Skip to main content

ollama_embeddings

Generates vector embeddings from text, using the Ollama API.

This processor sends text to a large language model served by Ollama and generates a vector embedding for each message. By default it starts and runs a local Ollama server, or you can connect to an existing server using the server_address field.

# Config fields, showing default values
processor:
  label: ""
  ollama_embeddings:
    cache_directory: ""
    download_url: ""
    model: "" # No default (required)
    runner:
      batch_size: 0
      context_size: 0
      gpu_layers: 0
      threads: 0
      use_mmap: false
    server_address: ""
    text: ""

Examples​

Generate a vector embedding for the contents of each message using a local Ollama server.

processor:
  ollama_embeddings:
    model: nomic-embed-text

Fields​

cache_directory​

If server_address is not set, the directory used to download the Ollama binary and store the model cache.

Type: string
Default: ""

download_url​

If server_address is not set, the URL to download the Ollama binary from. By default this points to the official Ollama release for your platform.

Type: string
Default: ""

model​

The name of the Ollama LLM to use, for example nomic-embed-text, mxbai-embed-large, or all-minilm.

Type: string

runner​

Options for the model runner that are applied when the model is first loaded into memory.

Type: object

runner.batch_size​

The maximum number of requests to process in parallel.

Type: int
Default: 0

runner.context_size​

Sets the size of the context window used to generate the next token.

Type: int
Default: 0

runner.gpu_layers​

The number of model layers to offload to the GPU for computation.

Type: int
Default: 0

runner.threads​

The number of threads to use during generation.

Type: int
Default: 0

runner.use_mmap​

Map the model into memory. This is only supported on Unix systems.

Type: bool
Default: false

server_address​

The address of the Ollama server to use. Leave this field blank and the processor starts and runs a local Ollama server.

Type: string
Default: ""

text​

The text you want to create vector embeddings for. By default the processor submits the entire message payload as a string. This field supports interpolation functions.

Type: string
Default: ""