1

backend/app/services/providers/mistral_client.py

@@ -9,8 +9,7 @@ from backend.app.config import settings
 
 
 class MistralClient:
-    endpoint = "https://api.mistral.ai/v1/chat/completions"
-    model = "pixtral-12b-2409"
+    endpoint = "https://api.mistral.ai/v1/ocr"
 
     def ocr_image(self, image_path: Path) -> str:
         if not settings.mistral_api_key:
@@ -23,20 +22,9 @@ class MistralClient:
                 "Authorization": f"Bearer {settings.mistral_api_key}",
             },
             json={
-                "model": self.model,
-                "messages": [
-                    {
-                        "role": "user",
-                        "content": [
-                            {
-                                "type": "text",
-                                "text": "Extract all text from this image and format it as Markdown. If there are tables, represent them using Markdown table syntax. Do not include commentary.",
-                            },
-                            {"type": "image_url", "image_url": data_url},
-                        ],
-                    }
-                ],
-                "max_tokens": 3000,
+                "model": settings.mistral_ocr_model,
+                "document": {"type": "image_url", "image_url": data_url},
+                "include_image_base64": False,
             },
             timeout=180,
         )
@@ -45,7 +33,13 @@ class MistralClient:
         if not response.ok:
             raise RuntimeError(f"Mistral error {response.status_code}: {response.text}")
         data = response.json()
-        return data["choices"][0]["message"]["content"]
+        pages = data.get("pages") or []
+        markdown_pages = [page.get("markdown", "").strip() for page in pages if page.get("markdown")]
+        if markdown_pages:
+            return "\n\n".join(markdown_pages)
+        if data.get("markdown"):
+            return data["markdown"].strip()
+        raise RuntimeError("Mistral OCR no devolvio Markdown")
 
     def _image_data_url(self, image_path: Path) -> str:
         encoded = base64.b64encode(image_path.read_bytes()).decode("ascii")