RAG & Knowledge Base

Let Agent Answer Questions Based on Your Documents

Import enterprise internal documents, manuals, and regulations into the knowledge base, and Agent can answer questions based on this content — with source citations for every conclusion.

Multi-Format Engine

Document Support

Supports PDF, Word, Excel, PPT, Markdown, HTML, CSV, and more formats. Upload files or enter URLs to import. Three document chunking strategies (fixed-length, recursive, semantic) to match different document structures. Create Markdown documents directly within the knowledge base.

.pdf
.docx
.xlsx
.pptx
.md
.html
.csv
.json
"How to audit procurement?"
Semantic Path
Finds "reviewing purchase orders" by vector proximity
Keyword Path
Matches "procurement" exactly in inverted index
Reranking Model
Winner: Section 4.2 - Internal Audit

Precise Retrieval

Not simple keyword matching. The system simultaneously retrieves from both 'semantic understanding' and 'keyword matching' dimensions, then uses ranking algorithms to find the most relevant content — semantic vector retrieval captures similar meaning with different wording, keyword retrieval ensures exact hits on proper nouns and IDs. Dual-path results are merged, ranked, and refined through a re-ranking model.

No need to deploy additional database services — built-in embedded vector database, zero external dependencies.

Traceable Conclusions

Every answer from Agent is annotated with sources:

Citation markers [1][2] pointing to specific document paragraphs
Citation alignment score: evaluates how well the answer matches evidence
Conflict detection: explicitly flags when multiple documents have contradicting views
Confidence assessment: provides answer confidence scores based on evidence quality
A structured citation panel displays the complete reference source list. Lets users verify AI's judgments rather than blindly trusting them.
Source-Grounded Response

[1] orders above ¥50,000 require three independent quotes

Evidence
1
policy_v2.pdf98%
Section 1.4: Order Thresholds...
Knowledge Cluster
2,482 CHUNKS
Policy_Audit.pdfProcessed
Manual_v2.docxIndexing

Knowledge Base Management

Complete lifecycle management: create, edit, and delete knowledge bases. Documents are processed asynchronously after upload, with failed documents retryable. View, edit, and delete individual document chunks with in-chunk text search. Knowledge bases can be bound to specific Agents, auto-retrieving relevant content at runtime.

Semantic Chunking

Dedicated knowledge base detail page with document table and chunk browser, supporting direct navigation from list to document and chunk management.

Developers

Explore our Source Available code on GitHub, contribute to the connector ecosystem, or integrate FIM One into your own applications.

git clone https://github.com/fim-ai/fim-one.git && ./start.sh

Enterprise

Need private deployment, custom connectors, or professional support? Our team is ready to help you scale your AI transformation.

Private Deploy & Isolation
SSO & Audit Logs
1-on-1 Dedicated Support
SLA Availability Guarantee