Merge branch 'dev' into k_reranker

This commit is contained in:
Timothy Jaeryang Baek
2025-03-26 20:50:31 -07:00
committed by GitHub
147 changed files with 6065 additions and 1350 deletions
+7
View File
@@ -358,6 +358,7 @@ async def get_rag_config(request: Request, user=Depends(get_admin_user)):
"content_extraction": {
"engine": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
"tika_server_url": request.app.state.config.TIKA_SERVER_URL,
"docling_server_url": request.app.state.config.DOCLING_SERVER_URL,
"document_intelligence_config": {
"endpoint": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
"key": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
@@ -428,6 +429,7 @@ class DocumentIntelligenceConfigForm(BaseModel):
class ContentExtractionConfig(BaseModel):
engine: str = ""
tika_server_url: Optional[str] = None
docling_server_url: Optional[str] = None
document_intelligence_config: Optional[DocumentIntelligenceConfigForm] = None
@@ -540,6 +542,9 @@ async def update_rag_config(
request.app.state.config.TIKA_SERVER_URL = (
form_data.content_extraction.tika_server_url
)
request.app.state.config.DOCLING_SERVER_URL = (
form_data.content_extraction.docling_server_url
)
if form_data.content_extraction.document_intelligence_config is not None:
request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT = (
form_data.content_extraction.document_intelligence_config.endpoint
@@ -648,6 +653,7 @@ async def update_rag_config(
"content_extraction": {
"engine": request.app.state.config.CONTENT_EXTRACTION_ENGINE,
"tika_server_url": request.app.state.config.TIKA_SERVER_URL,
"docling_server_url": request.app.state.config.DOCLING_SERVER_URL,
"document_intelligence_config": {
"endpoint": request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
"key": request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,
@@ -994,6 +1000,7 @@ def process_file(
loader = Loader(
engine=request.app.state.config.CONTENT_EXTRACTION_ENGINE,
TIKA_SERVER_URL=request.app.state.config.TIKA_SERVER_URL,
DOCLING_SERVER_URL=request.app.state.config.DOCLING_SERVER_URL,
PDF_EXTRACT_IMAGES=request.app.state.config.PDF_EXTRACT_IMAGES,
DOCUMENT_INTELLIGENCE_ENDPOINT=request.app.state.config.DOCUMENT_INTELLIGENCE_ENDPOINT,
DOCUMENT_INTELLIGENCE_KEY=request.app.state.config.DOCUMENT_INTELLIGENCE_KEY,