Files
simstudioai--sim/apps/sim/app/api/tools/firecrawl/parse/route.ts
T
wehub-resource-sync d25d482dc2
CI / Migrate Dev DB (push) Has been skipped
CI / Detect Version (push) Has been cancelled
CI / Migrate DB (push) Has been cancelled
CI / Build Dev ECR (./docker/app.Dockerfile, ECR_APP) (push) Has been cancelled
CI / Build Dev ECR (./docker/db.Dockerfile, ECR_MIGRATIONS) (push) Has been cancelled
CI / Build Dev ECR (./docker/pii.Dockerfile, ECR_PII) (push) Has been cancelled
CI / Build Dev ECR (./docker/realtime.Dockerfile, ECR_REALTIME) (push) Has been cancelled
CI / Deploy Trigger.dev (Dev) (push) Has been cancelled
CI / Build AMD64 (./docker/app.Dockerfile, ECR_APP, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build AMD64 (./docker/db.Dockerfile, ECR_MIGRATIONS, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build AMD64 (./docker/pii.Dockerfile, ECR_PII, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build AMD64 (./docker/realtime.Dockerfile, ECR_REALTIME, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/app.Dockerfile, ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/db.Dockerfile, ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/pii.Dockerfile, ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Build ARM64 (GHCR Only) (./docker/realtime.Dockerfile, ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/migrations) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/pii) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/realtime) (push) Has been cancelled
CI / Create GHCR Manifests (ghcr.io/simstudioai/simstudio) (push) Has been cancelled
CI / Check Docs Changes (push) Has been cancelled
CI / Process Docs (push) Has been cancelled
CI / Create GitHub Release (push) Has been cancelled
CI / Test and Build (push) Has been cancelled
Publish CLI Package / publish-npm (push) Has been cancelled
Publish Python SDK / publish-pypi (push) Has been cancelled
Publish TypeScript SDK / publish-npm (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 13:20:55 +08:00

102 lines
3.6 KiB
TypeScript

import { createLogger } from '@sim/logger'
import { toError } from '@sim/utils/errors'
import { type NextRequest, NextResponse } from 'next/server'
import { firecrawlParseContract } from '@/lib/api/contracts/tools'
import { parseRequest } from '@/lib/api/server'
import { checkInternalAuth } from '@/lib/auth/hybrid'
import { generateRequestId } from '@/lib/core/utils/request'
import { withRouteHandler } from '@/lib/core/utils/with-route-handler'
import { processFilesToUserFiles } from '@/lib/uploads/utils/file-utils'
import { downloadServableFileFromStorage } from '@/lib/uploads/utils/file-utils.server'
import { docNotReadyResponse } from '@/lib/uploads/utils/servable-file-response'
import { assertToolFileAccess } from '@/app/api/files/authorization'
export const dynamic = 'force-dynamic'
const logger = createLogger('FirecrawlParseAPI')
export const POST = withRouteHandler(async (request: NextRequest) => {
const requestId = generateRequestId()
try {
const authResult = await checkInternalAuth(request, { requireWorkflowId: false })
if (!authResult.success || !authResult.userId) {
logger.warn(`[${requestId}] Unauthorized Firecrawl parse attempt`, {
error: authResult.error || 'Missing userId',
})
return NextResponse.json(
{ success: false, error: authResult.error || 'Unauthorized' },
{ status: 401 }
)
}
const parsed = await parseRequest(firecrawlParseContract, request, {})
if (!parsed.success) return parsed.response
const validatedData = parsed.data.body
const [userFile] = processFilesToUserFiles([validatedData.file], requestId, logger)
if (!userFile) {
return NextResponse.json({ success: false, error: 'File input is required' }, { status: 400 })
}
logger.info(`[${requestId}] Firecrawl parse request`, {
fileName: userFile.name,
size: userFile.size,
})
const denied = await assertToolFileAccess(userFile.key, authResult.userId, requestId, logger)
if (denied) return denied
const { buffer, contentType } = await downloadServableFileFromStorage(
userFile,
requestId,
logger
)
const formData = new FormData()
const blob = new Blob([new Uint8Array(buffer)], {
type: contentType || userFile.type || 'application/octet-stream',
})
formData.append('file', blob, userFile.name)
if (validatedData.options && Object.keys(validatedData.options).length > 0) {
formData.append('options', JSON.stringify(validatedData.options))
}
const firecrawlResponse = await fetch('https://api.firecrawl.dev/v2/parse', {
method: 'POST',
headers: {
Authorization: `Bearer ${validatedData.apiKey}`,
},
body: formData,
})
if (!firecrawlResponse.ok) {
const errorText = await firecrawlResponse.text()
logger.error(`[${requestId}] Firecrawl API error:`, errorText)
return NextResponse.json(
{
success: false,
error: `Firecrawl API error: ${errorText || firecrawlResponse.statusText}`,
},
{ status: firecrawlResponse.status }
)
}
const firecrawlData = await firecrawlResponse.json()
logger.info(`[${requestId}] Firecrawl parse successful`)
return NextResponse.json({
success: true,
output: firecrawlData.data ?? firecrawlData,
})
} catch (error) {
const notReady = docNotReadyResponse(error)
if (notReady) return notReady
logger.error(`[${requestId}] Error in Firecrawl parse:`, error)
return NextResponse.json({ success: false, error: toError(error).message }, { status: 500 })
}
})