Run a local CLI workflow with Ollama generation and local embeddings, without a Voyage API key.
• Ollama is installed and running locally.
• The llama3.2:3b model is already pulled in Ollama.
• vai nano setup has already completed successfully.
See the exact VAI command, the matching Voyage AI layer, and the MongoDB query shape behind the demo.
vai embed "Local inference keeps retrieval private, fast, and API-key free." --local --dimensions 256
The --local flag switches the command from hosted embeddings to the local voyage-4-nano bridge. That keeps the demo private, API-key free, and fast to re-run.
Share or copy this demo
Keep it lightweight. The prepared text stays behind the buttons.
Share
Copy
LinkedIn opens the share dialog and copies the prepared text so you can paste it in quickly.
The full walkthrough is included here so anyone can replay the demo exactly as published.
More shareable workflows from the same VAI demo library.
Compare fixed, sentence, and markdown chunking on the same sample document before any embedding or storage layer is introduced.
VAI command
vai chunk /tmp/sample.md --strategy markdown
Show Under the Hood
Prerequisites
The `vai` CLI is installed locally. No API key is required for chunking-only workflows.
Build a tiny Atlas-backed RAG chat flow using local nano embeddings and Ollama for generation.
VAI command
vai chat --db "$DEMO_DB" --collection "$DEMO_COLLECTION" --local --llm-provider ollama --llm-model "$OLLAMA_MODEL" --llm-base-url http://localhost:11434 --no-history --no-stream
Show Under the Hood
Prerequisites
Ollama is installed and running locally.
Walk through the core vai embedding commands: model discovery, embedding generation, explainers, and similarity.
VAI command
vai embed "What is MongoDB Atlas?"
Show Under the Hood
Prerequisites
A valid VOYAGE_API_KEY is set in the environment.
