices[0].message.content or ""
-            log.info("AI resposta: %s", raw[:150])
+
+            if self.mode == "hf":
+                # HuggingFace InferenceClient — suporte nativo a multimodal
+                resp = self.client.chat_completion(
+                    messages=[{
+                        "role": "user",
+                        "content": [
+                            {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64," + img_b64}},
+                            {"type": "text", "text": PROMPT},
+                        ],
+                    }],
+                    max_tokens=400,
+                    temperature=0.1,
+                )
+                raw = resp.choices[0].message.content or ""
+            else:
+                # NVIDIA NIM — OpenAI-compatible
+                resp = self.client.chat.completions.create(
+                    model=self.model,
+                    messages=[{
+                        "role": "user",
+                        "content": [
+                            {"type": "image_url", "image_url": {"url": "data:image/jpeg;base64," + img_b64}},
+                            {"type": "text", "text": PROMPT},
+                        ],
+                    }],
+                    max_tokens=400,
+                    temperature=0.1,
+                )
+                raw = resp.choices[0].message.content or ""
+
+            log.info("AI resposta: %s", raw[:200])
             result = self._parse(raw)
             result["_ai_success"] = True
             return result
+
         except Exception as e:
             log.error("Erro na API de IA: %s", e)
             return self._fallback()
 
     def get_embedding(self, description: dict) -> list:
-        """
-        Embedding da descricao. Se IA falhou (_ai_success=False),
-        usa vetor aleatorio para evitar que todos os fallbacks virem o mesmo animal.
-        """
+        """Embedding da descricao. Aleatorio se IA falhou (evita falsos matches)."""
         if not description.get("_ai_success", True):
             log.info("Fallback IA — embedding aleatorio")
             v = np.random.randn(384).astype(np.float32)