Individual skill
orchardcore-ai-documents
Skill for CrestApps AI Documents in Orchard Core 4.0 (CrestApps.OrchardCore 3.0). Covers document upload, text and figure extraction, chunking, embedding and RAG for chat interactions, AI profiles, profile templates, chat sessions and widgets, the AI Documents index with its embedding deployment, InteractionDocumentSettings and DocumentsMetadata, Chunk and Hierarchical retrieval, the largest indexable document, figure descriptions with the vision slot, upload scanning through Orchard Core FileCreationService and ClamAV, file storage, document cleanup, the PowerPoint, Word and PDF agents, and IAIChatDocumentEventHandler. Use it for CrestApps.OrchardCore.AI.Documents, CrestApps.OrchardCore.AI.Documents.ChatInteractions, CrestApps.OrchardCore.AI.Documents.Profiles, CrestApps.OrchardCore.AI.Documents.ChatSessions, IAIDocumentStore, IDocumentFileStore, IVectorSearchService, IUploadedFileScanner, OrchardUploadedFileScanner, and AIProfileSessionDocumentsMetadata.
plugins/crestapps-orchardcore/skills/orchardcore-ai-documents/SKILL.md
Source commit d86d04f234b1b2bd8145368a2544490f9d557596
What was checked
- Matches the observed repository HEAD
- Yes
- Scanner rules are current
- Yes
- Repository scan complete
- No
- Skill scan complete
- No
- Observed behavior
- Instructions only
- Last checked
- Nov 6, 2026
These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.
Install this skill
Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.
An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.
Repository context
- Repository stars (not skill ratings)
- 13
- Repository last updated
- Oct 21, 2026
- License
- MIT
Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.
- agent-skills Repository topic
- ai Repository topic
- ai-agents-framework Repository topic
- dotnet Repository topic
- mcp Repository topic
- mcp-server Repository topic
- orchardcore Repository topic
- devops Derived category
Files and excerpt
File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.
Read excerpt
# Orchard Core AI Documents
## Configure document upload and RAG
You are an Orchard Core expert. Generate configuration, recipes, and code that let users and administrators attach documents to CrestApps AI chat surfaces, and let the model retrieve from them.
### Guidelines
- The base feature `CrestApps.OrchardCore.AI.Documents` is `EnabledByDependencyOnly`. It depends on `CrestApps.OrchardCore.AI.Chat.Interactions` and `OrchardCore.Indexing`, and comes along with any of the sub-features below.
- Embeddable documents follow upload, scan, extract, chunk, embed, index, and vector search. Tabular files (`.csv`, `.tsv`, `.xlsx`, `.xls`) are non-embeddable; they are loaded into the conversation's tabular workspace instead.
- Indexing needs an **AI Documents** index profile from `CrestApps.OrchardCore.AI.Documents.Elasticsearch` or `CrestApps.OrchardCore.AI.Documents.AzureAI` (see `orchardcore-ai-documents-elasticsearch` and `orchardcore-ai-documents-azureai`).
- The AI Documents index names its embedding deployment. The picker lists deployments in the `embedding` slot, so the deployment must declare `textEmbedding`. It is locked once the index exists.
- Pick the active index once. Changing it later loses access to documents of existing sessions.
- PDF and Office formats need the extractor features (see `orchardcore-ai-documents-extractors`). Azure Blob Storage is optional (see `orchardcore-ai-documents-azure-storage`).