Unverified50% confidenceFactExact time
Knowledge base sources supported by the system include: website crawling (sitemap), PDF/DOCX/TXT/MD documents, image OCR, handwritten FAQs, internal team repositories and audio transcription text.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/19/2026
First Seen
Valid until: 1/17/2027
Sources
Related Entities
Related Claims
UnverifiedDify's knowledge base module supports uploading formats such as PDF, Word, and web pages, and has built-in vector databases including Weaviate, Qdrant, and Milvus as storage backends.73% similarUnverifiedThe data types XERJ supports include code indexing, documents and PDFs, log retrieval and Agent memory.69% similarUnverifiedDify's RAG pipeline supports vectorizing enterprise internal documents (PDF, Word, databases, etc.) and storing them in a knowledge base for model retrieval.69% similarUnverifiedLlamaIndex支持PDF、Word、数据库、API等上百种数据源的数据连接66% similarUnverifiedThis open-source project is a memory-driven business data assistant that integrates RAG, the MCP tool protocol, and RBAC access control, built around the concept of evidence-backed responses, where every generated chart or KPI answer cites the exact SQL queries, data tables, and knowledge documents used.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1071596API
curl https://kongchang.com/api/v1/knowledge/claims/1071596MCP
get_claim(id=1071596)