Pipeline

MongoDB Atlas

Embeddings

RAG

End-to-End Atlas Pipeline

Run the full workflow in one command: create sample docs, chunk them, embed them, store them in Atlas, and auto-create the vector index.

MongoDB Atlas

API key

View Source Tape Open Docs

Prerequisites

• A valid VOYAGE_API_KEY is set in the environment.

• MongoDB Atlas is configured through MONGODB_URI or vai config set mongodb-uri.

Under the hood

See the exact VAI command, the matching Voyage AI layer, and the MongoDB query shape behind the demo.

vai pipeline /tmp/vai-demo-docs/ --db vai_demo --collection knowledge --create-index

This is the highest-leverage ingestion demo in the gallery: one command orchestrates chunking, embedding, Atlas writes, and optional vector index creation.

Share or copy this demo

Keep it lightweight. The prepared text stays behind the buttons.

Open canonical URL

Copy

LinkedIn opens the share dialog and copies the prepared text so you can paste it in quickly.

Exact commands

The full walkthrough is included here so anyone can replay the demo exactly as published.

$mkdir -p /tmp/vai-demo-docs

$echo 'MongoDB Atlas Vector Search enables semantic similarity search at scale.' > /tmp/vai-demo-docs/atlas.md

$echo 'Voyage AI embedding models convert text into high-dimensional vectors.' > /tmp/vai-demo-docs/embeddings.md

$echo 'Retrieval-Augmented Generation grounds LLM responses in your own documents.' > /tmp/vai-demo-docs/rag.md

$ls /tmp/vai-demo-docs/

$echo '=> vai pipeline: files -> chunk -> embed -> store in Atlas, one command'

$echo '=> each batch: POST /v1/embeddings model:voyage-4-large input_type:document'

$vai pipeline /tmp/vai-demo-docs/ --db vai_demo --collection knowledge --create-index

$echo '=> verifying documents landed in Atlas...'

$vai collections --db vai_demo

$echo '=> verifying vector search index was created...'

$vai index list --db vai_demo --collection knowledge

$echo '=> collection indexed and ready to query'

Related demos

More shareable workflows from the same VAI demo library.

Retrieval

Reranking

Featured

Two-Stage Retrieval With Reranking

Walk through the classic retrieval stack: embed the query, run Atlas vector search, rerank the candidates, then compare the result to a vector-only pass.

Atlas

API key

VAI command

vai query 'how does vector search work?' --db vai_demo --collection knowledge --model voyage-4-lite

Show Under the Hood

Prerequisites

A valid VOYAGE_API_KEY is set in the environment.

View DemoSource

RAG

Local Inference

Featured

Local RAG Chat With Ollama And Nano

Build a tiny Atlas-backed RAG chat flow using local nano embeddings and Ollama for generation.

Requires Ollama

Atlas

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.

View DemoSource

Chunking

Preprocessing

Chunking Strategies Before Embedding

Compare fixed, sentence, and markdown chunking on the same sample document before any embedding or storage layer is introduced.

Offline-capable

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.

View DemoSource