Qubrid AI

opencollection: 1.0.0
info:
  name: Qubrid AI RAG API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Knowledge Bases
    type: folder
  items:
  - info:
      name: List knowledge bases
      type: http
    http:
      method: GET
      url: https://platform.qubrid.com/api/v1/rag/knowledge-bases
    docs: Returns a list of all knowledge bases associated with the authenticated user's account, including their name, document
      count, and processing status.
  - info:
      name: Create a knowledge base
      type: http
    http:
      method: POST
      url: https://platform.qubrid.com/api/v1/rag/knowledge-bases
      body:
        type: json
        data: '{}'
    docs: Creates a new knowledge base for storing and retrieving enterprise documents. The knowledge base serves as a container
      for documents that will be chunked, embedded, and indexed for retrieval-augmented generation queries.
  - info:
      name: Retrieve a knowledge base
      type: http
    http:
      method: GET
      url: https://platform.qubrid.com/api/v1/rag/knowledge-bases/:knowledge_base_id
      params:
      - name: knowledge_base_id
        value: ''
        type: path
        description: The unique identifier of the knowledge base.
    docs: Returns details about a specific knowledge base including its configuration, document count, total chunk count,
      and embedding model used.
  - info:
      name: Delete a knowledge base
      type: http
    http:
      method: DELETE
      url: https://platform.qubrid.com/api/v1/rag/knowledge-bases/:knowledge_base_id
      params:
      - name: knowledge_base_id
        value: ''
        type: path
        description: The unique identifier of the knowledge base.
    docs: Permanently deletes a knowledge base and all of its associated documents, embeddings, and vector index data. This
      action cannot be undone.
- info:
    name: Documents
    type: folder
  items:
  - info:
      name: List documents in a knowledge base
      type: http
    http:
      method: GET
      url: https://platform.qubrid.com/api/v1/rag/knowledge-bases/:knowledge_base_id/documents
      params:
      - name: knowledge_base_id
        value: ''
        type: path
        description: The unique identifier of the knowledge base.
    docs: Returns a list of all documents uploaded to the specified knowledge base, including their name, size, processing
      status, and chunk count.
  - info:
      name: Upload a document
      type: http
    http:
      method: POST
      url: https://platform.qubrid.com/api/v1/rag/knowledge-bases/:knowledge_base_id/documents
      params:
      - name: knowledge_base_id
        value: ''
        type: path
        description: The unique identifier of the knowledge base.
      body:
        type: multipart-form
        data: []
    docs: Uploads a new document to the specified knowledge base. The document will be automatically processed, chunked into
      segments, and embedded using the knowledge base's configured embedding model. Supported formats include PDF, TXT, CSV,
      DOCX, and other common document types.
  - info:
      name: Delete a document
      type: http
    http:
      method: DELETE
      url: https://platform.qubrid.com/api/v1/rag/knowledge-bases/:knowledge_base_id/documents/:document_id
      params:
      - name: knowledge_base_id
        value: ''
        type: path
        description: The unique identifier of the knowledge base.
      - name: document_id
        value: ''
        type: path
        description: The unique identifier of the document.
    docs: Deletes a document from the knowledge base and removes all associated chunks and embeddings from the vector index.
- info:
    name: RAG Queries
    type: folder
  items:
  - info:
      name: Query with RAG
      type: http
    http:
      method: POST
      url: https://platform.qubrid.com/api/v1/rag/query
      body:
        type: json
        data: '{}'
    docs: Performs a retrieval-augmented generation query against a specified knowledge base. The API retrieves the most relevant
      document chunks based on semantic similarity to the query, then uses them as context for a large language model to generate
      an accurate, grounded response. The response includes both the generated answer and the source document references used.
bundled: true