Ingestion
Parse files with verified OCR or document extraction, preserve section metadata and record document versions.
AGENT USE CASE · SOURCE-FIRST
Documents & RAG agents.
A document agent normally combines extraction, indexed retrieval, a generation model and permissions. Embedding models support retrieval; they do not replace the agent's reasoning model.
What must be evaluated?
Retrieval
Evaluate multilingual search, recall, reranking and citation alignment against representative private documents.
Permissions
Filter retrieval by document-level access before sending snippets to the model; never rely on prompt instructions for access control.
Locality
Audit embeddings, logs, backups, telemetry and external connectors: a local LLM by itself does not make the whole document pipeline private.
23 catalog candidates and components
These model records are included by catalog modality or category, not by a verified task-success benchmark. Follow their primary sources before testing.
MiniMax-M3Core candidate · MiniMax Community LicenseInspect model →K2-Horizon-375B-A23BCore candidate · apache-2.0Inspect model →MiMo-V2.6-Pro-RLCore candidate · mitInspect model →GLM-5.3Core candidate · otherInspect model →Kimi-K3Core candidate · otherInspect model →GLM-5.3-FlashCore candidate · mitInspect model →DeepSeek-V4.1-FlashCore candidate · mitInspect model →Qwen3.8-27BCore candidate · apache-2.0Inspect model →InklingCore candidate · apache-2.0Inspect model →NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16Core candidate · otherInspect model →Muse-Glimmer-30BCore candidate · apache-2.0Inspect model →gpt-oss-120bCore candidate · apache-2.0Inspect model →gemma-4-26B-A4B-itCore candidate · apache-2.0Inspect model →Mistral Small 4 119B A6BCore candidate · apache-2.0Inspect model →Olmo-3-7B-ThinkCore candidate · apache-2.0Inspect model →K2-Horizon-3.7BCore candidate · apache-2.0Inspect model →K2-Horizon-MoVA-36B-A4BCore candidate · apache-2.0Inspect model →clef-omniSupporting component · apache-2.0Inspect model →pplx-embed-v2-late-0.6bSupporting component · mitInspect model →pplx-embed-v2-late-9bSupporting component · mitInspect model →Darwin-27B-ZTCSupporting component · apache-2.0Inspect model →Granite 4.2 30BCore candidate · apache-2.0Inspect model →LightOnOCR-3-4BSupporting component · apache-2.0Inspect model →
Reference architecture
Documents & permissions→Extraction & embeddings→Access-filtered retrieval→Generation & grounded citations
Every step needs its own provenance, permissions and monitoring. An embedding checkpoint is not an answer-generation model.
COMMON QUESTIONS
Frequently asked questions
Can an embedding model act as the entire document agent?
No. It provides retrieval vectors or similarity signals. A separate controller and often a generation model are still needed.
Is RAG automatically GDPR-compliant?
No. Compliance depends on processing purposes, data flows, retention, permissions and legal obligations.
READ THE ORIGINALS
Documentation and primary sources
Evidence before recommendation
Neither an eligible model category nor an untested runtime implies demonstrated agent task success. For documented source claims, consult the capability evidence ledger and then apply deployment constraints in the selector.
Evaluate before deployment.
Model metadata is source-linked; agent task success, tool-call reliability and production readiness require separate tests.
Review the methodology → Return to the explorer →