commander - using ornith-ai/Ornith-1.0-9B-GGUF as the model and documenting the results

 After trying out a couple of model, I decides to see if using a different model would sway the results differently. I am using ornith-ai/Ornith-1.0-9B-GGUF. model here.  Noticed that I have added "openai" in front of the model name otherwise it throw an error message.

import os

from dotenv import load_dotenv

from google.adk.agents import LlmAgent

from google.adk.models.lite_llm import LiteLlm

from google.adk.tools import google_search

# Create a LiteLLM model pointing to your local server

model = LiteLlm(

    model="openai/ornith-ai/Ornith-1.0-9B-GGUF",

    api_base="http://localhost:8888/v1",  # Your local server

    api_key="sk-unsloth-4d0a1b198bd177a2a72ee1954585342a" ,

    temperature=0.0

)

from app.prompt import ROOT_AGENT_INSTRUCTION

from app.tools.container_toolset import (

    container_image_finder_tool, run_container_command_tool

)

load_dotenv()

root_agent = LlmAgent(

    name="commander",

    description="Agent that read, understand and execute commands specified in a README or external HTTPS URL document.",

    model=model,

    instruction="You are a command execution agent. You are given a README.",

    tools=[container_image_finder_tool, run_container_command_tool]

)

This is my README-test.md file which contains a node command. So technically we should be using a nodejs image to run this.

# Hello Test

Run these commands to verify the setup.

```bash

echo "hello from the container"

uname -a

node -v

echo "complete"

```

```bash

echo "hello 222222"

```

And let's look at the results, ornith is not able to follow the instructions to read from start to end and then dertermine the image to use. 

Here is the output from the command line. I did run it a couple of times to ensure it is not a one time thingie. 

As you can see here, it tries and use 'ubuntu' image.

Learnings - So different model behaves differently and often require extensive testing before we can row this out. 

Troubleshooting tips

Getting this error during runtime - thene we need to use 

 model="openai/ornith-ai/Ornith-1.0-9B-GGUF instead of 

 model="ornith-ai/Ornith-1.0-9B-GGUF".

Error message

litellm.exceptions.BadRequestError: litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider you are trying to call. You passed model=ornith-ai/Ornith-1.0-9B-GGUF' litellm.exceptions.BadRequestError:' is not recognized as an internal or external command, operable program or batch file'.