zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-14 00:48:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

Go: implement provider: MinerU (#14990)

Browse Source 
### What problem does this PR solve?

Implement MinerU Provider

**The following functionalities are now supported:**

**MinerU**
----
- [x] Parse file
- [x] Show task
- [ ] ~~List tasks~~

**Verified examples from the CLI:**
```plaintext
RAGFlow(user)> parse with 'vlm@test@mineru' file 'https://arxiv.org/pdf/2505.09358'
+--------------------------------------+
| task_id                              |
+--------------------------------------+
| 142ac8ea-d9d0-4a68-a2d1-d3af67635dc9 |
+--------------------------------------+

RAGFlow(user)> show 'test@mineru' task '142ac8ea-d9d0-4a68-a2d1-d3af67635dc9'
+--------------------------------------------+-------+
| content                                    | index |
+--------------------------------------------+-------+
| Task is running... Progress: 17 / 18 pages | 0     |
+--------------------------------------------+-------+

RAGFlow(user)> show 'test@mineru' task '142ac8ea-d9d0-4a68-a2d1-d3af67635dc9'
+--------------------------------------------------------------------------------------------+-------+
| content                                                                                    | index |
+--------------------------------------------------------------------------------------------+-------+
| https://cdn-mineru.openxlab.org.cn/pdf/2026-05-18/142ac8ea-d9d0-4a68-a2d1-d3af67635dc9.zip | 0     |
+--------------------------------------------------------------------------------------------+-------+

```


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
This commit is contained in:
Haruko386
2026-05-19 10:49:33 +08:00
committed by GitHub
parent 525a87be0f
commit db9e782747
8 changed files with 310 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
internal/cli/user_command.go
View File

@@ -2381,11 +2381,16 @@ func (c *RAGFlowClient) ParseFileUserCommand(cmd *Command) (ResponseIf, error) {
filename, ok = cmd.Params["file"].(string)
if ok {
// read file and convert to base64
var err error
fileContent, err = os.ReadFile(filename)
if err != nil {
return nil, fmt.Errorf("failed to read file: %w", err)
// For online file
if strings.HasPrefix(filename, "http://") || strings.HasPrefix(filename, "https://") {
fileURL = filename
} else {
// read file and convert to base64
var err error
fileContent, err = os.ReadFile(filename)
if err != nil {
return nil, fmt.Errorf("failed to read file: %w", err)
}
}
} else {
fileURL, ok = cmd.Params["url"].(string)