Create an Empty Knowledge Base
Creates an empty knowledge base. Add documents to it with Create Document by Text or Create Document by File.
Request body
Name of the knowledge base.
Description of the knowledge base.
high_quality uses embedding models for precise search; economy uses keyword-based indexing.
Controls who can access this knowledge base. only_me restricts to the creator, all_team_members grants access to the entire workspace, partial_members grants access to specified members.
vendor for internal knowledge base, external for external knowledge base.
Embedding model name. Use the model field from Get Available Models with model_type=text-embedding.
Embedding model provider identifier, formatted as organization/plugin_name/provider_name (e.g. langgenius/openai/openai). A bare name like openai expands to langgenius/<name>/<name> and works only for langgenius-published plugins.
Get valid values from the provider field of Get Available Models with model_type=text-embedding.
ID of the external knowledge API connection.
ID of the external knowledge base.
Response
Knowledge base created successfully.
Unique identifier of the knowledge base.
Display name of the knowledge base. Unique within the workspace.
Optional text describing the purpose or contents of the knowledge base.
Provider type. vendor for internally managed, external for external knowledge base connections.
Controls who can access this knowledge base. Possible values: only_me, all_team_members, partial_members.
Data source type of the documents, null if not yet configured.
high_quality uses embedding models for precise search; economy uses keyword-based indexing.
Number of applications currently using this knowledge base.
Total number of documents in the knowledge base.
Total word count across all documents.
ID of the user who created the knowledge base.
Display name of the creator.
Creation timestamp (Unix epoch in seconds).
ID of the user who last updated the knowledge base.
Last update timestamp (Unix epoch in seconds).
Name of the embedding model used for indexing.
Embedding model provider identifier, formatted as organization/plugin_name/provider_name (e.g. langgenius/openai/openai). Legacy knowledge bases may return the bare short form (e.g. openai).
Whether the configured embedding model is currently available.
Document chunking mode. text_model for standard text chunking, hierarchical_model for parent-child structure, qa_model for QA pair extraction.
Whether built-in metadata fields (e.g., document_name, uploader) are enabled.
Pipeline ID, if a custom processing pipeline is configured.
Runtime processing mode.
Chunk structure configuration.
Whether the knowledge base is published.
Total number of documents.
Number of documents that are enabled and available.
Whether API access is enabled for this knowledge base.
Whether multimodal content processing is enabled.
Display name of the knowledge base maintainer. null if not set.
Account IDs of members granted access when permission is partial_members. Always present on the update response; on the detail response, present only when permission is partial_members.