Skip to content

feat: Add crawl4ai as an option for local scrape #11553

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
relic664 wants to merge 6 commits into
base: main
Choose a base branch
from
Draft

feat: Add crawl4ai as an option for local scrape #11553

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
98ed3ee
Feature: support for localy hosted Crawl4AI scraping, WARNING: needs …
lukolszewski Nov 13, 2025
8731432
Merge remote-tracking branch 'upstream/main' into feature/crawl4ai-wi…
relic664 Jan 28, 2026
04629af
add fit strategy
relic664 Jan 28, 2026
6a35d80
basic UI support
relic664 Jan 28, 2026
e897e5f
add to spec, require api url
relic664 Jan 28, 2026
7b3ee37
Merge branch 'main' into feature/crawl4ai-with-fit
relic664 Jan 29, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions client/src/components/SidePanel/Agents/Search/ApiKeyDialog.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -152,6 +152,20 @@ export default function ApiKeyDialog({
},
},
},
{
key: ScraperProviders.CRAWL4AI,
label: localize('com_ui_web_search_provider_crawl4ai'),
inputs: {
crawl4aiApiUrl: {
placeholder: localize('com_ui_web_search_crawl4ai_instance_url'),
type: 'text' as const,
},
crawl4aiApiKey: {
placeholder: localize('com_ui_web_search_crawl4ai_api_key'),
type: 'password' as const,
},
},
},
];

const [dropdownOpen, setDropdownOpen] = useState({
Expand Down
4 changes: 4 additions & 0 deletions client/src/hooks/Plugins/useAuthSearchTool.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,6 +16,8 @@ export type SearchApiKeyFormData = {
firecrawlApiUrl: string;
jinaApiKey: string;
jinaApiUrl: string;
crawl4aiApiUrl: string;
crawl4aiApiKey: string;
cohereApiKey: string;
};

Expand Down Expand Up @@ -56,6 +58,8 @@ const useAuthSearchTool = (options?: { isEntityTool: boolean }) => {
firecrawlApiUrl: data.firecrawlApiUrl,
jinaApiKey: data.jinaApiKey,
jinaApiUrl: data.jinaApiUrl,
crawl4aiApiUrl: data.crawl4aiApiUrl,
crawl4aiApiKey: data.crawl4aiApiKey,
cohereApiKey: data.cohereApiKey,
}).reduce(
(acc, [key, value]) => {
Expand Down
3 changes: 3 additions & 0 deletions client/src/locales/en/translation.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1429,6 +1429,7 @@
"com_ui_web_search_provider": "Search Provider",
"com_ui_web_search_provider_searxng": "SearXNG",
"com_ui_web_search_provider_serper": "Serper API",
"com_ui_web_search_provider_crawl4ai": "Crawl4AI API",
"com_ui_web_search_provider_serper_key": "Get your Serper API key",
"com_ui_web_search_reading": "Reading results",
"com_ui_web_search_reranker": "Reranker",
Expand All @@ -1444,6 +1445,8 @@
"com_ui_web_search_scraper_serper_key": "Get your Serper API key",
"com_ui_web_search_searxng_api_key": "Enter SearXNG API Key (optional)",
"com_ui_web_search_searxng_instance_url": "SearXNG Instance URL",
"com_ui_web_search_crawl4ai_api_key": "Enter Crawl4AI API Key (optional)",
"com_ui_web_search_crawl4ai_instance_url": "Crawl4AI Instance URL",
"com_ui_web_searching": "Searching the web",
"com_ui_web_searching_again": "Searching the web again",
"com_ui_weekend_morning": "Happy weekend",
Expand Down
2 changes: 2 additions & 0 deletions packages/api/src/app/AppService.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -128,6 +128,8 @@ describe('AppService', () => {
firecrawlApiKey: '${FIRECRAWL_API_KEY}',
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
searxngInstanceUrl: '${SEARXNG_INSTANCE_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
}),
memory: undefined,
endpoints: expect.objectContaining({
Expand Down
36 changes: 36 additions & 0 deletions packages/api/src/web/web.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,6 +83,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
};
Expand Down Expand Up @@ -304,6 +306,8 @@ describe('web.ts', () => {
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
cohereApiKey: '${COHERE_API_KEY}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
};

Expand Down Expand Up @@ -355,6 +359,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
// Specify which services to use
Expand Down Expand Up @@ -449,6 +455,8 @@ describe('web.ts', () => {
jinaApiKey: '${CUSTOM_JINA_KEY}',
jinaApiUrl: '${CUSTOM_JINA_URL}',
cohereApiKey: '${CUSTOM_COHERE_KEY}',
crawl4aiApiUrl: '${CUSTOM_CRAWL4AI_URL}',
crawl4aiApiKey: '${CUSTOM_CRAWL4AI_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
// Specify which services to use
searchProvider: 'serper' as SearchProviders,
Expand Down Expand Up @@ -519,6 +527,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
};
Expand Down Expand Up @@ -581,6 +591,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
};
Expand Down Expand Up @@ -691,6 +703,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
searchProvider: 'serper' as SearchProviders,
Expand Down Expand Up @@ -732,6 +746,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
scraperProvider: 'firecrawl' as ScraperProviders,
Expand Down Expand Up @@ -773,6 +789,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
rerankerType: 'jina' as RerankerTypes,
Expand Down Expand Up @@ -820,6 +838,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
searchProvider: 'invalid-provider' as SearchProviders,
Expand Down Expand Up @@ -855,6 +875,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
rerankerType: 'jina' as RerankerTypes,
Expand Down Expand Up @@ -906,6 +928,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
};
Expand Down Expand Up @@ -947,6 +971,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
firecrawlOptions: {
Expand Down Expand Up @@ -1007,6 +1033,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
scraperTimeout: 15000, // This should take priority
firecrawlOptions: {
Expand Down Expand Up @@ -1049,6 +1077,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
firecrawlOptions: {
includeTags: ['p'],
Expand Down Expand Up @@ -1088,6 +1118,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
firecrawlOptions: {
timeout: 12000, // Only timeout provided
Expand Down Expand Up @@ -1125,6 +1157,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
firecrawlOptions: {
formats: ['html', 'markdown'], // Only formats provided
Expand Down Expand Up @@ -1162,6 +1196,8 @@ describe('web.ts', () => {
firecrawlApiUrl: '${FIRECRAWL_API_URL}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
firecrawlOptions: {
timeout: 8000,
Expand Down
3 changes: 2 additions & 1 deletion packages/api/src/web/web.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -120,7 +120,8 @@ export async function loadWebSearchAuth({
}
}

if (requiredKeys.length === 0) continue;
// If there are no required keys and no optional keys, skip this service
if (requiredKeys.length === 0 && optionalKeys.length === 0) continue;

const requiredAuthFields = extractWebSearchEnvVars({
keys: requiredKeys,
Expand Down
11 changes: 11 additions & 0 deletions packages/data-provider/src/config.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -813,6 +813,7 @@ export enum SearchProviders {
export enum ScraperProviders {
FIRECRAWL = 'firecrawl',
SERPER = 'serper',
CRAWL4AI = 'crawl4ai',
}

export enum RerankerTypes {
Expand All @@ -833,6 +834,8 @@ export const webSearchSchema = z.object({
firecrawlApiKey: z.string().optional().default('${FIRECRAWL_API_KEY}'),
firecrawlApiUrl: z.string().optional().default('${FIRECRAWL_API_URL}'),
firecrawlVersion: z.string().optional().default('${FIRECRAWL_VERSION}'),
crawl4aiApiKey: z.string().optional().default('${CRAWL4AI_API_KEY}'),
crawl4aiApiUrl: z.string().optional().default('${CRAWL4AI_API_URL}'),
jinaApiKey: z.string().optional().default('${JINA_API_KEY}'),
jinaApiUrl: z.string().optional().default('${JINA_API_URL}'),
cohereApiKey: z.string().optional().default('${COHERE_API_KEY}'),
Expand Down Expand Up @@ -874,6 +877,14 @@ export const webSearchSchema = z.object({
.optional(),
})
.optional(),
crawl4aiOptions: z
.object({
extractionStrategy: z.string().optional(),
chunkingStrategy: z.string().optional(),
timeout: z.number().optional(),
fitStrategy: z.string().optional()
})
.optional(),
});

export type TWebSearchConfig = DeepPartial<z.infer<typeof webSearchSchema>>;
Expand Down
5 changes: 5 additions & 0 deletions packages/data-schemas/src/app/web.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,8 @@ describe('loadWebSearchConfig', () => {
firecrawlVersion: '${FIRECRAWL_VERSION}',
jinaApiKey: '${JINA_API_KEY}',
jinaApiUrl: '${JINA_API_URL}',
crawl4aiApiUrl: '${CRAWL4AI_API_URL}',
crawl4aiApiKey: '${CRAWL4AI_API_KEY}',
cohereApiKey: '${COHERE_API_KEY}',
safeSearch: SafeSearchTypes.MODERATE,
});
Expand Down Expand Up @@ -154,20 +156,23 @@ describe('loadWebSearchConfig', () => {
expect(result?.searxngInstanceUrl).toBe('${SEARXNG_INSTANCE_URL}');
expect(result?.firecrawlApiUrl).toBe('${FIRECRAWL_API_URL}');
expect(result?.jinaApiUrl).toBe('${JINA_API_URL}');
expect(result?.crawl4aiApiUrl).toBe('${CRAWL4AI_API_URL}');
});

it('should preserve custom URLs', () => {
const config: TCustomConfig['webSearch'] = {
searxngInstanceUrl: 'https://custom-searxng.com',
firecrawlApiUrl: 'https://custom-firecrawl.com',
jinaApiUrl: 'https://custom-jina.com',
crawl4aiApiUrl: 'https://custom-crawl4ai.com'
};

const result = loadWebSearchConfig(config);

expect(result?.searxngInstanceUrl).toBe('https://custom-searxng.com');
expect(result?.firecrawlApiUrl).toBe('https://custom-firecrawl.com');
expect(result?.jinaApiUrl).toBe('https://custom-jina.com');
expect(result?.crawl4aiApiUrl).toBe('https://custom-crawl4ai.com');
});
});
});
10 changes: 10 additions & 0 deletions packages/data-schemas/src/app/web.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,6 +23,12 @@ export const webSearchAuth = {
serper: {
serperApiKey: 1 as const,
},
crawl4ai: {
/** Optional (0) - works without API key for public deployments */
crawl4aiApiKey: 0 as const,
/** Optional (0) */
crawl4aiApiUrl: 1 as const,
},
},
rerankers: {
jina: {
Expand Down Expand Up @@ -69,6 +75,8 @@ export function loadWebSearchConfig(
const firecrawlApiKey = config?.firecrawlApiKey ?? '${FIRECRAWL_API_KEY}';
const firecrawlApiUrl = config?.firecrawlApiUrl ?? '${FIRECRAWL_API_URL}';
const firecrawlVersion = config?.firecrawlVersion ?? '${FIRECRAWL_VERSION}';
const crawl4aiApiKey = config?.crawl4aiApiKey ?? '${CRAWL4AI_API_KEY}';
const crawl4aiApiUrl = config?.crawl4aiApiUrl ?? '${CRAWL4AI_API_URL}';
const jinaApiKey = config?.jinaApiKey ?? '${JINA_API_KEY}';
const jinaApiUrl = config?.jinaApiUrl ?? '${JINA_API_URL}';
const cohereApiKey = config?.cohereApiKey ?? '${COHERE_API_KEY}';
Expand All @@ -85,6 +93,8 @@ export function loadWebSearchConfig(
firecrawlApiKey,
firecrawlApiUrl,
firecrawlVersion,
crawl4aiApiKey,
crawl4aiApiUrl,
searxngInstanceUrl,
};
}
2 changes: 2 additions & 0 deletions packages/data-schemas/src/types/web.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,8 @@ export type TWebSearchKeys =
| 'firecrawlApiKey'
| 'firecrawlApiUrl'
| 'firecrawlVersion'
| 'crawl4aiApiKey'
| 'crawl4aiApiUrl'
| 'jinaApiKey'
| 'jinaApiUrl'
| 'cohereApiKey';
Expand Down