Chaining optimizers

Some projects benefit from running two or more optimizers back-to-back. For example, use MetaPrompt to improve wording, then Parameter optimizer to fine-tune sampling settings. This guide explains why you might chain runs, the trade-offs, and the APIs you use to pass prompts and metadata between stages.

Strategy patterns

Example pipeline

1
from opik_optimizer import MetaPromptOptimizer, ParameterOptimizer, ChatPrompt
2
from opik_optimizer.parameter_optimizer import ParameterSearchSpace
3
4
meta = MetaPromptOptimizer(model="openai/gpt-4o")
5
parameter = ParameterOptimizer(model="openai/gpt-4o")
6
7
meta_result = meta.optimize_prompt(
8
    prompt=prompt,
9
    dataset=dataset,
10
    metric=metric,
11
    max_trials=4,
12
)
13
14
# Reuse the optimized prompt from the first stage
15
optimized_prompt = prompt.with_messages(meta_result.prompt)
16
17
search_space = ParameterSearchSpace(parameters=[
18
    {"name": "temperature", "distribution": "float", "low": 0.1, "high": 0.9},
19
    {"name": "top_p", "distribution": "float", "low": 0.7, "high": 1.0},
20
])
21
22
final_result = parameter.optimize_parameter(
23
    prompt=optimized_prompt,
24
    dataset=dataset,
25
    metric=metric,
26
    parameter_space=search_space,
27
    max_trials=20,
28
)

Checklist

• Freeze datasets and metrics between stages to keep comparisons fair.
• Use validation datasets consistently – if you provide a validation_dataset in the first stage, use the same split in subsequent stages to ensure fair comparison and avoid overfitting.
• Log pipeline metadata (e.g., experiment_config={"pipeline": "hierarchical_then_param"}) so dashboards show lineage.
• Budget tokens – chained runs multiply costs; start with smaller n_samples and increase once results look promising.
• Reuse OptimizationResult – every optimizer returns an OptimizationResult, so you can pass result.prompt (and result.details, result.history) directly into the next stage without rebuilding state.

Automation tips

• Use Makefiles or CI workflows to run stage 1 → stage 2 with clear checkpoints.
• Store intermediate prompts in version control alongside metadata (optimizer, score, dataset).
• Notify stakeholders with summary reports generated from final_result.history.

Related docs

• Optimize prompts
• Few-Shot Bayesian optimizer
• HRPO (Hierarchical Reflective Prompt Optimizer)
• Parameter optimizer