Go: add file parse command (#14892)

### 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                                                       |
+----------------------------------------------------------+

RAGFlow(user)> list 'test@gitee' tasks;
+---------+----------------------------------+
| status  | task_id                          |
+---------+----------------------------------+
| success | C3FX4MQNKY5MGC6ZFMIXIAMJKHCEBQB5 |
+---------+----------------------------------+
RAGFlow(user)> show 'test@gitee' task 'C3FX4MQNKY5MGC6ZFMIXIAMJKHCEBQB5';
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+
| content                                                                                                                                                                                                                                                          | index |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+
| # PDF 1: Purpose of RAGFlow  

RAGFlow is an open source Retrieval-Augmented Generation (RAG) engine designed to turn raw documents into reliable context for large language models.Its purpose is to make it practical to build an Al assistant that can ans... | 1     |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+

```

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
This commit is contained in:
Jin Hai
2026-05-15 12:29:52 +08:00
committed by GitHub
parent 547b8cf9d8
commit 3a5df08c76
46 changed files with 1533 additions and 160 deletions

View File

@@ -2284,6 +2284,179 @@ func (c *RAGFlowClient) OCRUserCommand(cmd *Command) (ResponseIf, error) {
return &result, nil
}
func (c *RAGFlowClient) ParseFileUserCommand(cmd *Command) (ResponseIf, error) {
if c.HTTPClient.APIToken == "" && c.HTTPClient.LoginToken == "" {
return nil, fmt.Errorf("API token not set. Please login first")
}
if c.ServerType != "user" {
return nil, fmt.Errorf("this command is only allowed in USER mode")
}
var providerName, instanceName, modelName string
// Check if composite_model_name is provided in command
if compositeModelName, ok := cmd.Params["composite_model_name"].(string); ok && compositeModelName != "" {
names := strings.Split(compositeModelName, "@")
if len(names) != 3 {
return nil, fmt.Errorf("model name must be in format 'model@instance@provider'")
}
providerName = names[2]
instanceName = names[1]
modelName = names[0]
} else if c.CurrentModel != nil {
// Use current model if set
providerName = c.CurrentModel.Provider
instanceName = c.CurrentModel.Instance
modelName = c.CurrentModel.Model
} else {
return nil, fmt.Errorf("model name not provided and no current model set. Use 'use model' command first")
}
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")
}
}
payload := map[string]interface{}{
"provider_name": providerName,
"instance_name": instanceName,
"model_name": modelName,
}
if fileContent != nil {
payload["content"] = fileContent
} else {
payload["url"] = fileURL
}
url := "/file/parse"
resp, err := c.HTTPClient.Request("POST", url, "web", nil, payload)
if err != nil {
return nil, fmt.Errorf("failed to PARSE document: %w", err)
}
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to PARSE document: HTTP %d, body: %s", resp.StatusCode, string(resp.Body))
}
var result CommonDataResponse
if err = json.Unmarshal(resp.Body, &result); err != nil {
return nil, fmt.Errorf("PARSE document failed: invalid JSON (%w)", err)
}
if result.Code != 0 {
return nil, fmt.Errorf("%s", result.Message)
}
result.Duration = resp.Duration
return &result, nil
}
func (c *RAGFlowClient) ListTasksUserCommand(cmd *Command) (ResponseIf, error) {
if c.HTTPClient.APIToken == "" && c.HTTPClient.LoginToken == "" {
return nil, fmt.Errorf("API token not set. Please login first")
}
if c.ServerType != "user" {
return nil, fmt.Errorf("this command is only allowed in USER mode")
}
var providerName, instanceName string
// Check if composite_instance_name is provided in command
if compositeModelName, ok := cmd.Params["composite_instance_name"].(string); ok && compositeModelName != "" {
names := strings.Split(compositeModelName, "@")
if len(names) != 2 {
return nil, fmt.Errorf("model name must be in format 'instance@provider'")
}
providerName = names[1]
instanceName = names[0]
} else {
return nil, fmt.Errorf("no provider name or instance name")
}
url := fmt.Sprintf("/providers/%s/instances/%s/tasks", providerName, instanceName)
resp, err := c.HTTPClient.Request("GET", url, "web", nil, nil)
if err != nil {
return nil, fmt.Errorf("failed to list tasks: %w", err)
}
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to list tasks: HTTP %d, body: %s", resp.StatusCode, string(resp.Body))
}
var result CommonResponse
if err = json.Unmarshal(resp.Body, &result); err != nil {
return nil, fmt.Errorf("list tasks failed: invalid JSON (%w)", err)
}
if result.Code != 0 {
return nil, fmt.Errorf("%s", result.Message)
}
result.Duration = resp.Duration
return &result, nil
}
func (c *RAGFlowClient) ShowTaskUserCommand(cmd *Command) (ResponseIf, error) {
if c.HTTPClient.APIToken == "" && c.HTTPClient.LoginToken == "" {
return nil, fmt.Errorf("API token not set. Please login first")
}
if c.ServerType != "user" {
return nil, fmt.Errorf("this command is only allowed in USER mode")
}
var providerName, instanceName string
// Check if composite_instance_name is provided in command
if compositeModelName, ok := cmd.Params["composite_instance_name"].(string); ok && compositeModelName != "" {
names := strings.Split(compositeModelName, "@")
if len(names) != 2 {
return nil, fmt.Errorf("model name must be in format 'instance@provider'")
}
providerName = names[1]
instanceName = names[0]
} else {
return nil, fmt.Errorf("no provider name or instance name")
}
taskID, ok := cmd.Params["task_id"].(string)
if !ok {
return nil, fmt.Errorf("task id not provided")
}
url := fmt.Sprintf("/providers/%s/instances/%s/tasks/%s", providerName, instanceName, taskID)
resp, err := c.HTTPClient.Request("GET", url, "web", nil, nil)
if err != nil {
return nil, fmt.Errorf("failed to get task: %w", err)
}
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to get task: HTTP %d, body: %s", resp.StatusCode, string(resp.Body))
}
var result TaskResponse
if err = json.Unmarshal(resp.Body, &result); err != nil {
return nil, fmt.Errorf("get task failed: invalid JSON (%w)", err)
}
if result.Code != 0 {
return nil, fmt.Errorf("%s", result.Message)
}
result.Duration = resp.Duration
return &result, nil
}
func (c *RAGFlowClient) CheckProviderConnection(cmd *Command) (ResponseIf, error) {
if c.HTTPClient.APIToken == "" && c.HTTPClient.LoginToken == "" {
return nil, fmt.Errorf("API token not set. Please login first")