gmakstutis/openrag
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 1

Merge pull request #141 from langflow-ai/docling-settings

Browse source 
Update docling preset options
This commit is contained in:
Mike Fortman 2025-09-30 13:13:06 -05:00 • committed by GitHub
commit f54479cf48
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
8 changed files with 211 additions and 184 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
frontend/components/ui/switch.tsx
View file

@ -11,7 +11,7 @@ const Switch = React.forwardRef<
>(({ className, ...props }, ref) => ( >(({ className, ...props }, ref) => (
<SwitchPrimitives.Root <SwitchPrimitives.Root
className={cn( className={cn(
"peer inline-flex h-6 w-11 shrink-0 cursor-pointer items-center rounded-full border-2 border-transparent transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 focus-visible:ring-offset-background disabled:cursor-not-allowed disabled:opacity-50 data-[state=checked]:bg-primary data-[state=unchecked]:bg-input", "peer inline-flex h-6 w-11 shrink-0 cursor-pointer items-center rounded-full border-2 border-transparent transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 focus-visible:ring-offset-background disabled:cursor-not-allowed disabled:opacity-50 data-[state=checked]:bg-primary data-[state=unchecked]:bg-muted",
className className
)} )}
{...props} {...props}
@ -19,7 +19,7 @@ const Switch = React.forwardRef<
> >
<SwitchPrimitives.Thumb <SwitchPrimitives.Thumb
className={cn( className={cn(
"pointer-events-none block h-5 w-5 rounded-full bg-background shadow-lg ring-0 transition-transform data-[state=checked]:translate-x-5 data-[state=unchecked]:translate-x-0" "pointer-events-none block h-5 w-5 rounded-full bg-background shadow-lg ring-0 transition-transform data-[state=checked]:translate-x-5 data-[state=unchecked]:translate-x-0 data-[state=unchecked]:bg-primary"
)} )}
/> />
</SwitchPrimitives.Root> </SwitchPrimitives.Root>

4
frontend/src/app/api/mutations/useUpdateFlowSettingMutation.ts
View file

@ -8,7 +8,9 @@ interface UpdateFlowSettingVariables {
llm_model?: string; llm_model?: string;
system_prompt?: string; system_prompt?: string;
embedding_model?: string; embedding_model?: string;
doclingPresets?: string; table_structure?: boolean;
ocr?: boolean;
picture_descriptions?: boolean;
chunk_size?: number; chunk_size?: number;
chunk_overlap?: number; chunk_overlap?: number;
} }

4
frontend/src/app/api/queries/useGetSettingsQuery.ts
View file

@ -13,7 +13,9 @@ export interface KnowledgeSettings {
embedding_model?: string; embedding_model?: string;
chunk_size?: number; chunk_size?: number;
chunk_overlap?: number; chunk_overlap?: number;
doclingPresets?: string; table_structure?: boolean;
ocr?: boolean;
picture_descriptions?: boolean;
} }
export interface Settings { export interface Settings {

167
frontend/src/app/settings/page.tsx
View file

@ -22,9 +22,9 @@ import {
CardTitle, CardTitle,
} from "@/components/ui/card"; } from "@/components/ui/card";
import { Checkbox } from "@/components/ui/checkbox"; import { Checkbox } from "@/components/ui/checkbox";
import { Switch } from "@/components/ui/switch";
import { Input } from "@/components/ui/input"; import { Input } from "@/components/ui/input";
import { Label } from "@/components/ui/label"; import { Label } from "@/components/ui/label";
import { RadioGroup, RadioGroupItem } from "@/components/ui/radio-group";
import { import {
Select, Select,
SelectContent, SelectContent,
@ -39,11 +39,6 @@ import { DEFAULT_AGENT_SETTINGS, DEFAULT_KNOWLEDGE_SETTINGS, UI_CONSTANTS } from
import { getFallbackModels, type ModelProvider } from "./helpers/model-helpers"; import { getFallbackModels, type ModelProvider } from "./helpers/model-helpers";
import { ModelSelectItems } from "./helpers/model-select-item"; import { ModelSelectItems } from "./helpers/model-select-item";
import { LabelWrapper } from "@/components/label-wrapper"; import { LabelWrapper } from "@/components/label-wrapper";
import {
Tooltip,
TooltipContent,
TooltipTrigger,
} from "@radix-ui/react-tooltip";
const { MAX_SYSTEM_PROMPT_CHARS } = UI_CONSTANTS; const { MAX_SYSTEM_PROMPT_CHARS } = UI_CONSTANTS;
@ -112,7 +107,9 @@ function KnowledgeSourcesPage() {
const [systemPrompt, setSystemPrompt] = useState<string>(""); const [systemPrompt, setSystemPrompt] = useState<string>("");
const [chunkSize, setChunkSize] = useState<number>(1024); const [chunkSize, setChunkSize] = useState<number>(1024);
const [chunkOverlap, setChunkOverlap] = useState<number>(50); const [chunkOverlap, setChunkOverlap] = useState<number>(50);
const [processingMode, setProcessingMode] = useState<string>("standard"); const [tableStructure, setTableStructure] = useState<boolean>(false);
const [ocr, setOcr] = useState<boolean>(false);
const [pictureDescriptions, setPictureDescriptions] = useState<boolean>(false);
// Fetch settings using React Query // Fetch settings using React Query
const { data: settings = {} } = useGetSettingsQuery({ const { data: settings = {} } = useGetSettingsQuery({
@ -195,12 +192,24 @@ function KnowledgeSourcesPage() {
} }
}, [settings.knowledge?.chunk_overlap]); }, [settings.knowledge?.chunk_overlap]);
// Sync processing mode with settings data // Sync docling settings with settings data
useEffect(() => { useEffect(() => {
if (settings.knowledge?.doclingPresets) { if (settings.knowledge?.table_structure !== undefined) {
setProcessingMode(settings.knowledge.doclingPresets); setTableStructure(settings.knowledge.table_structure);
} }
}, [settings.knowledge?.doclingPresets]); }, [settings.knowledge?.table_structure]);
useEffect(() => {
if (settings.knowledge?.ocr !== undefined) {
setOcr(settings.knowledge.ocr);
}
}, [settings.knowledge?.ocr]);
useEffect(() => {
if (settings.knowledge?.picture_descriptions !== undefined) {
setPictureDescriptions(settings.knowledge.picture_descriptions);
}
}, [settings.knowledge?.picture_descriptions]);
// Update model selection immediately // Update model selection immediately
const handleModelChange = (newModel: string) => { const handleModelChange = (newModel: string) => {
@ -231,11 +240,20 @@ function KnowledgeSourcesPage() {
debouncedUpdate({ chunk_overlap: numValue }); debouncedUpdate({ chunk_overlap: numValue });
}; };
// Update processing mode // Update docling settings
const handleProcessingModeChange = (mode: string) => { const handleTableStructureChange = (checked: boolean) => {
setProcessingMode(mode); setTableStructure(checked);
// Update the configuration setting (backend will also update the flow automatically) updateFlowSettingMutation.mutate({ table_structure: checked });
debouncedUpdate({ doclingPresets: mode }); };
const handleOcrChange = (checked: boolean) => {
setOcr(checked);
updateFlowSettingMutation.mutate({ ocr: checked });
};
const handlePictureDescriptionsChange = (checked: boolean) => {
setPictureDescriptions(checked);
updateFlowSettingMutation.mutate({ picture_descriptions: checked });
}; };
// Helper function to get connector icon // Helper function to get connector icon
@ -569,7 +587,9 @@ function KnowledgeSourcesPage() {
// Only reset form values if the API call was successful // Only reset form values if the API call was successful
setChunkSize(DEFAULT_KNOWLEDGE_SETTINGS.chunk_size); setChunkSize(DEFAULT_KNOWLEDGE_SETTINGS.chunk_size);
setChunkOverlap(DEFAULT_KNOWLEDGE_SETTINGS.chunk_overlap); setChunkOverlap(DEFAULT_KNOWLEDGE_SETTINGS.chunk_overlap);
setProcessingMode(DEFAULT_KNOWLEDGE_SETTINGS.processing_mode); setTableStructure(false);
setOcr(false);
setPictureDescriptions(false);
closeDialog(); // Close after successful completion closeDialog(); // Close after successful completion
}) })
.catch((error) => { .catch((error) => {
@ -1063,76 +1083,61 @@ function KnowledgeSourcesPage() {
</div> </div>
</div> </div>
</div> </div>
<div className="space-y-3"> <div className="">
<Label className="text-base font-medium">Ingestion presets</Label> <div className="flex items-center justify-between py-3 border-b border-border">
<RadioGroup <div className="flex-1">
value={processingMode} <Label
onValueChange={handleProcessingModeChange} htmlFor="table-structure"
className="space-y-3" className="text-base font-medium cursor-pointer pb-3"
> >
<div className="flex items-center space-x-3"> Table Structure
<RadioGroupItem value="standard" id="standard" /> </Label>
<div className="flex-1"> <div className="text-sm text-muted-foreground">
<Label Capture table structure during ingest.
htmlFor="standard"
className="text-base font-medium cursor-pointer"
>
No OCR
</Label>
<div className="text-sm text-muted-foreground">
Fast ingest for documents with selectable text. Images are
ignored.
</div>
</div> </div>
</div> </div>
<div className="flex items-center space-x-3"> <Switch
<RadioGroupItem value="ocr" id="ocr" /> id="table-structure"
<div className="flex-1"> checked={tableStructure}
<Label onCheckedChange={handleTableStructureChange}
htmlFor="ocr" />
className="text-base font-medium cursor-pointer" </div>
> <div className="flex items-center justify-between py-3 border-b border-border">
OCR <div className="flex-1">
</Label> <Label
<div className="text-sm text-muted-foreground"> htmlFor="ocr"
Extracts text from images and scanned pages. className="text-base font-medium cursor-pointer pb-3"
</div> >
OCR
</Label>
<div className="text-sm text-muted-foreground">
Extracts text from images/PDFs. Ingest is slower when enabled.
</div> </div>
</div> </div>
<div className="flex items-center space-x-3"> <Switch
<RadioGroupItem id="ocr"
value="picture_description" checked={ocr}
id="picture_description" onCheckedChange={handleOcrChange}
/> />
<div className="flex-1"> </div>
<Label <div className="flex items-center justify-between py-3">
htmlFor="picture_description" <div className="flex-1">
className="text-base font-medium cursor-pointer" <Label
> htmlFor="picture-descriptions"
OCR + Captions className="text-base font-medium cursor-pointer pb-3"
</Label> >
<div className="text-sm text-muted-foreground"> Picture Descriptions
Extracts text from images and scanned pages. Generates </Label>
short image captions. <div className="text-sm text-muted-foreground">
</div> Adds captions for images. Ingest is slower when enabled.
</div> </div>
</div> </div>
<div className="flex items-center space-x-3"> <Switch
<RadioGroupItem value="VLM" id="VLM" /> id="picture-descriptions"
<div className="flex-1"> checked={pictureDescriptions}
<Label onCheckedChange={handlePictureDescriptionsChange}
htmlFor="VLM" />
className="text-base font-medium cursor-pointer" </div>
>
VLM
</Label>
<div className="text-sm text-muted-foreground">
Extracts text from layout-aware parsing of text, tables,
and sections.
</div>
</div>
</div>
</RadioGroup>
</div> </div>
</div> </div>
</CardContent> </CardContent>

29
frontend/src/components/ui/switch.tsx
View file

@ -1,29 +0,0 @@
"use client"
import * as React from "react"
import * as SwitchPrimitives from "@radix-ui/react-switch"
import { cn } from "@/lib/utils"
const Switch = React.forwardRef<
React.ElementRef<typeof SwitchPrimitives.Root>,
React.ComponentPropsWithoutRef<typeof SwitchPrimitives.Root>
>(({ className, ...props }, ref) => (
<SwitchPrimitives.Root
className={cn(
"peer inline-flex h-6 w-11 shrink-0 cursor-pointer items-center rounded-full border-2 border-transparent transition-colors focus-visible:outline-none focus-visible:ring-2 focus-visible:ring-ring focus-visible:ring-offset-2 focus-visible:ring-offset-background disabled:cursor-not-allowed disabled:opacity-50 data-[state=checked]:bg-primary data-[state=unchecked]:bg-input",
className
)}
{...props}
ref={ref}
>
<SwitchPrimitives.Thumb
className={cn(
"pointer-events-none block h-5 w-5 rounded-full bg-background shadow-lg ring-0 transition-transform data-[state=checked]:translate-x-5 data-[state=unchecked]:translate-x-0"
)}
/>
</SwitchPrimitives.Root>
))
Switch.displayName = SwitchPrimitives.Root.displayName
export { Switch }

4
frontend/src/lib/constants.ts
View file

@ -12,7 +12,9 @@ export const DEFAULT_AGENT_SETTINGS = {
export const DEFAULT_KNOWLEDGE_SETTINGS = { export const DEFAULT_KNOWLEDGE_SETTINGS = {
chunk_size: 1000, chunk_size: 1000,
chunk_overlap: 200, chunk_overlap: 200,
processing_mode: "standard" table_structure: false,
ocr: false,
picture_descriptions: false
} as const; } as const;
/** /**

179
src/api/settings.py
View file

@ -17,35 +17,30 @@ logger = get_logger(__name__)
# Docling preset configurations # Docling preset configurations
def get_docling_preset_configs(): def get_docling_preset_configs(table_structure=False, ocr=False, picture_descriptions=False):
"""Get docling preset configurations with platform-specific settings""" """Get docling preset configurations based on toggle settings
Args:
table_structure: Enable table structure parsing (default: False)
ocr: Enable OCR for text extraction from images (default: False)
picture_descriptions: Enable picture descriptions/captions (default: False)
"""
is_macos = platform.system() == "Darwin" is_macos = platform.system() == "Darwin"
return { config = {
"standard": {"do_ocr": False}, "do_ocr": ocr,
"ocr": {"do_ocr": True, "ocr_engine": "ocrmac" if is_macos else "easyocr"}, "ocr_engine": "ocrmac" if is_macos else "easyocr",
"picture_description": { "do_table_structure": table_structure,
"do_ocr": True, "do_picture_classification": picture_descriptions,
"ocr_engine": "ocrmac" if is_macos else "easyocr", "do_picture_description": picture_descriptions,
"do_picture_classification": True, "picture_description_local": {
"do_picture_description": True, "repo_id": "HuggingFaceTB/SmolVLM-256M-Instruct",
"picture_description_local": { "prompt": "Describe this image in a few sentences.",
"repo_id": "HuggingFaceTB/SmolVLM-256M-Instruct", }
"prompt": "Describe this image in a few sentences.",
},
},
"VLM": {
"pipeline": "vlm",
"vlm_pipeline_model_local": {
"repo_id": "ds4sd/SmolDocling-256M-preview-mlx-bf16"
if is_macos
else "ds4sd/SmolDocling-256M-preview",
"response_format": "doctags",
"inference_framework": "mlx",
},
},
} }
return config
async def get_settings(request, session_manager): async def get_settings(request, session_manager):
"""Get application settings""" """Get application settings"""
@ -71,7 +66,9 @@ async def get_settings(request, session_manager):
"embedding_model": knowledge_config.embedding_model, "embedding_model": knowledge_config.embedding_model,
"chunk_size": knowledge_config.chunk_size, "chunk_size": knowledge_config.chunk_size,
"chunk_overlap": knowledge_config.chunk_overlap, "chunk_overlap": knowledge_config.chunk_overlap,
"doclingPresets": knowledge_config.doclingPresets, "table_structure": knowledge_config.table_structure,
"ocr": knowledge_config.ocr,
"picture_descriptions": knowledge_config.picture_descriptions,
}, },
"agent": { "agent": {
"llm_model": agent_config.llm_model, "llm_model": agent_config.llm_model,
@ -178,7 +175,9 @@ async def update_settings(request, session_manager):
"system_prompt", "system_prompt",
"chunk_size", "chunk_size",
"chunk_overlap", "chunk_overlap",
"doclingPresets", "table_structure",
"ocr",
"picture_descriptions",
"embedding_model", "embedding_model",
} }
@ -255,32 +254,68 @@ async def update_settings(request, session_manager):
# Don't fail the entire settings update if flow update fails # Don't fail the entire settings update if flow update fails
# The config will still be saved # The config will still be saved
if "doclingPresets" in body: if "table_structure" in body:
preset_configs = get_docling_preset_configs() if not isinstance(body["table_structure"], bool):
valid_presets = list(preset_configs.keys())
if body["doclingPresets"] not in valid_presets:
return JSONResponse( return JSONResponse(
{ {"error": "table_structure must be a boolean"}, status_code=400
"error": f"doclingPresets must be one of: {', '.join(valid_presets)}"
},
status_code=400,
) )
current_config.knowledge.doclingPresets = body["doclingPresets"] current_config.knowledge.table_structure = body["table_structure"]
config_updated = True config_updated = True
# Also update the flow with the new docling preset # Also update the flow with the new docling settings
try: try:
flows_service = _get_flows_service() flows_service = _get_flows_service()
await flows_service.update_flow_docling_preset( preset_config = get_docling_preset_configs(
body["doclingPresets"], preset_configs[body["doclingPresets"]] table_structure=body["table_structure"],
) ocr=current_config.knowledge.ocr,
logger.info( picture_descriptions=current_config.knowledge.picture_descriptions
f"Successfully updated docling preset in flow to '{body['doclingPresets']}'"
) )
await flows_service.update_flow_docling_preset("custom", preset_config)
logger.info(f"Successfully updated table_structure setting in flow")
except Exception as e: except Exception as e:
logger.error(f"Failed to update docling preset in flow: {str(e)}") logger.error(f"Failed to update docling settings in flow: {str(e)}")
# Don't fail the entire settings update if flow update fails
# The config will still be saved if "ocr" in body:
if not isinstance(body["ocr"], bool):
return JSONResponse(
{"error": "ocr must be a boolean"}, status_code=400
)
current_config.knowledge.ocr = body["ocr"]
config_updated = True
# Also update the flow with the new docling settings
try:
flows_service = _get_flows_service()
preset_config = get_docling_preset_configs(
table_structure=current_config.knowledge.table_structure,
ocr=body["ocr"],
picture_descriptions=current_config.knowledge.picture_descriptions
)
await flows_service.update_flow_docling_preset("custom", preset_config)
logger.info(f"Successfully updated ocr setting in flow")
except Exception as e:
logger.error(f"Failed to update docling settings in flow: {str(e)}")
if "picture_descriptions" in body:
if not isinstance(body["picture_descriptions"], bool):
return JSONResponse(
{"error": "picture_descriptions must be a boolean"}, status_code=400
)
current_config.knowledge.picture_descriptions = body["picture_descriptions"]
config_updated = True
# Also update the flow with the new docling settings
try:
flows_service = _get_flows_service()
preset_config = get_docling_preset_configs(
table_structure=current_config.knowledge.table_structure,
ocr=current_config.knowledge.ocr,
picture_descriptions=body["picture_descriptions"]
)
await flows_service.update_flow_docling_preset("custom", preset_config)
logger.info(f"Successfully updated picture_descriptions setting in flow")
except Exception as e:
logger.error(f"Failed to update docling settings in flow: {str(e)}")
if "chunk_size" in body: if "chunk_size" in body:
if not isinstance(body["chunk_size"], int) or body["chunk_size"] <= 0: if not isinstance(body["chunk_size"], int) or body["chunk_size"] <= 0:
@ -624,48 +659,56 @@ def _get_flows_service():
async def update_docling_preset(request, session_manager): async def update_docling_preset(request, session_manager):
"""Update docling preset in the ingest flow""" """Update docling settings in the ingest flow - deprecated endpoint, use /settings instead"""
try: try:
# Parse request body # Parse request body
body = await request.json() body = await request.json()
# Validate preset parameter # Support old preset-based API for backwards compatibility
if "preset" not in body: if "preset" in body:
return JSONResponse( # Map old presets to new toggle settings
{"error": "preset parameter is required"}, status_code=400 preset_map = {
) "standard": {"table_structure": False, "ocr": False, "picture_descriptions": False},
"ocr": {"table_structure": False, "ocr": True, "picture_descriptions": False},
"picture_description": {"table_structure": False, "ocr": True, "picture_descriptions": True},
"VLM": {"table_structure": False, "ocr": False, "picture_descriptions": False},
}
preset = body["preset"] preset = body["preset"]
preset_configs = get_docling_preset_configs() if preset not in preset_map:
return JSONResponse(
{"error": f"Invalid preset '{preset}'. Valid presets: {', '.join(preset_map.keys())}"},
status_code=400,
)
if preset not in preset_configs: settings = preset_map[preset]
valid_presets = list(preset_configs.keys()) else:
return JSONResponse( # Support new toggle-based API
{ settings = {
"error": f"Invalid preset '{preset}'. Valid presets: {', '.join(valid_presets)}" "table_structure": body.get("table_structure", False),
}, "ocr": body.get("ocr", False),
status_code=400, "picture_descriptions": body.get("picture_descriptions", False),
) }
# Get the preset configuration # Get the preset configuration
preset_config = preset_configs[preset] preset_config = get_docling_preset_configs(**settings)
# Use the helper function to update the flow # Use the helper function to update the flow
flows_service = _get_flows_service() flows_service = _get_flows_service()
await flows_service.update_flow_docling_preset(preset, preset_config) await flows_service.update_flow_docling_preset("custom", preset_config)
logger.info(f"Successfully updated docling preset to '{preset}' in ingest flow") logger.info(f"Successfully updated docling settings in ingest flow")
return JSONResponse( return JSONResponse(
{ {
"message": f"Successfully updated docling preset to '{preset}'", "message": f"Successfully updated docling settings",
"preset": preset, "settings": settings,
"preset_config": preset_config, "preset_config": preset_config,
} }
) )
except Exception as e: except Exception as e:
logger.error("Failed to update docling preset", error=str(e)) logger.error("Failed to update docling settings", error=str(e))
return JSONResponse( return JSONResponse(
{"error": f"Failed to update docling preset: {str(e)}"}, status_code=500 {"error": f"Failed to update docling settings: {str(e)}"}, status_code=500
) )

4
src/config/config_manager.py
View file

@ -27,7 +27,9 @@ class KnowledgeConfig:
embedding_model: str = "text-embedding-3-small" embedding_model: str = "text-embedding-3-small"
chunk_size: int = 1000 chunk_size: int = 1000
chunk_overlap: int = 200 chunk_overlap: int = 200
doclingPresets: str = "standard" table_structure: bool = False
ocr: bool = False
picture_descriptions: bool = False
@dataclass @dataclass