feat: Adds document intelligence model configuration (#19692)

* Adds document intelligence model configuration

Enables the configuration of the Document Intelligence model to be used by the RAG pipeline.

This allows users to specify the model they want to use for document processing, providing flexibility and control over the extraction process.

* Added Titel to Document Intelligence Model Config

Added Titel to Document Intelligence Model Config

backend/open_webui/config.py

@@ -2590,6 +2590,12 @@ DOCUMENT_INTELLIGENCE_KEY = PersistentConfig(
     os.getenv("DOCUMENT_INTELLIGENCE_KEY", ""),
 )
 
+DOCUMENT_INTELLIGENCE_MODEL = PersistentConfig(
+    "DOCUMENT_INTELLIGENCE_MODEL",
+    "rag.document_intelligence_model",
+    os.getenv("DOCUMENT_INTELLIGENCE_MODEL", "prebuilt-layout"),
+)
+
 MISTRAL_OCR_API_BASE_URL = PersistentConfig(
     "MISTRAL_OCR_API_BASE_URL",
     "rag.MISTRAL_OCR_API_BASE_URL",

backend/open_webui/main.py

@@ -273,6 +273,7 @@ from open_webui.config import (
     DOCLING_PARAMS,
     DOCUMENT_INTELLIGENCE_ENDPOINT,
     DOCUMENT_INTELLIGENCE_KEY,
+    DOCUMENT_INTELLIGENCE_MODEL,
     MISTRAL_OCR_API_BASE_URL,
     MISTRAL_OCR_API_KEY,
     RAG_TEXT_SPLITTER,
@@ -871,6 +872,7 @@ app.state.config.DOCLING_API_KEY = DOCLING_API_KEY
 app.state.config.DOCLING_PARAMS = DOCLING_PARAMS
 app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = DOCUMENT_INTELLIGENCE_ENDPOINT
 app.state.config.DOCUMENT_INTELLIGENCE_KEY = DOCUMENT_INTELLIGENCE_KEY
+app.state.config.DOCUMENT_INTELLIGENCE_MODEL = DOCUMENT_INTELLIGENCE_MODEL
 app.state.config.MISTRAL_OCR_API_BASE_URL = MISTRAL_OCR_API_BASE_URL
 app.state.config.MISTRAL_OCR_API_KEY = MISTRAL_OCR_API_KEY
 app.state.config.MINERU_API_MODE = MINERU_API_MODE

backend/open_webui/retrieval/loaders/main.py

@@ -322,12 +322,14 @@ class Loader:
                     file_path=file_path,
                     api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
                     api_key=self.kwargs.get("DOCUMENT_INTELLIGENCE_KEY"),
+                    api_model=self.kwargs.get("DOCUMENT_INTELLIGENCE_MODEL"),
                 )
             else:
                 loader = AzureAIDocumentIntelligenceLoader(
                     file_path=file_path,
                     api_endpoint=self.kwargs.get("DOCUMENT_INTELLIGENCE_ENDPOINT"),
                     azure_credential=DefaultAzureCredential(),
+                    api_model=self.kwargs.get("DOCUMENT_INTELLIGENCE_MODEL"),
                 )
         elif self.engine == "mineru" and file_ext in [
             "pdf"

backend/open_webui/routers/retrieval.py

@@ -468,6 +468,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
         "DOCLING_PARAMS": request.app.state.config.DOCLING_PARAMS,
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
+        "DOCUMENT_INTELLIGENCE_MODEL": request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL,
         "MISTRAL_OCR_API_BASE_URL": request.app.state.config.MISTRAL_OCR_API_BASE_URL,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
         # MinerU settings
@@ -647,6 +648,7 @@ class ConfigForm(BaseModel):
     DOCLING_PARAMS: Optional[dict] = None
     DOCUMENT_INTELLIGENCE_ENDPOINT: Optional[str] = None
     DOCUMENT_INTELLIGENCE_KEY: Optional[str] = None
+    DOCUMENT_INTELLIGENCE_MODEL: Optional[str] = None
     MISTRAL_OCR_API_BASE_URL: Optional[str] = None
     MISTRAL_OCR_API_KEY: Optional[str] = None
 
@@ -842,6 +844,11 @@ async def update_rag_config(
         if form_data.DOCUMENT_INTELLIGENCE_KEY is not None
         else request.app.state.config.DOCUMENT_INTELLIGENCE_KEY
     )
+    request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL = (
+        form_data.DOCUMENT_INTELLIGENCE_MODEL
+        if form_data.DOCUMENT_INTELLIGENCE_MODEL is not None
+        else request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL
+    )
 
     request.app.state.config.MISTRAL_OCR_API_BASE_URL = (
         form_data.MISTRAL_OCR_API_BASE_URL
@@ -1131,6 +1138,7 @@ async def update_rag_config(
         "DOCLING_PARAMS": request.app.state.config.DOCLING_PARAMS,
         "DOCUMENT_INTELLIGENCE_ENDPOINT": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
         "DOCUMENT_INTELLIGENCE_KEY": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
+        "DOCUMENT_INTELLIGENCE_MODEL": request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL,
         "MISTRAL_OCR_API_BASE_URL": request.app.state.config.MISTRAL_OCR_API_BASE_URL,
         "MISTRAL_OCR_API_KEY": request.app.state.config.MISTRAL_OCR_API_KEY,
         # MinerU settings
@@ -1543,6 +1551,7 @@ def process_file(
                         PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES,
                         DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
                         DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
+                        DOCUMENT_INTELLIGENCE_MODEL=request.app.state.config.DOCUMENT_INTELLIGENCE_MODEL,
                         MISTRAL_OCR_API_BASE_URL=request.app.state.config.MISTRAL_OCR_API_BASE_URL,
                         MISTRAL_OCR_API_KEY=request.app.state.config.MISTRAL_OCR_API_KEY,
                         MINERU_API_MODE=request.app.state.config.MINERU_API_MODE,

src/lib/apis/retrieval/index.ts

@@ -35,6 +35,7 @@ type ChunkConfigForm = {
 type DocumentIntelligenceConfigForm = {
 	key: string;
 	endpoint: string;
+	model: string;
 };
 
 type ContentExtractConfigForm = {

src/lib/components/admin/Settings/Documents.svelte

@@ -597,6 +597,18 @@
 									required={false}
 								/>
 							</div>
+							<div class="my-0.5 flex flex-col w-full">
+								<div class=" mb-1 text-xs font-medium">{$i18n.t('Document Intelligence Model')}</div>
+								<div class="flex w-full">
+									<div class="flex-1 mr-2">
+										<input
+											class="flex-1 w-full text-sm bg-transparent outline-hidden"
+											placeholder={$i18n.t('Enter Document Intelligence Model')}
+											bind:value={RAGConfig.DOCUMENT_INTELLIGENCE_MODEL}
+										/>
+									</div>
+								</div>
+							</div>
 						{:else if RAGConfig.CONTENT_EXTRACTION_ENGINE === 'mistral_ocr'}
 							<div class="my-0.5 flex gap-2 pr-2">
 								<input

src/lib/i18n/locales/en-GB/translation.json

@@ -462,6 +462,7 @@
 	"Docling Server URL required.": "",
 	"Document": "",
 	"Document Intelligence": "",
+	"Document Intelligence Model": "",
 	"Document Intelligence endpoint required.": "",
 	"Documentation": "",
 	"Documents": "",
@@ -564,6 +565,7 @@
 	"Enter Docling Server URL": "",
 	"Enter Document Intelligence Endpoint": "",
 	"Enter Document Intelligence Key": "",
+	"Enter Document Intelligence Model": "",
 	"Enter domains separated by commas (e.g., example.com,site.org,!excludedsite.com)": "",
 	"Enter Exa API Key": "",
 	"Enter External Document Loader API Key": "",

src/lib/i18n/locales/en-US/translation.json

@@ -462,6 +462,7 @@
 	"Docling Server URL required.": "",
 	"Document": "",
 	"Document Intelligence": "",
+	"Document Intelligence Model": "",
 	"Document Intelligence endpoint required.": "",
 	"Documentation": "",
 	"Documents": "",
@@ -564,6 +565,7 @@
 	"Enter Docling Server URL": "",
 	"Enter Document Intelligence Endpoint": "",
 	"Enter Document Intelligence Key": "",
+	"Enter Document Intelligence Model": "",
 	"Enter domains separated by commas (e.g., example.com,site.org,!excludedsite.com)": "",
 	"Enter Exa API Key": "",
 	"Enter External Document Loader API Key": "",