unique_sdk 0.9.22__tar.gz → 0.9.26__tar.gz

{unique_sdk-0.9.22 → unique_sdk-0.9.26}/CHANGELOG.md

@@ -5,6 +5,18 @@ 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).
 
+## [0.9.26] - 2025-05-13
+- Add the possibility to specify ingestionConfig when creating or updating a Content.
+
+## [0.9.25] - 2025-05-02
+- Fixed typos in `README.md`, including incorrect `sdk.utils` imports and code example errors.
+
+## [0.9.24] - 2025-04-23
+- Make `chatId` property in `Search.CreateParams` optional
+
+## [0.9.23] - 2025-03-25
+- Define programming language classifier explicitly for python 3.11
+
 ## [0.9.22] - 2025-02-25
 - update the retry_on_error to only `APIError` and `APIConnectionError` update the `resp["error"]` to be `resp.get("error")` to avoid key error
 

{unique_sdk-0.9.22 → unique_sdk-0.9.26}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_sdk
-Version: 0.9.22
+Version: 0.9.26
 Summary: 
 License: MIT
 Author: Martin Fadler
@@ -297,6 +297,11 @@ createdContent = upload_file(
     "test.pdf",
     "application/pdf",
     "scope_stcj2osgbl722m22jayidx0n",
+    ingestionConfig={
+        "chunkMaxTokens": 1000,
+        "chunkStrategy": "default",
+        "uniqueIngestionMode": "standard",
+    },
 )
 
 def upload_file(
@@ -306,6 +311,7 @@ def upload_file(
     displayed_filename,
     mimeType,
     scope_or_unique_path,
+    ingestion_config=None,
 ):
     size = os.path.getsize(path_to_file)
     createdContent = unique_sdk.Content.upsert(
@@ -315,6 +321,7 @@ def upload_file(
             "key": displayed_filename,
             "title": displayed_filename,
             "mimeType": mimeType,
+            "ingestionConfig": ingestionConfig,
         },
         scopeId=scope_or_unique_path,
     )
@@ -340,6 +347,7 @@ def upload_file(
             "title": displayed_filename,
             "mimeType": mimeType,
             "byteSize": size,
+            "ingestionConfig": ingestionConfig,
         },
         scopeId=scope_or_unique_path,
         readUrl=createdContent.readUrl,
@@ -544,6 +552,7 @@ These are the options are available for `searchType`:
 `scopeIds` Specifies a collection of scope IDs to confine the search.
 `language` Optional. The language specification for full text search.
 `reranker` Optional. The reranker service to be used for re-ranking the search results.
+`chatId` Optional, adds the documents uploaded in this chat to the scope of searched documents.
 
 ```python
 search = unique_sdk.Search.create(
@@ -715,7 +724,7 @@ A metadata filter such as the one designed above can be used in a `Search.create
 
 ### Chat History
 
-#### `unique_sdk.util.chat_history.load_history`
+#### `unique_sdk.utils.chat_history.load_history`
 
 A helper function that makes sure the chat history is fully loaded and cut to the size of the token window that it fits into the next round of chat interactions.
 
@@ -733,7 +742,7 @@ history = unique_sdk.utils.chat_history.load_history(
 )
 ```
 
-#### `unique_sdk.util.chat_history.convert_chat_history_to_injectable_string`
+#### `unique_sdk.utils.chat_history.convert_chat_history_to_injectable_string`
 
 convert history into a string that can be injected into a prompt. it als returns the token length of the converted history.
 
@@ -747,7 +756,7 @@ chat_history-string, chat_context_token_length = unique_sdk.utils.chat_history.c
 
 Interacting with the knowledge-base.
 
-#### `unique_sdk.util.file_io.download_content`
+#### `unique_sdk.utils.file_io.download_content`
 
 download files and save them into a folder in `/tmp`
 
@@ -763,7 +772,7 @@ pdfFile = download_content(
 }
 ```
 
-#### `unique_sdk.util.file_io.upload_file`
+#### `unique_sdk.utils.file_io.upload_file`
 
 Allows for uploading files that then get ingested in a scope or a chat.
 
@@ -773,15 +782,15 @@ createdContent = upload_file(
     userId=userId,
     path_to_file="/tmp/hello.pdf",
     displayed_filename="hello.pdf",
-    mimeType="application/pdf",
-    uploadScope="scope_stcj2osgbl722m22jayidx0n",
+    mime_type="application/pdf",
+    scope_or_unique_path="scope_stcj2osgbl722m22jayidx0n",
     chat_id=None,
 )
 ```
 
 ### Sources
 
-#### `unique_sdk.util.sources.merge_sources`
+#### `unique_sdk.utils.sources.merge_sources`
 
 Merges multiple search results based on their 'id', removing redundant document and info markers.
 
@@ -810,15 +819,15 @@ search = unique_sdk.Search.create(
     chatOnly=False,
 )
 
-searchContext = unique_sdk.util.token.pick_search_results_for_token_window(
+searchContext = unique_sdk.utils.token.pick_search_results_for_token_window(
         search["data"], config["maxTokens"] - historyLength
     )
 
-searchContext = unique_sdk.util.sources.merge_sources(search)
+searchContext = unique_sdk.utils.sources.merge_sources(search)
 
 ```
 
-#### `unique_sdk.util.sources.sort_sources`
+#### `unique_sdk.utils.sources.sort_sources`
 
 Sort sources by order of appearance in documents
 
@@ -835,14 +844,14 @@ search = unique_sdk.Search.create(
     chatOnly=False,
 )
 
-searchContext = unique_sdk.util.token.pick_search_results_for_token_window(
+searchContext = unique_sdk.utils.token.pick_search_results_for_token_window(
         search["data"], config["maxTokens"] - historyLength
     )
 
-searchContext = unique_sdk.util.sources.sort_sources(search)
+searchContext = unique_sdk.utils.sources.sort_sources(search)
 ```
 
-#### `unique_sdk.util.sources.post_process_sources`
+#### `unique_sdk.utils.sources.post_process_sources`
 
 Post-processes the provided text by converting source references into superscript numerals (required
 format by backend to display sources in the chat window)
@@ -869,7 +878,7 @@ text_with_sup = post_process_sources(text)
 
 ### Token
 
-#### unique_sdk.util.token.pick_search_results_for_token_window
+#### unique_sdk.utils.token.pick_search_results_for_token_window
 
 Selects and returns a list of search results that fit within a specified token limit.
 
@@ -898,12 +907,12 @@ search = unique_sdk.Search.create(
     chatOnly=False,
 )
 
-searchContext = unique_sdk.util.token.pick_search_results_for_token_window(
+searchContext = unique_sdk.utils.token.pick_search_results_for_token_window(
         search["data"], config["maxTokens"] - historyLength
     )
 ```
 
-#### unique_sdk.util.token.count_tokens
+#### unique_sdk.utils.token.count_tokens
 
 Counts the number of tokens in the provided text.
 
@@ -920,7 +929,7 @@ Returns:
 
 ```python
 hello = "hello you!"
-searchContext = unique_sdk.util.token.count_tokens(hello)
+searchContext = unique_sdk.utils.token.count_tokens(hello)
 ```
 
 ## Error Handling
@@ -940,6 +949,18 @@ 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).
 
+## [0.9.26] - 2025-05-13
+- Add the possibility to specify ingestionConfig when creating or updating a Content.
+
+## [0.9.25] - 2025-05-02
+- Fixed typos in `README.md`, including incorrect `sdk.utils` imports and code example errors.
+
+## [0.9.24] - 2025-04-23
+- Make `chatId` property in `Search.CreateParams` optional
+
+## [0.9.23] - 2025-03-25
+- Define programming language classifier explicitly for python 3.11
+
 ## [0.9.22] - 2025-02-25
 - update the retry_on_error to only `APIError` and `APIConnectionError` update the `resp["error"]` to be `resp.get("error")` to avoid key error
 

{unique_sdk-0.9.22 → unique_sdk-0.9.26}/README.md

@@ -282,6 +282,11 @@ createdContent = upload_file(
     "test.pdf",
     "application/pdf",
     "scope_stcj2osgbl722m22jayidx0n",
+    ingestionConfig={
+        "chunkMaxTokens": 1000,
+        "chunkStrategy": "default",
+        "uniqueIngestionMode": "standard",
+    },
 )
 
 def upload_file(
@@ -291,6 +296,7 @@ def upload_file(
     displayed_filename,
     mimeType,
     scope_or_unique_path,
+    ingestion_config=None,
 ):
     size = os.path.getsize(path_to_file)
     createdContent = unique_sdk.Content.upsert(
@@ -300,6 +306,7 @@ def upload_file(
             "key": displayed_filename,
             "title": displayed_filename,
             "mimeType": mimeType,
+            "ingestionConfig": ingestionConfig,
         },
         scopeId=scope_or_unique_path,
     )
@@ -325,6 +332,7 @@ def upload_file(
             "title": displayed_filename,
             "mimeType": mimeType,
             "byteSize": size,
+            "ingestionConfig": ingestionConfig,
         },
         scopeId=scope_or_unique_path,
         readUrl=createdContent.readUrl,
@@ -529,6 +537,7 @@ These are the options are available for `searchType`:
 `scopeIds` Specifies a collection of scope IDs to confine the search.
 `language` Optional. The language specification for full text search.
 `reranker` Optional. The reranker service to be used for re-ranking the search results.
+`chatId` Optional, adds the documents uploaded in this chat to the scope of searched documents.
 
 ```python
 search = unique_sdk.Search.create(
@@ -700,7 +709,7 @@ A metadata filter such as the one designed above can be used in a `Search.create
 
 ### Chat History
 
-#### `unique_sdk.util.chat_history.load_history`
+#### `unique_sdk.utils.chat_history.load_history`
 
 A helper function that makes sure the chat history is fully loaded and cut to the size of the token window that it fits into the next round of chat interactions.
 
@@ -718,7 +727,7 @@ history = unique_sdk.utils.chat_history.load_history(
 )
 ```
 
-#### `unique_sdk.util.chat_history.convert_chat_history_to_injectable_string`
+#### `unique_sdk.utils.chat_history.convert_chat_history_to_injectable_string`
 
 convert history into a string that can be injected into a prompt. it als returns the token length of the converted history.
 
@@ -732,7 +741,7 @@ chat_history-string, chat_context_token_length = unique_sdk.utils.chat_history.c
 
 Interacting with the knowledge-base.
 
-#### `unique_sdk.util.file_io.download_content`
+#### `unique_sdk.utils.file_io.download_content`
 
 download files and save them into a folder in `/tmp`
 
@@ -748,7 +757,7 @@ pdfFile = download_content(
 }
 ```
 
-#### `unique_sdk.util.file_io.upload_file`
+#### `unique_sdk.utils.file_io.upload_file`
 
 Allows for uploading files that then get ingested in a scope or a chat.
 
@@ -758,15 +767,15 @@ createdContent = upload_file(
     userId=userId,
     path_to_file="/tmp/hello.pdf",
     displayed_filename="hello.pdf",
-    mimeType="application/pdf",
-    uploadScope="scope_stcj2osgbl722m22jayidx0n",
+    mime_type="application/pdf",
+    scope_or_unique_path="scope_stcj2osgbl722m22jayidx0n",
     chat_id=None,
 )
 ```
 
 ### Sources
 
-#### `unique_sdk.util.sources.merge_sources`
+#### `unique_sdk.utils.sources.merge_sources`
 
 Merges multiple search results based on their 'id', removing redundant document and info markers.
 
@@ -795,15 +804,15 @@ search = unique_sdk.Search.create(
     chatOnly=False,
 )
 
-searchContext = unique_sdk.util.token.pick_search_results_for_token_window(
+searchContext = unique_sdk.utils.token.pick_search_results_for_token_window(
         search["data"], config["maxTokens"] - historyLength
     )
 
-searchContext = unique_sdk.util.sources.merge_sources(search)
+searchContext = unique_sdk.utils.sources.merge_sources(search)
 
 ```
 
-#### `unique_sdk.util.sources.sort_sources`
+#### `unique_sdk.utils.sources.sort_sources`
 
 Sort sources by order of appearance in documents
 
@@ -820,14 +829,14 @@ search = unique_sdk.Search.create(
     chatOnly=False,
 )
 
-searchContext = unique_sdk.util.token.pick_search_results_for_token_window(
+searchContext = unique_sdk.utils.token.pick_search_results_for_token_window(
         search["data"], config["maxTokens"] - historyLength
     )
 
-searchContext = unique_sdk.util.sources.sort_sources(search)
+searchContext = unique_sdk.utils.sources.sort_sources(search)
 ```
 
-#### `unique_sdk.util.sources.post_process_sources`
+#### `unique_sdk.utils.sources.post_process_sources`
 
 Post-processes the provided text by converting source references into superscript numerals (required
 format by backend to display sources in the chat window)
@@ -854,7 +863,7 @@ text_with_sup = post_process_sources(text)
 
 ### Token
 
-#### unique_sdk.util.token.pick_search_results_for_token_window
+#### unique_sdk.utils.token.pick_search_results_for_token_window
 
 Selects and returns a list of search results that fit within a specified token limit.
 
@@ -883,12 +892,12 @@ search = unique_sdk.Search.create(
     chatOnly=False,
 )
 
-searchContext = unique_sdk.util.token.pick_search_results_for_token_window(
+searchContext = unique_sdk.utils.token.pick_search_results_for_token_window(
         search["data"], config["maxTokens"] - historyLength
     )
 ```
 
-#### unique_sdk.util.token.count_tokens
+#### unique_sdk.utils.token.count_tokens
 
 Counts the number of tokens in the provided text.
 
@@ -905,7 +914,7 @@ Returns:
 
 ```python
 hello = "hello you!"
-searchContext = unique_sdk.util.token.count_tokens(hello)
+searchContext = unique_sdk.utils.token.count_tokens(hello)
 ```
 
 ## Error Handling

{unique_sdk-0.9.22 → unique_sdk-0.9.26}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_sdk"
-version = "0.9.22"
+version = "0.9.26"
 description = ""
 authors = [
     "Martin Fadler <martin.fadler@unique.ch>",
@@ -9,6 +9,9 @@ authors = [
 ]
 readme = ["README.md", "CHANGELOG.md"]
 license = "MIT"
+classifiers = [
+    "Programming Language :: Python :: 3.11"
+]
 
 [tool.poetry.dependencies]
 python = "^3.11"

{unique_sdk-0.9.22 → unique_sdk-0.9.26}/unique_sdk/api_resources/_content.py

@@ -65,8 +65,28 @@ class Content(APIResource["Content"]):
         where: "Content.ContentWhereInput"
         chatId: NotRequired[str]
 
-    class IngestionConfig(TypedDict):
+    class CustomApiOptions(TypedDict):
+        apiIdentifier: str
+        apiPayload: Optional[str]
+        customisationType: str
+
+    class VttConfig(TypedDict, total=False):
+        languageModel: Optional[str]
+
+    class IngestionConfig(TypedDict, total=False):
+        chunkMaxTokens: Optional[int]
+        chunkMaxTokensOnePager: Optional[int]
+        chunkMinTokens: Optional[int]
+        chunkStrategy: Optional[str]
+        customApiOptions: Optional[List["Content.CustomApiOptions"]]
+        documentMinTokens: Optional[int]
+        excelReadMode: Optional[str]
+        jpgReadMode: Optional[str]
+        pdfReadMode: Optional[str]
+        pptReadMode: Optional[str]
         uniqueIngestionMode: str
+        vttConfig: Optional["Content.VttConfig"]
+        wordReadMode: Optional[str]
 
     class Input(TypedDict):
         key: str

{unique_sdk-0.9.22 → unique_sdk-0.9.26}/unique_sdk/api_resources/_search.py

@@ -8,7 +8,7 @@ class Search(APIResource["Search"]):
     OBJECT_NAME: ClassVar[Literal["search.search"]] = "search.search"
 
     class CreateParams(RequestOptions):
-        chatId: str
+        chatId: NotRequired[Optional[str]]
         searchString: str
         searchType: Literal["VECTOR", "COMBINED"]
         language: NotRequired[Optional[str]]

{unique_sdk-0.9.22 → unique_sdk-0.9.26}/unique_sdk/utils/file_io.py

@@ -1,10 +1,12 @@
 import os
 import tempfile
 from pathlib import Path
+from typing import Optional
 
 import requests
 
 import unique_sdk
+from unique_sdk.api_resources._content import Content
 
 
 # download readUrl a random directory in /tmp
@@ -38,19 +40,21 @@ def upload_file(
     mime_type,
     scope_or_unique_path=None,
     chat_id=None,
+    ingestion_config: Optional[Content.IngestionConfig] = None,
 ):
     # check that chatid or scope_or_unique_path is provided
     if not chat_id and not scope_or_unique_path:
         raise ValueError("chat_id or scope_or_unique_path must be provided")
 
     size = os.path.getsize(path_to_file)
-    createdContent = unique_sdk.Content.upsert(
+    createdContent = Content.upsert(
         user_id=userId,
         company_id=companyId,
         input={
             "key": displayed_filename,
             "title": displayed_filename,
             "mimeType": mime_type,
+            "ingestionConfig": ingestion_config,  # Pass ingestionConfig here
         },
         scopeId=scope_or_unique_path,
         chatId=chat_id,
@@ -78,6 +82,7 @@ def upload_file(
                 "title": displayed_filename,
                 "mimeType": mime_type,
                 "byteSize": size,
+                "ingestionConfig": ingestion_config,
             },
             fileUrl=createdContent.readUrl,
             chatId=chat_id,
@@ -91,6 +96,7 @@ def upload_file(
                 "title": displayed_filename,
                 "mimeType": mime_type,
                 "byteSize": size,
+                "ingestionConfig": ingestion_config,
             },
             fileUrl=createdContent.readUrl,
             scopeId=scope_or_unique_path,