Train KB from Image
lyzr_kb_train_imageUpload an image and train it into a knowledge base to enable AI retrieval and analysis of visual content.
Instructions
Upload and train an image file into a knowledge base.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"rag_id": "<rag_id>",
"file_content_base64": "<file_content_base64>",
"filename": "<filename>"
},
"name": "lyzr_kb_train_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| rag_id | Yes | The ID of the RAG system to train | |
| filename | Yes | Name of the file being uploaded | |
| mime_type | No | MIME type of the file (optional) | |
| chunk_size | No | Chunk size for splitting the document (default 1000) | |
| extra_info | No | Extra metadata JSON string (default "{}") | |
| chunk_overlap | No | Chunk overlap for splitting the document (default 100) | |
| parser_config | No | Optional JSON string with parser configuration | |
| file_content_base64 | Yes | Base64-encoded contents of the file to train |