ollama_chat

Beta

Available in: Self-Managed

License: This component requires an enterprise license. You can either upgrade to an Enterprise Edition license, or generate a trial license key that's valid for 30 days.

Generates responses to messages in a chat conversation using the Ollama API and external tools.

Introduced in version 4.32.0.

  • Common

  • Advanced

# Common configuration fields, showing default values
label: ""
ollama_chat:
  model: llama3.1 # No default (required)
  prompt: "" # No default (optional)
  image: 'root = this.image.decode("base64")' # Decode base64 encoded image. No default (optional)
  response_format: text
  max_tokens: 0 # No default (optional)
  temperature: 0 # No default (optional)
  save_prompt_metadata: false
  tools: [] # No default (required)
  runner:
    context_size: 0 # No default (optional)
    batch_size: 0 # No default (optional)
  server_address: http://127.0.0.1:11434 # No default (optional)
# All configuration fields, showing default values
label: ""
ollama_chat:
  model: llama3.1 # No default (required)
  prompt: "" # No default (optional)
  system_prompt: "" # No default (optional)
  image: 'root = this.image.decode("base64")' # Decode base64 encoded image. No default (optional)
  response_format: text
  max_tokens: 0 # No default (optional)
  temperature: 0 # No default (optional)
  num_keep: 0 # No default (optional)
  seed: 42 # No default (optional)
  top_k: 0 # No default (optional)
  top_p: 0 # No default (optional)
  repeat_penalty: 0 # No default (optional)
  presence_penalty: 0 # No default (optional)
  frequency_penalty: 0 # No default (optional)
  stop: [] # No default (optional)
  save_prompt_metadata: false
  max_tool_calls: 3
  tools: [] # No default (required)
  runner:
    context_size: 0 # No default (optional)
    batch_size: 0 # No default (optional)
    gpu_layers: 0 # No default (optional)
    threads: 0 # No default (optional)
    use_mmap: false # No default (optional)
    use_mlock: false # No default (optional)
  server_address: http://127.0.0.1:11434 # No default (optional)
  cache_directory: /opt/cache/connect/ollama # No default (optional)
  download_url: "" # No default (optional)

This processor sends prompts to your chosen Ollama large language model (LLM) and generates text from the responses using the Ollama API and external tools.

By default, the processor starts and runs a locally-installed Ollama server. Alternatively, to use an already running Ollama server, add your server details to the server_address field. You can download and install Ollama from the Ollama website.

For more information, see the Ollama documentation and examples.

Fields

model

The name of the Ollama LLM to use. For a full list of models, see the Ollama website.

Type: string

# Examples

model: llama3.1

model: gemma2

model: qwen2

model: phi3

prompt

The prompt you want to generate a response for. By default, the processor submits the entire payload as a string. This field supports interpolation functions.

Type: string

system_prompt

The system prompt to submit to the Ollama LLM. This field supports interpolation functions.

Type: string

image

An optional image to submit along with the prompt value. The result is a byte array.

Type: bloblang

# Examples

image: 'root = this.image.decode("base64")' # Decode base64 encoded image

response_format

The format of the response the Ollama model generates. If specifying JSON output, then the prompt should specify that the output should be in JSON as well.

Type: string

Default: "text"

Options: text , json .

max_tokens

The maximum number of tokens to predict and output. Limiting the amount of output means that requests are processed faster and have a fixed limit on the cost.

Type: int

temperature

The temperature of the model. Increasing the temperature makes the model answer more creatively.

Type: int

num_keep

Specify the number of tokens from the initial prompt to retain when the model resets its internal context. By default, this value is set to 4. Use -1 to retain all tokens from the initial prompt.

Type: int

seed

Sets the random number seed to use for generation. Setting this to a specific number will make the model generate the same text for the same prompt.

Type: int

# Examples

seed: 42

top_k

Reduces the probability of generating nonsense. A higher value, for example 100, will give more diverse answers. A lower value, for example 10, will be more conservative.

Type: int

top_p

Works together with top-k. A higher value, for example 0.95, will lead to more diverse text. A lower value, for example 0.5, will generate more focused and conservative text.

Type: float

repeat_penalty

Sets how strongly to penalize repetitions. A higher value, for example 1.5, will penalize repetitions more strongly. A lower value, for example 0.9, will be more lenient.

Type: float

presence_penalty

Positive values penalize new tokens if they have appeared in the text so far. This increases the model’s likelihood to talk about new topics.

Type: float

frequency_penalty

Positive values penalize new tokens based on the frequency of their appearance in the text so far. This decreases the model’s likelihood to repeat the same line verbatim.

Type: float

stop

Sets the stop sequences to use. When this pattern is encountered, the LLM stops generating text and returns the final response.

Type: array

save_prompt_metadata

Set to true to save the prompt value to a metadata field (@prompt) on the corresponding output message. If you use the system_prompt field, its value is also saved to an @system_prompt metadata field on each output message.

Type: bool

Default: false

max_tool_calls

The maximum number of sequential calls you can make to external tools to retrieve additional information to answer a prompt.

Type: int

Default: 3

tools

The external tools the LLM can invoke, such as functions, APIs, or web browsing. You can build a series of processors that include definitions of these tools, and the specified LLM can choose when to invoke them to help answer a prompt. For more information, see examples.

Type: string

tools[].name

The name of the external tool you want to use.

Type: string

tools[].description

A description of what the tool does. The LLM uses this to decide when to invoke the tool.

Type: string

tools[].parameters

The parameters the LLM needs to provide to invoke the tool.

Type: object

tools[].parameters.required

The parameters you must define.

Type: array

Default: []

tools[].parameters.properties

The required inputs to invoke the tool.

Type: object

tools[].parameters.properties.<name>.type

The data type of the parameter.

Type: string

tools[].parameters.properties.<name>.description

A description of the parameter.

Type: string

tools[].parameters.properties.<name>.enum

Sets this parameter to a enum, and defines the specific set of values the LLM must use.

Type: array

Default: []

tools[].processors

The Redpanda Connect processors to execute when the LLM invokes the external tool.

Type: array

runner

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

Type: object

runner.context_size

Sets the size of the context window used to generate the next token. Using a larger context window uses more memory and takes longer to process.

Type: int

runner.batch_size

The maximum number of requests to process in parallel.

Type: int

runner.gpu_layers

This option allows offloading some layers to the GPU for computation. This generally results in increased performance. By default, the runtime decides the number of layers dynamically.

Type: int

runner.threads

Set the number of threads to use during generation. For optimal performance, it is recommended to set this value to the number of physical CPU cores your system has. By default, the runtime decides the optimal number of threads.

Type: int

runner.use_mmap

Map the model into memory. This is only support on unix systems and allows loading only the necessary parts of the model as needed.

Type: bool

runner.use_mlock

Lock the model in memory, preventing it from being swapped out when memory-mapped. This option can improve performance but reduces some of the advantages of memory-mapping because it uses more RAM to run and can slow down load times as the model loads into RAM.

Type: bool

server_address

The address of the Ollama server to use. Leave the field blank and the processor starts and runs a local Ollama server or specify the address of your own local or remote server.

Type: string

# Examples

server_address: http://127.0.0.1:11434

cache_directory

If server_address is not set - the directory to download the Ollama binary and use as a model cache.

Type: string

# Examples

cache_directory: /opt/cache/connect/ollama

download_url

If server_address is not set - the URL to download the Ollama binary from. Defaults to the official Ollama GitHub release for this platform.

Type: string

Examples

  • Analyze an image and generate a description for it

  • Use a series of processors to make calls to external tools

This configuration fetches image URLs from stdin and uses the LLaVA LLM to describe the images.

input:
  stdin:
    scanner:
      lines: {}
pipeline:
  processors:
    - http:
        verb: GET
        url: "${!content().string()}"
    - ollama_chat:
        model: llava
        prompt: "Describe the following image"
        image: "root = content()"
output:
  stdout:
    codec: lines

In this configuration, the LLama 3.2 model executes a number of processors, which make a tool call to retrieve weather data for a specific city.

input:
  generate:
    count: 1
    mapping: |
      root = "What is the weather like in Chicago?"
pipeline:
  processors:
    - ollama_chat:
        model: llama3.2
        prompt: "${!content().string()}"
        tools:
          - name: GetWeather
            description: "Retrieve the weather for a specific city"
            parameters:
              required: ["city"]
              properties:
                city:
                  type: string
                  description: the city to look up the weather for
            processors:
              - http:
                  verb: GET
                  url: 'https://wttr.in/${!this.city}?T'
                  headers:
                    User-Agent: curl/8.11.1 # Returns a text string from the weather website
output:
  stdout: {}