Merge branch 'main' into knowledge-status

.env.example

@@ -8,6 +8,8 @@ LANGFLOW_SECRET_KEY=
 # flow ids for chat and ingestion flows
 LANGFLOW_CHAT_FLOW_ID=1098eea1-6649-4e1d-aed1-b77249fb8dd0
 LANGFLOW_INGEST_FLOW_ID=5488df7c-b93f-4f87-a446-b67028bc0813
+# Ingest flow using docling
+LANGFLOW_INGEST_FLOW_ID=1402618b-e6d1-4ff2-9a11-d6ce71186915
 NUDGES_FLOW_ID=ebc01d31-1976-46ce-a385-b0240327226c
 
 # Set a strong admin password for OpenSearch; a bcrypt hash is generated at

frontend/src/app/knowledge/chunks/page.tsx

@@ -1,17 +1,14 @@
 "use client";
 
 import {
-  Building2,
-  Cloud,
-  FileText,
-  HardDrive,
+  ArrowLeft,
+  Copy,
+  File as FileIcon,
   Loader2,
   Search,
 } from "lucide-react";
-import { Suspense, useCallback, useEffect, useState } from "react";
+import { Suspense, useCallback, useEffect, useMemo, useState } from "react";
 import { useRouter, useSearchParams } from "next/navigation";
-import { SiGoogledrive } from "react-icons/si";
-import { TbBrandOnedrive } from "react-icons/tb";
 import { ProtectedRoute } from "@/components/protected-route";
 import { Button } from "@/components/ui/button";
 import { useKnowledgeFilter } from "@/contexts/knowledge-filter-context";
@@ -21,22 +18,16 @@ import {
   type File,
   useGetSearchQuery,
 } from "../../api/queries/useGetSearchQuery";
+import { Label } from "@/components/ui/label";
+import { Checkbox } from "@/components/ui/checkbox";
+import { Input } from "@/components/ui/input";
 
-// Function to get the appropriate icon for a connector type
-function getSourceIcon(connectorType?: string) {
-  switch (connectorType) {
-    case "google_drive":
-      return <SiGoogledrive className="h-4 w-4 text-foreground" />;
-    case "onedrive":
-      return <TbBrandOnedrive className="h-4 w-4 text-foreground" />;
-    case "sharepoint":
-      return <Building2 className="h-4 w-4 text-foreground" />;
-    case "s3":
-      return <Cloud className="h-4 w-4 text-foreground" />;
-    default:
-      return <HardDrive className="h-4 w-4 text-muted-foreground" />;
-  }
-}
+const getFileTypeLabel = (mimetype: string) => {
+  if (mimetype === "application/pdf") return "PDF";
+  if (mimetype === "text/plain") return "Text";
+  if (mimetype === "application/msword") return "Word Document";
+  return "Unknown";
+};
 
 function ChunksPageContent() {
   const router = useRouter();
@@ -46,10 +37,47 @@ function ChunksPageContent() {
 
   const filename = searchParams.get("filename");
   const [chunks, setChunks] = useState<ChunkResult[]>([]);
+  const [chunksFilteredByQuery, setChunksFilteredByQuery] = useState<
+    ChunkResult[]
+  >([]);
+  const [selectedChunks, setSelectedChunks] = useState<Set<number>>(new Set());
+
+  // Calculate average chunk length
+  const averageChunkLength = useMemo(
+    () =>
+      chunks.reduce((acc, chunk) => acc + chunk.text.length, 0) /
+        chunks.length || 0,
+    [chunks]
+  );
+
+  const [selectAll, setSelectAll] = useState(false);
+  const [queryInputText, setQueryInputText] = useState(
+    parsedFilterData?.query ?? ""
+  );
 
   // Use the same search query as the knowledge page, but we'll filter for the specific file
   const { data = [], isFetching } = useGetSearchQuery("*", parsedFilterData);
 
+  useEffect(() => {
+    if (queryInputText === "") {
+      setChunksFilteredByQuery(chunks);
+    } else {
+      setChunksFilteredByQuery(
+        chunks.filter((chunk) =>
+          chunk.text.toLowerCase().includes(queryInputText.toLowerCase())
+        )
+      );
+    }
+  }, [queryInputText, chunks]);
+
+  const handleCopy = useCallback((text: string) => {
+    navigator.clipboard.writeText(text);
+  }, []);
+
+  const fileData = (data as File[]).find(
+    (file: File) => file.filename === filename
+  );
+
   // Extract chunks for the specific file
   useEffect(() => {
     if (!filename || !(data as File[]).length) {
@@ -57,16 +85,37 @@ function ChunksPageContent() {
       return;
     }
 
-    const fileData = (data as File[]).find(
-      (file: File) => file.filename === filename
-    );
     setChunks(fileData?.chunks || []);
   }, [data, filename]);
 
+  // Set selected state for all checkboxes when selectAll changes
+  useEffect(() => {
+    if (selectAll) {
+      setSelectedChunks(new Set(chunks.map((_, index) => index)));
+    } else {
+      setSelectedChunks(new Set());
+    }
+  }, [selectAll, setSelectedChunks, chunks]);
+
   const handleBack = useCallback(() => {
-    router.back();
+    router.push("/knowledge");
   }, [router]);
 
+  const handleChunkCardCheckboxChange = useCallback(
+    (index: number) => {
+      setSelectedChunks((prevSelected) => {
+        const newSelected = new Set(prevSelected);
+        if (newSelected.has(index)) {
+          newSelected.delete(index);
+        } else {
+          newSelected.add(index);
+        }
+        return newSelected;
+      });
+    },
+    [setSelectedChunks]
+  );
+
   if (!filename) {
     return (
       <div className="flex items-center justify-center h-64">
@@ -83,7 +132,7 @@ function ChunksPageContent() {
 
   return (
     <div
-      className={`fixed inset-0 md:left-72 top-[53px] flex flex-col transition-all duration-300 ${
+      className={`fixed inset-0 md:left-72 top-[53px] flex flex-row transition-all duration-300 ${
         isMenuOpen && isPanelOpen
           ? "md:right-[704px]"
           : // Both open: 384px (menu) + 320px (KF panel)
@@ -98,29 +147,47 @@ function ChunksPageContent() {
     >
       <div className="flex-1 flex flex-col min-h-0 px-6 py-6">
         {/* Header */}
-        <div className="flex items-center justify-between mb-6">
-          <div className="flex items-center gap-3">
-            <Button
-              variant="ghost"
-              size="sm"
-              onClick={handleBack}
-              className="text-muted-foreground hover:text-foreground px-2"
-            >
-              ← Back
+        <div className="flex flex-col mb-6">
+          <div className="flex items-center gap-3 mb-2">
+            <Button variant="ghost" onClick={handleBack}>
+              <ArrowLeft size={18} />
+              <FileIcon className="text-muted-foreground" size={18} />
+              <h1 className="text-lg font-semibold">
+                {filename.replace(/\.[^/.]+$/, "")}
+              </h1>
             </Button>
-            <div className="flex flex-col">
-              <h2 className="text-lg font-semibold">Document Chunks</h2>
-              <p className="text-sm text-muted-foreground truncate max-w-md">
-                {decodeURIComponent(filename)}
-              </p>
-            </div>
           </div>
-          <div className="text-sm text-muted-foreground">
-            {!isFetching && chunks.length > 0 && (
-              <span>
-                {chunks.length} chunk{chunks.length !== 1 ? "s" : ""} found
-              </span>
-            )}
+          <div className="flex items-center gap-3 pl-4 mt-2">
+            <div className="flex items-center gap-2">
+              <Checkbox
+                id="selectAllChunks"
+                checked={selectAll}
+                onCheckedChange={(handleSelectAll) =>
+                  setSelectAll(!!handleSelectAll)
+                }
+              />
+              <Label
+                htmlFor="selectAllChunks"
+                className="font-medium text-muted-foreground whitespace-nowrap cursor-pointer"
+              >
+                Select all
+              </Label>
+            </div>
+            <div className="flex-1 flex items-center gap-2">
+              <Input
+                name="search-query"
+                id="search-query"
+                type="text"
+                defaultValue={parsedFilterData?.query}
+                value={queryInputText}
+                onChange={(e) => setQueryInputText(e.target.value)}
+                placeholder="Search chunks..."
+                className="flex-1 bg-muted/20 rounded-lg border border-border/50 px-4 py-3 focus-visible:ring-1 focus-visible:ring-ring"
+              />
+              <Button variant="outline" size="sm">
+                <Search />
+              </Button>
+            </div>
           </div>
         </div>
 
@@ -147,41 +214,130 @@ function ChunksPageContent() {
             </div>
           ) : (
             <div className="space-y-4 pb-6">
-              {chunks.map((chunk, index) => (
+              {chunksFilteredByQuery.map((chunk, index) => (
                 <div
                   key={chunk.filename + index}
-                  className="bg-muted/20 rounded-lg p-4 border border-border/50"
+                  className="bg-muted rounded-lg p-4 border border-border/50"
                 >
                   <div className="flex items-center justify-between mb-2">
-                    <div className="flex items-center gap-2">
-                      <FileText className="h-4 w-4 text-blue-400" />
-                      <span className="font-medium truncate">
-                        {chunk.filename}
+                    <div className="flex items-center gap-3">
+                      <div>
+                        <Checkbox
+                          checked={selectedChunks.has(index)}
+                          onCheckedChange={() =>
+                            handleChunkCardCheckboxChange(index)
+                          }
+                        />
+                      </div>
+                      <span className="text-sm font-bold">
+                        Chunk {chunk.page}
                       </span>
-                      {chunk.connector_type && (
-                        <div className="ml-2">
-                          {getSourceIcon(chunk.connector_type)}
-                        </div>
-                      )}
+                      <span className="bg-background p-1 rounded text-xs text-muted-foreground/70">
+                        {chunk.text.length} chars
+                      </span>
+                      <div className="py-1">
+                        <Button
+                          className="p-1"
+                          onClick={() => handleCopy(chunk.text)}
+                          variant="ghost"
+                          size="xs"
+                        >
+                          <Copy className="text-muted-foreground" />
+                        </Button>
+                      </div>
                     </div>
-                    <span className="text-xs text-green-400 bg-green-400/20 px-2 py-1 rounded">
-                      {chunk.score.toFixed(2)}
-                    </span>
+
+                    {/* TODO: Update to use active toggle */}
+                    {/* <span className="px-2 py-1 text-green-500">
+                      <Switch
+                        className="ml-2 bg-green-500"
+                        checked={true}
+                      />
+                      Active
+                    </span> */}
                   </div>
-                  <div className="flex items-center gap-4 text-sm text-muted-foreground mb-3">
-                    <span>{chunk.mimetype}</span>
-                    <span>Page {chunk.page}</span>
-                    {chunk.owner_name && <span>Owner: {chunk.owner_name}</span>}
-                  </div>
-                  <p className="text-sm text-foreground/90 leading-relaxed">
+                  <blockquote className="text-sm text-muted-foreground leading-relaxed border-l-2 border-input ml-1.5 pl-4">
                     {chunk.text}
-                  </p>
+                  </blockquote>
                 </div>
               ))}
             </div>
           )}
         </div>
       </div>
+      {/* Right panel - Summary (TODO), Technical details,  */}
+      <div className="w-[320px] py-20 px-2">
+        <div className="mb-8">
+          <h2 className="text-xl font-semibold mt-3 mb-4">Technical details</h2>
+          <dl>
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Total chunks</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+                {chunks.length}
+              </dd>
+            </div>
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Avg length</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+                {averageChunkLength.toFixed(0)} chars
+              </dd>
+            </div>
+            {/* TODO: Uncomment after data is available */}
+            {/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Process time</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+              </dd>
+            </div>
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Model</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+              </dd>
+            </div> */}
+          </dl>
+        </div>
+        <div className="mb-8">
+          <h2 className="text-xl font-semibold mt-2 mb-3">Original document</h2>
+          <dl>
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Name</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+                {fileData?.filename}
+              </dd>
+            </div>
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Type</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+                {fileData ? getFileTypeLabel(fileData.mimetype) : "Unknown"}
+              </dd>
+            </div>
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Size</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+                {fileData?.size
+                  ? `${Math.round(fileData.size / 1024)} KB`
+                  : "Unknown"}
+              </dd>
+            </div>
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Uploaded</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+                N/A
+              </dd>
+            </div>
+            {/* TODO: Uncomment after data is available */}
+            {/* <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Source</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0"></dd>
+            </div> */}
+            <div className="sm:grid sm:grid-cols-3 sm:gap-4 sm:px-0 mb-2.5">
+              <dt className="text-sm/6 text-muted-foreground">Updated</dt>
+              <dd className="mt-1 text-sm/6 text-gray-100 sm:col-span-2 sm:mt-0">
+                N/A
+              </dd>
+            </div>
+          </dl>
+        </div>
+      </div>
     </div>
   );
 }

frontend/src/app/settings/page.tsx

@@ -152,6 +152,7 @@ function KnowledgeSourcesPage() {
     },
   });
 
+
   // Debounced update function
   const debouncedUpdate = useDebounce(
     (variables: Parameters<typeof updateFlowSettingMutation.mutate>[0]) => {
@@ -219,6 +220,7 @@ function KnowledgeSourcesPage() {
   // Update processing mode
   const handleProcessingModeChange = (mode: string) => {
     setProcessingMode(mode);
+    // Update the configuration setting (backend will also update the flow automatically)
     debouncedUpdate({ doclingPresets: mode });
   };
 

src/agent.py

@@ -106,7 +106,6 @@ async def async_response_stream(
     model: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
-    tweaks: dict = None,
     log_prefix: str = "response",
 ):
     logger.info("User prompt received", prompt=prompt)
@@ -121,8 +120,6 @@ async def async_response_stream(
         }
         if previous_response_id is not None:
             request_params["previous_response_id"] = previous_response_id
-        if tweaks:
-            request_params["tweaks"] = tweaks
 
         if "x-api-key" not in client.default_headers:
             if hasattr(client, "api_key") and extra_headers is not None:
@@ -199,7 +196,6 @@ async def async_response(
     model: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
-    tweaks: dict = None,
     log_prefix: str = "response",
 ):
     try:
@@ -214,8 +210,6 @@ async def async_response(
         }
         if previous_response_id is not None:
             request_params["previous_response_id"] = previous_response_id
-        if tweaks:
-            request_params["tweaks"] = tweaks
         if extra_headers:
             request_params["extra_headers"] = extra_headers
 
@@ -249,7 +243,6 @@ async def async_stream(
     model: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
-    tweaks: dict = None,
     log_prefix: str = "response",
 ):
     async for chunk in async_response_stream(
@@ -258,7 +251,6 @@ async def async_stream(
         model,
         extra_headers=extra_headers,
         previous_response_id=previous_response_id,
-        tweaks=tweaks,
         log_prefix=log_prefix,
     ):
         yield chunk
@@ -271,7 +263,6 @@ async def async_langflow(
     prompt: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
-    tweaks: dict = None,
 ):
     response_text, response_id, response_obj = await async_response(
         langflow_client,
@@ -279,7 +270,6 @@ async def async_langflow(
         flow_id,
         extra_headers=extra_headers,
         previous_response_id=previous_response_id,
-        tweaks=tweaks,
         log_prefix="langflow",
     )
     return response_text, response_id
@@ -292,7 +282,6 @@ async def async_langflow_stream(
     prompt: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
-    tweaks: dict = None,
 ):
     logger.debug("Starting langflow stream", prompt=prompt)
     try:
@@ -302,8 +291,7 @@ async def async_langflow_stream(
             flow_id,
             extra_headers=extra_headers,
             previous_response_id=previous_response_id,
-            tweaks=tweaks,
-            log_prefix="langflow",
+                log_prefix="langflow",
         ):
             logger.debug(
                 "Yielding chunk from langflow stream",
@@ -463,7 +451,6 @@ async def async_langflow_chat(
     user_id: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
-    tweaks: dict = None,
     store_conversation: bool = True,
 ):
     logger.debug(
@@ -497,7 +484,6 @@ async def async_langflow_chat(
         flow_id,
         extra_headers=extra_headers,
         previous_response_id=previous_response_id,
-        tweaks=tweaks,
         log_prefix="langflow",
     )
     logger.debug(
@@ -576,7 +562,6 @@ async def async_langflow_chat_stream(
     user_id: str,
     extra_headers: dict = None,
     previous_response_id: str = None,
-    tweaks: dict = None,
 ):
     logger.debug(
         "async_langflow_chat_stream called",
@@ -603,7 +588,6 @@ async def async_langflow_chat_stream(
         flow_id,
         extra_headers=extra_headers,
         previous_response_id=previous_response_id,
-        tweaks=tweaks,
         log_prefix="langflow",
     ):
         # Extract text content to build full response for history

src/api/settings.py

@@ -7,6 +7,7 @@ from config.settings import (
     LANGFLOW_CHAT_FLOW_ID,
     LANGFLOW_INGEST_FLOW_ID,
     LANGFLOW_PUBLIC_URL,
+    DOCLING_COMPONENT_ID,
     clients,
     get_openrag_config,
     config_manager,
@@ -46,22 +47,7 @@ def get_docling_preset_configs():
     }
 
 
-def get_docling_tweaks(docling_preset: str = None) -> dict:
-    """Get Langflow tweaks for docling component based on preset"""
-    if not docling_preset:
-        # Get current preset from config
-        openrag_config = get_openrag_config()
-        docling_preset = openrag_config.knowledge.doclingPresets
 
-    preset_configs = get_docling_preset_configs()
-
-    if docling_preset not in preset_configs:
-        docling_preset = "standard"  # fallback
-
-    preset_config = preset_configs[docling_preset]
-    docling_serve_opts = json.dumps(preset_config)
-
-    return {"DoclingRemote-ayRdw": {"docling_serve_opts": docling_serve_opts}}
 
 
 async def get_settings(request, session_manager):
@@ -234,6 +220,15 @@ async def update_settings(request, session_manager):
             current_config.knowledge.doclingPresets = body["doclingPresets"]
             config_updated = True
 
+            # Also update the flow with the new docling preset
+            try:
+                await _update_flow_docling_preset(body["doclingPresets"], preset_configs[body["doclingPresets"]])
+                logger.info(f"Successfully updated docling preset in flow to '{body['doclingPresets']}'")
+            except Exception as e:
+                logger.error(f"Failed to update docling preset in flow: {str(e)}")
+                # Don't fail the entire settings update if flow update fails
+                # The config will still be saved
+
         if "chunk_size" in body:
             if not isinstance(body["chunk_size"], int) or body["chunk_size"] <= 0:
                 return JSONResponse(
@@ -527,3 +522,93 @@ async def onboarding(request, flows_service):
             {"error": f"Failed to update onboarding settings: {str(e)}"},
             status_code=500,
         )
+
+
+async def _update_flow_docling_preset(preset: str, preset_config: dict):
+    """Helper function to update docling preset in the ingest flow"""
+    if not LANGFLOW_INGEST_FLOW_ID:
+        raise ValueError("LANGFLOW_INGEST_FLOW_ID is not configured")
+
+    # Get the current flow data from Langflow
+    response = await clients.langflow_request(
+        "GET", f"/api/v1/flows/{LANGFLOW_INGEST_FLOW_ID}"
+    )
+
+    if response.status_code != 200:
+        raise Exception(f"Failed to get ingest flow: HTTP {response.status_code} - {response.text}")
+
+    flow_data = response.json()
+
+    # Find the target node in the flow using environment variable
+    nodes = flow_data.get("data", {}).get("nodes", [])
+    target_node = None
+    target_node_index = None
+
+    for i, node in enumerate(nodes):
+        if node.get("id") == DOCLING_COMPONENT_ID:
+            target_node = node
+            target_node_index = i
+            break
+
+    if target_node is None:
+        raise Exception(f"Docling component '{DOCLING_COMPONENT_ID}' not found in ingest flow")
+
+    # Update the docling_serve_opts value directly in the existing node
+    if (target_node.get("data", {}).get("node", {}).get("template", {}).get("docling_serve_opts")):
+        flow_data["data"]["nodes"][target_node_index]["data"]["node"]["template"]["docling_serve_opts"]["value"] = preset_config
+    else:
+        raise Exception(f"docling_serve_opts field not found in node '{DOCLING_COMPONENT_ID}'")
+
+    # Update the flow via PATCH request
+    patch_response = await clients.langflow_request(
+        "PATCH", f"/api/v1/flows/{LANGFLOW_INGEST_FLOW_ID}", json=flow_data
+    )
+
+    if patch_response.status_code != 200:
+        raise Exception(f"Failed to update ingest flow: HTTP {patch_response.status_code} - {patch_response.text}")
+
+
+async def update_docling_preset(request, session_manager):
+    """Update docling preset in the ingest flow"""
+    try:
+        # Parse request body
+        body = await request.json()
+
+        # Validate preset parameter
+        if "preset" not in body:
+            return JSONResponse(
+                {"error": "preset parameter is required"},
+                status_code=400
+            )
+
+        preset = body["preset"]
+        preset_configs = get_docling_preset_configs()
+
+        if preset not in preset_configs:
+            valid_presets = list(preset_configs.keys())
+            return JSONResponse(
+                {"error": f"Invalid preset '{preset}'. Valid presets: {', '.join(valid_presets)}"},
+                status_code=400
+            )
+
+        # Get the preset configuration
+        preset_config = preset_configs[preset]
+
+        # Use the helper function to update the flow
+        await _update_flow_docling_preset(preset, preset_config)
+
+        logger.info(f"Successfully updated docling preset to '{preset}' in ingest flow")
+
+        return JSONResponse({
+            "message": f"Successfully updated docling preset to '{preset}'",
+            "preset": preset,
+            "preset_config": preset_config
+        })
+
+    except Exception as e:
+        logger.error("Failed to update docling preset", error=str(e))
+        return JSONResponse(
+            {"error": f"Failed to update docling preset: {str(e)}"},
+            status_code=500
+        )
+

src/config/settings.py

@@ -544,6 +544,9 @@ OLLAMA_LLM_TEXT_COMPONENT_ID = os.getenv(
     "OLLAMA_LLM_TEXT_COMPONENT_ID", "OllamaModel-XDGqZ"
 )
 
+# Docling component ID for ingest flow
+DOCLING_COMPONENT_ID = os.getenv("DOCLING_COMPONENT_ID", "DoclingRemote-78KoX")
+
 # Global clients instance
 clients = AppClients()
 

src/main.py

@@ -971,12 +971,23 @@ async def create_app():
             "/onboarding",
             require_auth(services["session_manager"])(
                 partial(
-                    settings.onboarding, 
+                    settings.onboarding,
                     flows_service=services["flows_service"]
                 )
             ),
             methods=["POST"],
         ),
+        # Docling preset update endpoint
+        Route(
+            "/settings/docling-preset",
+            require_auth(services["session_manager"])(
+                partial(
+                    settings.update_docling_preset,
+                    session_manager=services["session_manager"]
+                )
+            ),
+            methods=["PATCH"],
+        ),
         Route(
             "/nudges",
             require_auth(services["session_manager"])(

src/services/chat_service.py

@@ -2,7 +2,6 @@ import json
 from config.settings import NUDGES_FLOW_ID, clients, LANGFLOW_URL, LANGFLOW_CHAT_FLOW_ID
 from agent import async_chat, async_langflow, async_chat_stream
 from auth_context import set_auth_context
-from api.settings import get_docling_tweaks
 from utils.logging_config import get_logger
 
 logger = get_logger(__name__)
@@ -127,8 +126,6 @@ class ChatService:
                 "Langflow client not initialized. Ensure LANGFLOW is reachable or set LANGFLOW_KEY."
             )
 
-        # Get docling tweaks based on current configuration
-        docling_tweaks = get_docling_tweaks()
 
         if stream:
             from agent import async_langflow_chat_stream
@@ -140,7 +137,6 @@ class ChatService:
                 user_id,
                 extra_headers=extra_headers,
                 previous_response_id=previous_response_id,
-                tweaks=docling_tweaks,
             )
         else:
             from agent import async_langflow_chat
@@ -152,7 +148,6 @@ class ChatService:
                 user_id,
                 extra_headers=extra_headers,
                 previous_response_id=previous_response_id,
-                tweaks=docling_tweaks,
             )
             response_data = {"response": response_text}
             if response_id:
@@ -202,8 +197,6 @@ class ChatService:
 
         from agent import async_langflow_chat
 
-        # Get docling tweaks (might not be used by nudges flow, but keeping consistent)
-        docling_tweaks = get_docling_tweaks()
 
         response_text, response_id = await async_langflow_chat(
             langflow_client,
@@ -211,7 +204,6 @@ class ChatService:
             prompt,
             user_id,
             extra_headers=extra_headers,
-            tweaks=docling_tweaks,
             store_conversation=False,
         )
         response_data = {"response": response_text}
@@ -242,8 +234,6 @@ class ChatService:
                 raise ValueError(
                     "Langflow client not initialized. Ensure LANGFLOW is reachable or set LANGFLOW_KEY."
                 )
-            # Get docling tweaks based on current configuration
-            docling_tweaks = get_docling_tweaks()
 
             response_text, response_id = await async_langflow(
                 langflow_client=langflow_client,
@@ -251,7 +241,6 @@ class ChatService:
                 prompt=document_prompt,
                 extra_headers=extra_headers,
                 previous_response_id=previous_response_id,
-                tweaks=docling_tweaks,
             )
         else:  # chat
             # Set auth context for chat tools and provide user_id