/v1/spaces| Name | Type | Required | Description |
|---|---|---|---|
X-API-Key | string | Optional |
namestringRequireddescriptionobjectavatar_urlobjectavatar_keyobjecttemplate_keyobjectenabled_toolsobjectapply_pii_pseudonymizationbooleanapply_oii_pseudonymizationbooleanapply_pii_to_knowledge_searchbooleaninclude_full_file_contentbooleanfast_pdf_extractionbooleanWhen enabled, PDFs uploaded in this space skip Docling and use fast pypdf text extraction. Much faster on large documents, but LOWER QUALITY than the default Docling route: no table structure and no layout/reading-order reconstruction. Scanned PDFs still use OCR/VLM.system_prompt_templateobjectknowledge_search_guidelinesobjectcurl -X POST '/api-proxy/v1/spaces' \
-H 'Authorization: Bearer <YOUR_TOKEN>' \
-H 'Content-Type: application/json' \
-d '{
"name": "string",
"description": {},
"avatar_url": {},
"avatar_key": {},
"template_key": {},
"enabled_tools": {},
"apply_pii_pseudonymization": false,
"apply_oii_pseudonymization": true,
"apply_pii_to_knowledge_search": true,
"include_full_file_content": false,
"fast_pdf_extraction": false,
"system_prompt_template": {},
"knowledge_search_guidelines": {}
}'No response body documented
curl -X POST '/api-proxy/v1/spaces' \
-H 'Authorization: Bearer <YOUR_TOKEN>' \
-H 'Content-Type: application/json' \
-d '{
"name": "string",
"description": {},
"avatar_url": {},
"avatar_key": {},
"template_key": {},
"enabled_tools": {},
"apply_pii_pseudonymization": false,
"apply_oii_pseudonymization": true,
"apply_pii_to_knowledge_search": true,
"include_full_file_content": false,
"fast_pdf_extraction": false,
"system_prompt_template": {},
"knowledge_search_guidelines": {}
}'No response body documented