New Features 🌟
- **Add Keras Agents**: Intelli now supports the loading of offline open-source models using `KerasAgent`.
- **Supported Offline Models**: `gemma_2b_en`, `gemma_instruct_2b_en`, `gemma_7b_en`, `gemma_instruct_7b_en`, `mistral_7b_en`, `mistral_instruct_7b_en`.
Using the New Features 💻
To use the new Keras Agent, instantiate the `KerasAgent` class with the appropriate parameters:
python
from intelli.flow.agents.kagent import KerasAgent
Setting up a Gemma agent
gemma_params = {
"model": "gemma_instruct_2b_en",
"max_length": 200
}
gemma_agent = KerasAgent(agent_type="text",
mission="writing assistant",
model_params=gemma_params,
log=True)
Prepare the tasks with the user instructions:
python
from intelli.flow.input.task_input import TextTaskInput
from intelli.flow.tasks.task import Task
Sample task to write blog post
task1 = Task(
TextTaskInput("write blog post about electric cars"), gemma_agent, log=True
)
Create more tasks as needed
Execute tasks using `SequenceFlow`. The example below shows a single task, but you can include additional tasks for text, image, or vision:
python
from intelli.flow.sequence_flow import SequenceFlow
Start SequenceFlow
flow = SequenceFlow([task1], log=True)
final_result = flow.start()
Fore more details check [the docs](https://docs.intellinode.ai/docs/python/flows/kagent).