Merge pull request #122 from patrickfleith/release/0.0.27

Release/0.0.27

Author: patrickfleith

README.md

@@ -103,8 +103,8 @@ config = ClassificationDatasetConfig(
 ```python
 # Create LLM providers
 providers = [
-    OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
-    AnthropicProvider(model_id="claude-3-5-haiku-latest"),
+    OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     GeminiProvider(model_id="gemini-2.0-flash")
 ]
 ```

datafast/examples/classification_trail_conditions_example.py

@@ -58,8 +58,8 @@
 
 # Set up providers
 providers = [
-    OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
-    AnthropicProvider(model_id="claude-3-5-haiku-latest")
+    OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
+    AnthropicProvider(model_id="claude-haiku-4-5-20251001")
 ]
 
 # Generate dataset

datafast/examples/generic_pipeline_example.py

@@ -42,7 +42,7 @@ def main():
             model_id="gpt-5-mini-2025-08-07",
             temperature=1
             ),
-        # AnthropicProvider(model_id="claude-3-5-haiku-latest"),
+        # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
         # GeminiProvider(model_id="gemini-2.5-flash-lite", rpm_limit=15),
         # OllamaProvider(model_id="gemma3:4b"),
     ]

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

@@ -46,9 +46,9 @@
 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"),
+    # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     # 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

@@ -25,8 +25,8 @@ def main():
 
     # 2. Initialize LLM providers
     providers = [
-        OpenAIProvider(model_id="gpt-4.1-mini-2025-04-14"),
-        # AnthropicProvider(model_id="claude-3-5-haiku-latest"),
+        OpenAIProvider(model_id="gpt-5-mini-2025-08-07"),
+        # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
         # 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/quickstart_example.py

@@ -35,7 +35,7 @@
 
 providers = [
     OpenAIProvider(model_id="gpt-5-nano-2025-08-07"),
-    # AnthropicProvider(model_id="claude-3-5-haiku-latest"),
+    # AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     # GeminiProvider(model_id="gemini-2.0-flash"),
     # OllamaProvider(model_id="gemma3:12b")
 ]

datafast/examples/raw_text_space_engineering_example.py

@@ -42,8 +42,8 @@ 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
-        AnthropicProvider(model_id="claude-3-5-haiku-latest"),
+        OpenAIProvider(model_id="gpt-5-mini-2025-08-07"), # You may want to use stronger models
+        AnthropicProvider(model_id="claude-haiku-4-5-20251001"),
     ]
 
     # 3. Generate the dataset