feat(ocr): Azure Document Intelligence provider (prebuilt-read, analyze+poll)

open-sse/config/ocrRegistry.ts

@@ -62,6 +62,48 @@ export function getOcrTransformation(providerId: string): OcrTransformation {
   return OCR_PROVIDERS[providerId]?.transformation ?? MISTRAL_PASSTHROUGH;
 }
 
+const AZURE_DI_API_VERSION = "2024-11-30";
+
+function azureDiSource(document: Record<string, unknown> | undefined): Record<string, string> {
+  if (!document) return {};
+  const url = String(document.document_url ?? document.image_url ?? "");
+  if (url.startsWith("data:")) {
+    const comma = url.indexOf(",");
+    return { base64Source: comma >= 0 ? url.slice(comma + 1) : "" };
+  }
+  return url ? { urlSource: url } : {};
+}
+
+export const AZURE_DI_TRANSFORMATION: OcrTransformation = {
+  buildRequest({ baseUrl, token, body, modelId }) {
+    const root = baseUrl.replace(/\/+$/, "");
+    return {
+      url: `${root}/documentintelligence/documentModels/${modelId}:analyze?api-version=${AZURE_DI_API_VERSION}&outputContentFormat=markdown`,
+      init: {
+        method: "POST",
+        headers: { "Content-Type": "application/json", "Ocp-Apim-Subscription-Key": token },
+        body: JSON.stringify(azureDiSource(body.document as Record<string, unknown>)),
+      },
+    };
+  },
+  pollUrl(res) {
+    return res.headers.get("Operation-Location");
+  },
+  parseResponse(raw) {
+    const r = raw as {
+      analyzeResult?: { content?: string; pages?: unknown[] };
+    };
+    const pageCount = r.analyzeResult?.pages?.length ?? 1;
+    // Azure devolve o markdown do documento inteiro em content; espelhamos no shape
+    // Mistral com uma "página" agregada por padrão (índice 0), preservando pageCount.
+    return {
+      pages: [{ index: 0, markdown: r.analyzeResult?.content ?? "" }],
+      model: "prebuilt-read",
+      usage_info: { pages_processed: pageCount },
+    };
+  },
+};
+
 export const OCR_PROVIDERS: Record<string, OcrProvider> = {
   mistral: {
     id: "mistral",
@@ -70,6 +112,14 @@ export const OCR_PROVIDERS: Record<string, OcrProvider> = {
     authHeader: "bearer",
     models: [{ id: "mistral-ocr-latest", name: "Mistral OCR" }],
   },
+  "azure-document-intelligence": {
+    id: "azure-document-intelligence",
+    baseUrl: "",
+    authType: "apikey",
+    authHeader: "Ocp-Apim-Subscription-Key",
+    models: [{ id: "prebuilt-read", name: "Azure Document Intelligence (Read)" }],
+    transformation: AZURE_DI_TRANSFORMATION,
+  },
 };
 
 /**

tests/unit/ocr-registry-transformations.test.ts

@@ -26,3 +26,49 @@ test("passthrough parseResponse returns the body unchanged (Mistral is the canon
   const raw = { pages: [{ index: 0, markdown: "hello" }], model: "mistral-ocr-latest" };
   assert.deepEqual(MISTRAL_PASSTHROUGH.parseResponse(raw), raw);
 });
+
+test("azure-document-intelligence builds the prebuilt-read:analyze request", () => {
+  const t = getOcrTransformation("azure-document-intelligence");
+  const { url, init } = t.buildRequest({
+    baseUrl: "https://myres.cognitiveservices.azure.com",
+    token: "azkey",
+    body: { document: { type: "document_url", document_url: "https://x/d.pdf" } },
+    modelId: "prebuilt-read",
+  });
+  assert.equal(
+    url,
+    "https://myres.cognitiveservices.azure.com/documentintelligence/documentModels/prebuilt-read:analyze?api-version=2024-11-30&outputContentFormat=markdown"
+  );
+  assert.equal((init.headers as Record<string, string>)["Ocp-Apim-Subscription-Key"], "azkey");
+  const sent = JSON.parse(String(init.body));
+  assert.equal(sent.urlSource, "https://x/d.pdf");
+});
+
+test("azure-document-intelligence extracts poll URL and parses analyzeResult into Mistral shape", () => {
+  const t = getOcrTransformation("azure-document-intelligence");
+  const res = new Response(null, {
+    status: 202,
+    headers: { "Operation-Location": "https://poll/op/1" },
+  });
+  assert.equal(t.pollUrl?.(res), "https://poll/op/1");
+  const parsed = t.parseResponse({
+    status: "succeeded",
+    analyzeResult: { content: "# doc text", pages: [{ pageNumber: 1 }] },
+  });
+  assert.equal(parsed.pages.length, 1);
+  assert.equal(parsed.pages[0].index, 0);
+  assert.equal(parsed.pages[0].markdown, "# doc text");
+  assert.equal(parsed.model, "prebuilt-read");
+});
+
+test("azure DI maps base64/image_url documents to base64Source/urlSource", () => {
+  const t = getOcrTransformation("azure-document-intelligence");
+  const { init } = t.buildRequest({
+    baseUrl: "https://r.example.com",
+    token: "k",
+    body: { document: { type: "image_url", image_url: "data:image/png;base64,AAAA" } },
+    modelId: "prebuilt-read",
+  });
+  const sent = JSON.parse(String(init.body));
+  assert.equal(sent.base64Source, "AAAA");
+});