unique_toolkit 1.17.1__tar.gz → 1.17.3__tar.gz

{unique_toolkit-1.17.1 → unique_toolkit-1.17.3}/CHANGELOG.md

@@ -5,8 +5,16 @@ 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).
 
+
+## [1.17.3] - 2025-10-27
+- Update Hallucination check citation regex parsing pattern
+
+## [1.17.2] - 2025-10-23
+- Adding model `AZURE_GPT_5_PRO_2025_1006` and `litellm:openai-gpt-5-pro` to `language_model/info.py`
+
 ## [1.17.1] - 2025-10-23
 - Fix hallucination check input with all cited reference chunks.
+
 ## [1.17.0] - 2025-10-22
 - Add more options to display sub agent answers in the chat.
 

{unique_toolkit-1.17.1 → unique_toolkit-1.17.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 1.17.1
+Version: 1.17.3
 Summary: 
 License: Proprietary
 Author: Cedric Klinkert
@@ -118,8 +118,16 @@ 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).
 
+
+## [1.17.3] - 2025-10-27
+- Update Hallucination check citation regex parsing pattern
+
+## [1.17.2] - 2025-10-23
+- Adding model `AZURE_GPT_5_PRO_2025_1006` and `litellm:openai-gpt-5-pro` to `language_model/info.py`
+
 ## [1.17.1] - 2025-10-23
 - Fix hallucination check input with all cited reference chunks.
+
 ## [1.17.0] - 2025-10-22
 - Add more options to display sub agent answers in the chat.
 

{unique_toolkit-1.17.1 → unique_toolkit-1.17.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_toolkit"
-version = "1.17.1"
+version = "1.17.3"
 description = ""
 authors = [
     "Cedric Klinkert <cedric.klinkert@unique.ch>",

{unique_toolkit-1.17.1 → unique_toolkit-1.17.3}/unique_toolkit/agentic/evaluation/hallucination/hallucination_evaluation.py

@@ -20,6 +20,7 @@ from unique_toolkit.chat.schemas import (
     ChatMessageAssessmentStatus,
     ChatMessageAssessmentType,
 )
+from unique_toolkit.language_model.reference import _preprocess_message
 from unique_toolkit.language_model.schemas import (
     LanguageModelStreamResponse,
 )
@@ -43,10 +44,15 @@ class HallucinationEvaluation(Evaluation):
         self, loop_response: LanguageModelStreamResponse
     ) -> EvaluationMetricResult:  # type: ignore
         all_chunks = self._reference_manager.get_chunks()
+
         # source numbers from original text
-        ref_pattern = r"\[source(\d+)\]"
+        ref_pattern = r"\[(\d+)\]"
         original_text = loop_response.message.original_text
-        source_number_matches = re.findall(ref_pattern, original_text)
+
+        # preprocess original text to deal with different source patterns
+        original_text_preprocessed = _preprocess_message(original_text)
+
+        source_number_matches = re.findall(ref_pattern, original_text_preprocessed)
         source_numbers = {int(num) for num in source_number_matches}
 
         referenced_chunks = [all_chunks[idx] for idx in source_numbers]

{unique_toolkit-1.17.1 → unique_toolkit-1.17.3}/unique_toolkit/language_model/infos.py

@@ -19,6 +19,7 @@ class LanguageModelName(StrEnum):
     AZURE_GPT_5_MINI_2025_0807 = "AZURE_GPT_5_MINI_2025_0807"
     AZURE_GPT_5_NANO_2025_0807 = "AZURE_GPT_5_NANO_2025_0807"
     AZURE_GPT_5_CHAT_2025_0807 = "AZURE_GPT_5_CHAT_2025_0807"
+    AZURE_GPT_5_PRO_2025_1006 = "AZURE_GPT_5_PRO_2025_1006"
     AZURE_GPT_4o_2024_0513 = "AZURE_GPT_4o_2024_0513"
     AZURE_GPT_4o_2024_0806 = "AZURE_GPT_4o_2024_0806"
     AZURE_GPT_4o_2024_1120 = "AZURE_GPT_4o_2024_1120"
@@ -52,6 +53,7 @@ class LanguageModelName(StrEnum):
     LITELLM_OPENAI_GPT_5_MINI = "litellm:openai-gpt-5-mini"
     LITELLM_OPENAI_GPT_5_NANO = "litellm:openai-gpt-5-nano"
     LITELLM_OPENAI_GPT_5_CHAT = "litellm:openai-gpt-5-chat"
+    LITELLM_OPENAI_GPT_5_PRO = "litellm:openai-gpt-5-pro"
     LITELLM_OPENAI_O1 = "litellm:openai-o1"
     LITELLM_OPENAI_O3 = "litellm:openai-o3"
     LITELLM_OPENAI_O3_DEEP_RESEARCH = "litellm:openai-o3-deep-research"
@@ -91,10 +93,12 @@ def get_encoder_name(model_name: LanguageModelName) -> EncoderName:
             | LMN.AZURE_GPT_5_MINI_2025_0807
             | LMN.AZURE_GPT_5_NANO_2025_0807
             | LMN.AZURE_GPT_5_CHAT_2025_0807
+            | LMN.AZURE_GPT_5_PRO_2025_1006
             | LMN.LITELLM_OPENAI_GPT_5
             | LMN.LITELLM_OPENAI_GPT_5_MINI
             | LMN.LITELLM_OPENAI_GPT_5_NANO
             | LMN.LITELLM_OPENAI_GPT_5_CHAT
+            | LMN.LITELLM_OPENAI_GPT_5_PRO
             | LMN.LITELLM_OPENAI_O1
             | LMN.LITELLM_OPENAI_O3
             | LMN.LITELLM_OPENAI_O3_DEEP_RESEARCH
@@ -334,6 +338,27 @@ class LanguageModelInfo(BaseModel):
                     deprecated_at=date(2026, 8, 7),
                     retirement_at=date(2026, 8, 7),
                 )
+            case LanguageModelName.AZURE_GPT_5_PRO_2025_1006:
+                return cls(
+                    name=model_name,
+                    provider=LanguageModelProvider.AZURE,
+                    version="2025-10-06",
+                    encoder_name=EncoderName.O200K_BASE,
+                    capabilities=[
+                        ModelCapabilities.FUNCTION_CALLING,
+                        ModelCapabilities.REASONING,
+                        ModelCapabilities.VISION,
+                        ModelCapabilities.STRUCTURED_OUTPUT,
+                    ],
+                    token_limits=LanguageModelTokenLimits(
+                        token_limit_input=272000, token_limit_output=128000
+                    ),
+                    info_cutoff_at=date(2024, 10, 30),
+                    published_at=date(2025, 10, 6),
+                    temperature_bounds=TemperatureBounds(
+                        min_temperature=1.0, max_temperature=1.0
+                    ),
+                )
             case LanguageModelName.AZURE_GPT_4_TURBO_2024_0409:
                 return cls(
                     name=model_name,
@@ -981,6 +1006,27 @@ class LanguageModelInfo(BaseModel):
                     deprecated_at=date(2026, 8, 7),
                     retirement_at=date(2026, 8, 7),
                 )
+            case LanguageModelName.LITELLM_OPENAI_GPT_5_PRO:
+                return cls(
+                    name=model_name,
+                    provider=LanguageModelProvider.LITELLM,
+                    version="2025-10-06",
+                    encoder_name=EncoderName.O200K_BASE,
+                    capabilities=[
+                        ModelCapabilities.FUNCTION_CALLING,
+                        ModelCapabilities.REASONING,
+                        ModelCapabilities.VISION,
+                        ModelCapabilities.STRUCTURED_OUTPUT,
+                    ],
+                    token_limits=LanguageModelTokenLimits(
+                        token_limit_input=272000, token_limit_output=128000
+                    ),
+                    info_cutoff_at=date(2024, 10, 30),
+                    published_at=date(2025, 10, 6),
+                    temperature_bounds=TemperatureBounds(
+                        min_temperature=1.0, max_temperature=1.0
+                    ),
+                )
             case LanguageModelName.LITELLM_OPENAI_O1:
                 return cls(
                     name=model_name,