fix vaious issues (#99)

src/autogluon_assistant/assistant.py

@@ -1,5 +1,4 @@
 import logging
-import os
 import signal
 from typing import Any, Dict, Union
 
@@ -102,15 +101,7 @@ def preprocess_task(self, task: TabularPredictionTask) -> TabularPredictionTask:
         task = self.inference_task(task)
         if self.feature_transformers_config:
             logger.info("Automatic feature generation starts...")
-            if "OPENAI_API_KEY" not in os.environ:
-                logger.info("No OpenAI API keys found, therefore, skip CAAFE")
-                fe_transformers = [
-                    instantiate(ft_config)
-                    for ft_config in self.feature_transformers_config
-                    if ft_config["_target_"] != "autogluon_assistant.transformer.CAAFETransformer"
-                ]
-            else:
-                fe_transformers = [instantiate(ft_config) for ft_config in self.feature_transformers_config]
+            fe_transformers = [instantiate(ft_config) for ft_config in self.feature_transformers_config]
             for fe_transformer in fe_transformers:
                 try:
                     with timeout(
@@ -122,7 +113,7 @@ def preprocess_task(self, task: TabularPredictionTask) -> TabularPredictionTask:
                     self.handle_exception(f"Task preprocessing: {fe_transformer.name}", e)
             logger.info("Automatic feature generation complete!")
         else:
-            logger.info("Automatic feature generation is disabled.")
+            logger.info("Automatic feature generation is disabled. ")
         return task
 
     def fit_predictor(self, task: TabularPredictionTask):

src/autogluon_assistant/constants.py

@@ -71,3 +71,10 @@
     MULTICLASS: ROC_AUC,
     REGRESSION: ROOT_MEAN_SQUARED_ERROR,
 }
+
+WHITE_LIST_LLM = [
+    "anthropic.claude-3-5-sonnet-20241022-v2:0",
+    "meta.llama3-1-405b-instruct-v1:0",
+    "anthropic.claude-3-5-haiku-20241022-v1:0",
+    "gpt-4o-2024-08-06" "anthropic.claude-3-5-sonnet-20240620-v1:0",
+]

src/autogluon_assistant/llm/llm.py

@@ -13,6 +13,8 @@
 from pydantic import BaseModel, Field
 from tenacity import retry, stop_after_attempt, wait_exponential
 
+from ..constants import WHITE_LIST_LLM
+
 logger = logging.getLogger(__name__)
 
 
@@ -115,11 +117,7 @@ def get_bedrock_models() -> List[str]:
         try:
             bedrock = boto3.client("bedrock", region_name="us-west-2")
             response = bedrock.list_foundation_models()
-            return [
-                model["modelId"]
-                for model in response["modelSummaries"]
-                if model["modelId"].startswith("anthropic.claude")
-            ]
+            return [model["modelId"] for model in response["modelSummaries"]]
         except Exception as e:
             print(f"Error fetching Bedrock models: {e}")
             return []
@@ -181,6 +179,9 @@ def get_chat_model(cls, config: DictConfig) -> Union[AssistantChatOpenAI, Assist
             config.model in valid_models
         ), f"{config.model} is not a valid model in: {valid_models} for provider {config.provider}"
 
+        if config.model not in WHITE_LIST_LLM:
+            logger.warning(f"{config.model} is not on the white list. Our white list models include {WHITE_LIST_LLM}")
+
         if config.provider == "openai":
             return LLMFactory._get_openai_chat_model(config)
         elif config.provider == "bedrock":

src/autogluon_assistant/transformer/feature_transformers/scentenceFT.py

@@ -29,48 +29,46 @@ def get_device_info():
     return DeviceInfo(cpu_count, gpu_devices)
 
 
-def huggingface_run(model, data):
-    if all(isinstance(x, str) for x in data) and any(len(x.split(" ")) > 10 for x in data):
-        data = np.where(pd.isna(data), "", data)
-        return model.encode(data).astype("float32")
-    else:
-        return np.zeros(len(data))
-
-
-def glove_run_one_proc(model, data):
-    embeddings = []
-    if all(isinstance(x, str) for x in data) and any(len(x.split(" ")) > 10 for x in data):
-        for text in data:
-            token_list = list(tokenize(text))
-            embed = model.get_mean_vector(token_list)
-            embeddings.append(embed)
-    else:
-        return np.zeros(len(data))
-    return np.stack(embeddings).astype("float32")
-
-
 class PretrainedEmbeddingTransformer(BaseFeatureTransformer):
     def __init__(self, model_name, **kwargs) -> None:
-        self.model_name = model_name
         if torch.cuda.is_available():
-            try:
-                self.model = SentenceTransformer(self.model_name)
-            except:
-                logger.warning(f"No model {self.model_name} is found.")
+            self.model_name = model_name
 
-        else:
+        if not torch.cuda.is_available():
             logger.warning("CUDA is not found. For an optimized user experience, we switched to the glove embeddings")
             self.model_name = "glove-wiki-gigaword"
             self.dim = 300
             self.max_num_procs = 16
+            self.cpu_count = int(os.environ.get("NUM_VISIBLE_CPUS", os.cpu_count()))
+
+    def _fit_dataframes(self, train_X: pd.DataFrame, train_y: pd.Series, **kwargs) -> None:
+        pass
+
+    def glove_run_one_proc(self, data):
+        embeddings = []
+        if all(isinstance(x, str) for x in data) and any(len(x.split(" ")) > 10 for x in data):
             try:
                 self.model = api.load(f"{self.model_name}-{self.dim}")
             except:
                 logger.warning(f"No model {self.model_name}-{self.dim} is found.")
-            self.cpu_count = int(os.environ.get("NUM_VISIBLE_CPUS", os.cpu_count()))
+            for text in data:
+                token_list = list(tokenize(text))
+                embed = self.model.get_mean_vector(token_list)
+                embeddings.append(embed)
+        else:
+            return np.zeros(len(data))
+        return np.stack(embeddings).astype("float32")
 
-    def _fit_dataframes(self, train_X: pd.DataFrame, train_y: pd.Series, **kwargs) -> None:
-        pass
+    def huggingface_run(self, data):
+        if all(isinstance(x, str) for x in data) and any(len(x.split(" ")) > 10 for x in data):
+            try:
+                self.model = SentenceTransformer(self.model_name)
+            except:
+                logger.warning(f"No model {self.model_name} is found.")
+            data = np.where(pd.isna(data), "", data)
+            return self.model.encode(data).astype("float32")
+        else:
+            return np.zeros(len(data))
 
     def _transform_dataframes(self, train_X: pd.DataFrame, test_X: pd.DataFrame) -> Tuple[pd.DataFrame, pd.DataFrame]:
         assert (
@@ -79,15 +77,11 @@ def _transform_dataframes(self, train_X: pd.DataFrame, test_X: pd.DataFrame) ->
 
         for series_name in train_X.columns.values.tolist():
             if torch.cuda.is_available():
-                transformed_train_column = huggingface_run(self.model, np.transpose(train_X[series_name].to_numpy()).T)
-                transformed_test_column = huggingface_run(self.model, np.transpose(test_X[series_name].to_numpy()).T)
+                transformed_train_column = self.huggingface_run(np.transpose(train_X[series_name].to_numpy()).T)
+                transformed_test_column = self.huggingface_run(np.transpose(test_X[series_name].to_numpy()).T)
             else:
-                transformed_train_column = glove_run_one_proc(
-                    self.model, np.transpose(train_X[series_name].to_numpy()).T
-                )
-                transformed_test_column = glove_run_one_proc(
-                    self.model, np.transpose(test_X[series_name].to_numpy()).T
-                )
+                transformed_train_column = self.glove_run_one_proc(np.transpose(train_X[series_name].to_numpy()).T)
+                transformed_test_column = self.glove_run_one_proc(np.transpose(test_X[series_name].to_numpy()).T)
 
             if transformed_train_column.any() and transformed_test_column.any():
                 transformed_train_column = pd.DataFrame(transformed_train_column)