Document RAG Using CLI
Description
Use command-line tools to build Document RAG workflows
Difficulty
Beginner
Duration
15 min
You will need
- TrustGraph deployed (Quick Start)
- Familiarity with Document RAG concepts
Goal
Use CLI tools to load documents, create Document RAG flows, and query using vector similarity search.
This guide covers the same Document RAG workflow as the Document RAG guide, but using command-line tools instead of the Workbench.
New to Document RAG? Read the Document RAG guide first to understand the concepts and limitations.
This guide demonstrates:
- Loading documents via CLI
- Creating Document RAG flows
- Querying with vector search
Step-by-Step Guide
Step 1: Load Your Document
Download and load the example document:
wget -O phantom-cargo.md https://raw.githubusercontent.com/trustgraph-ai/example-data/refs/heads/main/tracking/operation-phantom-cargo.md
tg-add-library-document \
--name "PHANTOM CARGO" \
--description "Intelligence report: Operation PHANTOM CARGO" \
--tags 'maritime,intelligence,cargo,grey arms' \
--id https://trustgraph.ai/doc/phantom-cargo \
--kind text/plain \
phantom-cargo.md
Step 2: Create a Collection
Create an ‘intelligence’ collection:
tg-set-collection -n Intelligence -d 'Intelligence analysis' intelligence
Step 3: Create the Flow
Create a Document RAG flow:
tg-start-flow -n document-rag -i doc-rag -d "Document RAG"
Step 4: Submit the Document for Processing
Submit the document for processing:
tg-start-library-processing \
--flow-id doc-rag \
--document-id https://trustgraph.ai/doc/phantom-cargo \
--collection intelligence \
--processing-id urn:processing-01
Step 5: Monitoring (Optional)
Processing is fast for Document RAG. For monitoring details, see the Document RAG guide monitoring section.
Step 6: Query with Document RAG
Query using vector similarity search:
tg-invoke-document-rag \
-f doc-rag -C intelligence \
-q 'What is the PHANTOM CARGO report about?'
Expected output:
The PHANTOM CARGO report is about an operation that detected unusual shipping
patterns involving a Dubai-based freight company, Meridian Logistics LLC...
Next Steps
Related CLI Commands
tg-add-library-document- Add documents to librarytg-set-collection- Create collectionstg-start-flow- Start processing flowstg-invoke-document-rag- Query with Document RAG
Other Guides
- Document RAG (Workbench) - Full walkthrough with concepts and limitations
- Graph RAG - Leverage knowledge graph relationships
- Ontology RAG - Use structured schemas for extraction
- Troubleshooting - Common issues