connectors onhttps://docs.gathr.ai/gathr-unlimited/7.6.0/tags/connectors/Recent content in connectors onHugo -- gohugo.ioTue, 03 Jan 2023 21:01:49 +0530Connect Content Sourcehttps://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/kb-connect-source/Tue, 03 Jan 2023 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/kb-connect-source/Connect your Knowledge Base to one of the available data sources. Step 1: Select a Data Source # Choose from available connectors such as Web Scrapper, Amazon S3, or File Upload. Step 2: Configure the Knowledge Base # Based on the selected data source, configure the Knowledge Base. Refer to connector specific documentation for more details: Web Scraper Amazon S3 File UploadAmazon S3 (Coming Soon)https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/knowledge-base-sources/kb-amazon-s3/Tue, 03 Jan 2023 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/knowledge-base-sources/kb-amazon-s3/ 👉 This data source is under development. Documentation will be updated once available.File Uploadhttps://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/knowledge-base-sources/kb-file-upload/Tue, 03 Jan 2023 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/knowledge-base-sources/kb-file-upload/Step 2: Configure the Knowledge Base # Select the extraction method: Sitemap Scan, Targeted URL(s), or Website Crawl. Enter the website URL or relevant source details. Configure advanced settings as needed (anti-bot scraping, skip image processing, AI provider, etc.). 💡 Ensure the source website has a valid sitemap.xml for optimal extraction. Use advanced settings for custom requirements. Scheduling Syncs →Web Scraperhttps://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/knowledge-base-sources/kb-web-scraper/Tue, 03 Jan 2023 21:01:49 +0530https://docs.gathr.ai/gathr-unlimited/7.6.0/docs/knowledge-base/knowledge-base-sources/kb-web-scraper/Configure Web Scraper for your Knowledge Base. Extraction Method # Create or update knowledge base using one of the supported options. Website Crawl: Extract data recursively from Website till the specified depth. Targeted URL(s): Extract data from the specified Website URLs. Sitemap Scan: Extract data from Website using sitemap. Website URL # Enter the Website URL to generate knowledge base. A valid URL should be provided, for example: https://example.com. 💡 For Sitemap Scan option, ensure the source website has a valid sitemap.