zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-23 00:46:42 +08:00
Code Issues Packages Projects Releases Wiki Activity

Go: fix OCR command (#14891)

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

RAGFlow(user)> ocr with 'hunyuanocr@test@gitee' file './picture.png'
+----------------------------------------------------------+
| text                                                     |
+----------------------------------------------------------+
| 生活不是等待风暴过去，而是学会在雨中翩翩起舞。

——佚名                                                       |
+----------------------------------------------------------+

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2026-05-13 17:29:53 +08:00
committed by GitHub
parent 8cb2bf04fb
commit b18640d228
35 changed files with 215 additions and 62 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
internal/cli/user_command.go
View File

@@ -2092,22 +2092,36 @@ func (c *RAGFlowClient) OCRUserCommand(cmd *Command) (ResponseIf, error) {
return nil, fmt.Errorf("model name not provided and no current model set. Use 'use model' command first")
}
filename, ok := cmd.Params["file"].(string)
if !ok {
return nil, fmt.Errorf("text not provided")
var filename string
var fileURL string
var ok bool
var fileContent []byte
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)
}
} else {
fileURL, ok = cmd.Params["url"].(string)
if !ok {
return nil, fmt.Errorf("file or url not provided")
}
}
// read file and convert to base64
text, err := os.ReadFile(filename)
if err != nil {
return nil, fmt.Errorf("failed to read file: %w", err)
}
base64Text := base64.StdEncoding.EncodeToString(text)
payload := map[string]interface{}{
"provider_name": providerName,
"instance_name": instanceName,
"model_name": modelName,
"content": base64Text,
}
if fileContent != nil {
payload["content"] = fileContent
} else {
payload["url"] = fileURL
}
url := "/file/ocr"
@@ -2119,7 +2133,7 @@ func (c *RAGFlowClient) OCRUserCommand(cmd *Command) (ResponseIf, error) {
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to OCR document: HTTP %d, body: %s", resp.StatusCode, string(resp.Body))
}
var result CommonResponse
var result CommonDataResponse
if err = json.Unmarshal(resp.Body, &result); err != nil {
return nil, fmt.Errorf("OCR document failed: invalid JSON (%w)", err)
}

37
internal/cli/user_parser.go
View File

@@ -2822,20 +2822,33 @@ func (p *Parser) parseOCRCommand() (*Command, error) {
}
p.nextToken()
if p.curToken.Type != TokenFile {
return nil, fmt.Errorf("expected FILE to OCR")
}
p.nextToken() // consume FILE
file, err := p.parseQuotedString()
if err != nil {
return nil, err
}
p.nextToken()
cmd := NewCommand("ocr_user_command")
switch p.curToken.Type {
case TokenFile:
p.nextToken()
var file string
file, err = p.parseQuotedString()
if err != nil {
return nil, err
}
cmd.Params["file"] = file
p.nextToken()
case TokenURL:
p.nextToken()
var url string
url, err = p.parseQuotedString()
if err != nil {
return nil, err
}
cmd.Params["url"] = url
p.nextToken()
default:
return nil, fmt.Errorf("expected FILE or URL")
}
cmd.Params["composite_model_name"] = compositeModelName
cmd.Params["file"] = file
return cmd, nil
}