Tutorial — Multi-modal AI

Embed text with Qwen3-Embedding

Qwen3-Embedding 0.6B is the default permissive-licensed text embedder on Tenzro. EmbeddingGemma-300M adds Matryoshka truncation (768/512/256/128) when you want compact vectors with controlled quality loss.

Level: Beginner
Time: ~10 min
Prerequisites: Tenzro CLI installed
Stack: CLI · JSON-RPC

Load a text embedding model

Pick a model from the catalog. Qwen3-Embedding 0.6B is fast and permissive.

curl -X POST https://rpc.tenzro.network -H 'content-type: application/json'   -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_loadTextEmbeddingModel","params":["qwen3-embedding-0.6b"]}'

Embed a string

The runtime returns an L2-normalized vector ready for cosine similarity.

tenzro embed-text run \
  --model qwen3-embedding-0.6b \
  --input "the open network for autonomous AI" \
  --normalize

Use Matryoshka truncation

EmbeddingGemma supports compact dims with on-the-fly re-normalization — useful when you store millions of vectors.

tenzro embed-text run \
  --model embeddinggemma-300m \
  --input "compact vector for retrieval" \
  --requested-dim 256 \
  --normalize

Call from JSON-RPC

The same shape is available over RPC for integration into your own indexers.

curl -s https://rpc.tenzro.network -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_textEmbed","params":{"model":"qwen3-embedding-0.6b","text":"hello"}}'

Open the docs →Browse all tutorials

← All tutorials