feat: add region configuration for Mistral OCR on Vertex AI

Add separate region configuration for Mistral OCR to resolve conflicts with
Gemini 3 models that require the global endpoint.

Changes:
- Add `region` field to OCR schema in data-provider
- Add `MISTRAL_VERTEX_REGION` environment variable support
- Add `getRegionConfig()` helper function
- Update `performGoogleVertexOCR()` to accept region parameter
- Add region resolution logic with priority: config > MISTRAL_VERTEX_REGION > GOOGLE_LOC
- Maintains full backward compatibility

This follows the pattern established by Anthropic Vertex AI configuration.

packages/api/src/files/mistral/crud.ts

@@ -317,6 +317,23 @@ function getModelConfig(ocrConfig?: TCustomConfig['ocr']): string {
   return modelConfig.trim();
 }
 
+/**
+ * Gets the region configuration for Vertex AI
+ */
+function getRegionConfig(ocrConfig?: TCustomConfig['ocr']): string | undefined {
+  const regionConfig = ocrConfig?.region || '';
+
+  if (!regionConfig.trim()) {
+    return undefined;
+  }
+
+  if (envVarRegex.test(regionConfig)) {
+    return extractEnvVariable(regionConfig) || undefined;
+  }
+
+  return regionConfig.trim();
+}
+
 /**
  * Determines document type based on file
  */
@@ -606,15 +623,18 @@ async function performGoogleVertexOCR({
   accessToken,
   projectId,
   model,
+  region,
   documentType = 'document_url',
 }: {
   url: string;
   accessToken: string;
   projectId: string;
   model: string;
+  region?: string;
   documentType?: 'document_url' | 'image_url';
 }): Promise<OCRResult> {
-  const location = process.env.GOOGLE_LOC || 'us-central1';
+  // Priority: function parameter > MISTRAL_VERTEX_REGION > GOOGLE_LOC > default
+  const location = region || process.env.MISTRAL_VERTEX_REGION || process.env.GOOGLE_LOC || 'us-central1';
   const modelId = model || 'mistral-ocr-2505';
 
   let baseURL: string;
@@ -693,6 +713,7 @@ export const uploadGoogleVertexMistralOCR = async (
   try {
     const { serviceAccount, accessToken } = await loadGoogleAuthConfig();
     const model = getModelConfig(context.req.config?.ocr);
+    const region = getRegionConfig(context.req.config?.ocr);
 
     const { content: buffer } = await readFileAsBuffer(context.file.path, {
       fileSize: context.file.size,
@@ -706,6 +727,7 @@ export const uploadGoogleVertexMistralOCR = async (
       accessToken,
       projectId: serviceAccount.project_id!,
       model,
+      region,
       documentType,
     });
 

packages/data-provider/src/config.ts

@@ -882,6 +882,7 @@ export const ocrSchema = z.object({
   mistralModel: z.string().optional(),
   apiKey: z.string().optional().default('${OCR_API_KEY}'),
   baseURL: z.string().optional().default('${OCR_BASEURL}'),
+  region: z.string().optional().default('${MISTRAL_VERTEX_REGION}'),
   strategy: z.nativeEnum(OCRStrategy).default(OCRStrategy.MISTRAL_OCR),
 });