update OpenAI model ID from gpt-4.1-mini to gpt-5-mini-2025-08-07 across all files

Author: patrickfleith

README.md

@@ -103,7 +103,7 @@ config = ClassificationDatasetConfig(
 ```python
 # Create LLM providers
 providers = [
-    OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
+    OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
     AnthropicProvider(model_id="claude-3-5-haiku-latest"),
     GeminiProvider(model_id="gemini-2.0-flash")
 ]

datafast/examples/classification_trail_conditions_example.py

@@ -58,7 +58,7 @@
 
 # Set up providers
 providers = [
-    OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
+    OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
     AnthropicProvider(model_id="claude-3-5-haiku-latest")
 ]
 

datafast/examples/generic_pipeline_row_model_example.py

@@ -32,7 +32,7 @@
     question="Qu'est ce qui t'a plu?",
 
     # System fields
-    model_id="gpt-4",
+    model_id="gpt-5-mini-2025-08-07",
     language="fr"
 )
 

datafast/examples/inspect_dataset_example.py

@@ -46,7 +46,7 @@
 from datafast.llms import OpenAIProvider, AnthropicProvider, GeminiProvider
 
 providers = [
-    OpenAIProvider(model_id="gpt-4.1-nano"),
+    OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
     # Uncomment to use additional providers
     # AnthropicProvider(model_id="claude-3-5-haiku-latest"),
     # GeminiProvider(model_id="gemini-2.0-flash"),

datafast/examples/mcq_contextual_example.py

@@ -50,9 +50,9 @@ def main():
         output_file="mcq_ar6_contextual_dataset.jsonl",
     )
 
-    # 3. Initialize OpenAI provider with gpt-4.1-mini
+    # 3. Initialize OpenAI provider with gpt-5-mini-2025-08-07
     providers = [
-        OpenAIProvider(model_id="gpt-4.1-mini"),
+        OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
     ]
 
     # 4. Generate the dataset

datafast/examples/mcq_example.py

@@ -25,7 +25,7 @@ def main():
 
     # 2. Initialize LLM providers
     providers = [
-        OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
+        OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
         # AnthropicProvider(model_id="claude-3-5-haiku-latest"),
         # GeminiProvider(model_id="gemini-2.0-flash"),
     ]

datafast/examples/preference_dataset_example.py

@@ -44,10 +44,10 @@ def main():
     )
 
     # 2. Initialize LLM providers
-    question_gen_llm = OpenAIProvider(model_id="gpt-4.1-mini")
+    question_gen_llm = OpenAIProvider(model_id="gpt-5-mini-2025-08-07")
     chosen_response_gen_llm = AnthropicProvider(model_id="claude-3-7-sonnet-latest")
     rejected_response_gen_llm = GeminiProvider(model_id="gemini-2.0-flash")
-    judge_llm = OpenAIProvider(model_id="gpt-4.1")
+    judge_llm = OpenAIProvider(model_id="gpt-5-mini-2025-08-07")
 
     # 3. Generate the dataset
     dataset = PreferenceDataset(config)

datafast/examples/raw_text_space_engineering_example.py

@@ -42,7 +42,7 @@ def main():
 
     # 2. Create LLM providers with specific models
     providers = [
-        OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"), # You may want to use stronger models
+        OpenAIProvider(model_id="gpt-5-mini-2025-08-07"), # You may want to use stronger models
         AnthropicProvider(model_id="claude-3-5-haiku-latest"),
     ]
 

datafast/llms.py

@@ -242,7 +242,7 @@ def env_key_name(self) -> str:
 
     def __init__(
         self,
-        model_id: str = "gpt-4.1-mini-2025-04-14",
+        model_id: str = "gpt-5-mini-2025-08-07",
         api_key: str | None = None,
         temperature: float | None = None,
         max_completion_tokens: int | None = None,
@@ -252,7 +252,7 @@ def __init__(
         """Initialize the OpenAI provider.
 
         Args:
-            model_id: The model ID (defaults to gpt-4.1-mini-2025-04-14)
+            model_id: The model ID (defaults to gpt-5-mini-2025-08-07)
             api_key: API key (if None, will get from environment)
             temperature: The sampling temperature to be used, between 0 and 2. Higher values like 0.8 produce more random outputs, while lower values like 0.2 make outputs more focused and deterministic
             max_completion_tokens: An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
@@ -419,7 +419,7 @@ def env_key_name(self) -> str:
 
     def __init__(
             self,
-            model_id: str = "openai/gpt-4.1-mini",  # for default model
+            model_id: str = "openai/gpt-5-mini",  # for default model
             api_key: str | None = None,
             temperature: float | None = None,
             max_completion_tokens: int | None = None,
@@ -429,7 +429,7 @@ def __init__(
         """Initialize the OpenRouter provider.
 
         Args:
-            model_id: The model ID (defaults to openai/gpt-4.1-mini)
+            model_id: The model ID (defaults to openai/gpt-5-mini)
             api_key: API key (if None, will get from environment)
             temperature: Temperature for generation (0.0 to 1.0)
             max_completion_tokens: Maximum tokens to generate

docs/guides/generating_mcq_datasets.md

@@ -183,7 +183,7 @@ Configure one or more LLM providers to generate your dataset:
 
 ```python
 providers = [
-    OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
+    OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
     AnthropicProvider(model_id="claude-3-5-haiku-latest"),
     GeminiProvider(model_id="gemini-2.0-flash")
 ]
@@ -272,7 +272,7 @@ def main():
 
     # 2. Initialize LLM providers
     providers = [
-        OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
+        OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
         # Add more providers as needed
         # AnthropicProvider(model_id="claude-3-5-haiku-latest"),
         # GeminiProvider(model_id="gemini-2.0-flash"),