import { Callout, Tabs } from "@/docs/components";

Knowledge

<div className="status-badge status-stable">Stable</div>

Upload documents and query your knowledge base for RAG applications.

Upload Document

<div className="api-endpoint"> <span className="method-badge method-badge-post">POST</span> <span className="path">/api/v1/documents/upload-file</span> </div>

Upload one or more documents to your knowledge base using multipart form data.

Request

Use multipart/form-data with the files field:

bash

curl -X POST "https://elizacloud.ai/api/v1/documents/upload-file" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -F "[email protected]" \
  -F "characterId=optional_agent_id"

Parameters

Parameter	Type	Required	Description
`files`	file[]	✓	One or more files to upload (max 5)
`characterId`	string		Associate with a specific agent

Upload Limits

Limit	Value
Max file size	5 MB per file
Max files per batch	5 files
Max total batch size	5 MB

Supported Formats

Format	Extensions
PDF	`.pdf`
Text	`.txt`, `.md`
Documents	`.doc`, `.docx`
Web	`.html`
Data	`.json`, `.csv`

Response

json

{
  "success": true,
  "data": [
    {
      "id": "doc_abc123",
      "filename": "document.pdf",
      "type": "application/pdf",
      "size": 1048576,
      "uploadedAt": 1705312800000,
      "fragmentCount": 42,
      "status": "success"
    }
  ],
  "message": "Successfully uploaded 1 file(s)",
  "successCount": 1,
  "failedCount": 0,
  "totalCount": 1
}

List Documents

<div className="api-endpoint"> <span className="method-badge method-badge-get">GET</span> <span className="path">/api/v1/documents</span> </div>

Get all documents in your knowledge base.

Response

json

{
  "documents": [
    {
      "id": "doc_abc123",
      "name": "company-handbook.pdf",
      "size": 2097152,
      "chunks": 85,
      "createdAt": "2024-01-15T10:30:00Z"
    }
  ],
  "total": 15
}

Query Knowledge

<div className="api-endpoint"> <span className="method-badge method-badge-get">GET</span> <span className="path">/api/v1/documents/query</span> </div>

Search your knowledge base.

Request

json

{
  "query": "How do I reset my password?",
  "limit": 5,
  "minScore": 0.7
}

Parameters

Parameter	Type	Required	Description
`query`	string	✓	Search query
`limit`	integer		Max results (default: 5)
`minScore`	number		Minimum similarity (0-1)

Response

json

{
  "results": [
    {
      "content": "To reset your password, go to Settings > Security > Reset Password...",
      "score": 0.92,
      "documentId": "doc_abc123",
      "documentName": "user-guide.pdf"
    }
  ]
}

Get Document

<div className="api-endpoint"> <span className="method-badge method-badge-get">GET</span> <span className="path">/api/v1/documents/{"{id}"}</span> </div>

Get document details.

Delete Document

<div className="api-endpoint"> <span className="method-badge method-badge-delete">DELETE</span> <span className="path">/api/v1/documents/{"{id}"}</span> </div>

Remove a document from your knowledge base.

Check Document

<div className="api-endpoint"> <span className="method-badge method-badge-post">POST</span> <span className="path">/api/v1/documents/check</span> </div>

Check whether an agent or character has documents.

<Callout type="info"> Documents are stored in the runtime documents table and chunked for search. </Callout>