File size: 6,314 Bytes
96abbd8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
"""
Configuration file for simple RAG evaluation
Contains prompt templates and other settings
"""

from pathlib import Path

# ============================================
# Prompt Templates
# ============================================

# Default Gurobi prompt template
GUROBI_PROMPT = {
    "system": """You are a helpful Assistant with expertise in mathematical modeling and the Gurobi solver. When the User provides an OR question, you will analyze it, build a detailed mathematical model, and provide the Gurobi code to solve it.

Your response should follow these steps:
1. Carefully analyze the problem to identify decision variables, objective, and constraints.

2. Develop a complete mathematical model, explicitly defining:
    - Sets
    - Parameters
    - Decision Variables (and their types)
    - Objective Function
    - Constraints
3. Provide the corresponding Gurobi Python code to implement the model.

Implementation guardrails:
- Use `gurobipy` exclusively (avoid cvxpy/pulp/copty imports).
- When indexing tupledict variables across periods, introduce an explicit sentinel index (e.g., period 0) for initial conditions instead of accessing undefined keys like `x[-1]`.
- Define any Big-M constants explicitly using bounds derived from the data before they appear in constraints.
- Keep the model linear/integer; if a relationship seems non-linear, introduce auxiliary variables and linearization rather than exponentiation or log constraints.
- Always ensure every symbol referenced in constraints/objective (such as `M`, helper dictionaries, etc.) is declared in the code block.
""",
    "user": """Problem:
{question}

Provide a complete solution with mathematical model and Gurobi code.
"""
}

# ============================================
# Model Configuration
# ============================================

# Supported models and their default temperatures
MODEL_CONFIGS = {
    "gpt-4o": {"temperature": 0.01, "max_tokens": 8192},
    "gpt-4o-mini": {"temperature": 0.01, "max_tokens": 8192},
    "deepseek-chat": {"temperature": 0.01, "max_tokens": 8192},
    "gemini-2.0-flash-exp": {"temperature": 0.01, "max_tokens": 8192},
    "gemini-2.5-pro": {"temperature": 0.01, "max_tokens": 8192},
}

# ============================================
# Evaluation Configuration
# ============================================

EVAL_CONFIG = {
    # Execution settings
    "timeout": 60,  # seconds
    "max_retries": 3,
    
    # Answer comparison settings
    "tolerance": 0.05,  # 5% relative tolerance by default
    "use_relative_tolerance": True,
    "absolute_tolerance": 1e-3,  # for zero objective values
    
    # Output settings
    "save_code": True,
    "save_output": False,  # whether to save stdout/stderr
    "verbose": False,
}

# ============================================
# Dataset Configuration
# ============================================

# Supported datasets
DATASETS = [
    "ComplexLP",
    "EasyLP",
    "IndustryOR",
    "NL4OPT",
    "NLP4LP",
    "ReSocratic",
    "ComplexOR",
    "OPT-Principled",
]

DATASET_ALIASES = {
    "complexlp_clean": "ComplexLP",
    "easylp_clean": "EasyLP",
    "industryor_clean": "IndustryOR",
    "industryor_v2": "IndustryOR",
    "industryor_fixedv2": "IndustryOR",
    "industryor_fixedv2_clean": "IndustryOR",
    "nl4opt": "NL4OPT",
    "nl4opt_clean": "NL4OPT",
    "nlp4lp_clean": "NLP4LP",
    "complexor_clean": "ComplexOR",
    "resocratic_clean": "ReSocratic",
    "combined": "OPT-Principled",
    "combined_dataset": "OPT-Principled",
    "opt-principled_clean": "OPT-Principled",
}

# Dataset-specific settings (if needed)
DATASET_CONFIG = {
    "ComplexLP": {"tolerance": 0.05},
    "EasyLP": {"tolerance": 0.01},
    "IndustryOR": {"tolerance": 0.05},
    "OPT-Principled": {"tolerance": 0.05},
}

# ============================================
# Utility Functions
# ============================================

def get_prompt_template(template_name="default"):
    """Get prompt template by name"""
    templates = {
        "default": GUROBI_PROMPT,
    }
    return templates.get(template_name, GUROBI_PROMPT)


def get_model_config(model_name):
    """Get configuration for a specific model"""
    return MODEL_CONFIGS.get(model_name, {"temperature": 0.01, "max_tokens": 8192})


def get_dataset_config(dataset_name):
    """Get configuration for a specific dataset"""
    return DATASET_CONFIG.get(normalize_dataset_name(dataset_name), {"tolerance": 0.05})


def normalize_dataset_name(dataset_name: str) -> str:
    """Map historical dataset names to the canonical OPEN benchmark names."""
    if not dataset_name:
        return dataset_name

    name = dataset_name.strip()
    if name.endswith(".jsonl"):
        name = name[:-6]

    alias = DATASET_ALIASES.get(name.casefold())
    if alias:
        return alias

    for canonical_name in DATASETS:
        if canonical_name.casefold() == name.casefold():
            return canonical_name

    if name.endswith("_clean"):
        base_name = name[:-6]
        for canonical_name in DATASETS:
            if canonical_name.casefold() == base_name.casefold():
                return canonical_name

    return name


def get_benchmark_dirs(project_root: Path) -> list[Path]:
    """Return benchmark directories in priority order for the migrated OPEN layout."""
    return [
        project_root.parent.parent / "data" / "benchmarks",
        project_root / "clean_benchmarks",
        project_root.parent / "clean_benchmarks",
    ]


def find_benchmark_path(project_root: Path, dataset_name: str) -> Path:
    """Locate the benchmark file for a dataset, accepting legacy names as input."""
    normalized_name = normalize_dataset_name(dataset_name)
    candidate_names = [normalized_name]
    raw_name = dataset_name[:-6] if dataset_name.endswith(".jsonl") else dataset_name
    if raw_name not in candidate_names:
        candidate_names.append(raw_name)

    for directory in get_benchmark_dirs(project_root):
        for name in candidate_names:
            candidate = directory / f"{name}.jsonl"
            if candidate.exists():
                return candidate

    raise FileNotFoundError(
        f"Dataset '{dataset_name}' not found. Checked directories: "
        f"{[str(path) for path in get_benchmark_dirs(project_root)]}"
    )