unique_toolkit 0.5.3__tar.gz → 0.5.5__tar.gz

{unique_toolkit-0.5.3 → unique_toolkit-0.5.5}/CHANGELOG.md

@@ -5,6 +5,14 @@ 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).
 
+## [0.5.5] - 2024-07-30
+- Added parameters to `ContentService.search_content_chunks` and `ContentService.async_search_content_chunks`
+  - `reranker_config` to optinally reranker the search results
+  - `search_language` to specify a language for full-text-search
+
+## [0.5.4] - 2024-07-26
+- correct ChatMessage schema
+
 ## [0.5.3] - 2024-07-25
 - downgrade numpy version to ^1.26.4 to be compatible with langchain libraries (require numpy<2.0)
 

{unique_toolkit-0.5.3 → unique_toolkit-0.5.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 0.5.3
+Version: 0.5.5
 Summary: 
 License: MIT
 Author: Martin Fadler
@@ -18,7 +18,7 @@ Requires-Dist: regex (>=2024.5.15,<2025.0.0)
 Requires-Dist: requests (>=2.32.3,<3.0.0)
 Requires-Dist: tiktoken (>=0.7.0,<0.8.0)
 Requires-Dist: typing-extensions (>=4.9.0,<5.0.0)
-Requires-Dist: unique-sdk (>=0.8.10,<0.9.0)
+Requires-Dist: unique-sdk (>=0.9,<0.10)
 Description-Content-Type: text/markdown
 
 # Unique Toolkit
@@ -102,6 +102,14 @@ 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).
 
+## [0.5.5] - 2024-07-30
+- Added parameters to `ContentService.search_content_chunks` and `ContentService.async_search_content_chunks`
+  - `reranker_config` to optinally reranker the search results
+  - `search_language` to specify a language for full-text-search
+
+## [0.5.4] - 2024-07-26
+- correct ChatMessage schema
+
 ## [0.5.3] - 2024-07-25
 - downgrade numpy version to ^1.26.4 to be compatible with langchain libraries (require numpy<2.0)
 

{unique_toolkit-0.5.3 → unique_toolkit-0.5.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_toolkit"
-version = "0.5.3"
+version = "0.5.5"
 description = ""
 authors = [
     "Martin Fadler <martin.fadler@unique.ch>",
@@ -16,7 +16,7 @@ python = "^3.11"
 typing-extensions = "^4.9.0"
 pydantic = "^2.8.2"
 pyhumps = "^3.8.0"
-unique-sdk = "^0.8.10"
+unique-sdk = "^0.9"
 numpy = "^1.26.4"
 python-dotenv = "^1.0.1"
 requests = "^2.32.3"

{unique_toolkit-0.5.3 → unique_toolkit-0.5.5}/unique_toolkit/chat/schemas.py

@@ -21,7 +21,7 @@ class ChatMessage(BaseModel):
     object: str | None = None
     content: str = Field(alias="text")
     role: ChatMessageRole
-    debug_info: dict = {}
+    debug_info: dict | None = {}
 
     # TODO make sdk return role consistently in lowercase
     # Currently needed as sdk returns role in uppercase

{unique_toolkit-0.5.3 → unique_toolkit-0.5.5}/unique_toolkit/content/schemas.py

@@ -88,3 +88,9 @@ class ContentUploadInput(BaseModel):
     owner_type: Optional[str] = None
     owner_id: Optional[str] = None
     byte_size: Optional[int] = None
+
+
+class RerankerConfig(BaseModel):
+    model_config = model_config
+    deployment_name: str
+    options: dict | None = None

{unique_toolkit-0.5.3 → unique_toolkit-0.5.5}/unique_toolkit/content/service.py

@@ -14,10 +14,13 @@ from unique_toolkit.content.schemas import (
     ContentChunk,
     ContentSearchType,
     ContentUploadInput,
+    RerankerConfig,
 )
 
 
 class ContentService:
+    DEFAULT_SEARCH_LANGUAGE = "english"
+
     def __init__(self, state: ChatState, logger: Optional[logging.Logger] = None):
         self.state = state
         self.logger = logger or logging.getLogger(__name__)
@@ -27,6 +30,8 @@ class ContentService:
         search_string: str,
         search_type: ContentSearchType,
         limit: int,
+        reranker_config: Optional[RerankerConfig] = None,
+        search_language: str = DEFAULT_SEARCH_LANGUAGE,
         scope_ids: Optional[list[str]] = None,
     ) -> list[ContentChunk]:
         """
@@ -36,16 +41,20 @@ class ContentService:
             search_string (str): The search string.
             search_type (ContentSearchType): The type of search to perform.
             limit (int): The maximum number of results to return.
+            reranker_config (Optional[RerankerConfig]): The reranker configuration. Defaults to None.
+            search_language (str): The language for the full-text search. Defaults to "english".
             scope_ids (Optional[list[str]]): The scope IDs. Defaults to None.
 
         Returns:
             list[ContentChunk]: The search results.
         """
         return self._trigger_search_content_chunks(
-            search_string,
-            search_type,
-            limit,
-            scope_ids,
+            search_string=search_string,
+            search_type=search_type,
+            limit=limit,
+            reranker_config=reranker_config,
+            search_language=search_language,
+            scope_ids=scope_ids,
         )
 
     @to_async
@@ -55,7 +64,9 @@ class ContentService:
         search_string: str,
         search_type: ContentSearchType,
         limit: int,
-        scope_ids: Optional[list[str]],
+        reranker_config: Optional[RerankerConfig] = None,
+        search_language: str = DEFAULT_SEARCH_LANGUAGE,
+        scope_ids: Optional[list[str]] = None,
     ):
         """
         Performs an asynchronous search for content chunks in the knowledge base.
@@ -64,16 +75,20 @@ class ContentService:
             search_string (str): The search string.
             search_type (ContentSearchType): The type of search to perform.
             limit (int): The maximum number of results to return.
+            reranker_config (Optional[RerankerConfig]): The reranker configuration. Defaults to None.
+            search_language (str): The language for the full-text search. Defaults to "english".
             scope_ids (Optional[list[str]]): The scope IDs. Defaults to [].
 
         Returns:
             list[ContentChunk]: The search results.
         """
         return self._trigger_search_content_chunks(
-            search_string,
-            search_type,
-            limit,
-            scope_ids,
+            search_string=search_string,
+            search_type=search_type,
+            limit=limit,
+            reranker_config=reranker_config,
+            search_language=search_language,
+            scope_ids=scope_ids,
         )
 
     def _trigger_search_content_chunks(
@@ -81,7 +96,9 @@ class ContentService:
         search_string: str,
         search_type: ContentSearchType,
         limit: int,
-        scope_ids: Optional[list[str]],
+        reranker_config: Optional[RerankerConfig] = None,
+        search_language: str = DEFAULT_SEARCH_LANGUAGE,
+        scope_ids: Optional[list[str]] = None,
     ) -> list[ContentChunk]:
         scope_ids = scope_ids or self.state.scope_ids or []
 
@@ -97,6 +114,8 @@ class ContentService:
                 searchType=search_type.name,
                 scopeIds=scope_ids,
                 limit=limit,
+                reranker=reranker_config,
+                language=search_language,
                 chatOnly=self.state.chat_only,
             )
         except Exception as e:
@@ -323,8 +342,6 @@ class ContentService:
             Exception: If the download fails.
         """
 
-        print("download chat id", chat_id)
-
         url = f"{unique_sdk.api_base}/content/{content_id}/file"
         if chat_id:
             url = f"{url}?chatId={chat_id}"