sdg-hub 0.1.2__tar.gz → 0.1.3__tar.gz

{sdg_hub-0.1.2/src/sdg_hub.egg-info → sdg_hub-0.1.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.1.2
+Version: 0.1.3
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -36,7 +36,7 @@ Requires-Dist: flask>=3.0.2; extra == "web-interface"
 Requires-Dist: pyyaml>=6.0.1; extra == "web-interface"
 Requires-Dist: flask-wtf>=1.2.2; extra == "web-interface"
 Provides-Extra: vllm
-Requires-Dist: vllm<0.8.4,>=0.8.0; extra == "vllm"
+Requires-Dist: vllm>=0.9.1; extra == "vllm"
 Requires-Dist: torch>=2.0.0; extra == "vllm"
 Requires-Dist: transformers>=4.37.0; extra == "vllm"
 Requires-Dist: accelerate>=0.21.0; extra == "vllm"

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/pyproject.toml

@@ -55,7 +55,7 @@ web_interface = [
     "flask-wtf>=1.2.2",
 ]
 vllm = [
-    "vllm>=0.8.0,<0.8.4",
+    "vllm>=0.9.1",
     "torch>=2.0.0",
     "transformers>=4.37.0",
     "accelerate>=0.21.0",

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.1.2'
-__version_tuple__ = version_tuple = (0, 1, 2)
+__version__ = version = '0.1.3'
+__version_tuple__ = version_tuple = (0, 1, 3)

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/configs/annotations/simple_annotations.yaml

@@ -1,4 +1,4 @@
-system: null
+system: "You are a helpful assistant that annotates text."
 introduction: "Task Description: Data Annotation"
 principles: null
 examples: null

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/configs/knowledge/evaluate_relevancy.yaml

@@ -9,7 +9,7 @@ principles: |
   
   For each question, assign a score of 1 point if the response meets the criteria, and 0 points if it does not. After evaluating each question, provide detailed feedback explaining your reasoning behind the scores awarded.
 
-  Conclude your evaluation with a final result, strictly using the following format: 'Total Score: X'. The total score should represent the sum of points assigned for each question, with a maximum possible score of 2 points.
+  Conclude your evaluation with a total score as a final result. The total score should represent the sum of points assigned for each question, with a maximum possible score of 2 points.
   Only evaluate the response based on the above criteria, do not create new questions.
 
 examples: |
@@ -49,7 +49,6 @@ examples: |
   0
   [End of Score]
 
-
   Example 3:
   [Start of Question]
   What are the benefits of electric vehicles?

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/flow_runner.py

@@ -42,6 +42,7 @@ def run_flow(
     debug: bool = False,
     dataset_start_index: int = 0,
     dataset_end_index: Optional[int] = None,
+    api_key: Optional[str] = None,
 ) -> None:
     """Process the dataset using the specified configuration.
 
@@ -69,6 +70,8 @@ def run_flow(
         Start index for dataset slicing, by default 0.
     dataset_end_index : Optional[int], optional
         End index for dataset slicing, by default None.
+    api_key : Optional[str], optional
+        API key for the remote endpoint. If not provided, will use OPENAI_API_KEY environment variable, by default None.
 
     Returns
     -------
@@ -137,9 +140,9 @@ def run_flow(
             ) from e
 
         # Validate API configuration
-        openai_api_key = os.environ.get("OPENAI_API_KEY")
+        openai_api_key = api_key or os.environ.get("OPENAI_API_KEY")
         if not openai_api_key or openai_api_key == "EMPTY":
-            logger.warning("OPENAI_API_KEY not set or is 'EMPTY'. API calls may fail.")
+            logger.warning("API key not provided and OPENAI_API_KEY not set or is 'EMPTY'. API calls may fail.")
 
         openai_api_base = endpoint
         if not openai_api_base:
@@ -349,6 +352,12 @@ def run_flow(
 @click.option(
     "--dataset_end_index", type=int, default=None, help="End index of the dataset."
 )
+@click.option(
+    "--api_key",
+    type=str,
+    default=None,
+    help="API key for the remote endpoint. If not provided, will use OPENAI_API_KEY environment variable.",
+)
 def main(
     ds_path: str,
     bs: int,
@@ -361,6 +370,7 @@ def main(
     debug: bool,
     dataset_start_index: int,
     dataset_end_index: Optional[int],
+    api_key: Optional[str],
 ) -> None:
     """CLI entry point for running data generation flows.
 
@@ -388,6 +398,8 @@ def main(
         Start index for dataset slicing.
     dataset_end_index : Optional[int]
         End index for dataset slicing.
+    api_key : Optional[str]
+        API key for the remote endpoint. If not provided, will use OPENAI_API_KEY environment variable.
 
     Returns
     -------
@@ -406,6 +418,7 @@ def main(
             debug=debug,
             dataset_start_index=dataset_start_index,
             dataset_end_index=dataset_end_index,
+            api_key=api_key,
         )
     except (
         DatasetLoadError,

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/flows/generation/knowledge/mmlu_bench.yaml

@@ -2,7 +2,7 @@
   block_config:
     block_name: gen_mmlu_knowledge
     config_path: configs/knowledge/mcq_generation.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - mmlubench_question
       - mmlubench_answer

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/flows/generation/knowledge/simple_knowledge.yaml

@@ -2,7 +2,7 @@
   block_config:
     block_name: gen_knowledge
     config_path: configs/knowledge/simple_generate_qa.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - output
   gen_kwargs:

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/flows/generation/knowledge/synth_knowledge.yaml

@@ -2,7 +2,7 @@
   block_config:
     block_name: gen_knowledge
     config_path: configs/knowledge/generate_questions_responses.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - question
       - response
@@ -20,7 +20,7 @@
   block_config:
     block_name: eval_faithfulness_qa_pair
     config_path: configs/knowledge/evaluate_faithfulness.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - explanation
       - judgment
@@ -43,7 +43,7 @@
   block_config:
     block_name: eval_relevancy_qa_pair
     config_path: configs/knowledge/evaluate_relevancy.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - feedback
       - score
@@ -67,7 +67,7 @@
   block_config:
     block_name: eval_verify_question
     config_path: configs/knowledge/evaluate_question.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - explanation
       - rating

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub/flows/generation/knowledge/synth_knowledge1.5.yaml

@@ -8,7 +8,7 @@
   block_config:
     block_name: gen_detailed_summary
     config_path: configs/knowledge/detailed_summary.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - summary_detailed
   gen_kwargs:
@@ -20,7 +20,7 @@
   block_config:
     block_name: gen_atomic_facts
     config_path: configs/knowledge/atomic_facts.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - summary_atomic_facts
   gen_kwargs:
@@ -31,7 +31,7 @@
   block_config:
     block_name: gen_extractive_summary
     config_path: configs/knowledge/extractive_summary.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - summary_extractive
   gen_kwargs:
@@ -60,7 +60,7 @@
   block_config:
     block_name: knowledge generation
     config_path: configs/knowledge/generate_questions.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - question
     parser_kwargs:
@@ -74,7 +74,7 @@
   block_config:
     block_name: knowledge generation
     config_path: configs/knowledge/generate_responses.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - response
   gen_kwargs:
@@ -85,7 +85,7 @@
   block_config:
     block_name: eval_faithfulness_qa_pair
     config_path: configs/knowledge/evaluate_faithfulness.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - explanation
       - judgment
@@ -106,7 +106,7 @@
   block_config:
     block_name: eval_relevancy_qa_pair
     config_path: configs/knowledge/evaluate_relevancy.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - feedback
       - score
@@ -128,7 +128,7 @@
   block_config:
     block_name: eval_verify_question
     config_path: configs/knowledge/evaluate_question.yaml
-    model_id: mistralai/Mixtral-8x7B-Instruct-v0.1
+    model_id: meta-llama/Llama-3.3-70B-Instruct
     output_cols:
       - explanation
       - rating

{sdg_hub-0.1.2 → sdg_hub-0.1.3/src/sdg_hub.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sdg_hub
-Version: 0.1.2
+Version: 0.1.3
 Summary: Synthetic Data Generation
 Author-email: Red Hat AI Innovation <abhandwa@redhat.com>
 License: Apache-2.0
@@ -36,7 +36,7 @@ Requires-Dist: flask>=3.0.2; extra == "web-interface"
 Requires-Dist: pyyaml>=6.0.1; extra == "web-interface"
 Requires-Dist: flask-wtf>=1.2.2; extra == "web-interface"
 Provides-Extra: vllm
-Requires-Dist: vllm<0.8.4,>=0.8.0; extra == "vllm"
+Requires-Dist: vllm>=0.9.1; extra == "vllm"
 Requires-Dist: torch>=2.0.0; extra == "vllm"
 Requires-Dist: transformers>=4.37.0; extra == "vllm"
 Requires-Dist: accelerate>=0.21.0; extra == "vllm"

{sdg_hub-0.1.2 → sdg_hub-0.1.3}/src/sdg_hub.egg-info/requires.txt

@@ -24,7 +24,7 @@ langchain-text-splitters
 docling>=2.3.0
 
 [vllm]
-vllm<0.8.4,>=0.8.0
+vllm>=0.9.1
 torch>=2.0.0
 transformers>=4.37.0
 accelerate>=0.21.0