refactor: update core components to generalize prompt optimization

Author: heyjustinai

README.md

@@ -24,11 +24,11 @@
 
 
 
-prompt-ops is a Python package that **automatically optimizes prompts** for Llama models. It transforms prompts that work well with other LLMs into prompts that are optimized for Llama models, improving performance and reliability.
+prompt-ops is a Python package that **automatically optimizes prompts** for Llama models. It transforms prompts that work well with other LLMs into prompts that are optimized for LLM models, improving performance and reliability.
 
 **Key Benefits:**
 - **No More Trial and Error**: Stop manually tweaking prompts to get better results
-- **Fast Optimization**: Get Llama-optimized prompts in minutes with template-based optimization
+- **Fast Optimization**: Get model-optimized prompts in minutes with template-based optimization
 - **Data-Driven Improvements**: Use your own examples to create prompts that work for your specific use case
 - **Measurable Results**: Evaluate prompt performance with customizable metrics
 
@@ -66,7 +66,7 @@ To get started with prompt-ops, you'll need:
 2. [**Prepare your dataset**](#preparing-your-data): Create a JSON file with query-response pairs for evaluation and optimization
 3. **Configure optimization**: Set up a simple YAML file with your dataset and preferences (see [example configuration](configs/facility-simple.yaml))
 4. [**Run optimization**](#step-4-run-optimization): Execute a single command to transform your prompt
-5. [**Get results**](#prompt-transformation-example): Receive a Llama-optimized prompt with performance metrics
+5. [**Get results**](#prompt-transformation-example): Receive a model-optimized prompt with performance metrics
 
 
 ## Real-world Results

src/prompt_ops/core/migrator.py

@@ -25,7 +25,6 @@
 from .exceptions import EvaluationError, OptimizationError
 from .prompt_strategies import BaseStrategy
 from .utils import json_to_yaml_file
-from .utils.llama_utils import is_llama_model
 from .utils.logging import get_logger
 
 
@@ -73,31 +72,8 @@ def __init__(
         self.valset = valset
         self.testset = testset
 
-        # Determine if we're using a Llama model
-        if model_family is None and task_model is not None:
-            # Try to extract model name from task_model
-            if hasattr(task_model, "model_name"):
-                model_name = task_model.model_name
-            else:
-                model_name = str(task_model)
-
-            if is_llama_model(model_name):
-                self.model_family = "llama"
-            else:
-                logging.warning(
-                    f"Model '{model_name}' does not appear to be a Llama model. "
-                    f"This library is optimized for Llama models and may not work as expected."
-                )
-                self.model_family = (
-                    "llama"  # Default to Llama anyway since that's our focus
-                )
-        else:
-            self.model_family = model_family or "llama"
-            if self.model_family != "llama":
-                logging.warning(
-                    f"Model family '{self.model_family}' specified, but this library "
-                    f"is optimized for Llama models and may not work as expected."
-                )
+        # Set model family if provided (model-agnostic, no defaults)
+        self.model_family = model_family
 
         self._optimized_program = None
         self.logger = get_logger()
@@ -112,7 +88,6 @@ def optimize(
         file_path: str = None,
         save_yaml: bool = True,
         user_prompt: str = None,
-        use_llama_tips: bool = True,
     ) -> Any:
         """
         Optimize a prompt using the configured strategy.
@@ -136,14 +111,6 @@ def optimize(
         if "text" not in prompt_data:
             raise ValueError("prompt_data must contain a 'text' key.")
 
-        if use_llama_tips:
-            from .utils.llama_utils import get_llama_tips
-
-            model_tips = get_llama_tips()
-
-            if "model_tips" not in prompt_data:
-                prompt_data["model_tips"] = model_tips
-
         trainset = trainset if trainset is not None else self.trainset
         valset = valset if valset is not None else self.valset
         testset = testset if testset is not None else self.testset