unique_toolkit 1.36.0__tar.gz → 1.43.10__tar.gz

{unique_toolkit-1.36.0 → unique_toolkit-1.43.10}/CHANGELOG.md

@@ -5,6 +5,108 @@ 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).
 
+## [1.43.10] - 2026-01-21
+- Lowering the max iterations of the main agents and hard blocking Qwen3 from using too many agent rounds
+
+## [1.43.9] - 2026-01-20
+- Fix system message role conversion in responses API mode (was incorrectly set to "user", now correctly set to "system")
+
+## [1.43.8] - 2026-01-16
+- Add local CI testing commands via poethepoet (poe lint, poe test, poe ci-typecheck, etc.)
+
+## [1.43.7] - 2026-01-15
+- Cleanup hallucination config that is displayed in space config
+
+## [1.43.6] - 2026-01-13
+- Update message execution pipeline functions and service
+
+## [1.43.5] - 2026-01-13
+- Add deptry to dev dependencies for CI dependency checks
+- Fix missing base_settings fixture parameter in FastAPI test
+
+## [1.43.4] - 2026-01-14
+- chore(deps-dev): bump aiohttp from 3.13.2 to 3.13.3
+
+## [1.43.3] - 2026-01-13
+- Changing default `assessment_type` in `SubAgentEvaluationServiceConfig` to `HALLUCINATION`
+
+## [1.43.2] - 2026-01-12
+- `DocxGeneratorService`: Alignment need to be specified by the template rather than in code
+
+## [1.43.1] - 2026-01-12
+- Remove accidental example report.md from repo
+
+## [1.43.0] - 2026-01-11
+- Add `WriteUpAgent` as an experimental service
+
+## [1.42.9] - 2026-01-11
+- Include feature flag to have message logs compatible with new ChatUI
+
+## [1.42.8] - 2026-01-08
+- Add validator to `BaseMetadata` in case `additional_sheet_information` is empty
+- Add more code snippets to create references and pull file metadata
+
+## [1.42.7] - 2026-01-08
+- Add aliases for endpoint secret env var.
+
+## [1.42.6] - 2026-01-07
+- Remove double redundant condition
+
+## [1.42.5] - 2026-01-07
+- Add Mapping of metadata to the `search_content` calls
+- Remove additional indentation by the markdown to docx converter
+
+## [1.42.4] - 2026-01-07
+- Added `additionalSheetInformation` to magic table event.
+
+## [1.42.3] - 2026-01-05
+- Added example code for agentic table
+
+## [1.42.2] - 2026-01-05
+- Fix naming of code interpreter tool in its `ToolPrompts`.
+
+## [1.42.1] - 2025-01-05
+- Version bump of SDK
+
+## [1.42.0] - 2025-01-05
+- Add new params for elicitation to `call_tool` api
+
+## [1.41.0] - 2025-12-29
+- Add `AgenticTable` service to unique_toolkit
+
+## [1.40.0] - 2025-12-22
+- Add option to use retrieve referenced chunks from their order
+- Add `hide_in_chat` parameter to `upload_to_chat_from_bytes` and `upload_to_chat_from_bytes_async`
+- Hide code interpreter files in chat 
+- Code Interpreter files are now uploaded to chat by default
+
+## [1.39.2] - 2025-12-18
+- Add `litellm:gemini-3-flash-preview`, `litellm:openai-gpt-5-2` and `litellm:openai-gpt-5-2-thinking` to `language_model/info.py`
+
+## [1.39.1] - 2025-12-17
+- Add GPT-5.2, GPT-5.2_CHAT to supported models list
+
+## [1.39.0] - 2025-12-17
+- Adding simpler shortterm message abilities to chat service
+
+## [1.38.4] - 2025-12-17
+- Improving handling of tool calls with Qwen models
+
+## [1.38.3] - 2025-12-17
+- Move the failsafe exception to root folder of unique_toolkit from agentic tools
+
+## [1.38.2] - 2025-12-17
+- Fixing bug that language model infos were not loaded correctly
+
+## [1.38.1] - 2025-12-16
+- chore(deps): Bump urllib3 from 2.5.0 to 2.6.2 and unique_sdk from 0.10.48 to 0.10.58 to ensure urllib3 transitively
+
+## [1.38.0] - 2025-12-15
+- Including capability to load LanguageModelInfos in env variable
+
+## [1.37.0] - 2025-12-15
+- Adding a prompt appendix to enforce forced tool calls when using Qwen models
+
 ## [1.36.0] - 2025-12-11
 - Add support for a sub agent tool system reminder when no references are present in the sub agent response.
 
@@ -103,8 +205,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [1.28.1] - 2025-11-19
 - Remove `chat_service` from DocXGeneratorService
-
-## [1.28.1] - 2025-11-19
 - Set review standards in pyright for toolkit
 - Refactor type check pipeline
 
@@ -541,9 +641,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [0.8.26] - 2025-08-27
 - Optimized MCP manager
 
-## [0.8.26] - 2025-08-27
-- Optimized MCP manager
-
 ## [0.8.25] - 2025-08-27
 - Load environment variables automatically from plattform dirs or environment
 - General Endpoint definition utility
@@ -565,8 +662,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.8.20] - 2025-08-24
 - Fixed forced-tool-calls
-
-## [0.8.20] - 2025-08-05
 - Bump SDK version to support the latest features.
 
 ## [0.8.19] - 2025-08-24
@@ -801,8 +896,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.6.3] - 2025-02-27
 - Simplified imports for services. `from unique_toolkit.language_model import LanguageModelService` -> `from unique_toolkit import LanguageModelService` to reduce number of import lines.
-
-## [0.6.3] - 2025-02-26
 - Add `builder` method to `LanguageModelMessages` class
 
 ## [0.6.2] - 2025-02-25

{unique_toolkit-1.36.0 → unique_toolkit-1.43.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 1.36.0
+Version: 1.43.10
 Summary: 
 License: Proprietary
 Author: Cedric Klinkert
@@ -9,25 +9,27 @@ Requires-Python: >=3.12,<4.0
 Classifier: License :: Other/Proprietary License
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: aiohttp (>=3.12.0,<4.0.0)
 Requires-Dist: docxtpl (>=0.20.1,<0.21.0)
+Requires-Dist: httpx (>=0.28.0,<0.29.0)
 Requires-Dist: jambo (>=0.1.2,<0.2.0)
 Requires-Dist: jinja2 (>=3.1.6,<4.0.0)
 Requires-Dist: markdown-it-py (>=4.0.0,<5.0.0)
-Requires-Dist: mkdocs-mermaid2-plugin (>=1.2.2,<2.0.0)
-Requires-Dist: mkdocs-multirepo-plugin (>=0.8.3,<0.9.0)
 Requires-Dist: numpy (>=2.1.0,<3.0.0)
 Requires-Dist: openai (>=1.99.9,<2.0.0)
+Requires-Dist: pandas (>=2.3.0,<3.0.0)
 Requires-Dist: pillow (>=10.4.0,<11.0.0)
 Requires-Dist: platformdirs (>=4.0.0,<5.0.0)
 Requires-Dist: pydantic (>=2.8.2,<3.0.0)
 Requires-Dist: pydantic-settings (>=2.10.1,<3.0.0)
 Requires-Dist: pyhumps (>=3.8.0,<4.0.0)
-Requires-Dist: python-dotenv (>=1.0.1,<2.0.0)
+Requires-Dist: python-docx (>=1.1.0,<2.0.0)
 Requires-Dist: regex (>=2024.5.15,<2025.0.0)
+Requires-Dist: requests (>=2.32.0,<3.0.0)
 Requires-Dist: sseclient (>=0.0.27,<0.0.28)
 Requires-Dist: tiktoken (>=0.12.0,<0.13.0)
 Requires-Dist: typing-extensions (>=4.9.0,<5.0.0)
-Requires-Dist: unique-sdk (>=0.10.48,<0.11.0)
+Requires-Dist: unique-sdk (>=0.10.67,<0.11.0)
 Description-Content-Type: text/markdown
 
 # Unique Toolkit
@@ -41,9 +43,25 @@ The Toolkit is structured along the following domains:
 - `unique_toolkit.language_model`
 - `unique_toolkit.short_term_memory`
 
-Each domain comprises a set of functions (in `functions.py`) and a service class (in `service.py`) which encapsulates the basic functionalities to interact with the domain entities, the schemas (in `schemas.py`) used in the service and required for interacting with the service functions, utility functions (in `utils.py`) which give additional functionality to interact with the domain entities (all domains except embedding) and other domain specific functionalities which are explained in the respective domain documentation.
+Each domain comprises a set of schemas (in `schemas.py`) are used in functions (in `functions.py`) which encapsulates the basic functionalities to interact with the plattform. 
+The above domains represent the internal structure of the Unique platform.
 
-In addition, the `unique_toolkit.app` module provides functions to initialize apps that interact with the Unique platform. It also includes some utility functions to run async tasks in parallel (async webserver and app implementation required).
+For the `developers` we expose interfaces via `services` classes that correspond directly to an frontend or an entity the `user` interacts with. 
+
+The following services are currently available:
+
+| Service | Responsability |
+|--|--|
+| ChatService | All interactions with the chat interface | 
+| KnowledgeBaseService | All interaction with the knowledgebase |
+
+The services can be directly import as 
+
+```
+from unique_toolkit import ChatService, KnowledgeBaseService
+
+
+In addition, the `unique_toolkit.app` module provides functions to initialize apps and dev utilities to interact with the Unique platform. 
 
 ## Changelog
 
@@ -65,7 +83,6 @@ The `unique_toolkit.app` module encompasses functions for initializing and secur
 The `unique_toolkit.chat` module encompasses all chat related functionality.
 
 - `functions.py` comprises the functions to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message.
-- `service.py` comprises the ChatService and provides an interface to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message and stream complete.
 - `schemas.py` comprises all relevant schemas, e.g., ChatMessage, used in the ChatService.
 - `utils.py` comprises utility functions to use and convert ChatMessage objects in assistants, e.g., convert_chat_history_to_injectable_string converts the chat history to a string that can be injected into a prompt. 
 
@@ -74,11 +91,10 @@ The `unique_toolkit.chat` module encompasses all chat related functionality.
 The `unique_toolkit.content` module encompasses all content related functionality. Content can be any type of textual data that is stored in the Knowledgebase on the Unique platform. During the ingestion of the content, the content is parsed, split in chunks, indexed, and stored in the database.
 
 - `functions.py` comprises the functions to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message.
-- `service.py` comprises the ContentService and provides an interface to interact with the content, e.g., search content, search content chunks, upload and download content.
 - `schemas.py` comprises all relevant schemas, e.g., Content and ContentChunk, used in the ContentService.
 - `utils.py` comprise utility functions to manipulate Content and ContentChunk objects, e.g., sort_content_chunks and merge_content_chunks.
 
-## Embedding
+## Embedding (To be Deprecated)
 
 The `unique_toolkit.embedding` module encompasses all embedding related functionality. Embeddings are used to represent textual data in a high-dimensional space. The embeddings can be used to calculate the similarity between two texts, for instance.
 
@@ -86,40 +102,130 @@ The `unique_toolkit.embedding` module encompasses all embedding related function
 - `service.py` encompasses the EmbeddingService and provides an interface to interact with the embeddings, e.g., embed text and calculate the similarity between two texts.
 - `schemas.py` comprises all relevant schemas, e.g., Embeddings, used in the EmbeddingService.
 
-## Language Model
+## Language Model 
 
 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_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.
 - `utils.py` comprises utility functions to parse the output of the language model, e.g., convert_string_to_json finds and parses the last json object in a string.
 
-## Short Term Memory
+## Short Term Memory 
 
 The `unique_toolkit.short_term_memory` module encompasses all short term memory related functionality.
 
 - `functions.py` comprises the functions to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message.
-- `service.py` comprises the ShortTermMemoryService and provides an interface to interact with the short term memory, e.g., create memory.
 - `schemas.py` comprises all relevant schemas, e.g., ShortTermMemory, used in the ShortTermMemoryService.
+# Changelog
 
-# Development instructions
+All notable changes to this project will be documented in this file.
 
-1. Install poetry on your system (through `brew` or `pipx`).
+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).
 
-2. Install `pyenv` and install python 3.11. `pyenv` is recommended as otherwise poetry uses the python version used to install itself and not the user preferred python version.
+## [1.43.10] - 2026-01-21
+- Lowering the max iterations of the main agents and hard blocking Qwen3 from using too many agent rounds
 
-3. If you then run `python --version` in your terminal, you should be able to see python version as specified in `.python-version`.
+## [1.43.9] - 2026-01-20
+- Fix system message role conversion in responses API mode (was incorrectly set to "user", now correctly set to "system")
 
-4. Then finally run `poetry install` to install the package and all dependencies.
-# Changelog
+## [1.43.8] - 2026-01-16
+- Add local CI testing commands via poethepoet (poe lint, poe test, poe ci-typecheck, etc.)
 
-All notable changes to this project will be documented in this file.
+## [1.43.7] - 2026-01-15
+- Cleanup hallucination config that is displayed in space config
 
-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).
+## [1.43.6] - 2026-01-13
+- Update message execution pipeline functions and service
+
+## [1.43.5] - 2026-01-13
+- Add deptry to dev dependencies for CI dependency checks
+- Fix missing base_settings fixture parameter in FastAPI test
+
+## [1.43.4] - 2026-01-14
+- chore(deps-dev): bump aiohttp from 3.13.2 to 3.13.3
+
+## [1.43.3] - 2026-01-13
+- Changing default `assessment_type` in `SubAgentEvaluationServiceConfig` to `HALLUCINATION`
+
+## [1.43.2] - 2026-01-12
+- `DocxGeneratorService`: Alignment need to be specified by the template rather than in code
+
+## [1.43.1] - 2026-01-12
+- Remove accidental example report.md from repo
+
+## [1.43.0] - 2026-01-11
+- Add `WriteUpAgent` as an experimental service
+
+## [1.42.9] - 2026-01-11
+- Include feature flag to have message logs compatible with new ChatUI
+
+## [1.42.8] - 2026-01-08
+- Add validator to `BaseMetadata` in case `additional_sheet_information` is empty
+- Add more code snippets to create references and pull file metadata
+
+## [1.42.7] - 2026-01-08
+- Add aliases for endpoint secret env var.
+
+## [1.42.6] - 2026-01-07
+- Remove double redundant condition
+
+## [1.42.5] - 2026-01-07
+- Add Mapping of metadata to the `search_content` calls
+- Remove additional indentation by the markdown to docx converter
+
+## [1.42.4] - 2026-01-07
+- Added `additionalSheetInformation` to magic table event.
+
+## [1.42.3] - 2026-01-05
+- Added example code for agentic table
+
+## [1.42.2] - 2026-01-05
+- Fix naming of code interpreter tool in its `ToolPrompts`.
+
+## [1.42.1] - 2025-01-05
+- Version bump of SDK
+
+## [1.42.0] - 2025-01-05
+- Add new params for elicitation to `call_tool` api
+
+## [1.41.0] - 2025-12-29
+- Add `AgenticTable` service to unique_toolkit
+
+## [1.40.0] - 2025-12-22
+- Add option to use retrieve referenced chunks from their order
+- Add `hide_in_chat` parameter to `upload_to_chat_from_bytes` and `upload_to_chat_from_bytes_async`
+- Hide code interpreter files in chat 
+- Code Interpreter files are now uploaded to chat by default
+
+## [1.39.2] - 2025-12-18
+- Add `litellm:gemini-3-flash-preview`, `litellm:openai-gpt-5-2` and `litellm:openai-gpt-5-2-thinking` to `language_model/info.py`
+
+## [1.39.1] - 2025-12-17
+- Add GPT-5.2, GPT-5.2_CHAT to supported models list
+
+## [1.39.0] - 2025-12-17
+- Adding simpler shortterm message abilities to chat service
+
+## [1.38.4] - 2025-12-17
+- Improving handling of tool calls with Qwen models
+
+## [1.38.3] - 2025-12-17
+- Move the failsafe exception to root folder of unique_toolkit from agentic tools
+
+## [1.38.2] - 2025-12-17
+- Fixing bug that language model infos were not loaded correctly
+
+## [1.38.1] - 2025-12-16
+- chore(deps): Bump urllib3 from 2.5.0 to 2.6.2 and unique_sdk from 0.10.48 to 0.10.58 to ensure urllib3 transitively
+
+## [1.38.0] - 2025-12-15
+- Including capability to load LanguageModelInfos in env variable
+
+## [1.37.0] - 2025-12-15
+- Adding a prompt appendix to enforce forced tool calls when using Qwen models
 
 ## [1.36.0] - 2025-12-11
 - Add support for a sub agent tool system reminder when no references are present in the sub agent response.
@@ -219,8 +325,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [1.28.1] - 2025-11-19
 - Remove `chat_service` from DocXGeneratorService
-
-## [1.28.1] - 2025-11-19
 - Set review standards in pyright for toolkit
 - Refactor type check pipeline
 
@@ -657,9 +761,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ## [0.8.26] - 2025-08-27
 - Optimized MCP manager
 
-## [0.8.26] - 2025-08-27
-- Optimized MCP manager
-
 ## [0.8.25] - 2025-08-27
 - Load environment variables automatically from plattform dirs or environment
 - General Endpoint definition utility
@@ -681,8 +782,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.8.20] - 2025-08-24
 - Fixed forced-tool-calls
-
-## [0.8.20] - 2025-08-05
 - Bump SDK version to support the latest features.
 
 ## [0.8.19] - 2025-08-24
@@ -917,8 +1016,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [0.6.3] - 2025-02-27
 - Simplified imports for services. `from unique_toolkit.language_model import LanguageModelService` -> `from unique_toolkit import LanguageModelService` to reduce number of import lines.
-
-## [0.6.3] - 2025-02-26
 - Add `builder` method to `LanguageModelMessages` class
 
 ## [0.6.2] - 2025-02-25

{unique_toolkit-1.36.0 → unique_toolkit-1.43.10}/README.md

@@ -9,9 +9,25 @@ The Toolkit is structured along the following domains:
 - `unique_toolkit.language_model`
 - `unique_toolkit.short_term_memory`
 
-Each domain comprises a set of functions (in `functions.py`) and a service class (in `service.py`) which encapsulates the basic functionalities to interact with the domain entities, the schemas (in `schemas.py`) used in the service and required for interacting with the service functions, utility functions (in `utils.py`) which give additional functionality to interact with the domain entities (all domains except embedding) and other domain specific functionalities which are explained in the respective domain documentation.
+Each domain comprises a set of schemas (in `schemas.py`) are used in functions (in `functions.py`) which encapsulates the basic functionalities to interact with the plattform. 
+The above domains represent the internal structure of the Unique platform.
 
-In addition, the `unique_toolkit.app` module provides functions to initialize apps that interact with the Unique platform. It also includes some utility functions to run async tasks in parallel (async webserver and app implementation required).
+For the `developers` we expose interfaces via `services` classes that correspond directly to an frontend or an entity the `user` interacts with. 
+
+The following services are currently available:
+
+| Service | Responsability |
+|--|--|
+| ChatService | All interactions with the chat interface | 
+| KnowledgeBaseService | All interaction with the knowledgebase |
+
+The services can be directly import as 
+
+```
+from unique_toolkit import ChatService, KnowledgeBaseService
+
+
+In addition, the `unique_toolkit.app` module provides functions to initialize apps and dev utilities to interact with the Unique platform. 
 
 ## Changelog
 
@@ -33,7 +49,6 @@ The `unique_toolkit.app` module encompasses functions for initializing and secur
 The `unique_toolkit.chat` module encompasses all chat related functionality.
 
 - `functions.py` comprises the functions to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message.
-- `service.py` comprises the ChatService and provides an interface to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message and stream complete.
 - `schemas.py` comprises all relevant schemas, e.g., ChatMessage, used in the ChatService.
 - `utils.py` comprises utility functions to use and convert ChatMessage objects in assistants, e.g., convert_chat_history_to_injectable_string converts the chat history to a string that can be injected into a prompt. 
 
@@ -42,11 +57,10 @@ The `unique_toolkit.chat` module encompasses all chat related functionality.
 The `unique_toolkit.content` module encompasses all content related functionality. Content can be any type of textual data that is stored in the Knowledgebase on the Unique platform. During the ingestion of the content, the content is parsed, split in chunks, indexed, and stored in the database.
 
 - `functions.py` comprises the functions to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message.
-- `service.py` comprises the ContentService and provides an interface to interact with the content, e.g., search content, search content chunks, upload and download content.
 - `schemas.py` comprises all relevant schemas, e.g., Content and ContentChunk, used in the ContentService.
 - `utils.py` comprise utility functions to manipulate Content and ContentChunk objects, e.g., sort_content_chunks and merge_content_chunks.
 
-## Embedding
+## Embedding (To be Deprecated)
 
 The `unique_toolkit.embedding` module encompasses all embedding related functionality. Embeddings are used to represent textual data in a high-dimensional space. The embeddings can be used to calculate the similarity between two texts, for instance.
 
@@ -54,31 +68,19 @@ The `unique_toolkit.embedding` module encompasses all embedding related function
 - `service.py` encompasses the EmbeddingService and provides an interface to interact with the embeddings, e.g., embed text and calculate the similarity between two texts.
 - `schemas.py` comprises all relevant schemas, e.g., Embeddings, used in the EmbeddingService.
 
-## Language Model
+## Language Model 
 
 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_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.
 - `utils.py` comprises utility functions to parse the output of the language model, e.g., convert_string_to_json finds and parses the last json object in a string.
 
-## Short Term Memory
+## Short Term Memory 
 
 The `unique_toolkit.short_term_memory` module encompasses all short term memory related functionality.
 
 - `functions.py` comprises the functions to manage and load the chat history and interact with the chat ui, e.g., creating a new assistant message.
-- `service.py` comprises the ShortTermMemoryService and provides an interface to interact with the short term memory, e.g., create memory.
-- `schemas.py` comprises all relevant schemas, e.g., ShortTermMemory, used in the ShortTermMemoryService.
-
-# Development instructions
-
-1. Install poetry on your system (through `brew` or `pipx`).
-
-2. Install `pyenv` and install python 3.11. `pyenv` is recommended as otherwise poetry uses the python version used to install itself and not the user preferred python version.
-
-3. If you then run `python --version` in your terminal, you should be able to see python version as specified in `.python-version`.
-
-4. Then finally run `poetry install` to install the package and all dependencies.
+- `schemas.py` comprises all relevant schemas, e.g., ShortTermMemory, used in the ShortTermMemoryService.

{unique_toolkit-1.36.0 → unique_toolkit-1.43.10}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_toolkit"
-version = "1.36.0"
+version = "1.43.10"
 description = ""
 authors = [
     "Cedric Klinkert <cedric.klinkert@unique.ch>",
@@ -21,7 +21,6 @@ typing-extensions = "^4.9.0"
 pydantic = "^2.8.2"
 pyhumps = "^3.8.0"
 numpy = "^2.1.0"
-python-dotenv = "^1.0.1"
 regex = "^2024.5.15"
 tiktoken = "^0.12.0"
 pydantic-settings = "^2.10.1"
@@ -29,13 +28,16 @@ sseclient = "^0.0.27"
 openai = "^1.99.9"
 platformdirs = "^4.0.0"
 pillow = "^10.4.0"
-unique-sdk = "^0.10.48"
+unique-sdk = "^0.10.67"
 jambo = "^0.1.2"
 jinja2 = "^3.1.6"
-mkdocs-multirepo-plugin = "^0.8.3"
-mkdocs-mermaid2-plugin = "^1.2.2"
 docxtpl = "^0.20.1"
 markdown-it-py = "^4.0.0"
+python-docx = "^1.1.0"
+requests = "^2.32.0"
+httpx = "^0.28.0"
+aiohttp = "^3.12.0"
+pandas = "^2.3.0"
 
 [tool.poetry.group.langchain]
 optional = true
@@ -44,6 +46,7 @@ optional = true
 openai = "^1.97.0"
 langchain = "^0.3.27"
 langchain-openai = "^0.3.28"
+langchain-core = "^0.3.0"
 
 [tool.poetry.group.fastapi]
 optional = true
@@ -62,10 +65,9 @@ pytest-cov = "^4.1.0"
 pre-commit = "^3.7.1"
 pytest-asyncio = "^0.23.8"
 pytest-mock = "^3.14.0"
-platformdirs = "^4.0.0"
-pillow = "^10.4.0"
 ipykernel = "^6.29.5"
-jinja2 = "^3.1.6"
+deptry = "^0.24.0"
+poethepoet = "^0.32.0"
 # unique-sdk = { path = "../unique_sdk" }
 mkdocs = "^1.6.1"
 mkdocs-material = "^9.6.11"
@@ -76,12 +78,31 @@ entangled-cli = "^2.1.13"
 mkdocs-entangled-plugin = "^0.4.0"
 isort = "^6.0.1"
 mkdocs-codeinclude-plugin = "^0.2.1"
-aiohttp = "^3.12.15"
+aiohttp = "^3.13.3"
+pandas = "^2.3.3"
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
+[tool.poe.tasks]
+lint = "ruff check ."
+lint-fix = "ruff check . --fix"
+format = "ruff format ."
+test = "pytest"
+typecheck = "basedpyright"
+depcheck = "deptry ."
+coverage = "pytest --cov=unique_toolkit --cov-report=term-missing"
+ci-typecheck = { shell = "bash $(git rev-parse --show-toplevel)/.github/scripts/dev.sh typecheck" }
+ci-coverage = { shell = "bash $(git rev-parse --show-toplevel)/.github/scripts/dev.sh coverage" }
+
+[tool.deptry]
+known_first_party = ["unique_toolkit"]
+extend_exclude = ["docs", "tests", "unique_toolkit/.*/test", "unique_toolkit/.*/tests"]
+
+[tool.deptry.per_rule_ignores]
+DEP004 = ["langchain_openai", "langchain_core"]
+
 [tool.ruff]
 target-version = "py311"
 exclude = [".venv", "docs"]
@@ -91,15 +112,6 @@ exclude = [".venv", "docs"]
 extend-select = ["I"]
 
 [tool.basedpyright]
-# Type checking mode: "off", "basic", "standard", "strict", "recommended", or "all"
 typeCheckingMode = "standard"
-# Exclude test files, virtual environments, and site-packages from type checking
-excludePaths = [
-    "**/test_*.py",
-    "**/tests/**",
-    "**/.venv/**",
-    "**/venv/**",
-    "**/site-packages/**",
-    "**/__pycache__/**",
-    "**/.pytest_cache/**",
-]
+include = ["unique_toolkit"]
+exclude = ["**/tests/**", "**/test_*.py"]

{unique_toolkit-1.36.0 → unique_toolkit-1.43.10}/unique_toolkit/_common/docx_generator/schemas.py

@@ -1,5 +1,4 @@
 from docx.document import Document as DocumentObject
-from docx.enum.text import WD_PARAGRAPH_ALIGNMENT
 from docxtpl import DocxTemplate
 from pydantic import BaseModel
 
@@ -7,45 +6,39 @@ from pydantic import BaseModel
 class HeadingField(BaseModel):
     text: str
     level: int = 4
-    alignment: WD_PARAGRAPH_ALIGNMENT = WD_PARAGRAPH_ALIGNMENT.LEFT
 
     def add(self, doc: DocumentObject):
         p = doc.add_heading(self.text, level=self.level)
-        p.alignment = self.alignment
         return p
 
     def __str__(self):
-        return f"HeadingField(text={self.text}, level={self.level}, alignment={self.alignment})"
+        return f"HeadingField(text={self.text}, level={self.level})"
 
 
 class ParagraphField(BaseModel):
     text: str
     style: str | None = None
-    alignment: WD_PARAGRAPH_ALIGNMENT = WD_PARAGRAPH_ALIGNMENT.LEFT
 
     def add(self, doc: DocumentObject):
         p = doc.add_paragraph(self.text, style=self.style)
-        p.alignment = self.alignment
         return p
 
     def __str__(self):
-        return f"ParagraphField(text={self.text}, style={self.style}, alignment={self.alignment})"
+        return f"ParagraphField(text={self.text}, style={self.style})"
 
 
 class RunField(BaseModel):
     text: str
     italic: bool | None = False
     bold: bool | None = False
-    alignment: WD_PARAGRAPH_ALIGNMENT = WD_PARAGRAPH_ALIGNMENT.LEFT
 
     def __str__(self):
-        return f"RunField(text={self.text}, italic={self.italic}, alignment={self.alignment})"
+        return f"RunField(text={self.text}, italic={self.italic}, bold={self.bold})"
 
 
 class RunsField(BaseModel):
     runs: list[RunField]
     style: str | None = None
-    alignment: WD_PARAGRAPH_ALIGNMENT = WD_PARAGRAPH_ALIGNMENT.LEFT
 
     def add(self, doc: DocumentObject):
         if not self.runs:
@@ -60,7 +53,7 @@ class RunsField(BaseModel):
         return p
 
     def __str__(self):
-        return f"RunsField(runs={self.runs}, style={self.style}, alignment={self.alignment})"
+        return f"RunsField(runs={self.runs}, style={self.style})"
 
 
 class ContentField(BaseModel):