[Bug]: 添加大型资源文件时，无法进行有效的切分和生成.abstract.md 和.overview.md #386
Description
Bug Description
当添加大型的 pdf 文件，例如 药典，只有文件切分，无法生成有效的.abstract.md 和.overview.md
Steps to Reproduce
- 配置 ov.conf 如下
{
"storage": {
"workspace": "/Users/aaa/.openviking/workspace"
},
"log": {
"level": "INFO",
"output": "stdout"
},
"embedding": {
"dense": {
"api_base": "https://ark.cn-beijing.volces.com/api/v3",
"api_key": "a5b*****f0177",
"provider": "volcengine",
"dimension": 1024,
"model": "doubao-embedding-vision-250615"
}
},
"vlm": {
"provider" : "volcengine",
"model" : "doubao-seed-1-8-251228",
"api_key" : "a5b*****f0177",
"api_base" : "https://ark.cn-beijing.volces.com/api/v3"
}
}
- 执行python -m openviking serve
- curl -X POST http://localhost:1933/api/v1/resources \
-H "Content-Type: application/json"
-d '{"path": "https://www.ynxzy.com/temp/1686884123423.pdf"}'
Expected Behavior
有效的拆分和总结抽象
Actual Behavior
整份文件只有拆分
.abstract.md 和.overview.md 内容都为Directory overview
无法通过 search 方法查找到对应的内容
Minimal Reproducible Example
Error Logs
OpenViking Version
0.1.18
Python Version
3.11.6
Operating System
macOS
Model Backend
Volcengine (Doubao)
Additional Context
No response
Metadata
Metadata
Assignees
Labels
Type
Projects
Status