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

Merge branch 'main' into pre-release-fixes

Browse source
This commit is contained in:
Sebastián Estévez 2025-10-06 14:47:56 -04:00 • committed by GitHub
commit baa779f690
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
22 changed files with 1882 additions and 1299 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

66
frontend/components/duplicate-handling-dialog.tsx Normal file
View file

@ -0,0 +1,66 @@
"use client";
import { RotateCcw } from "lucide-react";
import type React from "react";
import { Button } from "./ui/button";
import {
Dialog,
DialogContent,
DialogDescription,
DialogFooter,
DialogHeader,
DialogTitle,
} from "./ui/dialog";
interface DuplicateHandlingDialogProps {
open: boolean;
onOpenChange: (open: boolean) => void;
onOverwrite: () => void | Promise<void>;
isLoading?: boolean;
}
export const DuplicateHandlingDialog: React.FC<
DuplicateHandlingDialogProps
> = ({ open, onOpenChange, onOverwrite, isLoading = false }) => {
const handleOverwrite = async () => {
await onOverwrite();
onOpenChange(false);
};
return (
<Dialog open={open} onOpenChange={onOpenChange}>
<DialogContent className="sm:max-w-[450px]">
<DialogHeader>
<DialogTitle>Overwrite document</DialogTitle>
<DialogDescription className="pt-2 text-muted-foreground">
Overwriting will replace the existing document with another version.
This can't be undone.
</DialogDescription>
</DialogHeader>
<DialogFooter className="flex-row gap-2 justify-end">
<Button
type="button"
variant="ghost"
onClick={() => onOpenChange(false)}
disabled={isLoading}
size="sm"
>
Cancel
</Button>
<Button
type="button"
variant="default"
size="sm"
onClick={handleOverwrite}
disabled={isLoading}
className="flex items-center gap-2 !bg-accent-amber-foreground hover:!bg-foreground text-primary-foreground"
>
<RotateCcw className="h-3.5 w-3.5" />
Overwrite
</Button>
</DialogFooter>
</DialogContent>
</Dialog>
);
};

1189
frontend/components/knowledge-dropdown.tsx
View file

File diff suppressed because it is too large Load diff

2
frontend/components/logo/ibm-logo.tsx
View file

@ -9,7 +9,7 @@ export default function IBMLogo(props: React.SVGProps<SVGSVGElement>) {
{...props}
>
<title>IBM watsonx.ai Logo</title>
<g clip-path="url(#clip0_2620_2081)">
<g clipPath="url(#clip0_2620_2081)">
<path
d="M13 12.0007C12.4477 12.0007 12 12.4484 12 13.0007C12 13.0389 12.0071 13.0751 12.0112 13.1122C10.8708 14.0103 9.47165 14.5007 8 14.5007C5.86915 14.5007 4 12.5146 4 10.2507C4 7.90722 5.9065 6.00072 8.25 6.00072H8.5V5.00072H8.25C5.3552 5.00072 3 7.35592 3 10.2507C3 11.1927 3.2652 12.0955 3.71855 12.879C2.3619 11.6868 1.5 9.94447 1.5 8.00072C1.5 6.94312 1.74585 5.93432 2.23095 5.00292L1.34375 4.54102C0.79175 5.60157 0.5 6.79787 0.5 8.00072C0.5 12.1362 3.8645 15.5007 8 15.5007C9.6872 15.5007 11.2909 14.9411 12.6024 13.9176C12.7244 13.9706 12.8586 14.0007 13 14.0007C13.5523 14.0007 14 13.553 14 13.0007C14 12.4484 13.5523 12.0007 13 12.0007Z"
fill="currentColor"

2
frontend/components/ui/input.tsx
View file

@ -44,7 +44,7 @@ const Input = React.forwardRef<HTMLInputElement, InputProps>(
placeholder={placeholder}
className={cn(
"primary-input",
icon && "pl-9",
icon && "!pl-9",
type === "password" && "!pr-8",
icon ? inputClassName : className
)}

47
frontend/src/app/api/mutations/useCancelTaskMutation.ts Normal file
View file

@ -0,0 +1,47 @@
import {
type UseMutationOptions,
useMutation,
useQueryClient,
} from "@tanstack/react-query";
export interface CancelTaskRequest {
taskId: string;
}
export interface CancelTaskResponse {
status: string;
task_id: string;
}
export const useCancelTaskMutation = (
options?: Omit<
UseMutationOptions<CancelTaskResponse, Error, CancelTaskRequest>,
"mutationFn"
>
) => {
const queryClient = useQueryClient();
async function cancelTask(
variables: CancelTaskRequest,
): Promise<CancelTaskResponse> {
const response = await fetch(`/api/tasks/${variables.taskId}/cancel`, {
method: "POST",
});
if (!response.ok) {
const errorData = await response.json().catch(() => ({}));
throw new Error(errorData.error || "Failed to cancel task");
}
return response.json();
}
return useMutation({
mutationFn: cancelTask,
onSuccess: () => {
// Invalidate tasks query to refresh the list
queryClient.invalidateQueries({ queryKey: ["tasks"] });
},
...options,
});
};

5
frontend/src/app/api/queries/useGetSearchQuery.ts
View file

@ -29,6 +29,7 @@ export interface ChunkResult {
owner_email?: string;
file_size?: number;
connector_type?: string;
index?: number;
}
export interface File {
@ -55,7 +56,7 @@ export interface File {
export const useGetSearchQuery = (
query: string,
queryData?: ParsedQueryData | null,
options?: Omit<UseQueryOptions, "queryKey" | "queryFn">,
options?: Omit<UseQueryOptions, "queryKey" | "queryFn">
) => {
const queryClient = useQueryClient();
@ -184,7 +185,7 @@ export const useGetSearchQuery = (
queryFn: getFiles,
...options,
},
queryClient,
queryClient
);
return queryResult;

79
frontend/src/app/api/queries/useGetTasksQuery.ts Normal file
View file

@ -0,0 +1,79 @@
import {
type UseQueryOptions,
useQuery,
useQueryClient,
} from "@tanstack/react-query";
export interface Task {
task_id: string;
status:
| "pending"
| "running"
| "processing"
| "completed"
| "failed"
| "error";
total_files?: number;
processed_files?: number;
successful_files?: number;
failed_files?: number;
running_files?: number;
pending_files?: number;
created_at: string;
updated_at: string;
duration_seconds?: number;
result?: Record<string, unknown>;
error?: string;
files?: Record<string, Record<string, unknown>>;
}
export interface TasksResponse {
tasks: Task[];
}
export const useGetTasksQuery = (
options?: Omit<UseQueryOptions<Task[]>, "queryKey" | "queryFn">
) => {
const queryClient = useQueryClient();
async function getTasks(): Promise<Task[]> {
const response = await fetch("/api/tasks");
if (!response.ok) {
throw new Error("Failed to fetch tasks");
}
const data: TasksResponse = await response.json();
return data.tasks || [];
}
const queryResult = useQuery(
{
queryKey: ["tasks"],
queryFn: getTasks,
refetchInterval: (query) => {
// Only poll if there are tasks with pending or running status
const data = query.state.data;
if (!data || data.length === 0) {
return false; // Stop polling if no tasks
}
const hasActiveTasks = data.some(
(task: Task) =>
task.status === "pending" ||
task.status === "running" ||
task.status === "processing"
);
return hasActiveTasks ? 3000 : false; // Poll every 3 seconds if active tasks exist
},
refetchIntervalInBackground: true,
staleTime: 0, // Always consider data stale to ensure fresh updates
gcTime: 5 * 60 * 1000, // Keep in cache for 5 minutes
...options,
},
queryClient,
);
return queryResult;
};

604
frontend/src/app/knowledge/chunks/page.tsx
View file

@ -1,179 +1,204 @@
"use client";
import { ArrowLeft, Check, Copy, Loader2, Search } from "lucide-react";
import { Suspense, useCallback, useEffect, useMemo, useState } from "react";
import { ArrowLeft, Check, Copy, Loader2, Search, X } from "lucide-react";
import { useRouter, useSearchParams } from "next/navigation";
import { Suspense, useCallback, useEffect, useMemo, useState } from "react";
// import { Label } from "@/components/ui/label";
// import { Checkbox } from "@/components/ui/checkbox";
import { filterAccentClasses } from "@/components/knowledge-filter-panel";
import { ProtectedRoute } from "@/components/protected-route";
import { Button } from "@/components/ui/button";
import { Checkbox } from "@/components/ui/checkbox";
import { Input } from "@/components/ui/input";
import { Label } from "@/components/ui/label";
import { useKnowledgeFilter } from "@/contexts/knowledge-filter-context";
import { useLayout } from "@/contexts/layout-context";
import { useTask } from "@/contexts/task-context";
import {
type ChunkResult,
type File,
useGetSearchQuery,
type ChunkResult,
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";
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";
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();
const searchParams = useSearchParams();
const { isMenuOpen } = useTask();
const { totalTopOffset } = useLayout();
const { parsedFilterData, isPanelOpen } = useKnowledgeFilter();
const router = useRouter();
const searchParams = useSearchParams();
const { selectedFilter, setSelectedFilter, parsedFilterData, isPanelOpen } =
useKnowledgeFilter();
const { isMenuOpen } = useTask();
const { totalTopOffset } = useLayout();
const filename = searchParams.get("filename");
const [chunks, setChunks] = useState<ChunkResult[]>([]);
const [chunksFilteredByQuery, setChunksFilteredByQuery] = useState<
ChunkResult[]
>([]);
const [selectedChunks, setSelectedChunks] = useState<Set<number>>(new Set());
const [activeCopiedChunkIndex, setActiveCopiedChunkIndex] = useState<
number | null
>(null);
const filename = searchParams.get("filename");
const [chunks, setChunks] = useState<ChunkResult[]>([]);
const [chunksFilteredByQuery, setChunksFilteredByQuery] = useState<
ChunkResult[]
>([]);
const [selectedChunks, setSelectedChunks] = useState<Set<number>>(new Set());
const [activeCopiedChunkIndex, setActiveCopiedChunkIndex] = useState<
number | null
>(null);
// Calculate average chunk length
const averageChunkLength = useMemo(
() =>
chunks.reduce((acc, chunk) => acc + chunk.text.length, 0) /
chunks.length || 0,
[chunks]
);
// 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 ?? ""
);
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);
// 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]);
useEffect(() => {
if (queryInputText === "") {
setChunksFilteredByQuery(chunks);
} else {
setChunksFilteredByQuery(
chunks.filter((chunk) =>
chunk.text.toLowerCase().includes(queryInputText.toLowerCase()),
),
);
}
}, [queryInputText, chunks]);
const handleCopy = useCallback((text: string, index: number) => {
// Trim whitespace and remove new lines/tabs for cleaner copy
navigator.clipboard.writeText(text.trim().replace(/[\n\r\t]/gm, ""));
setActiveCopiedChunkIndex(index);
setTimeout(() => setActiveCopiedChunkIndex(null), 10 * 1000); // 10 seconds
}, []);
const handleCopy = useCallback((text: string, index: number) => {
// Trim whitespace and remove new lines/tabs for cleaner copy
navigator.clipboard.writeText(text.trim().replace(/[\n\r\t]/gm, ""));
setActiveCopiedChunkIndex(index);
setTimeout(() => setActiveCopiedChunkIndex(null), 10 * 1000); // 10 seconds
}, []);
const fileData = (data as File[]).find(
(file: File) => file.filename === filename
);
const fileData = (data as File[]).find(
(file: File) => file.filename === filename,
);
// Extract chunks for the specific file
useEffect(() => {
if (!filename || !(data as File[]).length) {
setChunks([]);
return;
}
// Extract chunks for the specific file
useEffect(() => {
if (!filename || !(data as File[]).length) {
setChunks([]);
return;
}
setChunks(fileData?.chunks || []);
}, [data, filename]);
setChunks(
fileData?.chunks?.map((chunk, i) => ({ ...chunk, index: i + 1 })) || [],
);
}, [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]);
// 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.push("/knowledge");
}, [router]);
const handleBack = useCallback(() => {
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]
);
// 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">
<div className="text-center">
<Search className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50" />
<p className="text-lg text-muted-foreground">No file specified</p>
<p className="text-sm text-muted-foreground/70 mt-2">
Please select a file from the knowledge page
</p>
</div>
</div>
);
}
if (!filename) {
return (
<div className="flex items-center justify-center h-64">
<div className="text-center">
<Search className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50" />
<p className="text-lg text-muted-foreground">No file specified</p>
<p className="text-sm text-muted-foreground/70 mt-2">
Please select a file from the knowledge page
</p>
</div>
</div>
);
}
return (
<div
className={`fixed inset-0 md:left-72 flex flex-row transition-all duration-300 ${
isMenuOpen && isPanelOpen
? "md:right-[704px]"
: // Both open: 384px (menu) + 320px (KF panel)
isMenuOpen
? "md:right-96"
: // Only menu open: 384px
isPanelOpen
? "md:right-80"
: // Only KF panel open: 320px
"md:right-6" // Neither open: 24px
}`}
style={{ top: `${totalTopOffset}px` }}
>
<div className="flex-1 flex flex-col min-h-0 px-6 py-6">
{/* Header */}
<div className="flex flex-col mb-6">
<div className="flex flex-row items-center gap-3 mb-6">
<Button variant="ghost" onClick={handleBack} size="sm">
<ArrowLeft size={24} />
</Button>
<h1 className="text-lg font-semibold">
{/* Removes file extension from filename */}
{filename.replace(/\.[^/.]+$/, "")}
</h1>
</div>
<div className="flex flex-col items-start mt-2">
<div className="flex-1 flex items-center gap-2 w-full max-w-[616px] mb-8">
<Input
name="search-query"
icon={!queryInputText.length ? <Search size={18} /> : null}
id="search-query"
type="text"
defaultValue={parsedFilterData?.query}
value={queryInputText}
onChange={(e) => setQueryInputText(e.target.value)}
placeholder="Search chunks..."
/>
</div>
<div className="flex items-center pl-4 gap-2">
return (
<div
className={`fixed inset-0 md:left-72 flex flex-row transition-all duration-300 ${
isMenuOpen && isPanelOpen
? "md:right-[704px]"
: // Both open: 384px (menu) + 320px (KF panel)
isMenuOpen
? "md:right-96"
: // Only menu open: 384px
isPanelOpen
? "md:right-80"
: // Only KF panel open: 320px
"md:right-6" // Neither open: 24px
}`}
style={{ top: `${totalTopOffset}px` }}
>
<div className="flex-1 flex flex-col min-h-0 px-6 py-6">
{/* Header */}
<div className="flex flex-col mb-6">
<div className="flex flex-row items-center gap-3 mb-6">
<Button variant="ghost" onClick={handleBack} size="sm">
<ArrowLeft size={24} />
</Button>
<h1 className="text-lg font-semibold">
{/* Removes file extension from filename */}
{filename.replace(/\.[^/.]+$/, "")}
</h1>
</div>
<div className="flex flex-col items-start mt-2">
<div className="flex-1 flex items-center gap-2 w-full max-w-[640px]">
<div className="primary-input min-h-10 !flex items-center flex-nowrap focus-within:border-foreground transition-colors !p-[0.3rem]">
{selectedFilter?.name && (
<div
className={`flex items-center gap-1 h-full px-1.5 py-0.5 mr-1 rounded max-w-[25%] ${
filterAccentClasses[parsedFilterData?.color || "zinc"]
}`}
>
<span className="truncate">{selectedFilter?.name}</span>
<X
aria-label="Remove filter"
className="h-4 w-4 flex-shrink-0 cursor-pointer"
onClick={() => setSelectedFilter(null)}
/>
</div>
)}
<Search
className="h-4 w-4 ml-1 flex-shrink-0 text-placeholder-foreground"
strokeWidth={1.5}
/>
<input
className="bg-transparent w-full h-full ml-2 focus:outline-none focus-visible:outline-none font-mono placeholder:font-mono"
name="search-query"
id="search-query"
type="text"
placeholder="Enter your search query..."
onChange={(e) => setQueryInputText(e.target.value)}
value={queryInputText}
/>
</div>
</div>
{/* <div className="flex items-center pl-4 gap-2">
<Checkbox
id="selectAllChunks"
checked={selectAll}
@ -187,106 +212,114 @@ function ChunksPageContent() {
>
Select all
</Label>
</div>
</div>
</div>
</div> */}
</div>
</div>
{/* Content Area - matches knowledge page structure */}
<div className="flex-1 overflow-scroll pr-6">
{isFetching ? (
<div className="flex items-center justify-center h-64">
<div className="text-center">
<Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
<p className="text-lg text-muted-foreground">
Loading chunks...
</p>
</div>
</div>
) : chunks.length === 0 ? (
<div className="flex items-center justify-center h-64">
<div className="text-center">
<Search className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50" />
<p className="text-lg text-muted-foreground">No chunks found</p>
<p className="text-sm text-muted-foreground/70 mt-2">
This file may not have been indexed yet
</p>
</div>
</div>
) : (
<div className="space-y-4 pb-6">
{chunksFilteredByQuery.map((chunk, index) => (
<div
key={chunk.filename + index}
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-3">
<div>
{/* Content Area - matches knowledge page structure */}
<div className="flex-1 overflow-scroll pr-6">
{isFetching ? (
<div className="flex items-center justify-center h-64">
<div className="text-center">
<Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
<p className="text-lg text-muted-foreground">
Loading chunks...
</p>
</div>
</div>
) : chunks.length === 0 ? (
<div className="flex items-center justify-center h-64">
<div className="text-center">
<p className="text-xl font-semibold mb-2">No knowledge</p>
<p className="text-sm text-secondary-foreground">
Clear the knowledge filter or return to the knowledge page
</p>
</div>
</div>
) : (
<div className="space-y-4 pb-6">
{chunksFilteredByQuery.map((chunk, index) => (
<div
key={chunk.filename + index}
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-3">
{/* <div>
<Checkbox
checked={selectedChunks.has(index)}
onCheckedChange={() =>
handleChunkCardCheckboxChange(index)
}
/>
</div>
<span className="text-sm font-bold">
Chunk {chunk.page}
</span>
<span className="bg-background p-1 rounded text-xs text-muted-foreground/70">
{chunk.text.length} chars
</span>
<div className="py-1">
<Button
onClick={() => handleCopy(chunk.text, index)}
variant="ghost"
size="sm"
>
{activeCopiedChunkIndex === index ? (
<Check className="text-muted-foreground" />
) : (
<Copy className="text-muted-foreground" />
)}
</Button>
</div>
</div>
</div> */}
<span className="text-sm font-bold">
Chunk {chunk.index}
</span>
<span className="bg-background p-1 rounded text-xs text-muted-foreground/70">
{chunk.text.length} chars
</span>
<div className="py-1">
<Button
onClick={() => handleCopy(chunk.text, index)}
variant="ghost"
size="sm"
>
{activeCopiedChunkIndex === index ? (
<Check className="text-muted-foreground" />
) : (
<Copy className="text-muted-foreground" />
)}
</Button>
</div>
</div>
{/* TODO: Update to use active toggle */}
{/* <span className="px-2 py-1 text-green-500">
<span className="bg-background p-1 rounded text-xs text-muted-foreground/70">
{chunk.score.toFixed(2)} score
</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>
<blockquote className="text-sm text-muted-foreground leading-relaxed border-l-2 border-input ml-1.5 pl-4">
{chunk.text}
</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">
</div>
<blockquote className="text-sm text-muted-foreground leading-relaxed ml-1.5">
{chunk.text}
</blockquote>
</div>
))}
</div>
)}
</div>
</div>
{/* Right panel - Summary (TODO), Technical details, */}
{chunks.length > 0 && (
<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>
@ -296,76 +329,79 @@ function ChunksPageContent() {
<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">
</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">
</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">
</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">
{/* <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>
);
</div> */}
</dl>
</div>
</div>
)}
</div>
);
}
function ChunksPage() {
return (
<Suspense
fallback={
<div className="flex items-center justify-center h-64">
<div className="text-center">
<Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
<p className="text-lg text-muted-foreground">Loading...</p>
</div>
</div>
}
>
<ChunksPageContent />
</Suspense>
);
return (
<Suspense
fallback={
<div className="flex items-center justify-center h-64">
<div className="text-center">
<Loader2 className="h-12 w-12 mx-auto mb-4 text-muted-foreground/50 animate-spin" />
<p className="text-lg text-muted-foreground">Loading...</p>
</div>
</div>
}
>
<ChunksPageContent />
</Suspense>
);
}
export default function ProtectedChunksPage() {
return (
<ProtectedRoute>
<ChunksPage />
</ProtectedRoute>
);
return (
<ProtectedRoute>
<ChunksPage />
</ProtectedRoute>
);
}

148
frontend/src/app/knowledge/page.tsx
View file

@ -1,10 +1,24 @@
"use client";
import type { ColDef } from "ag-grid-community";
import type { ColDef, GetRowIdParams } from "ag-grid-community";
import { AgGridReact, type CustomCellRendererProps } from "ag-grid-react";
import { Building2, Cloud, HardDrive, Search, Trash2, X } from "lucide-react";
import {
Building2,
Cloud,
Globe,
HardDrive,
Search,
Trash2,
X,
} from "lucide-react";
import { useRouter } from "next/navigation";
import { type ChangeEvent, useCallback, useRef, useState } from "react";
import {
type ChangeEvent,
useCallback,
useEffect,
useRef,
useState,
} from "react";
import { SiGoogledrive } from "react-icons/si";
import { TbBrandOnedrive } from "react-icons/tb";
import { KnowledgeDropdown } from "@/components/knowledge-dropdown";
@ -18,14 +32,16 @@ import "@/components/AgGrid/registerAgGridModules";
import "@/components/AgGrid/agGridStyles.css";
import { toast } from "sonner";
import { KnowledgeActionsDropdown } from "@/components/knowledge-actions-dropdown";
import { filterAccentClasses } from "@/components/knowledge-filter-panel";
import { StatusBadge } from "@/components/ui/status-badge";
import { DeleteConfirmationDialog } from "../../../components/confirmation-dialog";
import { useDeleteDocument } from "../api/mutations/useDeleteDocument";
import { filterAccentClasses } from "@/components/knowledge-filter-panel";
// Function to get the appropriate icon for a connector type
function getSourceIcon(connectorType?: string) {
switch (connectorType) {
case "url":
return <Globe className="h-4 w-4 text-muted-foreground flex-shrink-0" />;
case "google_drive":
return (
<SiGoogledrive className="h-4 w-4 text-foreground flex-shrink-0" />
@ -47,7 +63,7 @@ function getSourceIcon(connectorType?: string) {
function SearchPage() {
const router = useRouter();
const { isMenuOpen, files: taskFiles } = useTask();
const { isMenuOpen, files: taskFiles, refreshTasks } = useTask();
const { totalTopOffset } = useLayout();
const { selectedFilter, setSelectedFilter, parsedFilterData, isPanelOpen } =
useKnowledgeFilter();
@ -56,15 +72,14 @@ function SearchPage() {
const deleteDocumentMutation = useDeleteDocument();
const { data = [], isFetching } = useGetSearchQuery(
useEffect(() => {
refreshTasks();
}, [refreshTasks]);
const { data: searchData = [], isFetching } = useGetSearchQuery(
parsedFilterData?.query || "*",
parsedFilterData
parsedFilterData,
);
const handleTableSearch = (e: ChangeEvent<HTMLInputElement>) => {
gridRef.current?.api.setGridOption("quickFilterText", e.target.value);
};
// Convert TaskFiles to File format and merge with backend results
const taskFilesAsFiles: File[] = taskFiles.map((taskFile) => {
return {
@ -77,13 +92,32 @@ function SearchPage() {
};
});
const backendFiles = data as File[];
// Create a map of task files by filename for quick lookup
const taskFileMap = new Map(
taskFilesAsFiles.map((file) => [file.filename, file]),
);
// Override backend files with task file status if they exist
const backendFiles = (searchData as File[])
.map((file) => {
const taskFile = taskFileMap.get(file.filename);
if (taskFile) {
// Override backend file with task file data (includes status)
return { ...file, ...taskFile };
}
return file;
})
.filter((file) => {
// Only filter out files that are currently processing AND in taskFiles
const taskFile = taskFileMap.get(file.filename);
return !taskFile || taskFile.status !== "processing";
});
const filteredTaskFiles = taskFilesAsFiles.filter((taskFile) => {
return (
taskFile.status !== "active" &&
!backendFiles.some(
(backendFile) => backendFile.filename === taskFile.filename
(backendFile) => backendFile.filename === taskFile.filename,
)
);
});
@ -91,41 +125,60 @@ function SearchPage() {
// Combine task files first, then backend files
const fileResults = [...backendFiles, ...filteredTaskFiles];
const handleTableSearch = (e: ChangeEvent<HTMLInputElement>) => {
gridRef.current?.api.setGridOption("quickFilterText", e.target.value);
};
const gridRef = useRef<AgGridReact>(null);
const [columnDefs] = useState<ColDef<File>[]>([
const columnDefs = [
{
field: "filename",
headerName: "Source",
checkboxSelection: true,
checkboxSelection: (params: CustomCellRendererProps<File>) =>
(params?.data?.status || "active") === "active",
headerCheckboxSelection: true,
initialFlex: 2,
minWidth: 220,
cellRenderer: ({ data, value }: CustomCellRendererProps<File>) => {
// Read status directly from data on each render
const status = data?.status || "active";
const isActive = status === "active";
console.log(data?.filename, status, "a");
return (
<button
type="button"
className="flex items-center gap-2 cursor-pointer hover:text-blue-600 transition-colors text-left w-full"
onClick={() => {
router.push(
`/knowledge/chunks?filename=${encodeURIComponent(
data?.filename ?? ""
)}`
);
}}
>
{getSourceIcon(data?.connector_type)}
<span className="font-medium text-foreground truncate">
{value}
</span>
</button>
<div className="flex items-center overflow-hidden w-full">
<div
className={`transition-opacity duration-200 ${
isActive ? "w-0" : "w-7"
}`}
></div>
<button
type="button"
className="flex items-center gap-2 cursor-pointer hover:text-blue-600 transition-colors text-left flex-1 overflow-hidden"
onClick={() => {
if (!isActive) {
return;
}
router.push(
`/knowledge/chunks?filename=${encodeURIComponent(
data?.filename ?? "",
)}`,
);
}}
>
{getSourceIcon(data?.connector_type)}
<span className="font-medium text-foreground truncate">
{value}
</span>
</button>
</div>
);
},
},
{
field: "size",
headerName: "Size",
valueFormatter: (params) =>
valueFormatter: (params: CustomCellRendererProps<File>) =>
params.value ? `${Math.round(params.value / 1024)} KB` : "-",
},
{
@ -135,13 +188,14 @@ function SearchPage() {
{
field: "owner",
headerName: "Owner",
valueFormatter: (params) =>
valueFormatter: (params: CustomCellRendererProps<File>) =>
params.data?.owner_name || params.data?.owner_email || "—",
},
{
field: "chunkCount",
headerName: "Chunks",
valueFormatter: (params) => params.data?.chunkCount?.toString() || "-",
valueFormatter: (params: CustomCellRendererProps<File>) =>
params.data?.chunkCount?.toString() || "-",
},
{
field: "avgScore",
@ -159,6 +213,7 @@ function SearchPage() {
field: "status",
headerName: "Status",
cellRenderer: ({ data }: CustomCellRendererProps<File>) => {
console.log(data?.filename, data?.status, "b");
// Default to 'active' status if no status is provided
const status = data?.status || "active";
return <StatusBadge status={status} />;
@ -166,6 +221,10 @@ function SearchPage() {
},
{
cellRenderer: ({ data }: CustomCellRendererProps<File>) => {
const status = data?.status || "active";
if (status !== "active") {
return null;
}
return <KnowledgeActionsDropdown filename={data?.filename || ""} />;
},
cellStyle: {
@ -182,7 +241,7 @@ function SearchPage() {
sortable: false,
initialFlex: 0,
},
]);
];
const defaultColDef: ColDef<File> = {
resizable: false,
@ -204,7 +263,7 @@ function SearchPage() {
try {
// Delete each file individually since the API expects one filename at a time
const deletePromises = selectedRows.map((row) =>
deleteDocumentMutation.mutateAsync({ filename: row.filename })
deleteDocumentMutation.mutateAsync({ filename: row.filename }),
);
await Promise.all(deletePromises);
@ -212,7 +271,7 @@ function SearchPage() {
toast.success(
`Successfully deleted ${selectedRows.length} document${
selectedRows.length > 1 ? "s" : ""
}`
}`,
);
setSelectedRows([]);
setShowBulkDeleteDialog(false);
@ -225,7 +284,7 @@ function SearchPage() {
toast.error(
error instanceof Error
? error.message
: "Failed to delete some documents"
: "Failed to delete some documents",
);
}
};
@ -270,16 +329,13 @@ function SearchPage() {
/>
</div>
)}
<Search
className="h-4 w-4 ml-1 flex-shrink-0 text-placeholder-foreground"
strokeWidth={1.5}
/>
<Search className="h-4 w-4 ml-1 flex-shrink-0 text-placeholder-foreground" />
<input
className="bg-transparent w-full h-full ml-2 focus:outline-none focus-visible:outline-none font-mono placeholder:font-mono"
name="search-query"
id="search-query"
type="text"
placeholder="Search your documents..."
placeholder="Enter your search query..."
onChange={handleTableSearch}
/>
</div>
@ -317,7 +373,7 @@ function SearchPage() {
</div>
<AgGridReact
className="w-full overflow-auto"
columnDefs={columnDefs}
columnDefs={columnDefs as ColDef<File>[]}
defaultColDef={defaultColDef}
loading={isFetching}
ref={gridRef}
@ -325,7 +381,7 @@ function SearchPage() {
rowSelection="multiple"
rowMultiSelectWithClick={false}
suppressRowClickSelection={true}
getRowId={(params) => params.data.filename}
getRowId={(params: GetRowIdParams<File>) => params.data?.filename}
domLayout="normal"
onSelectionChanged={onSelectionChanged}
noRowsOverlayComponent={() => (

72
frontend/src/app/settings/page.tsx
View file

@ -633,30 +633,54 @@ function KnowledgeSourcesPage() {
</div>
{/* Conditional Sync Settings or No-Auth Message */}
{
isNoAuthMode ? (
<Card className="border-yellow-500/50 bg-yellow-500/5">
<CardHeader>
<CardTitle className="text-lg text-yellow-600">
Cloud connectors are only available with auth mode enabled
</CardTitle>
<CardDescription className="text-sm">
Please provide the following environment variables and
restart:
</CardDescription>
</CardHeader>
<CardContent>
<div className="bg-muted rounded-md p-4 font-mono text-sm">
<div className="text-muted-foreground mb-2">
# make here
https://console.cloud.google.com/apis/credentials
</div>
<div>GOOGLE_OAUTH_CLIENT_ID=</div>
<div>GOOGLE_OAUTH_CLIENT_SECRET=</div>
</div>
</CardContent>
</Card>
) : null
{
isNoAuthMode ? (
<Card className="border-yellow-500">
<CardHeader>
<CardTitle className="text-lg">
Cloud connectors require authentication
</CardTitle>
<CardDescription className="text-sm">
Add the Google OAuth variables below to your <code>.env</code>{" "}
then restart the OpenRAG containers.
</CardDescription>
</CardHeader>
<CardContent>
<div className="bg-muted rounded-md p-4 font-mono text-sm">
<div className="text-muted-foreground">
<div>
<span className="mr-3 text-placeholder-foreground">
27
</span>
<span># Google OAuth</span>
</div>
<div>
<span className="mr-3 text-placeholder-foreground">
28
</span>
<span># Create credentials here:</span>
</div>
<div>
<span className="mr-3 text-placeholder-foreground">
29
</span>
<span>
# https://console.cloud.google.com/apis/credentials
</span>
</div>
</div>
<div>
<span className="mr-3 text-placeholder-foreground">30</span>
<span>GOOGLE_OAUTH_CLIENT_ID=</span>
</div>
<div>
<span className="mr-3 text-placeholder-foreground">31</span>
<span>GOOGLE_OAUTH_CLIENT_SECRET=</span>
</div>
</div>
</CardContent>
</Card>
) : null
// <div className="flex items-center justify-between py-4">
// <div>
// <h3 className="text-lg font-medium">Sync Settings</h3>

11
frontend/src/components/task-notification-menu.tsx
View file

@ -1,6 +1,6 @@
"use client"
import { useState } from 'react'
import { useEffect, useState } from 'react'
import { Bell, CheckCircle, XCircle, Clock, Loader2, ChevronDown, ChevronUp, X } from 'lucide-react'
import { Button } from '@/components/ui/button'
import { Card, CardContent, CardDescription, CardHeader, CardTitle } from '@/components/ui/card'
@ -8,9 +8,16 @@ import { Badge } from '@/components/ui/badge'
import { useTask, Task } from '@/contexts/task-context'
export function TaskNotificationMenu() {
const { tasks, isFetching, isMenuOpen, cancelTask } = useTask()
const { tasks, isFetching, isMenuOpen, isRecentTasksExpanded, cancelTask } = useTask()
const [isExpanded, setIsExpanded] = useState(false)
// Sync local state with context state
useEffect(() => {
if (isRecentTasksExpanded) {
setIsExpanded(true)
}
}, [isRecentTasksExpanded])
// Don't render if menu is closed
if (!isMenuOpen) return null

52
frontend/src/components/ui/animated-processing-icon.tsx
View file

@ -1,26 +1,16 @@
interface AnimatedProcessingIconProps {
className?: string;
size?: number;
}
import type { SVGProps } from "react";
export const AnimatedProcessingIcon = ({
className = "",
size = 10,
}: AnimatedProcessingIconProps) => {
const width = Math.round((size * 6) / 10);
const height = size;
return (
<svg
width={width}
height={height}
viewBox="0 0 6 10"
fill="none"
xmlns="http://www.w3.org/2000/svg"
className={className}
>
<style>
{`
export const AnimatedProcessingIcon = (props: SVGProps<SVGSVGElement>) => {
return (
<svg
viewBox="0 0 8 12"
fill="none"
xmlns="http://www.w3.org/2000/svg"
{...props}
>
<title>Processing</title>
<style>
{`
.dot-1 { animation: pulse-wave 1.5s infinite; animation-delay: 0s; }
.dot-2 { animation: pulse-wave 1.5s infinite; animation-delay: 0.1s; }
.dot-3 { animation: pulse-wave 1.5s infinite; animation-delay: 0.2s; }
@ -30,20 +20,18 @@ export const AnimatedProcessingIcon = ({
@keyframes pulse-wave {
0%, 60%, 100% {
opacity: 0.25;
transform: scale(1);
}
30% {
opacity: 1;
transform: scale(1.2);
}
}
`}
</style>
<circle className="dot-1" cx="1" cy="5" r="1" fill="currentColor" />
<circle className="dot-2" cx="1" cy="9" r="1" fill="currentColor" />
<circle className="dot-3" cx="5" cy="1" r="1" fill="currentColor" />
<circle className="dot-4" cx="5" cy="5" r="1" fill="currentColor" />
<circle className="dot-5" cx="5" cy="9" r="1" fill="currentColor" />
</svg>
);
</style>
<circle className="dot-1" cx="2" cy="6" r="1" fill="currentColor" />
<circle className="dot-2" cx="2" cy="10" r="1" fill="currentColor" />
<circle className="dot-3" cx="6" cy="2" r="1" fill="currentColor" />
<circle className="dot-4" cx="6" cy="6" r="1" fill="currentColor" />
<circle className="dot-5" cx="6" cy="10" r="1" fill="currentColor" />
</svg>
);
};

2
frontend/src/components/ui/status-badge.tsx
View file

@ -50,7 +50,7 @@ export const StatusBadge = ({ status, className }: StatusBadgeProps) => {
}`}
>
{status === "processing" && (
<AnimatedProcessingIcon className="text-current mr-2" size={10} />
<AnimatedProcessingIcon className="text-current h-3 w-3 shrink-0" />
)}
{config.label}
</div>

467
frontend/src/contexts/task-context.tsx
View file

@ -7,33 +7,18 @@ import {
useCallback,
useContext,
useEffect,
useRef,
useState,
} from "react";
import { toast } from "sonner";
import { useCancelTaskMutation } from "@/app/api/mutations/useCancelTaskMutation";
import {
type Task,
useGetTasksQuery,
} from "@/app/api/queries/useGetTasksQuery";
import { useAuth } from "@/contexts/auth-context";
export interface Task {
task_id: string;
status:
| "pending"
| "running"
| "processing"
| "completed"
| "failed"
| "error";
total_files?: number;
processed_files?: number;
successful_files?: number;
failed_files?: number;
running_files?: number;
pending_files?: number;
created_at: string;
updated_at: string;
duration_seconds?: number;
result?: Record<string, unknown>;
error?: string;
files?: Record<string, Record<string, unknown>>;
}
// Task interface is now imported from useGetTasksQuery
export interface TaskFile {
filename: string;
@ -51,27 +36,54 @@ interface TaskContextType {
files: TaskFile[];
addTask: (taskId: string) => void;
addFiles: (files: Partial<TaskFile>[], taskId: string) => void;
removeTask: (taskId: string) => void;
refreshTasks: () => Promise<void>;
cancelTask: (taskId: string) => Promise<void>;
isPolling: boolean;
isFetching: boolean;
isMenuOpen: boolean;
toggleMenu: () => void;
isRecentTasksExpanded: boolean;
setRecentTasksExpanded: (expanded: boolean) => void;
// React Query states
isLoading: boolean;
error: Error | null;
}
const TaskContext = createContext<TaskContextType | undefined>(undefined);
export function TaskProvider({ children }: { children: React.ReactNode }) {
const [tasks, setTasks] = useState<Task[]>([]);
const [files, setFiles] = useState<TaskFile[]>([]);
const [isPolling, setIsPolling] = useState(false);
const [isFetching, setIsFetching] = useState(false);
const [isMenuOpen, setIsMenuOpen] = useState(false);
const [isRecentTasksExpanded, setIsRecentTasksExpanded] = useState(false);
const previousTasksRef = useRef<Task[]>([]);
const { isAuthenticated, isNoAuthMode } = useAuth();
const queryClient = useQueryClient();
// Use React Query hooks
const {
data: tasks = [],
isLoading,
error,
refetch: refetchTasks,
isFetching,
} = useGetTasksQuery({
enabled: isAuthenticated || isNoAuthMode,
});
const cancelTaskMutation = useCancelTaskMutation({
onSuccess: () => {
toast.success("Task cancelled", {
description: "Task has been cancelled successfully",
});
},
onError: (error) => {
toast.error("Failed to cancel task", {
description: error.message,
});
},
});
const refetchSearch = useCallback(() => {
queryClient.invalidateQueries({
queryKey: ["search"],
@ -99,265 +111,216 @@ export function TaskProvider({ children }: { children: React.ReactNode }) {
[],
);
const fetchTasks = useCallback(async () => {
if (!isAuthenticated && !isNoAuthMode) return;
setIsFetching(true);
try {
const response = await fetch("/api/tasks");
if (response.ok) {
const data = await response.json();
const newTasks = data.tasks || [];
// Update tasks and check for status changes in the same state update
setTasks((prevTasks) => {
// Check for newly completed tasks to show toasts
if (prevTasks.length > 0) {
newTasks.forEach((newTask: Task) => {
const oldTask = prevTasks.find(
(t) => t.task_id === newTask.task_id,
);
// Update or add files from task.files if available
if (newTask.files && typeof newTask.files === "object") {
const taskFileEntries = Object.entries(newTask.files);
const now = new Date().toISOString();
taskFileEntries.forEach(([filePath, fileInfo]) => {
if (typeof fileInfo === "object" && fileInfo) {
const fileName = filePath.split("/").pop() || filePath;
const fileStatus = fileInfo.status as string;
// Map backend file status to our TaskFile status
let mappedStatus: TaskFile["status"];
switch (fileStatus) {
case "pending":
case "running":
mappedStatus = "processing";
break;
case "completed":
mappedStatus = "active";
break;
case "failed":
mappedStatus = "failed";
break;
default:
mappedStatus = "processing";
}
setFiles((prevFiles) => {
const existingFileIndex = prevFiles.findIndex(
(f) =>
f.source_url === filePath &&
f.task_id === newTask.task_id,
);
// Detect connector type based on file path or other indicators
let connectorType = "local";
if (filePath.includes("/") && !filePath.startsWith("/")) {
// Likely S3 key format (bucket/path/file.ext)
connectorType = "s3";
}
const fileEntry: TaskFile = {
filename: fileName,
mimetype: "", // We don't have this info from the task
source_url: filePath,
size: 0, // We don't have this info from the task
connector_type: connectorType,
status: mappedStatus,
task_id: newTask.task_id,
created_at:
typeof fileInfo.created_at === "string"
? fileInfo.created_at
: now,
updated_at:
typeof fileInfo.updated_at === "string"
? fileInfo.updated_at
: now,
};
if (existingFileIndex >= 0) {
// Update existing file
const updatedFiles = [...prevFiles];
updatedFiles[existingFileIndex] = fileEntry;
return updatedFiles;
} else {
// Add new file
return [...prevFiles, fileEntry];
}
});
}
});
}
if (
oldTask &&
oldTask.status !== "completed" &&
newTask.status === "completed"
) {
// Task just completed - show success toast
toast.success("Task completed successfully", {
description: `Task ${newTask.task_id} has finished processing.`,
action: {
label: "View",
onClick: () => console.log("View task", newTask.task_id),
},
});
refetchSearch();
// Dispatch knowledge updated event for all knowledge-related pages
console.log(
"Task completed successfully, dispatching knowledgeUpdated event",
);
window.dispatchEvent(new CustomEvent("knowledgeUpdated"));
// Remove files for this completed task from the files list
setFiles((prevFiles) =>
prevFiles.filter((file) => file.task_id !== newTask.task_id),
);
} else if (
oldTask &&
oldTask.status !== "failed" &&
oldTask.status !== "error" &&
(newTask.status === "failed" || newTask.status === "error")
) {
// Task just failed - show error toast
toast.error("Task failed", {
description: `Task ${newTask.task_id} failed: ${
newTask.error || "Unknown error"
}`,
});
// Files will be updated to failed status by the file parsing logic above
}
});
}
return newTasks;
});
}
} catch (error) {
console.error("Failed to fetch tasks:", error);
} finally {
setIsFetching(false);
// Handle task status changes and file updates
useEffect(() => {
if (tasks.length === 0) {
// Store current tasks as previous for next comparison
previousTasksRef.current = tasks;
return;
}
}, [isAuthenticated, isNoAuthMode, refetchSearch]); // Removed 'tasks' from dependencies to prevent infinite loop!
const addTask = useCallback((taskId: string) => {
// Immediately start aggressive polling for the new task
let pollAttempts = 0;
const maxPollAttempts = 30; // Poll for up to 30 seconds
// Check for task status changes by comparing with previous tasks
tasks.forEach((currentTask) => {
const previousTask = previousTasksRef.current.find(
(prev) => prev.task_id === currentTask.task_id,
);
const aggressivePoll = async () => {
try {
const response = await fetch("/api/tasks");
if (response.ok) {
const data = await response.json();
const newTasks = data.tasks || [];
const foundTask = newTasks.find(
(task: Task) => task.task_id === taskId,
);
// Only show toasts if we have previous data and status has changed
if (
(previousTask && previousTask.status !== currentTask.status) ||
(!previousTask && previousTasksRef.current.length !== 0)
) {
// Process files from failed task and add them to files list
if (currentTask.files && typeof currentTask.files === "object") {
const taskFileEntries = Object.entries(currentTask.files);
const now = new Date().toISOString();
if (foundTask) {
// Task found! Update the tasks state
setTasks((prevTasks) => {
// Check if task is already in the list
const exists = prevTasks.some((t) => t.task_id === taskId);
if (!exists) {
return [...prevTasks, foundTask];
taskFileEntries.forEach(([filePath, fileInfo]) => {
if (typeof fileInfo === "object" && fileInfo) {
// Use the filename from backend if available, otherwise extract from path
const fileName =
(fileInfo as any).filename ||
filePath.split("/").pop() ||
filePath;
const fileStatus = fileInfo.status as string;
// Map backend file status to our TaskFile status
let mappedStatus: TaskFile["status"];
switch (fileStatus) {
case "pending":
case "running":
mappedStatus = "processing";
break;
case "completed":
mappedStatus = "active";
break;
case "failed":
mappedStatus = "failed";
break;
default:
mappedStatus = "processing";
}
// Update existing task
return prevTasks.map((t) =>
t.task_id === taskId ? foundTask : t,
);
});
return; // Stop polling, we found it
}
setFiles((prevFiles) => {
const existingFileIndex = prevFiles.findIndex(
(f) =>
f.source_url === filePath &&
f.task_id === currentTask.task_id,
);
// Detect connector type based on file path or other indicators
let connectorType = "local";
if (filePath.includes("/") && !filePath.startsWith("/")) {
// Likely S3 key format (bucket/path/file.ext)
connectorType = "s3";
}
const fileEntry: TaskFile = {
filename: fileName,
mimetype: "", // We don't have this info from the task
source_url: filePath,
size: 0, // We don't have this info from the task
connector_type: connectorType,
status: mappedStatus,
task_id: currentTask.task_id,
created_at:
typeof fileInfo.created_at === "string"
? fileInfo.created_at
: now,
updated_at:
typeof fileInfo.updated_at === "string"
? fileInfo.updated_at
: now,
};
if (existingFileIndex >= 0) {
// Update existing file
const updatedFiles = [...prevFiles];
updatedFiles[existingFileIndex] = fileEntry;
return updatedFiles;
} else {
// Add new file
return [...prevFiles, fileEntry];
}
});
}
});
}
} catch (error) {
console.error("Aggressive polling failed:", error);
}
if (
previousTask &&
previousTask.status !== "completed" &&
currentTask.status === "completed"
) {
// Task just completed - show success toast with file counts
const successfulFiles = currentTask.successful_files || 0;
const failedFiles = currentTask.failed_files || 0;
pollAttempts++;
if (pollAttempts < maxPollAttempts) {
// Continue polling every 1 second for new tasks
setTimeout(aggressivePoll, 1000);
}
};
let description = "";
if (failedFiles > 0) {
description = `${successfulFiles} file${
successfulFiles !== 1 ? "s" : ""
} uploaded successfully, ${failedFiles} file${
failedFiles !== 1 ? "s" : ""
} failed`;
} else {
description = `${successfulFiles} file${
successfulFiles !== 1 ? "s" : ""
} uploaded successfully`;
}
// Start aggressive polling after a short delay to allow backend to process
setTimeout(aggressivePoll, 500);
}, []);
toast.success("Task completed", {
description,
action: {
label: "View",
onClick: () => {
setIsMenuOpen(true);
setIsRecentTasksExpanded(true);
},
},
});
setTimeout(() => {
setFiles((prevFiles) =>
prevFiles.filter(
(file) =>
file.task_id !== currentTask.task_id ||
file.status === "failed",
),
);
refetchSearch();
}, 500);
} else if (
previousTask &&
previousTask.status !== "failed" &&
previousTask.status !== "error" &&
(currentTask.status === "failed" || currentTask.status === "error")
) {
// Task just failed - show error toast
toast.error("Task failed", {
description: `Task ${currentTask.task_id} failed: ${
currentTask.error || "Unknown error"
}`,
});
}
}
});
// Store current tasks as previous for next comparison
previousTasksRef.current = tasks;
}, [tasks, refetchSearch]);
const addTask = useCallback(
(_taskId: string) => {
// React Query will automatically handle polling when tasks are active
// Just trigger a refetch to get the latest data
setTimeout(() => {
refetchTasks();
}, 500);
},
[refetchTasks],
);
const refreshTasks = useCallback(async () => {
await fetchTasks();
}, [fetchTasks]);
setFiles([]);
await refetchTasks();
}, [refetchTasks]);
const removeTask = useCallback((taskId: string) => {
setTasks((prev) => prev.filter((task) => task.task_id !== taskId));
}, []);
const cancelTask = useCallback(
async (taskId: string) => {
try {
const response = await fetch(`/api/tasks/${taskId}/cancel`, {
method: "POST",
});
if (response.ok) {
// Immediately refresh tasks to show the updated status
await fetchTasks();
toast.success("Task cancelled", {
description: `Task ${taskId.substring(0, 8)}... has been cancelled`,
});
} else {
const errorData = await response.json().catch(() => ({}));
throw new Error(errorData.error || "Failed to cancel task");
}
} catch (error) {
console.error("Failed to cancel task:", error);
toast.error("Failed to cancel task", {
description: error instanceof Error ? error.message : "Unknown error",
});
}
cancelTaskMutation.mutate({ taskId });
},
[fetchTasks],
[cancelTaskMutation],
);
const toggleMenu = useCallback(() => {
setIsMenuOpen((prev) => !prev);
}, []);
// Periodic polling for task updates
useEffect(() => {
if (!isAuthenticated && !isNoAuthMode) return;
setIsPolling(true);
// Initial fetch
fetchTasks();
// Set up polling interval - every 3 seconds (more responsive for active tasks)
const interval = setInterval(fetchTasks, 3000);
return () => {
clearInterval(interval);
setIsPolling(false);
};
}, [isAuthenticated, isNoAuthMode, fetchTasks]);
// Determine if we're polling based on React Query's refetch interval
const isPolling =
isFetching &&
tasks.some(
(task) =>
task.status === "pending" ||
task.status === "running" ||
task.status === "processing",
);
const value: TaskContextType = {
tasks,
files,
addTask,
addFiles,
removeTask,
refreshTasks,
cancelTask,
isPolling,
isFetching,
isMenuOpen,
toggleMenu,
isRecentTasksExpanded,
setRecentTasksExpanded: setIsRecentTasksExpanded,
isLoading,
error,
};
return <TaskContext.Provider value={value}>{children}</TaskContext.Provider>;

86
src/api/documents.py
View file

@ -6,14 +6,13 @@ from config.settings import INDEX_NAME
logger = get_logger(__name__)
async def delete_documents_by_filename(request: Request, document_service, session_manager):
"""Delete all documents with a specific filename"""
data = await request.json()
filename = data.get("filename")
async def check_filename_exists(request: Request, document_service, session_manager):
"""Check if a document with a specific filename already exists"""
filename = request.query_params.get("filename")
if not filename:
return JSONResponse({"error": "filename is required"}, status_code=400)
return JSONResponse({"error": "filename parameter is required"}, status_code=400)
user = request.state.user
jwt_token = session_manager.get_effective_jwt_token(user.user_id, request.state.jwt_token)
@ -22,34 +21,79 @@ async def delete_documents_by_filename(request: Request, document_service, sessi
opensearch_client = session_manager.get_user_opensearch_client(
user.user_id, jwt_token
)
# Search for any document with this exact filename
from utils.opensearch_queries import build_filename_search_body
search_body = build_filename_search_body(filename, size=1, source=["filename"])
logger.debug(f"Checking filename existence: {filename}")
response = await opensearch_client.search(
index=INDEX_NAME,
body=search_body
)
# Check if any hits were found
hits = response.get("hits", {}).get("hits", [])
exists = len(hits) > 0
logger.debug(f"Filename check result - exists: {exists}, hits: {len(hits)}")
return JSONResponse({
"exists": exists,
"filename": filename
}, status_code=200)
except Exception as e:
logger.error("Error checking filename existence", filename=filename, error=str(e))
error_str = str(e)
if "AuthenticationException" in error_str:
return JSONResponse({"error": "Access denied: insufficient permissions"}, status_code=403)
else:
return JSONResponse({"error": str(e)}, status_code=500)
async def delete_documents_by_filename(request: Request, document_service, session_manager):
"""Delete all documents with a specific filename"""
data = await request.json()
filename = data.get("filename")
if not filename:
return JSONResponse({"error": "filename is required"}, status_code=400)
user = request.state.user
jwt_token = session_manager.get_effective_jwt_token(user.user_id, request.state.jwt_token)
try:
# Get user's OpenSearch client
opensearch_client = session_manager.get_user_opensearch_client(
user.user_id, jwt_token
)
# Delete by query to remove all chunks of this document
delete_query = {
"query": {
"bool": {
"must": [
{"term": {"filename": filename}}
]
}
}
}
from utils.opensearch_queries import build_filename_delete_body
delete_query = build_filename_delete_body(filename)
logger.debug(f"Deleting documents with filename: {filename}")
result = await opensearch_client.delete_by_query(
index=INDEX_NAME,
body=delete_query,
conflicts="proceed"
)
deleted_count = result.get("deleted", 0)
logger.info(f"Deleted {deleted_count} chunks for filename {filename}", user_id=user.user_id)
return JSONResponse({
"success": True,
"deleted_chunks": deleted_count,
"filename": filename,
"message": f"All documents with filename '{filename}' deleted successfully"
}, status_code=200)
except Exception as e:
logger.error("Error deleting documents by filename", filename=filename, error=str(e))
error_str = str(e)

15
src/api/langflow_files.py
View file

@ -189,19 +189,20 @@ async def upload_and_ingest_user_file(
# Create temporary file for task processing
import tempfile
import os
# Read file content
content = await upload_file.read()
# Create temporary file
# Create temporary file with the actual filename (not a temp prefix)
# Store in temp directory but use the real filename
temp_dir = tempfile.gettempdir()
safe_filename = upload_file.filename.replace(" ", "_").replace("/", "_")
temp_fd, temp_path = tempfile.mkstemp(
suffix=f"_{safe_filename}"
)
temp_path = os.path.join(temp_dir, safe_filename)
try:
# Write content to temp file
with os.fdopen(temp_fd, 'wb') as temp_file:
with open(temp_path, 'wb') as temp_file:
temp_file.write(content)
logger.debug("Created temporary file for task processing", temp_path=temp_path)

106
src/api/router.py
View file

@ -13,27 +13,27 @@ logger = get_logger(__name__)
async def upload_ingest_router(
request: Request,
document_service=None,
langflow_file_service=None,
request: Request,
document_service=None,
langflow_file_service=None,
session_manager=None,
task_service=None
task_service=None,
):
"""
Router endpoint that automatically routes upload requests based on configuration.
- If DISABLE_INGEST_WITH_LANGFLOW is True: uses traditional OpenRAG upload (/upload)
- If DISABLE_INGEST_WITH_LANGFLOW is False (default): uses Langflow upload-ingest via task service
This provides a single endpoint that users can call regardless of backend configuration.
All langflow uploads are processed as background tasks for better scalability.
"""
try:
logger.debug(
"Router upload_ingest endpoint called",
disable_langflow_ingest=DISABLE_INGEST_WITH_LANGFLOW
"Router upload_ingest endpoint called",
disable_langflow_ingest=DISABLE_INGEST_WITH_LANGFLOW,
)
# Route based on configuration
if DISABLE_INGEST_WITH_LANGFLOW:
# Route to traditional OpenRAG upload
@ -42,8 +42,10 @@ async def upload_ingest_router(
else:
# Route to Langflow upload and ingest using task service
logger.debug("Routing to Langflow upload-ingest pipeline via task service")
return await langflow_upload_ingest_task(request, langflow_file_service, session_manager, task_service)
return await langflow_upload_ingest_task(
request, langflow_file_service, session_manager, task_service
)
except Exception as e:
logger.error("Error in upload_ingest_router", error=str(e))
error_msg = str(e)
@ -57,17 +59,14 @@ async def upload_ingest_router(
async def langflow_upload_ingest_task(
request: Request,
langflow_file_service,
session_manager,
task_service
request: Request, langflow_file_service, session_manager, task_service
):
"""Task-based langflow upload and ingest for single/multiple files"""
try:
logger.debug("Task-based langflow upload_ingest endpoint called")
form = await request.form()
upload_files = form.getlist("file")
if not upload_files or len(upload_files) == 0:
logger.error("No files provided in task-based upload request")
return JSONResponse({"error": "Missing files"}, status_code=400)
@ -77,14 +76,16 @@ async def langflow_upload_ingest_task(
settings_json = form.get("settings")
tweaks_json = form.get("tweaks")
delete_after_ingest = form.get("delete_after_ingest", "true").lower() == "true"
replace_duplicates = form.get("replace_duplicates", "false").lower() == "true"
# Parse JSON fields if provided
settings = None
tweaks = None
if settings_json:
try:
import json
settings = json.loads(settings_json)
except json.JSONDecodeError as e:
logger.error("Invalid settings JSON", error=str(e))
@ -93,6 +94,7 @@ async def langflow_upload_ingest_task(
if tweaks_json:
try:
import json
tweaks = json.loads(tweaks_json)
except json.JSONDecodeError as e:
logger.error("Invalid tweaks JSON", error=str(e))
@ -106,28 +108,37 @@ async def langflow_upload_ingest_task(
jwt_token = getattr(request.state, "jwt_token", None)
if not user_id:
return JSONResponse({"error": "User authentication required"}, status_code=401)
return JSONResponse(
{"error": "User authentication required"}, status_code=401
)
# Create temporary files for task processing
import tempfile
import os
temp_file_paths = []
original_filenames = []
try:
# Create temp directory reference once
temp_dir = tempfile.gettempdir()
for upload_file in upload_files:
# Read file content
content = await upload_file.read()
# Create temporary file
# Store ORIGINAL filename (not transformed)
original_filenames.append(upload_file.filename)
# Create temporary file with TRANSFORMED filename for filesystem safety
# Transform: spaces and / to underscore
safe_filename = upload_file.filename.replace(" ", "_").replace("/", "_")
temp_fd, temp_path = tempfile.mkstemp(
suffix=f"_{safe_filename}"
)
temp_path = os.path.join(temp_dir, safe_filename)
# Write content to temp file
with os.fdopen(temp_fd, 'wb') as temp_file:
with open(temp_path, "wb") as temp_file:
temp_file.write(content)
temp_file_paths.append(temp_path)
logger.debug(
@ -136,21 +147,22 @@ async def langflow_upload_ingest_task(
user_id=user_id,
has_settings=bool(settings),
has_tweaks=bool(tweaks),
delete_after_ingest=delete_after_ingest
delete_after_ingest=delete_after_ingest,
)
# Create langflow upload task
print(f"tweaks: {tweaks}")
print(f"settings: {settings}")
print(f"jwt_token: {jwt_token}")
print(f"user_name: {user_name}")
print(f"user_email: {user_email}")
print(f"session_id: {session_id}")
print(f"delete_after_ingest: {delete_after_ingest}")
print(f"temp_file_paths: {temp_file_paths}")
logger.debug(
f"Preparing to create langflow upload task: tweaks={tweaks}, settings={settings}, jwt_token={jwt_token}, user_name={user_name}, user_email={user_email}, session_id={session_id}, delete_after_ingest={delete_after_ingest}, temp_file_paths={temp_file_paths}",
)
# Create a map between temp_file_paths and original_filenames
file_path_to_original_filename = dict(zip(temp_file_paths, original_filenames))
logger.debug(
f"File path to original filename map: {file_path_to_original_filename}",
)
task_id = await task_service.create_langflow_upload_task(
user_id=user_id,
file_paths=temp_file_paths,
original_filenames=file_path_to_original_filename,
langflow_file_service=langflow_file_service,
session_manager=session_manager,
jwt_token=jwt_token,
@ -160,23 +172,28 @@ async def langflow_upload_ingest_task(
tweaks=tweaks,
settings=settings,
delete_after_ingest=delete_after_ingest,
replace_duplicates=replace_duplicates,
)
logger.debug("Langflow upload task created successfully", task_id=task_id)
return JSONResponse({
"task_id": task_id,
"message": f"Langflow upload task created for {len(upload_files)} file(s)",
"file_count": len(upload_files)
}, status_code=202) # 202 Accepted for async processing
return JSONResponse(
{
"task_id": task_id,
"message": f"Langflow upload task created for {len(upload_files)} file(s)",
"file_count": len(upload_files),
},
status_code=202,
) # 202 Accepted for async processing
except Exception:
# Clean up temp files on error
from utils.file_utils import safe_unlink
for temp_path in temp_file_paths:
safe_unlink(temp_path)
raise
except Exception as e:
logger.error(
"Task-based langflow upload_ingest endpoint failed",
@ -184,5 +201,6 @@ async def langflow_upload_ingest_task(
error=str(e),
)
import traceback
logger.error("Full traceback", traceback=traceback.format_exc())
return JSONResponse({"error": str(e)}, status_code=500)

11
src/main.py
View file

@ -953,6 +953,17 @@ async def create_app():
methods=["POST", "GET"],
),
# Document endpoints
Route(
"/documents/check-filename",
require_auth(services["session_manager"])(
partial(
documents.check_filename_exists,
document_service=services["document_service"],
session_manager=services["session_manager"],
)
),
methods=["GET"],
),
Route(
"/documents/delete-by-filename",
require_auth(services["session_manager"])(

131
src/models/processors.py
View file

@ -55,6 +55,96 @@ class TaskProcessor:
await asyncio.sleep(retry_delay)
retry_delay *= 2 # Exponential backoff
async def check_filename_exists(
self,
filename: str,
opensearch_client,
) -> bool:
"""
Check if a document with the given filename already exists in OpenSearch.
Returns True if any chunks with this filename exist.
"""
from config.settings import INDEX_NAME
from utils.opensearch_queries import build_filename_search_body
import asyncio
max_retries = 3
retry_delay = 1.0
for attempt in range(max_retries):
try:
# Search for any document with this exact filename
search_body = build_filename_search_body(filename, size=1, source=False)
response = await opensearch_client.search(
index=INDEX_NAME,
body=search_body
)
# Check if any hits were found
hits = response.get("hits", {}).get("hits", [])
return len(hits) > 0
except (asyncio.TimeoutError, Exception) as e:
if attempt == max_retries - 1:
logger.error(
"OpenSearch filename check failed after retries",
filename=filename,
error=str(e),
attempt=attempt + 1
)
# On final failure, assume document doesn't exist (safer to reprocess than skip)
logger.warning(
"Assuming filename doesn't exist due to connection issues",
filename=filename
)
return False
else:
logger.warning(
"OpenSearch filename check failed, retrying",
filename=filename,
error=str(e),
attempt=attempt + 1,
retry_in=retry_delay
)
await asyncio.sleep(retry_delay)
retry_delay *= 2 # Exponential backoff
async def delete_document_by_filename(
self,
filename: str,
opensearch_client,
) -> None:
"""
Delete all chunks of a document with the given filename from OpenSearch.
"""
from config.settings import INDEX_NAME
from utils.opensearch_queries import build_filename_delete_body
try:
# Delete all documents with this filename
delete_body = build_filename_delete_body(filename)
response = await opensearch_client.delete_by_query(
index=INDEX_NAME,
body=delete_body
)
deleted_count = response.get("deleted", 0)
logger.info(
"Deleted existing document chunks",
filename=filename,
deleted_count=deleted_count
)
except Exception as e:
logger.error(
"Failed to delete existing document",
filename=filename,
error=str(e)
)
raise
async def process_document_standard(
self,
file_path: str,
@ -527,6 +617,7 @@ class LangflowFileProcessor(TaskProcessor):
tweaks: dict = None,
settings: dict = None,
delete_after_ingest: bool = True,
replace_duplicates: bool = False,
):
super().__init__()
self.langflow_file_service = langflow_file_service
@ -539,6 +630,7 @@ class LangflowFileProcessor(TaskProcessor):
self.tweaks = tweaks or {}
self.settings = settings
self.delete_after_ingest = delete_after_ingest
self.replace_duplicates = replace_duplicates
async def process_item(
self, upload_task: UploadTask, item: str, file_task: FileTask
@ -554,37 +646,40 @@ class LangflowFileProcessor(TaskProcessor):
file_task.updated_at = time.time()
try:
# Compute hash and check if already exists
from utils.hash_utils import hash_id
file_hash = hash_id(item)
# Use the ORIGINAL filename stored in file_task (not the transformed temp path)
# This ensures we check/store the original filename with spaces, etc.
original_filename = file_task.filename or os.path.basename(item)
# Check if document already exists
# Check if document with same filename already exists
opensearch_client = self.session_manager.get_user_opensearch_client(
self.owner_user_id, self.jwt_token
)
if await self.check_document_exists(file_hash, opensearch_client):
file_task.status = TaskStatus.COMPLETED
file_task.result = {"status": "unchanged", "id": file_hash}
filename_exists = await self.check_filename_exists(original_filename, opensearch_client)
if filename_exists and not self.replace_duplicates:
# Duplicate exists and user hasn't confirmed replacement
file_task.status = TaskStatus.FAILED
file_task.error = f"File with name '{original_filename}' already exists"
file_task.updated_at = time.time()
upload_task.successful_files += 1
upload_task.failed_files += 1
return
elif filename_exists and self.replace_duplicates:
# Delete existing document before uploading new one
logger.info(f"Replacing existing document: {original_filename}")
await self.delete_document_by_filename(original_filename, opensearch_client)
# Read file content for processing
with open(item, 'rb') as f:
content = f.read()
# Create file tuple for upload
temp_filename = os.path.basename(item)
# Extract original filename from temp file suffix (remove tmp prefix)
if "_" in temp_filename:
filename = temp_filename.split("_", 1)[1] # Get everything after first _
else:
filename = temp_filename
content_type, _ = mimetypes.guess_type(filename)
# Create file tuple for upload using ORIGINAL filename
# This ensures the document is indexed with the original name
content_type, _ = mimetypes.guess_type(original_filename)
if not content_type:
content_type = 'application/octet-stream'
file_tuple = (filename, content, content_type)
file_tuple = (original_filename, content, content_type)
# Get JWT token using same logic as DocumentFileProcessor
# This will handle anonymous JWT creation if needed

3
src/models/tasks.py
View file

@ -20,7 +20,8 @@ class FileTask:
retry_count: int = 0
created_at: float = field(default_factory=time.time)
updated_at: float = field(default_factory=time.time)
filename: Optional[str] = None # Original filename for display
@property
def duration_seconds(self) -> float:
"""Duration in seconds from creation to last update"""

28
src/services/task_service.py
View file

@ -1,6 +1,5 @@
import asyncio
import random
from typing import Dict, Optional
import time
import uuid
@ -59,6 +58,7 @@ class TaskService:
file_paths: list,
langflow_file_service,
session_manager,
original_filenames: dict | None = None,
jwt_token: str = None,
owner_name: str = None,
owner_email: str = None,
@ -66,6 +66,7 @@ class TaskService:
tweaks: dict = None,
settings: dict = None,
delete_after_ingest: bool = True,
replace_duplicates: bool = False,
) -> str:
"""Create a new upload task for Langflow file processing with upload and ingest"""
# Use LangflowFileProcessor with user context
@ -82,18 +83,35 @@ class TaskService:
tweaks=tweaks,
settings=settings,
delete_after_ingest=delete_after_ingest,
replace_duplicates=replace_duplicates,
)
return await self.create_custom_task(user_id, file_paths, processor)
return await self.create_custom_task(user_id, file_paths, processor, original_filenames)
async def create_custom_task(self, user_id: str, items: list, processor) -> str:
async def create_custom_task(self, user_id: str, items: list, processor, original_filenames: dict | None = None) -> str:
"""Create a new task with custom processor for any type of items"""
import os
# Store anonymous tasks under a stable key so they can be retrieved later
store_user_id = user_id or AnonymousUser().user_id
task_id = str(uuid.uuid4())
# Create file tasks with original filenames if provided
normalized_originals = (
{str(k): v for k, v in original_filenames.items()} if original_filenames else {}
)
file_tasks = {
str(item): FileTask(
file_path=str(item),
filename=normalized_originals.get(
str(item), os.path.basename(str(item))
),
)
for item in items
}
upload_task = UploadTask(
task_id=task_id,
total_files=len(items),
file_tasks={str(item): FileTask(file_path=str(item)) for item in items},
file_tasks=file_tasks,
)
# Attach the custom processor to the task
@ -268,6 +286,7 @@ class TaskService:
"created_at": file_task.created_at,
"updated_at": file_task.updated_at,
"duration_seconds": file_task.duration_seconds,
"filename": file_task.filename,
}
# Count running and pending files
@ -322,6 +341,7 @@ class TaskService:
"created_at": file_task.created_at,
"updated_at": file_task.updated_at,
"duration_seconds": file_task.duration_seconds,
"filename": file_task.filename,
}
if file_task.status.value == "running":

55
src/utils/opensearch_queries.py Normal file
View file

@ -0,0 +1,55 @@
"""
Utility functions for constructing OpenSearch queries consistently.
"""
from typing import Union, List
def build_filename_query(filename: str) -> dict:
"""
Build a standardized query for finding documents by filename.
Args:
filename: The exact filename to search for
Returns:
A dict containing the OpenSearch query body
"""
return {
"term": {
"filename": filename
}
}
def build_filename_search_body(filename: str, size: int = 1, source: Union[bool, List[str]] = False) -> dict:
"""
Build a complete search body for checking if a filename exists.
Args:
filename: The exact filename to search for
size: Number of results to return (default: 1)
source: Whether to include source fields, or list of specific fields to include (default: False)
Returns:
A dict containing the complete OpenSearch search body
"""
return {
"query": build_filename_query(filename),
"size": size,
"_source": source
}
def build_filename_delete_body(filename: str) -> dict:
"""
Build a delete-by-query body for removing all documents with a filename.
Args:
filename: The exact filename to delete
Returns:
A dict containing the OpenSearch delete-by-query body
"""
return {
"query": build_filename_query(filename)
}