Skip to main content

​
mellea.backends.ollama

A model backend wrapping the Ollama Python SDK.

​
Functions

​
chat_response_delta_merge

chat_response_delta_merge(mot: ModelOutputThunk, delta: ollama.ChatResponse)
Merges the individual ChatResponse chunks from a streaming response into a single ChatResponse. Args:
  • mot: the ModelOutputThunk that the deltas are being used to populated.
  • delta: the most recent ollama ChatResponse.

​
Classes

​
OllamaModelBackend

A model that uses the Ollama Python SDK for local inference. Methods:

​
is_model_available

is_model_available(self, model_name)
Checks if a specific Ollama model is available locally. Args:
  • model_name: The name of the model to check for (e.g., “llama2”).
Returns:
  • True if the model is available, False otherwise.

​
generate_from_context

generate_from_context(self, action: Component | CBlock, ctx: Context)
See generate_from_chat_context.

​
generate_from_chat_context

generate_from_chat_context(self, action: Component | CBlock, ctx: Context) -> ModelOutputThunk
Generates a ModelOutputThunk. The final value for this object can be awaited. The new completion is generated from the provided Context using this backend’s Formatter. This implementation treats the Context as a chat history, and uses the ollama.Client.chat() interface to generate a completion. This will not always work, because sometimes we want to use non-chat models. Raises:
  • RuntimeError: If not called from a thread with a running event loop.

​
processing

processing(self, mot: ModelOutputThunk, chunk: ollama.ChatResponse, tools: dict[str, Callable])
Called during generation to add information from a single ChatResponse to the ModelOutputThunk.

​
post_processing

post_processing(self, mot: ModelOutputThunk, conversation: list[dict], tools: dict[str, Callable], format)
Called when generation is done.
⌘I