semantic-kernel 0.5.0.dev0__tar.gz → 0.9.0b1__tar.gz

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: semantic-kernel
-Version: 0.5.0.dev0
+Version: 0.9.0b1
 Summary: Semantic Kernel Python SDK
 Author: Microsoft
 Author-email: SK-Support@microsoft.com
@@ -13,13 +13,14 @@ Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: aiofiles (>=23.1.0,<24.0.0)
 Requires-Dist: aiohttp (>=3.8,<4.0)
-Requires-Dist: motor (>=3.3.1,<4.0.0)
+Requires-Dist: defusedxml (>=0.7.1,<0.8.0)
+Requires-Dist: motor (>=3.3.2,<4.0.0)
 Requires-Dist: numpy (>=1.24.2,<2.0.0)
 Requires-Dist: openai (>=1.0)
 Requires-Dist: openapi_core (>=0.18.0,<0.19.0)
 Requires-Dist: prance (>=23.6.21.0,<24.0.0.0)
 Requires-Dist: pydantic (>2)
-Requires-Dist: python-dotenv (==1.0.0)
+Requires-Dist: python-dotenv (==1.0.1)
 Requires-Dist: regex (>=2023.6.3,<2024.0.0)
 Description-Content-Type: text/markdown
 

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "semantic-kernel"
-version = "0.5.0.dev"
+version = "0.9.0.beta1"
 description = "Semantic Kernel Python SDK"
 authors = ["Microsoft <SK-Support@microsoft.com>"]
 readme = "pip/README.md"
@@ -12,32 +12,33 @@ aiohttp = "^3.8"
 numpy = "^1.24.2"
 openai = ">=1.0"
 aiofiles = "^23.1.0"
-python-dotenv = "1.0.0"
+python-dotenv = "1.0.1"
 regex = "^2023.6.3"
 openapi_core = "^0.18.0"
 prance = "^23.6.21.0"
 pydantic = ">2"
-motor = "^3.3.1"
+motor = "^3.3.2"
+defusedxml = "^0.7.1"
 
 [tool.poetry.group.dev.dependencies]
 pre-commit = "3.5.0"
-# please keep black and ruff version in sync with the ones in .pre-commit-config.yaml
-black = "^23.12.0"
-ruff = "0.1.8"
+black = ">=23.12.0"
+ruff = ">=0.2.2"
 ipykernel = "^6.21.1"
 pytest = "7.4.3"
 pytest-asyncio = "0.23.2"
 snoop = "0.4.3"
-pytest-cov = "4.1.0"
+pytest-cov = ">=4.1.0"
+mypy = ">=1.8.0"
 
 [tool.poetry.group.google_palm.dependencies]
-google-generativeai = { version = ">=0.1,<0.3", markers = "python_version >= '3.9'" }
+google-generativeai = { version = ">=0.1,<0.4", markers = "python_version >= '3.9'" }
 grpcio-status = { version = "^1.53.0", markers = "python_version >= '3.9'" }
 
 [tool.poetry.group.hugging_face.dependencies]
 transformers = "^4.28.1"
 sentence-transformers = "^2.2.2"
-torch = "2.0.0"
+torch = "2.2.0"
 
 [tool.poetry.group.qdrant.dependencies]
 qdrant-client = {version = "^1.3.2", python = ">=3.8,<3.12"}
@@ -50,7 +51,7 @@ pymilvus = "2.2.16"
 milvus = "2.2.16"
 
 [tool.poetry.group.weaviate.dependencies]
-weaviate-client = "^3.18.0"
+weaviate-client = ">=3.18,<5.0"
 
 [tool.poetry.group.pinecone.dependencies]
 pinecone-client = "^2.2.2"
@@ -68,15 +69,16 @@ azure-search-documents = {version = "11.4.0b9", allow-prereleases = true}
 azure-core = "^1.28.0"
 azure-identity = "^1.13.0"
 
+[tool.poetry.group.tests.dependencies]
+azure-search-documents = {version = "11.4.0b9", allow-prereleases = true}
+azure-core = "^1.28.0"
+
 [tool.poetry.group.usearch.dependencies]
 usearch = "1.1.1"
 pyarrow = ">=12.0.1,<15.0.0"
 
-[tool.isort]
-profile = "ruff"
-
 [tool.ruff]
-select = ["E", "F", "I"]
+lint.select = ["E", "F", "I"]
 line-length = 120
 
 [tool.black]

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/semantic_kernel/__init__.py

@@ -1,18 +1,12 @@
 # Copyright (c) Microsoft. All rights reserved.
 
 from semantic_kernel import core_plugins, memory
+from semantic_kernel.functions.kernel_arguments import KernelArguments
+from semantic_kernel.functions.kernel_function import KernelFunction
 from semantic_kernel.kernel import Kernel
-from semantic_kernel.orchestration.context_variables import ContextVariables
-from semantic_kernel.orchestration.kernel_context import KernelContext
-from semantic_kernel.orchestration.kernel_function_base import KernelFunctionBase
-from semantic_kernel.semantic_functions.chat_prompt_template import ChatPromptTemplate
-from semantic_kernel.semantic_functions.prompt_template import PromptTemplate
-from semantic_kernel.semantic_functions.prompt_template_config import (
+from semantic_kernel.prompt_template.prompt_template_config import (
     PromptTemplateConfig,
 )
-from semantic_kernel.semantic_functions.semantic_function_config import (
-    SemanticFunctionConfig,
-)
 from semantic_kernel.utils.logging import setup_logging
 from semantic_kernel.utils.null_logger import NullLogger
 from semantic_kernel.utils.settings import (
@@ -46,12 +40,8 @@ __all__ = [
     "google_palm_settings_from_dot_env",
     "redis_settings_from_dot_env",
     "PromptTemplateConfig",
-    "PromptTemplate",
-    "ChatPromptTemplate",
-    "SemanticFunctionConfig",
-    "ContextVariables",
-    "KernelFunctionBase",
-    "KernelContext",
+    "KernelArguments",
+    "KernelFunction",
     "memory",
     "core_plugins",
     "setup_logging",

semantic_kernel-0.9.0b1/semantic_kernel/connectors/ai/chat_completion_client_base.py

@@ -0,0 +1,68 @@
+# Copyright (c) Microsoft. All rights reserved.
+
+from abc import ABC, abstractmethod
+from typing import TYPE_CHECKING, AsyncIterable, Dict, List, Optional, Type
+
+from semantic_kernel.contents import ChatMessageContent
+from semantic_kernel.services.ai_service_client_base import AIServiceClientBase
+
+if TYPE_CHECKING:
+    from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
+    from semantic_kernel.contents import StreamingChatMessageContent
+    from semantic_kernel.contents.chat_history import ChatHistory
+
+
+class ChatCompletionClientBase(AIServiceClientBase, ABC):
+    def get_chat_message_content_class(self) -> Type[ChatMessageContent]:
+        """Get the chat message content types used by a class, default is ChatMessageContent."""
+        return ChatMessageContent
+
+    @abstractmethod
+    async def complete_chat(
+        self,
+        chat_history: "ChatHistory",
+        settings: "PromptExecutionSettings",
+    ) -> List["ChatMessageContent"]:
+        """
+        This is the method that is called from the kernel to get a response from a chat-optimized LLM.
+
+        Arguments:
+            chat_history {ChatHistory} -- A list of chats in a chat_history object, that can be
+                rendered into messages from system, user, assistant and tools.
+            settings {PromptExecutionSettings} -- Settings for the request.
+
+        Returns:
+            Union[str, List[str]] -- A string or list of strings representing the response(s) from the LLM.
+        """
+        pass
+
+    @abstractmethod
+    async def complete_chat_stream(
+        self,
+        chat_history: "ChatHistory",
+        settings: "PromptExecutionSettings",
+    ) -> AsyncIterable[List["StreamingChatMessageContent"]]:
+        """
+        This is the method that is called from the kernel to get a stream response from a chat-optimized LLM.
+
+        Arguments:
+            chat_history {ChatHistory} -- A list of chat chat_history, that can be rendered into a
+                set of chat_history, from system, user, assistant and function.
+            settings {PromptExecutionSettings} -- Settings for the request.
+
+        Yields:
+            A stream representing the response(s) from the LLM.
+        """
+        pass
+
+    def _prepare_chat_history_for_request(
+        self,
+        chat_history: "ChatHistory",
+    ) -> List[Dict[str, Optional[str]]]:
+        """
+        Prepare the chat history for a request, allowing customization of the key names for role/author,
+        and optionally overriding the role.
+        """
+        return [
+            message.model_dump(exclude_none=True, exclude=["metadata", "encoding"]) for message in chat_history.messages
+        ]

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/semantic_kernel/connectors/ai/embeddings/embedding_generator_base.py

@@ -3,11 +3,13 @@
 from abc import ABC, abstractmethod
 from typing import TYPE_CHECKING, List
 
+from semantic_kernel.services.ai_service_client_base import AIServiceClientBase
+
 if TYPE_CHECKING:
     from numpy import ndarray
 
 
-class EmbeddingGeneratorBase(ABC):
+class EmbeddingGeneratorBase(AIServiceClientBase, ABC):
     @abstractmethod
     async def generate_embeddings(self, texts: List[str]) -> "ndarray":
         pass

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/semantic_kernel/connectors/ai/google_palm/gp_prompt_execution_settings.py

@@ -3,6 +3,7 @@ from typing import Any, Dict, Iterable, List, Optional, Union
 from pydantic import Field, model_validator
 
 from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
+from semantic_kernel.exceptions import ServiceInvalidExecutionSettingsError
 
 # TODO: replace back with google types once pydantic issue is fixed.
 MessagesOptions = List[Dict[str, Any]]
@@ -38,4 +39,6 @@ class GooglePalmChatPromptExecutionSettings(GooglePalmPromptExecutionSettings):
     def validate_input(self):
         if self.prompt is not None:
             if self.messages or self.context or self.examples:
-                raise ValueError("Prompt cannot be used with messages, context or examples")
+                raise ServiceInvalidExecutionSettingsError(
+                    "Prompt cannot be used without messages, context or examples"
+                )

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/semantic_kernel/connectors/ai/google_palm/services/gp_chat_completion.py

@@ -2,10 +2,11 @@
 
 import logging
 import sys
-from typing import Any, Dict, List, Optional, Tuple
+from typing import Dict, List, Optional, Tuple
 
-from semantic_kernel.models.contents.chat_message_content import ChatMessageContent
-from semantic_kernel.models.contents.text_content import TextContent
+from semantic_kernel.contents.chat_message_content import ChatMessageContent
+from semantic_kernel.contents.text_content import TextContent
+from semantic_kernel.exceptions import ServiceInvalidRequestError, ServiceResponseException
 
 if sys.version_info >= (3, 9):
     from typing import Annotated
@@ -16,33 +17,31 @@ import google.generativeai as palm
 from google.generativeai.types import ChatResponse, MessageDict
 from pydantic import PrivateAttr, StringConstraints
 
-from semantic_kernel.connectors.ai.ai_exception import AIException
-from semantic_kernel.connectors.ai.ai_service_client_base import AIServiceClientBase
-from semantic_kernel.connectors.ai.chat_completion_client_base import (
-    ChatCompletionClientBase,
-)
+from semantic_kernel.connectors.ai.chat_completion_client_base import ChatCompletionClientBase
 from semantic_kernel.connectors.ai.google_palm.gp_prompt_execution_settings import (
     GooglePalmChatPromptExecutionSettings,
     GooglePalmPromptExecutionSettings,
 )
 from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
-from semantic_kernel.connectors.ai.text_completion_client_base import (
-    TextCompletionClientBase,
-)
+from semantic_kernel.connectors.ai.text_completion_client_base import TextCompletionClientBase
+from semantic_kernel.contents.chat_history import ChatHistory
+from semantic_kernel.contents.chat_role import ChatRole
 
 logger: logging.Logger = logging.getLogger(__name__)
 
+int_to_role = {1: ChatRole.USER, 2: ChatRole.SYSTEM, 3: ChatRole.ASSISTANT, 4: ChatRole.TOOL}
+
 
-class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBase, AIServiceClientBase):
+class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBase):
     api_key: Annotated[str, StringConstraints(strip_whitespace=True, min_length=1)]
-    _message_history: Optional[ChatResponse] = PrivateAttr()
+    _message_history: Optional[ChatHistory] = PrivateAttr()
+    service_id: Optional[str] = None
 
     def __init__(
         self,
         ai_model_id: str,
         api_key: str,
-        message_history: Optional[ChatResponse] = None,
-        log: Optional[Any] = None,
+        message_history: Optional[ChatHistory] = None,
     ):
         """
         Initializes a new instance of the GooglePalmChatCompletion class.
@@ -52,20 +51,17 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
                 https://developers.generativeai.google/models/language
             api_key {str} -- GooglePalm API key, see
                 https://developers.generativeai.google/products/palm
-            message_history {Optional[ChatResponse]} -- The message history to use for context. (Optional)
-            log {Optional[Any]} -- A logger to use for logging. (Optional)
+            message_history {Optional[ChatHistory]} -- The message history to use for context. (Optional)
         """
         super().__init__(
             ai_model_id=ai_model_id,
             api_key=api_key,
         )
-        if log:
-            logger.warning("The `log` parameter is deprecated. Please use the `logging` module instead.")
         self._message_history = message_history
 
     async def complete_chat(
         self,
-        messages: List[Dict[str, str]],
+        messages: ChatHistory,
         settings: GooglePalmPromptExecutionSettings,
     ) -> List[ChatMessageContent]:
         """
@@ -79,7 +75,7 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
         Returns:
             List[ChatMessageContent] -- A list of ChatMessageContent objects representing the response(s) from the LLM.
         """
-        settings.messages = [{"author": message["role"], "content": message["content"]} for message in messages]
+        settings.messages = self._prepare_chat_history_for_request(messages)
         if not settings.ai_model_id:
             settings.ai_model_id = self.ai_model_id
         response = await self._send_chat_request(settings)
@@ -99,13 +95,16 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
         Returns:
             ChatMessageContent -- The created chat message content.
         """
-        metadata = {"citation_metadata": candidate.get("citation_metadata"), "filters": response.filters}
+        metadata = {
+            "citation_metadata": candidate.get("citation_metadata"),
+            "filters": response.filters,
+            "choice_index": index,
+        }
         return ChatMessageContent(
-            choice_index=index,
             inner_content=response,
             ai_model_id=self.ai_model_id,
             metadata=metadata,
-            role=candidate.get("author"),
+            role=int_to_role[int(candidate.get("author"))],  # TODO: why is author coming back as '1'?
             content=candidate.get("content"),
         )
 
@@ -120,7 +119,6 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
         self,
         prompt: str,
         settings: GooglePalmPromptExecutionSettings,
-        **kwargs,
     ) -> List[TextContent]:
         """
         This is the method that is called from the kernel to get a response from a text-optimized LLM.
@@ -132,8 +130,6 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
         Returns:
             List[TextContent] -- A list of TextContent objects representing the response(s) from the LLM.
         """
-        if kwargs.get("logger"):
-            logger.warning("The `logger` parameter is deprecated. Please use the `logging` module instead.")
         settings.messages = [{"author": "user", "content": prompt}]
         if not settings.ai_model_id:
             settings.ai_model_id = self.ai_model_id
@@ -162,10 +158,7 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
         self,
         prompt: str,
         settings: GooglePalmPromptExecutionSettings,
-        **kwargs,
     ):
-        if kwargs.get("logger"):
-            logger.warning("The `logger` parameter is deprecated. Please use the `logging` module instead.")
         raise NotImplementedError("Google Palm API does not currently support streaming")
 
     async def _send_chat_request(
@@ -206,10 +199,7 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
             raise ValueError("The request settings cannot be `None`")
 
         if settings.messages[-1]["author"] != "user":
-            raise AIException(
-                AIException.ErrorCodes.InvalidRequest,
-                "The last message must be from the user",
-            )
+            raise ServiceInvalidRequestError("The last message must be from the user")
         try:
             palm.configure(api_key=self.api_key)
         except Exception as ex:
@@ -226,13 +216,27 @@ class GooglePalmChatCompletion(ChatCompletionClientBase, TextCompletionClientBas
                 )
             self._message_history = response  # Store response object for future use
         except Exception as ex:
-            raise AIException(
-                AIException.ErrorCodes.ServiceError,
+            raise ServiceResponseException(
                 "Google PaLM service failed to complete the prompt",
                 ex,
-            )
+            ) from ex
         return response
 
     def get_prompt_execution_settings_class(self) -> "PromptExecutionSettings":
         """Create a request settings object."""
         return GooglePalmChatPromptExecutionSettings
+
+    def _prepare_chat_history_for_request(
+        self,
+        chat_history: ChatHistory,
+    ) -> List[Dict[str, Optional[str]]]:
+        """
+        Prepare the chat history for a request, allowing customization of the key names for role/author,
+        and optionally overriding the role.
+        """
+        standard_out = super()._prepare_chat_history_for_request(chat_history)
+        for message in standard_out:
+            message["author"] = message.pop("role")
+        # The last message should always be from the user
+        standard_out[-1]["author"] = "user"
+        return standard_out

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/semantic_kernel/connectors/ai/google_palm/services/gp_text_completion.py

@@ -2,36 +2,32 @@
 
 import logging
 import sys
-from typing import Any, List, Optional
+from typing import List
 
-from semantic_kernel.models.contents.text_content import TextContent
+from semantic_kernel.contents.text_content import TextContent
+from semantic_kernel.exceptions import ServiceResponseException
 
 if sys.version_info >= (3, 9):
     from typing import Annotated
 else:
     from typing_extensions import Annotated
+
 import google.generativeai as palm
 from google.generativeai.types import Completion
 from google.generativeai.types.text_types import TextCompletion
 from pydantic import StringConstraints
 
-from semantic_kernel.connectors.ai.ai_exception import AIException
-from semantic_kernel.connectors.ai.ai_service_client_base import AIServiceClientBase
-from semantic_kernel.connectors.ai.google_palm.gp_prompt_execution_settings import (
-    GooglePalmTextPromptExecutionSettings,
-)
+from semantic_kernel.connectors.ai.google_palm.gp_prompt_execution_settings import GooglePalmTextPromptExecutionSettings
 from semantic_kernel.connectors.ai.prompt_execution_settings import PromptExecutionSettings
-from semantic_kernel.connectors.ai.text_completion_client_base import (
-    TextCompletionClientBase,
-)
+from semantic_kernel.connectors.ai.text_completion_client_base import TextCompletionClientBase
 
 logger: logging.Logger = logging.getLogger(__name__)
 
 
-class GooglePalmTextCompletion(TextCompletionClientBase, AIServiceClientBase):
+class GooglePalmTextCompletion(TextCompletionClientBase):
     api_key: Annotated[str, StringConstraints(strip_whitespace=True, min_length=1)]
 
-    def __init__(self, ai_model_id: str, api_key: str, log: Optional[Any] = None):
+    def __init__(self, ai_model_id: str, api_key: str):
         """
         Initializes a new instance of the GooglePalmTextCompletion class.
 
@@ -40,15 +36,10 @@ class GooglePalmTextCompletion(TextCompletionClientBase, AIServiceClientBase):
                 https://developers.generativeai.google/models/language
             api_key {str} -- GooglePalm API key, see
                 https://developers.generativeai.google/products/palm
-            log {Optional[Any]} -- The logger instance to use. (Optional) (Deprecated)
         """
         super().__init__(ai_model_id=ai_model_id, api_key=api_key)
-        if log:
-            logger.warning("The `log` parameter is deprecated. Please use the `logging` module instead.")
 
-    async def complete(
-        self, prompt: str, settings: GooglePalmTextPromptExecutionSettings, **kwargs
-    ) -> List[TextContent]:
+    async def complete(self, prompt: str, settings: GooglePalmTextPromptExecutionSettings) -> List[TextContent]:
         """
         This is the method that is called from the kernel to get a response from a text-optimized LLM.
 
@@ -72,11 +63,10 @@ class GooglePalmTextCompletion(TextCompletionClientBase, AIServiceClientBase):
         try:
             response = palm.generate_text(**settings.prepare_settings_dict())
         except Exception as ex:
-            raise AIException(
-                AIException.ErrorCodes.ServiceError,
+            raise ServiceResponseException(
                 "Google PaLM service failed to complete the prompt",
                 ex,
-            )
+            ) from ex
         return [self._create_text_content(response, candidate) for candidate in response.candidates]
 
     def _create_text_content(self, response: Completion, candidate: TextCompletion) -> TextContent:
@@ -97,7 +87,6 @@ class GooglePalmTextCompletion(TextCompletionClientBase, AIServiceClientBase):
         self,
         prompt: str,
         settings: GooglePalmTextPromptExecutionSettings,
-        logger: Optional[Any] = None,
     ):
         raise NotImplementedError("Google Palm API does not currently support streaming")
 

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/semantic_kernel/connectors/ai/google_palm/services/gp_text_embedding.py

@@ -8,18 +8,18 @@ if sys.version_info >= (3, 9):
     from typing import Annotated
 else:
     from typing_extensions import Annotated
+
 import google.generativeai as palm
 from numpy import array, ndarray
 from pydantic import StringConstraints
 
-from semantic_kernel.connectors.ai.ai_exception import AIException
-from semantic_kernel.connectors.ai.ai_service_client_base import AIServiceClientBase
 from semantic_kernel.connectors.ai.embeddings.embedding_generator_base import (
     EmbeddingGeneratorBase,
 )
+from semantic_kernel.exceptions import ServiceInvalidAuthError, ServiceResponseException
 
 
-class GooglePalmTextEmbedding(EmbeddingGeneratorBase, AIServiceClientBase):
+class GooglePalmTextEmbedding(EmbeddingGeneratorBase):
     api_key: Annotated[str, StringConstraints(strip_whitespace=True, min_length=1)]
 
     def __init__(self, ai_model_id: str, api_key: str) -> None:
@@ -47,10 +47,10 @@ class GooglePalmTextEmbedding(EmbeddingGeneratorBase, AIServiceClientBase):
         try:
             palm.configure(api_key=self.api_key)
         except Exception as ex:
-            raise PermissionError(
+            raise ServiceInvalidAuthError(
                 "Google PaLM service failed to configure. Invalid API key provided.",
                 ex,
-            )
+            ) from ex
         embeddings = []
         for text in texts:
             try:
@@ -60,9 +60,8 @@ class GooglePalmTextEmbedding(EmbeddingGeneratorBase, AIServiceClientBase):
                 )
                 embeddings.append(array(response["embedding"]))
             except Exception as ex:
-                raise AIException(
-                    AIException.ErrorCodes.ServiceError,
+                raise ServiceResponseException(
                     "Google PaLM service failed to generate the embedding.",
                     ex,
-                )
+                ) from ex
         return array(embeddings)

{semantic_kernel-0.5.0.dev0 → semantic_kernel-0.9.0b1}/semantic_kernel/connectors/ai/hugging_face/hf_prompt_execution_settings.py

@@ -26,15 +26,10 @@ class HuggingFacePromptExecutionSettings(PromptExecutionSettings):
 
     def prepare_settings_dict(self, **kwargs) -> Dict[str, Any]:
         gen_config = self.get_generation_config()
-        if "prompt" in kwargs and kwargs["prompt"] is not None:
-            return {
-                "text_inputs": kwargs["prompt"],
-                "generation_config": gen_config,
-                "num_return_sequences": self.num_return_sequences,
-                "do_sample": self.do_sample,
-            }
-        return {
+        settings = {
             "generation_config": gen_config,
             "num_return_sequences": self.num_return_sequences,
             "do_sample": self.do_sample,
         }
+        settings.update(kwargs)
+        return settings