feat(backend): add PDF extraction with OCR fallback and cache

backend/app/models.py

@@ -0,0 +1,55 @@
+"""Schemas Pydantic de entrada e saída da API."""
+
+from __future__ import annotations
+
+from typing import Literal
+
+from pydantic import BaseModel, Field
+
+
+class ChatMessage(BaseModel):
+    role: Literal["user", "assistant"]
+    content: str = Field(min_length=1, max_length=8000)
+
+
+class ChatRequest(BaseModel):
+    message: str = Field(min_length=1, max_length=4000)
+    history: list[ChatMessage] = Field(default_factory=list)
+
+
+class Source(BaseModel):
+    """Trecho bíblico recuperado, exibido no accordion de fontes."""
+
+    reference: str
+    text: str
+    book: str
+    chapter: int
+    verse: int
+    page: int
+    file: str
+    score: float = 0.0
+
+
+class StatusResponse(BaseModel):
+    state: Literal["ready", "indexing", "error"]
+    pdfs_total: int = 0
+    pdfs_indexed: int = 0
+    chunks: int = 0
+    model: str = ""
+    last_indexed_at: str | None = None
+    errors: list[str] = Field(default_factory=list)
+
+
+class HealthResponse(BaseModel):
+    status: Literal["ok"] = "ok"
+    llm_provider: str
+    indexing: Literal["ready", "indexing", "error"]
+    version: str = "1.0.0"
+
+
+class ReindexResponse(BaseModel):
+    state: Literal["indexing"] = "indexing"
+
+
+class SourcesResponse(BaseModel):
+    sources: list[Source] = Field(default_factory=list)