Embed
Turn text into an embedding vector with the embed model you pick, the way the LLM picks its model. Fires on its trigger and emits the vector and a trigger for the next node.
Fired. It runs when an event or a value lands on trigger, and pulls its other inputs at that moment.
Inputs
Section titled “Inputs”| Port | Type | Notes |
|---|---|---|
trigger |
event | Fires the node |
text |
text |
Outputs
Section titled “Outputs”| Port | Type | Notes |
|---|---|---|
embedding |
embedding | |
trigger |
event |
| Knob | Kind | Default | Notes |
|---|---|---|---|
model |
model | none | stays a knob (cannot become an input) |
Models that ship with Boltjar
Section titled “Models that ship with Boltjar”The picker lists the models of this kind installed in Ollama, read live, whether or not a manifest describes them. The ones below ship with a manifest, which adds a label, settings and what the model can do. Picking a model adds its own settings to the node as knobs, and each of those can become an input. Models explains when the list refreshes and how manifests work.
| Model | Id | Needs | Can |
|---|---|---|---|
| bge-m3 (Ollama) | ollama/bge-m3 |
Ollama |
Example
Section titled “Example”Turns text into a vector with a local model through Ollama. The default is bge-m3, which you add with ollama pull bge-m3. Fire trigger, and embedding goes into a Vectors node to index or search. If Ollama is not running, embedding comes out empty and a search finds nothing. If Ollama runs without the model, the graph stays Off, and its problems list says to pull the model in Connections.