unique_toolkit 1.50.3__tar.gz → 1.50.4__tar.gz

{unique_toolkit-1.50.3 → unique_toolkit-1.50.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: unique-toolkit
-Version: 1.50.3
+Version: 1.50.4
 Summary: 
 Author: Cedric Klinkert, Martin Fadler, Sadique Sheik, Fabian Schläpfer, Pascal Hauri, Ejiroghene Oki-Peter, Rami Azouz, Ricardo Visini, Sanzio Monti
 Author-email: Cedric Klinkert <cedric.klinkert@unique.ch>, Martin Fadler <martin.fadler@unique.ch>, Sadique Sheik <sadique@unique.ch>, Fabian Schläpfer <fabian@unique.ch>, Pascal Hauri <pascal@unique.ch>, Ejiroghene Oki-Peter <oki-peter.ejiroghene@unique.ai>, Rami Azouz <rami.ext@unique.ch>, Ricardo Visini <ricardo.visini@unique.ch>, Sanzio Monti <sanzio.monti@unique.ai>

{unique_toolkit-1.50.3 → unique_toolkit-1.50.4}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "unique_toolkit"
-version = "1.50.3"
+version = "1.50.4"
 description = ""
 readme = "README.md"
 requires-python = ">=3.12"

{unique_toolkit-1.50.3 → unique_toolkit-1.50.4}/unique_toolkit/content/functions.py

@@ -21,7 +21,11 @@ from unique_toolkit.content.schemas import (
     FolderInfo,
     PaginatedContentInfos,
 )
-from unique_toolkit.content.utils import map_contents, map_to_content_chunks
+from unique_toolkit.content.utils import (
+    _apply_ingestion_upload_url_override,
+    map_contents,
+    map_to_content_chunks,
+)
 
 logger = logging.getLogger(f"toolkit.{DOMAIN_NAME}.{__name__}")
 
@@ -450,6 +454,8 @@ def _trigger_upload_content(
         logger.error(error_msg)
         raise ValueError(error_msg)
 
+    write_url = _apply_ingestion_upload_url_override(write_url)
+
     headers = {
         "X-Ms-Blob-Content-Type": mime_type,
         "X-Ms-Blob-Type": "BlockBlob",
@@ -513,6 +519,7 @@ def _trigger_upload_content(
             scope_id=scope_id,
         )  # type: ignore
 
+    created_content["writeUrl"] = write_url
     return Content.model_validate(created_content, by_alias=True, by_name=True)
 
 
@@ -576,6 +583,8 @@ async def _trigger_upload_content_async(
         logger.error(error_msg)
         raise ValueError(error_msg)
 
+    write_url = _apply_ingestion_upload_url_override(write_url)
+
     headers = {
         "X-Ms-Blob-Content-Type": mime_type,
         "X-Ms-Blob-Type": "BlockBlob",
@@ -641,6 +650,7 @@ async def _trigger_upload_content_async(
             scope_id=scope_id,
         )
 
+    created_content["writeUrl"] = write_url
     return Content.model_validate(created_content, by_alias=True, by_name=True)
 
 

{unique_toolkit-1.50.3 → unique_toolkit-1.50.4}/unique_toolkit/content/utils.py

@@ -1,7 +1,10 @@
 from __future__ import annotations
 
+import logging
+import os
 import re
 from typing import TYPE_CHECKING
+from urllib.parse import urlparse
 
 import tiktoken
 import unique_sdk
@@ -9,9 +12,36 @@ from typing_extensions import deprecated
 
 from unique_toolkit.content.schemas import Content, ContentChunk, ContentMetadata
 
+logger = logging.getLogger(__name__)
+
 if TYPE_CHECKING:
     from unique_toolkit.language_model.infos import LanguageModelInfo
 
+INGESTION_UPLOAD_API_URL_INTERNAL_ENV = "INGESTION_UPLOAD_API_URL_INTERNAL"
+
+_ingestion_upload_api_url_internal: str | None = (
+    (v.strip() or None)
+    if (v := os.getenv(INGESTION_UPLOAD_API_URL_INTERNAL_ENV))
+    else None
+)
+
+
+def _apply_ingestion_upload_url_override(write_url: str) -> str:
+    """
+    If INGESTION_UPLOAD_API_URL_INTERNAL is set, replace the scheme+authority+path
+    of write_url with that value, preserving the query string (e.g. key=...).
+    Used when the toolkit runs in Kubernetes or a private network so uploads
+    go to a reachable ingestion service URL.
+    """
+    if not _ingestion_upload_api_url_internal:
+        return write_url
+    parsed = urlparse(write_url)
+    custom_base = _ingestion_upload_api_url_internal.rstrip("/")
+    logger.debug(
+        f"Overriding ingestion upload URL {parsed.scheme}://{parsed.hostname}{parsed.path} with: {custom_base}"
+    )
+    return custom_base + ("?" + parsed.query if parsed.query else "")
+
 
 def _map_content_id_to_chunks(content_chunks: list[ContentChunk]):
     doc_id_to_chunks: dict[str, list[ContentChunk]] = {}