unique_toolkit 1.9.0__tar.gz → 1.10.0__tar.gz

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/CHANGELOG.md

@@ -5,6 +5,15 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+
+## 1.10.0 - 2025-10-07
+- Introduce future proof knowledgebase service decoupled from chat
+- Extend chat service to download contents in the chat
+- Update documentation
+
+## [1.9.1] - 2025-10-06
+- Switch default model used in evaluation service from `GPT-3.5-turbo (0125)` to `GPT-4o (1120)`
+
 ## [1.9.0] - 2026-10-04
 - Define the RequestContext and add aihttp/httpx requestors
 

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 1.9.0
+Version: 1.10.0
 Summary: 
 License: Proprietary
 Author: Cedric Klinkert
@@ -24,7 +24,7 @@ Requires-Dist: regex (>=2024.5.15,<2025.0.0)
 Requires-Dist: sseclient (>=0.0.27,<0.0.28)
 Requires-Dist: tiktoken (>=0.7.0,<0.8.0)
 Requires-Dist: typing-extensions (>=4.9.0,<5.0.0)
-Requires-Dist: unique-sdk (>=0.10.0,<0.11.0)
+Requires-Dist: unique-sdk (>=0.10.28,<0.11.0)
 Description-Content-Type: text/markdown
 
 # Unique Toolkit
@@ -88,7 +88,7 @@ The `unique_toolkit.embedding` module encompasses all embedding related function
 The `unique_toolkit.language_model` module encompasses all language model related functionality and information on the different language models deployed through the 
 Unique platform.
 
-- `infos.py` comprises the information on all language models deployed through the Unique platform. We recommend to use the LanguageModel class, initialized with the LanguageModelName, e.g., LanguageModel(LanguageModelName.AZURE_GPT_35_TURBO_0125) to get the information on the specific language model like the name, version, token limits or retirement date.
+- `infos.py` comprises the information on all language models deployed through the Unique platform. We recommend to use the LanguageModel class, initialized with the LanguageModelName, e.g., LanguageModel(LanguageModelName.AZURE_GPT_4o_2024_1120) to get the information on the specific language model like the name, version, token limits or retirement date.
 - `functions.py` comprises the functions to complete and stream complete to chat.
 - `service.py` comprises the LanguageModelService and provides an interface to interact with the language models, e.g., complete. 
 - `schemas.py` comprises all relevant schemas, e.g., LanguageModelResponse, used in the LanguageModelService.
@@ -118,6 +118,15 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+
+## 1.10.0 - 2025-10-07
+- Introduce future proof knowledgebase service decoupled from chat
+- Extend chat service to download contents in the chat
+- Update documentation
+
+## [1.9.1] - 2025-10-06
+- Switch default model used in evaluation service from `GPT-3.5-turbo (0125)` to `GPT-4o (1120)`
+
 ## [1.9.0] - 2026-10-04
 - Define the RequestContext and add aihttp/httpx requestors
 

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/README.md

@@ -59,7 +59,7 @@ The `unique_toolkit.embedding` module encompasses all embedding related function
 The `unique_toolkit.language_model` module encompasses all language model related functionality and information on the different language models deployed through the 
 Unique platform.
 
-- `infos.py` comprises the information on all language models deployed through the Unique platform. We recommend to use the LanguageModel class, initialized with the LanguageModelName, e.g., LanguageModel(LanguageModelName.AZURE_GPT_35_TURBO_0125) to get the information on the specific language model like the name, version, token limits or retirement date.
+- `infos.py` comprises the information on all language models deployed through the Unique platform. We recommend to use the LanguageModel class, initialized with the LanguageModelName, e.g., LanguageModel(LanguageModelName.AZURE_GPT_4o_2024_1120) to get the information on the specific language model like the name, version, token limits or retirement date.
 - `functions.py` comprises the functions to complete and stream complete to chat.
 - `service.py` comprises the LanguageModelService and provides an interface to interact with the language models, e.g., complete. 
 - `schemas.py` comprises all relevant schemas, e.g., LanguageModelResponse, used in the LanguageModelService.

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_toolkit"
-version = "1.9.0"
+version = "1.10.0"
 description = ""
 authors = [
     "Cedric Klinkert <cedric.klinkert@unique.ch>",
@@ -27,7 +27,7 @@ sseclient = "^0.0.27"
 openai = "^1.99.9"
 platformdirs = "^4.0.0"
 pillow = "^10.4.0"
-unique-sdk = "^0.10.0"
+unique-sdk = "^0.10.28"
 jambo = "^0.1.2"
 mkdocs-multirepo-plugin = "^0.8.3"
 mkdocs-mermaid2-plugin = "^1.2.2"

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/unique_toolkit/__init__.py

@@ -2,6 +2,7 @@
 from unique_toolkit.chat import ChatService
 from unique_toolkit.content import ContentService
 from unique_toolkit.embedding import EmbeddingService
+from unique_toolkit.knowledge_base import KnowledgeBaseService
 from unique_toolkit.language_model import (
     LanguageModelMessages,
     LanguageModelName,
@@ -21,4 +22,5 @@ __all__ = [
     "ContentService",
     "EmbeddingService",
     "ShortTermMemoryService",
+    "KnowledgeBaseService",
 ]

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/unique_toolkit/_common/chunk_relevancy_sorter/config.py

@@ -2,7 +2,7 @@ from typing import Annotated, Any
 
 from pydantic import BaseModel, Field
 
-from unique_toolkit._common.default_language_model import DEFAULT_GPT_35_TURBO
+from unique_toolkit._common.default_language_model import DEFAULT_GPT_4o
 from unique_toolkit._common.validators import LMI, get_LMI_default_field
 from unique_toolkit.agentic.evaluation.context_relevancy.schema import (
     StructuredOutputConfig,
@@ -25,11 +25,11 @@ class ChunkRelevancySortConfig(BaseModel):
         description="The relevancy level order.",
     )
     language_model: LMI = get_LMI_default_field(
-        DEFAULT_GPT_35_TURBO,
+        DEFAULT_GPT_4o,
         description="The language model to use for the chunk relevancy sort.",
     )
     fallback_language_model: LMI = get_LMI_default_field(
-        DEFAULT_GPT_35_TURBO,
+        DEFAULT_GPT_4o,
         description="The language model to use as a fallback.",
     )
     additional_llm_options: dict[str, Any] = Field(

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/unique_toolkit/_common/chunk_relevancy_sorter/tests/test_service.py

@@ -14,7 +14,6 @@ from unique_toolkit._common.chunk_relevancy_sorter.schemas import (
 )
 from unique_toolkit._common.chunk_relevancy_sorter.service import ChunkRelevancySorter
 from unique_toolkit._common.default_language_model import (
-    DEFAULT_GPT_35_TURBO,
     DEFAULT_GPT_4o,
 )
 from unique_toolkit.agentic.evaluation.context_relevancy.schema import (
@@ -60,7 +59,7 @@ def config():
         relevancy_levels_to_consider=["high", "medium", "low"],
         relevancy_level_order={"high": 0, "medium": 1, "low": 2},
         language_model=LanguageModelInfo.from_name(DEFAULT_GPT_4o),
-        fallback_language_model=LanguageModelInfo.from_name(DEFAULT_GPT_35_TURBO),
+        fallback_language_model=LanguageModelInfo.from_name(DEFAULT_GPT_4o),
         structured_output_config=StructuredOutputConfig(
             enabled=False,
             extract_fact_list=False,

unique_toolkit-1.10.0/unique_toolkit/_common/default_language_model.py

@@ -0,0 +1,3 @@
+from unique_toolkit.language_model.infos import LanguageModelName
+
+DEFAULT_GPT_4o = LanguageModelName.AZURE_GPT_4o_2024_1120

unique_toolkit-1.10.0/unique_toolkit/_common/utils/files.py

@@ -0,0 +1,43 @@
+import mimetypes
+from enum import StrEnum
+
+
+class FileMimeType(StrEnum):
+    PDF = "application/pdf"
+    DOCX = "application/vnd.openxmlformats-officedocument.wordprocessingml.document"
+    DOC = "application/msword"
+    XLSX = "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
+    XLS = "application/vnd.ms-excel"
+    PPTX = "application/vnd.openxmlformats-officedocument.presentationml.presentation"
+    CSV = "text/csv"
+    HTML = "text/html"
+    MD = "text/markdown"
+    TXT = "text/plain"
+
+
+class ImageMimeType(StrEnum):
+    JPEG = "image/jpeg"
+    PNG = "image/png"
+    GIF = "image/gif"
+    BMP = "image/bmp"
+    WEBP = "image/webp"
+    TIFF = "image/tiff"
+    SVG = "image/svg+xml"
+
+
+def is_file_content(filename: str) -> bool:
+    mimetype, _ = mimetypes.guess_type(filename)
+
+    if not mimetype:
+        return False
+
+    return mimetype in FileMimeType.__members__.values()
+
+
+def is_image_content(filename: str) -> bool:
+    mimetype, _ = mimetypes.guess_type(filename)
+
+    if not mimetype:
+        return False
+
+    return mimetype in ImageMimeType.__members__.values()

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/unique_toolkit/agentic/evaluation/config.py

@@ -3,8 +3,9 @@ from typing import Any
 from humps import camelize
 from pydantic import BaseModel, ConfigDict, Field
 
+from unique_toolkit._common.default_language_model import DEFAULT_GPT_4o
 from unique_toolkit._common.validators import LMI
-from unique_toolkit.language_model.infos import LanguageModelInfo, LanguageModelName
+from unique_toolkit.language_model.infos import LanguageModelInfo
 
 from .schemas import (
     EvaluationMetricName,
@@ -24,7 +25,7 @@ class EvaluationMetricConfig(BaseModel):
     enabled: bool = False
     name: EvaluationMetricName
     language_model: LMI = LanguageModelInfo.from_name(
-        LanguageModelName.AZURE_GPT_35_TURBO_0125,
+        DEFAULT_GPT_4o,
     )
     additional_llm_options: dict[str, Any] = Field(
         default={},

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/unique_toolkit/agentic/evaluation/context_relevancy/service.py

@@ -4,7 +4,7 @@ from typing import overload
 from pydantic import BaseModel, ValidationError
 from typing_extensions import deprecated
 
-from unique_toolkit._common.default_language_model import DEFAULT_GPT_35_TURBO
+from unique_toolkit._common.default_language_model import DEFAULT_GPT_4o
 from unique_toolkit._common.validate_required_values import (
     validate_required_values,
 )
@@ -49,7 +49,7 @@ USER_MSG_KEY = "userPrompt"
 default_config = EvaluationMetricConfig(
     enabled=False,
     name=EvaluationMetricName.CONTEXT_RELEVANCY,
-    language_model=LanguageModelInfo.from_name(DEFAULT_GPT_35_TURBO),
+    language_model=LanguageModelInfo.from_name(DEFAULT_GPT_4o),
     custom_prompts={
         SYSTEM_MSG_KEY: CONTEXT_RELEVANCY_METRIC_SYSTEM_MSG,
         USER_MSG_KEY: CONTEXT_RELEVANCY_METRIC_USER_MSG,

{unique_toolkit-1.9.0 → unique_toolkit-1.10.0}/unique_toolkit/agentic/history_manager/history_manager.py

@@ -3,6 +3,7 @@ from typing import Annotated, Awaitable, Callable
 
 from pydantic import BaseModel, Field
 
+from unique_toolkit._common.default_language_model import DEFAULT_GPT_4o
 from unique_toolkit._common.validators import LMI
 from unique_toolkit.agentic.history_manager.loop_token_reducer import LoopTokenReducer
 from unique_toolkit.agentic.history_manager.utils import transform_chunks_to_string
@@ -10,7 +11,7 @@ from unique_toolkit.agentic.reference_manager.reference_manager import Reference
 from unique_toolkit.agentic.tools.config import get_configuration_dict
 from unique_toolkit.agentic.tools.schemas import ToolCallResponse
 from unique_toolkit.app.schemas import ChatEvent
-from unique_toolkit.language_model.infos import LanguageModelInfo, LanguageModelName
+from unique_toolkit.language_model.infos import LanguageModelInfo
 from unique_toolkit.language_model.schemas import (
     LanguageModelAssistantMessage,
     LanguageModelFunction,
@@ -61,9 +62,7 @@ class HistoryManagerConfig(BaseModel):
         description="The fraction of the max input tokens that will be reserved for the history.",
     )
 
-    language_model: LMI = LanguageModelInfo.from_name(
-        LanguageModelName.AZURE_GPT_4o_2024_1120
-    )
+    language_model: LMI = LanguageModelInfo.from_name(DEFAULT_GPT_4o)
 
     @property
     def max_history_tokens(self) -> int:

unique_toolkit-1.10.0/unique_toolkit/chat/deprecated/service.py

@@ -0,0 +1,232 @@
+from typing_extensions import deprecated
+
+from unique_toolkit.app.schemas import ChatEvent, Event
+from unique_toolkit.chat.functions import (
+    modify_message,
+)
+
+
+class ChatServiceDeprecated:
+    def __init__(self, event: ChatEvent | Event):
+        self._event = event
+        self._company_id: str = event.company_id
+        self._user_id: str = event.user_id
+        self._assistant_message_id: str = event.payload.assistant_message.id
+        self._user_message_id: str = event.payload.user_message.id
+        self._chat_id: str = event.payload.chat_id
+        self._assistant_id: str = event.payload.assistant_id
+        self._user_message_text: str = event.payload.user_message.text
+
+    @property
+    @deprecated(
+        "The event property is deprecated and will be removed in a future version.",
+    )
+    def event(self) -> Event | ChatEvent:
+        """Get the event object (deprecated).
+
+        Returns:
+            Event | BaseEvent | None: The event object.
+
+        """
+        return self._event
+
+    @property
+    @deprecated(
+        "The company_id property is deprecated and will be removed in a future version.",
+    )
+    def company_id(self) -> str:
+        """Get the company identifier (deprecated).
+
+        Returns:
+            str | None: The company identifier.
+
+        """
+        return self._company_id
+
+    @company_id.setter
+    @deprecated(
+        "The company_id setter is deprecated and will be removed in a future version.",
+    )
+    def company_id(self, value: str) -> None:
+        """Set the company identifier (deprecated).
+
+        Args:
+            value (str | None): The company identifier.
+
+        """
+        self._company_id = value
+
+    @property
+    @deprecated(
+        "The user_id property is deprecated and will be removed in a future version.",
+    )
+    def user_id(self) -> str:
+        """Get the user identifier (deprecated).
+
+        Returns:
+            str | None: The user identifier.
+
+        """
+        return self._user_id
+
+    @user_id.setter
+    @deprecated(
+        "The user_id setter is deprecated and will be removed in a future version.",
+    )
+    def user_id(self, value: str) -> None:
+        """Set the user identifier (deprecated).
+
+        Args:
+            value (str | None): The user identifier.
+
+        """
+        self._user_id = value
+
+    @property
+    @deprecated(
+        "The assistant_message_id property is deprecated and will be removed in a future version.",
+    )
+    def assistant_message_id(self) -> str:
+        """Get the assistant message identifier (deprecated).
+
+        Returns:
+            str | None: The assistant message identifier.
+
+        """
+        return self._assistant_message_id
+
+    @assistant_message_id.setter
+    @deprecated(
+        "The assistant_message_id setter is deprecated and will be removed in a future version.",
+    )
+    def assistant_message_id(self, value: str) -> None:
+        """Set the assistant message identifier (deprecated).
+
+        Args:
+            value (str | None): The assistant message identifier.
+
+        """
+        self._assistant_message_id = value
+
+    @property
+    @deprecated(
+        "The user_message_id property is deprecated and will be removed in a future version.",
+    )
+    def user_message_id(self) -> str:
+        """Get the user message identifier (deprecated).
+
+        Returns:
+            str | None: The user message identifier.
+
+        """
+        return self._user_message_id
+
+    @user_message_id.setter
+    @deprecated(
+        "The user_message_id setter is deprecated and will be removed in a future version.",
+    )
+    def user_message_id(self, value: str) -> None:
+        """Set the user message identifier (deprecated).
+
+        Args:
+            value (str | None): The user message identifier.
+
+        """
+        self._user_message_id = value
+
+    @property
+    @deprecated(
+        "The chat_id property is deprecated and will be removed in a future version.",
+    )
+    def chat_id(self) -> str:
+        """Get the chat identifier (deprecated).
+
+        Returns:
+            str | None: The chat identifier.
+
+        """
+        return self._chat_id
+
+    @chat_id.setter
+    @deprecated(
+        "The chat_id setter is deprecated and will be removed in a future version.",
+    )
+    def chat_id(self, value: str) -> None:
+        """Set the chat identifier (deprecated).
+
+        Args:
+            value (str | None): The chat identifier.
+
+        """
+        self._chat_id = value
+
+    @property
+    @deprecated(
+        "The assistant_id property is deprecated and will be removed in a future version.",
+    )
+    def assistant_id(self) -> str:
+        """Get the assistant identifier (deprecated).
+
+        Returns:
+            str | None: The assistant identifier.
+
+        """
+        return self._assistant_id
+
+    @assistant_id.setter
+    @deprecated(
+        "The assistant_id setter is deprecated and will be removed in a future version.",
+    )
+    def assistant_id(self, value: str) -> None:
+        """Set the assistant identifier (deprecated).
+
+        Args:
+            value (str | None): The assistant identifier.
+
+        """
+        self._assistant_id = value
+
+    @property
+    @deprecated(
+        "The user_message_text property is deprecated and will be removed in a future version.",
+    )
+    def user_message_text(self) -> str:
+        """Get the user message text (deprecated).
+
+        Returns:
+            str | None: The user message text.
+
+        """
+        return self._user_message_text
+
+    @user_message_text.setter
+    @deprecated(
+        "The user_message_text setter is deprecated and will be removed in a future version.",
+    )
+    def user_message_text(self, value: str) -> None:
+        """Set the user message text (deprecated).
+
+        Args:
+            value (str | None): The user message text.
+
+        """
+        self._user_message_text = value
+
+    @deprecated("Use `replace_debug_info`")
+    def update_debug_info(self, debug_info: dict):
+        """Updates the debug information for the chat session.
+
+        Args:
+            debug_info (dict): The new debug information.
+
+        """
+        return modify_message(
+            user_id=self._user_id,
+            company_id=self._company_id,
+            assistant_message_id=self._assistant_message_id,
+            chat_id=self._chat_id,
+            user_message_id=self._user_message_id,
+            user_message_text=self._user_message_text,
+            assistant=False,
+            debug_info=debug_info,
+        )