节点 / builtin / ai / aidependencies / embeddings
Ollama Embeddings
Turn text into embeddings with a model running in Ollama.
此内容尚不支持你的语言。
Turn text into vectors with an embedding model running in Ollama on your computer: free, private, no API key.
What it does
Section titled “What it does”Ollama Embeddings plugs into the Embeddings slot of a Local Knowledge node. It does not run on its own and has no output. When the knowledge base is filled or searched, the text goes to the Ollama app on your computer, at http://localhost:11434, and comes back as vectors (lists of numbers that capture meaning). Nothing leaves your machine.
A knowledge base remembers the embedding model it was built with and always uses it. So this node decides the model when a new, empty knowledge base is first filled. After that, connect the same node to search it.
When to use it
Section titled “When to use it”- You already run Ollama and want a specific open embedding model, such as
nomic-embed-text. - Private documents that must not go to a cloud service, with a model you choose in Ollama.
With nothing to install, Local Embeddings also runs on your device.
Inputs and settings
Section titled “Inputs and settings”| 设置项 | 类型 | 作用 |
|---|---|---|
| Model （必填） | Model picker | The model to use. |
The Model list shows the models installed in your Ollama; use the refresh button after you pull a new one. Pick an embedding model (for example after ollama pull nomic-embed-text), not a chat model.
Ollama must allow AWFlow to call it. Start it with:
- Chrome:
OLLAMA_ORIGINS=chrome-extension://linlkeaipfpnhddjkpcbmldionajfifa ollama serve - Firefox:
OLLAMA_ORIGINS=moz-extension://* ollama serve
When you publish or share the workflow, Model is cleared, so whoever installs it picks a model from their own Ollama.
Outputs
Section titled “Outputs”This node has no output port. It plugs into a slot on another node instead of passing items along.
- Embeddings slot of Local Knowledge
The vectors go to the knowledge base, not to the next node.
Dependencies and credentials
Section titled “Dependencies and credentials”None. This node needs no connection and has no slots for other nodes.
Example workflow
Section titled “Example workflow”- A Context Menu trigger on the page.
- Get All Text with Output field name
pageText. - Indexer with Input
{{ $input.pageText }}, a Recursive Character Text Splitter in its Text Splitter slot, and a Local Knowledge pointing to a new knowledge base in its Knowledge slot. - Ollama Embeddings in the Local Knowledge’s Embeddings slot, Model
nomic-embed-text:latest.
Common issues
Section titled “Common issues”- “Could not reach Ollama at localhost:11434. Make sure it is running and allows this extension (OLLAMA_ORIGINS).” Start Ollama, and restart it with
OLLAMA_ORIGINSset as shown above. - The list says “No models available”. Pull an embedding model, then press the refresh button.
- “… was built with … embeddings. Connect that embeddings node to use it.” The knowledge base was built with this Ollama model. Connect Ollama Embeddings with the same Model, and make sure Ollama is running.
- A “Model mismatch” warning in the run log. The knowledge base was built with another model, so this node was ignored. Disconnect it, or re-embed the knowledge base from its settings.
Related nodes
Section titled “Related nodes”- Ollama: Ollama chat models for your agents.
- Local Knowledge: the knowledge base it plugs into.
- Local Embeddings: in-browser embeddings, nothing to install.