add docling presets

2025-09-19 12:04:23 -05:00 · 2025-09-19 12:04:23 -05:00 · 88c9d60986
commit 88c9d60986
parent 9ad1fb3f4f
9 changed files with 156 additions and 57 deletions
--- a/config.yaml
+++ b/config.yaml
@ -20,10 +20,8 @@ knowledge:
  chunk_size: 1000
  # Overlap between chunks
  chunk_overlap: 200
-  # Enable OCR for image processing
-  ocr: true
-  # Enable picture descriptions using vision models
-  picture_descriptions: false
+  # Docling preset setting
+  doclingPresets: standard

 # AI agent configuration
 agent:
--- a/frontend/components/ui/radio-group.tsx
+++ b/frontend/components/ui/radio-group.tsx
@ -0,0 +1,44 @@
+"use client"
+
+import * as React from "react"
+import * as RadioGroupPrimitive from "@radix-ui/react-radio-group"
+import { Circle } from "lucide-react"
+
+import { cn } from "@/lib/utils"
+
+const RadioGroup = React.forwardRef<
+  React.ElementRef<typeof RadioGroupPrimitive.Root>,
+  React.ComponentPropsWithoutRef<typeof RadioGroupPrimitive.Root>
+>(({ className, ...props }, ref) => {
+  return (
+    <RadioGroupPrimitive.Root
+      className={cn("grid gap-2", className)}
+      {...props}
+      ref={ref}
+    />
+  )
+})
+RadioGroup.displayName = RadioGroupPrimitive.Root.displayName
+
+const RadioGroupItem = React.forwardRef<
+  React.ElementRef<typeof RadioGroupPrimitive.Item>,
+  React.ComponentPropsWithoutRef<typeof RadioGroupPrimitive.Item>
+>(({ className, ...props }, ref) => {
+  return (
+    <RadioGroupPrimitive.Item
+      ref={ref}
+      className={cn(
+        "aspect-square h-4 w-4 rounded-full border border-primary text-primary ring-offset-background focus:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 disabled:cursor-not-allowed disabled:opacity-50",
+        className
+      )}
+      {...props}
+    >
+      <RadioGroupPrimitive.Indicator className="flex items-center justify-center">
+        <Circle className="h-2.5 w-2.5 fill-current text-current" />
+      </RadioGroupPrimitive.Indicator>
+    </RadioGroupPrimitive.Item>
+  )
+})
+RadioGroupItem.displayName = RadioGroupPrimitive.Item.displayName
+
+export { RadioGroup, RadioGroupItem }
--- a/frontend/package-lock.json
+++ b/frontend/package-lock.json
@ -19,6 +19,7 @@
        "@radix-ui/react-label": "^2.1.7",
        "@radix-ui/react-navigation-menu": "^1.2.13",
        "@radix-ui/react-popover": "^1.1.15",
+        "@radix-ui/react-radio-group": "^1.3.8",
        "@radix-ui/react-select": "^2.2.5",
        "@radix-ui/react-separator": "^1.1.7",
        "@radix-ui/react-slider": "^1.3.6",
@ -1819,6 +1820,38 @@
        }
      }
    },
+    "node_modules/@radix-ui/react-radio-group": {
+      "version": "1.3.8",
+      "resolved": "https://registry.npmjs.org/@radix-ui/react-radio-group/-/react-radio-group-1.3.8.tgz",
+      "integrity": "sha512-VBKYIYImA5zsxACdisNQ3BjCBfmbGH3kQlnFVqlWU4tXwjy7cGX8ta80BcrO+WJXIn5iBylEH3K6ZTlee//lgQ==",
+      "license": "MIT",
+      "dependencies": {
+        "@radix-ui/primitive": "1.1.3",
+        "@radix-ui/react-compose-refs": "1.1.2",
+        "@radix-ui/react-context": "1.1.2",
+        "@radix-ui/react-direction": "1.1.1",
+        "@radix-ui/react-presence": "1.1.5",
+        "@radix-ui/react-primitive": "2.1.3",
+        "@radix-ui/react-roving-focus": "1.1.11",
+        "@radix-ui/react-use-controllable-state": "1.2.2",
+        "@radix-ui/react-use-previous": "1.1.1",
+        "@radix-ui/react-use-size": "1.1.1"
+      },
+      "peerDependencies": {
+        "@types/react": "*",
+        "@types/react-dom": "*",
+        "react": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc",
+        "react-dom": "^16.8 || ^17.0 || ^18.0 || ^19.0 || ^19.0.0-rc"
+      },
+      "peerDependenciesMeta": {
+        "@types/react": {
+          "optional": true
+        },
+        "@types/react-dom": {
+          "optional": true
+        }
+      }
+    },
    "node_modules/@radix-ui/react-roving-focus": {
      "version": "1.1.11",
      "resolved": "https://registry.npmjs.org/@radix-ui/react-roving-focus/-/react-roving-focus-1.1.11.tgz",
--- a/frontend/package.json
+++ b/frontend/package.json
@ -20,6 +20,7 @@
    "@radix-ui/react-label": "^2.1.7",
    "@radix-ui/react-navigation-menu": "^1.2.13",
    "@radix-ui/react-popover": "^1.1.15",
+    "@radix-ui/react-radio-group": "^1.3.8",
    "@radix-ui/react-select": "^2.2.5",
    "@radix-ui/react-separator": "^1.1.7",
    "@radix-ui/react-slider": "^1.3.6",
--- a/frontend/src/app/api/mutations/useUpdateFlowSettingMutation.ts
+++ b/frontend/src/app/api/mutations/useUpdateFlowSettingMutation.ts
@ -8,8 +8,7 @@ interface UpdateFlowSettingVariables {
  llm_model?: string;
  system_prompt?: string;
  embedding_model?: string;
-  ocr?: boolean;
-  picture_descriptions?: boolean;
+  doclingPresets?: string;
  chunk_size?: number;
  chunk_overlap?: number;
 }
--- a/frontend/src/app/api/queries/useGetSettingsQuery.ts
+++ b/frontend/src/app/api/queries/useGetSettingsQuery.ts
@ -13,8 +13,7 @@ export interface KnowledgeSettings {
  embedding_model?: string;
  chunk_size?: number;
  chunk_overlap?: number;
-  ocr?: boolean;
-  picture_descriptions?: boolean;
+  doclingPresets?: string;
 }

 export interface Settings {
--- a/frontend/src/app/settings/page.tsx
+++ b/frontend/src/app/settings/page.tsx
@ -22,6 +22,7 @@ import {
 import { Checkbox } from "@/components/ui/checkbox";
 import { Input } from "@/components/ui/input";
 import { Label } from "@/components/ui/label";
+import { RadioGroup, RadioGroupItem } from "@/components/ui/radio-group";
 import {
  Select,
  SelectContent,
@ -100,6 +101,7 @@ function KnowledgeSourcesPage() {
  const [systemPrompt, setSystemPrompt] = useState<string>("");
  const [chunkSize, setChunkSize] = useState<number>(1024);
  const [chunkOverlap, setChunkOverlap] = useState<number>(50);
+  const [processingMode, setProcessingMode] = useState<string>("standard");

  // Fetch settings using React Query
  const { data: settings = {} } = useGetSettingsQuery({
@ -175,6 +177,13 @@ function KnowledgeSourcesPage() {
    }
  }, [settings.knowledge?.chunk_overlap]);

+  // Sync processing mode with settings data
+  useEffect(() => {
+    if (settings.knowledge?.doclingPresets) {
+      setProcessingMode(settings.knowledge.doclingPresets);
+    }
+  }, [settings.knowledge?.doclingPresets]);
+
  // Update model selection immediately
  const handleModelChange = (newModel: string) => {
    updateFlowSettingMutation.mutate({ llm_model: newModel });
@ -204,6 +213,12 @@ function KnowledgeSourcesPage() {
    debouncedUpdate({ chunk_overlap: numValue });
  };

+  // Update processing mode
+  const handleProcessingModeChange = (mode: string) => {
+    setProcessingMode(mode);
+    debouncedUpdate({ doclingPresets: mode });
+  };
+

  // Helper function to get connector icon
  const getConnectorIcon = useCallback((iconName: string) => {
@ -777,40 +792,59 @@ function KnowledgeSourcesPage() {
                </div>
              </div>
            </div>
-            {/* <div className="flex items-center justify-between">
-              <div className="space-y-0.5">
-                <Label htmlFor="ocrEnabled" className="text-base font-medium">
-                  OCR
-                </Label>
-                <div className="text-sm text-muted-foreground">
-                  Extracts text from images/PDFs. Ingest is slower when enabled.
+            <div className="space-y-3">
+              <Label className="text-base font-medium">Ingest Presets</Label>
+              <RadioGroup
+                value={processingMode}
+                onValueChange={handleProcessingModeChange}
+                className="space-y-3"
+              >
+                <div className="flex items-center space-x-3">
+                  <RadioGroupItem value="standard" id="standard" />
+                  <div className="flex-1">
+                    <Label htmlFor="standard" className="text-base font-medium cursor-pointer">
+                      Standard
+                    </Label>
+                    <div className="text-sm text-muted-foreground">
+                      Fast ingest for text-based documents without images
+                    </div>
+                  </div>
                </div>
-              </div>
-              <Switch
-                id="ocrEnabled"
-                checked={ocrEnabled}
-                onCheckedChange={handleOcrChange}
-              />
+                <div className="flex items-center space-x-3">
+                  <RadioGroupItem value="ocr" id="ocr" />
+                  <div className="flex-1">
+                    <Label htmlFor="ocr" className="text-base font-medium cursor-pointer">
+                      Extract text from images
+                    </Label>
+                    <div className="text-sm text-muted-foreground">
+                      Uses OCR to extract text from images/PDFs. Ingest is slower when enabled
+                    </div>
+                  </div>
+                </div>
+                <div className="flex items-center space-x-3">
+                  <RadioGroupItem value="picture_description" id="picture_description" />
+                  <div className="flex-1">
+                    <Label htmlFor="picture_description" className="text-base font-medium cursor-pointer">
+                      Generate Description
+                    </Label>
+                    <div className="text-sm text-muted-foreground">
+                      Text extraction plust AI generated image descriptions
+                    </div>
+                  </div>
+                </div>
+                <div className="flex items-center space-x-3">
+                  <RadioGroupItem value="VLM" id="VLM" />
+                  <div className="flex-1">
+                    <Label htmlFor="VLM" className="text-base font-medium cursor-pointer">
+                      AI Vision
+                    </Label>
+                    <div className="text-sm text-muted-foreground">
+                      Advanced processing with vision language models. Highest quality but most expensive
+                    </div>
+                  </div>
+                </div>
+              </RadioGroup>
            </div>
-            <div className="flex items-center justify-between">
-              <div className="space-y-0.5">
-                <Label
-                  htmlFor="pictureDescriptions"
-                  className="text-base font-medium"
-                >
-                  Picture descriptions
-                </Label>
-                <div className="text-sm text-muted-foreground">
-                  Adds captions for images. Ingest is more expensive when
-                  enabled.
-                </div>
-              </div>
-              <Switch
-                id="pictureDescriptions"
-                checked={pictureDescriptionsEnabled}
-                onCheckedChange={handlePictureDescriptionsChange}
-              />
-            </div> */}
          </div>
        </CardContent>
      </Card>
--- a/frontend/src/components/layout-wrapper.tsx
+++ b/frontend/src/components/layout-wrapper.tsx
@ -104,7 +104,7 @@ export function LayoutWrapper({ children }: { children: React.ReactNode }) {
        <Navigation />
      </div>
      <main
-        className={`md:pl-72 transition-all duration-300 ${
+        className={`md:pl-72 transition-all duration-300 overflow-y-auto h-[calc(100vh-53px)] ${
          isMenuOpen && isPanelOpen
            ? "md:pr-[728px]"
            : // Both open: 384px (menu) + 320px (KF panel) + 24px (original padding)
--- a/src/api/settings.py
+++ b/src/api/settings.py
@ -38,8 +38,7 @@ async def get_settings(request, session_manager):
                "embedding_model": knowledge_config.embedding_model,
                "chunk_size": knowledge_config.chunk_size,
                "chunk_overlap": knowledge_config.chunk_overlap,
-                "ocr": knowledge_config.ocr,
-                "picture_descriptions": knowledge_config.picture_descriptions,
+                "doclingPresets": knowledge_config.doclingPresets,
            },
            "agent": {
                "llm_model": agent_config.llm_model,
@ -149,7 +148,7 @@ async def update_settings(request, session_manager):
        
        # Validate allowed fields
        allowed_fields = {
-            "llm_model", "system_prompt", "ocr", "picture_descriptions", 
+            "llm_model", "system_prompt", "doclingPresets",
            "chunk_size", "chunk_overlap"
        }
        
@ -174,22 +173,14 @@ async def update_settings(request, session_manager):
            config_updated = True
        
        # Update knowledge settings
-        if "ocr" in body:
-            if not isinstance(body["ocr"], bool):
+        if "doclingPresets" in body:
+            valid_presets = ["standard", "ocr", "picture_description", "VLM"]
+            if body["doclingPresets"] not in valid_presets:
                return JSONResponse(
-                    {"error": "ocr must be a boolean value"}, 
+                    {"error": f"doclingPresets must be one of: {', '.join(valid_presets)}"},
                    status_code=400
                )
-            current_config.knowledge.ocr = body["ocr"]
-            config_updated = True
-            
-        if "picture_descriptions" in body:
-            if not isinstance(body["picture_descriptions"], bool):
-                return JSONResponse(
-                    {"error": "picture_descriptions must be a boolean value"}, 
-                    status_code=400
-                )
-            current_config.knowledge.picture_descriptions = body["picture_descriptions"]
+            current_config.knowledge.doclingPresets = body["doclingPresets"]
            config_updated = True
            
        if "chunk_size" in body: