zlei6/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-07-25 09:53:29 +08:00
Code Issues Packages Projects Releases Wiki Activity

Go: use NATS as the message queue (#15327)

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

```
RAGFlow(admin)> mq publish 'msg2';
SUCCESS
RAGFlow(admin)> mq publish 'msg3';
SUCCESS
RAGFlow(admin)> mq list;
+---------+---------------+
| message | subject       |
+---------+---------------+
| msg1    | tasks.RAGFLOW |
| msg2    | tasks.RAGFLOW |
| msg3    | tasks.RAGFLOW |
+---------+---------------+
RAGFlow(admin)> mq pull 2;
+---------+---------------+
| message | subject       |
+---------+---------------+
| msg1    | tasks.RAGFLOW |
| msg2    | tasks.RAGFLOW |
+---------+---------------+
RAGFlow(admin)> mq pull noack;
+---------+---------------+
| message | subject       |
+---------+---------------+
| abc     | tasks.RAGFLOW |
+---------+---------------+
RAGFlow(admin)> mq show
+-------------------+----------------+--------+---------------+---------------+-------------------+---------------+
| ack_pending_count | consumer_count | memory | message_count | pending_count | redelivered_count | waiting_count |
+-------------------+----------------+--------+---------------+---------------+-------------------+---------------+
| 2                 | 1              | 0      | 2             | 0             | 1                 | 0             |
+-------------------+----------------+--------+---------------+---------------+-------------------+---------------+

RAGFlow(admin)> list ingestors;
+--------------+-------------------------------------------+--------+
| host         | name                                      | status |
+--------------+-------------------------------------------+--------+
| 192.168.1.38 | ingestor-8f0e4bd5650a4ac58b0151969fbf6935 | alive  |
+--------------+-------------------------------------------+--------+

RAGFlow(admin)> list ingestion tasks;
+----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+
| document_id                      | id                               | status    | step | user        | user_id                          |
+----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+
| ffe64fae423411f1a2d938a74640adcc | 90d3d0f6528941c1ac8eb0360effccc4 | COMPLETED | 5    | aaa@aaa.com | 2ba4881420fa11f19e9c38a74640adcc |
+----------------------------------+----------------------------------+-----------+------+-------------+----------------------------------+

RAGFlow(admin)> remove ingestion tasks '90d3d0f6528941c1ac8eb0360effccc4';
+---------+----------------------------------+
| delete  | task_id                          |
+---------+----------------------------------+
| success | 90d3d0f6528941c1ac8eb0360effccc4 |
+---------+----------------------------------+

RAGFlow(admin)> stop ingestion tasks 'e89e20d9a25848a1b79bd9345ddbfe1d';
+----------+----------------------------------+
| status   | task_id                          |
+----------+----------------------------------+
| STOPPING | e89e20d9a25848a1b79bd9345ddbfe1d |
+----------+----------------------------------+

# Publish a message
RAGFlow(admin)> mq publish 'cdd';
SUCCESS

# List current tasks in the message queue
RAGFlow(admin)> mq list
+----------------------------------+---------------+
| message                          | subject       |
+----------------------------------+---------------+
| 7ce392a3c1624cd2be4b5276e8825059 | tasks.RAGFLOW |
+----------------------------------+---------------+

# Consume a task from the message queue
RAGFlow(admin)> mq pull
+------+-----+----------------+
| ack  | id  | type           |
+------+-----+----------------+
| true | cdd | ingestion_test |
+------+-----+----------------+

# User mode
# List ingestion tasks, followed by dataset id
RAGFlow(user)> list ingestion tasks from '0abe79f9423311f1ad8d38a74640adcc';
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+
| create_date               | create_time   | dataset_id                       | document_id                      | id                               | schema | status    | update_date               | update_time   | user_id                          |
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+
| 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d |        | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc |
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+

RAGFlow(user)> list ingestion tasks;
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+
| create_date               | create_time   | dataset_id                       | document_id                      | id                               | schema | status    | update_date               | update_time   | user_id                          |
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+
| 2026-06-02T19:02:31+08:00 | 1780398151417 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | e89e20d9a25848a1b79bd9345ddbfe1d |        | COMPLETED | 2026-06-02T19:02:52+08:00 | 1780398172208 | 2ba4881420fa11f19e9c38a74640adcc |
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+

# Create an ingestion task
# First argument is document id, second argument is dataset id
RAGFlow(user)> start ingestion 'ffe64fae423411f1a2d938a74640adcc' from '0abe79f9423311f1ad8d38a74640adcc';
+----------------------------------+-------------------------------------------+
| document_id                      | result                                    |
+----------------------------------+-------------------------------------------+
| ffe64fae423411f1a2d938a74640adcc | task_id: 8d758cd14a8b4ba8ab505003fb52017d |
+----------------------------------+-------------------------------------------+

# Pause an ingestion task, first argument is ingestion id
RAGFlow(user)> stop ingestion '8d758cd14a8b4ba8ab505003fb52017d';
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+
| create_date               | create_time   | dataset_id                       | document_id                      | id                               | schema | status    | update_date               | update_time   | user_id                          |
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+
| 2026-05-30T20:21:06+08:00 | 1780143666289 | 0abe79f9423311f1ad8d38a74640adcc | ffe64fae423411f1a2d938a74640adcc | 8d758cd14a8b4ba8ab505003fb52017d |        | COMPLETED | 2026-05-30T20:21:26+08:00 | 1780143686431 | 2ba4881420fa11f19e9c38a74640adcc |
+---------------------------+---------------+----------------------------------+----------------------------------+----------------------------------+--------+-----------+---------------------------+---------------+----------------------------------+

# Delete an ingestion task
RAGFlow(api/default)> remove ingestion tasks 'f366450a27d54677aec1c7090add30f0';
+---------+----------------------------------+
| remove  | task_id                          |
+---------+----------------------------------+
| success | f366450a27d54677aec1c7090add30f0 |
+---------+----------------------------------+

```

### 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
2026-06-12 14:56:44 +08:00
committed by GitHub
parent 30724140d2
commit e96bc37d06
45 changed files with 2911 additions and 2337 deletions
Download Patch File Download Diff File Expand all files Collapse all files

169
internal/cli/user_command.go
View File

@@ -3273,6 +3273,173 @@ func formatRequestError(action string, err error) error {
}
}
func (c *CLI) ListUserIngestionTasks(cmd *Command) (ResponseIf, error) {
if c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].APIToken == nil && c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].LoginToken == nil {
return nil, fmt.Errorf("API token not set. Please login first")
}
if c.Config.CLIMode != APIMode {
return nil, fmt.Errorf("this command is only allowed in USER mode")
}
datasetID, ok := cmd.Params["dataset_id"].(*string)
if !ok {
datasetID = nil
}
payload := map[string]interface{}{
"dataset_id": datasetID,
}
resp, err := c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].Request("GET", "/datasets/ingestion/tasks", "web", nil, payload)
if err != nil {
return nil, fmt.Errorf("failed to list ingestion tasks: %w", err)
}
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to list ingestion 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 ingestion 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 *CLI) UserStartIngestionCommand(cmd *Command) (ResponseIf, error) {
if c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].APIToken == nil && c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].LoginToken == nil {
return nil, fmt.Errorf("API token not set. Please login first")
}
if c.Config.CLIMode != APIMode {
return nil, fmt.Errorf("this command is only allowed in USER mode")
}
documentID, ok := cmd.Params["document_id"].(string)
if !ok {
return nil, fmt.Errorf("document_id not provided")
}
datasetID, ok := cmd.Params["dataset_id"].(string)
if !ok {
return nil, fmt.Errorf("dataset_id not provided")
}
payload := map[string]interface{}{
"documents": []string{documentID},
"dataset_id": datasetID,
}
url := fmt.Sprintf("/datasets/%s/documents/parse", datasetID)
resp, err := c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].Request("POST", url, "web", nil, payload)
if err != nil {
return nil, fmt.Errorf("failed to ingest file: %w", err)
}
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to ingest file: 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("ingest file 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 *CLI) UserStopIngestionCommand(cmd *Command) (ResponseIf, error) {
if c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].APIToken == nil && c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].LoginToken == nil {
return nil, fmt.Errorf("API token not set. Please login first")
}
if c.Config.CLIMode != APIMode {
return nil, fmt.Errorf("this command is only allowed in USER mode")
}
tasks, ok := cmd.Params["tasks"].([]string)
if !ok {
return nil, fmt.Errorf("uri not provided")
}
payload := map[string]interface{}{
"tasks": tasks,
}
resp, err := c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].Request("PUT", "/datasets/ingestion/tasks", "web", nil, payload)
if err != nil {
return nil, fmt.Errorf("failed to ingest file: %w", err)
}
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to ingest file: 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("ingest file 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 *CLI) UserRemoveTaskCommand(cmd *Command) (ResponseIf, error) {
if c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].APIToken == nil && c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].LoginToken == nil {
return nil, fmt.Errorf("API token not set. Please login first")
}
if c.Config.CLIMode != APIMode {
return nil, fmt.Errorf("this command is only allowed in USER mode")
}
tasks, ok := cmd.Params["tasks"].([]string)
if !ok {
return nil, fmt.Errorf("tasks not provided")
}
payload := map[string]interface{}{
"tasks": tasks,
}
resp, err := c.APIServerClientMap[c.Config.APIClientConfig.CurrentAPIServer].Request("DELETE", "/datasets/ingestion/tasks", "web", nil, payload)
if err != nil {
return nil, fmt.Errorf("failed to remove tasks: %w", err)
}
if resp.StatusCode != 200 {
return nil, fmt.Errorf("failed to remove 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("remove 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 *CLI) ChunkCommand(cmd *Command) (ResponseIf, error) {
if c.Config.CLIMode != APIMode {
return nil, fmt.Errorf("this command is only allowed in USER mode")
@@ -3294,12 +3461,12 @@ func (c *CLI) ChunkCommand(cmd *Command) (ResponseIf, error) {
if explain {
fmt.Printf("Explain chunk file: %s, DSL: %s\n", filename, dsl)
} else {
// TODO: not implemented
fmt.Printf("Chunk file: %s, DSL: %s\n", filename, dsl)
}
var result SimpleResponse
result.Code = 0
result.Message = fmt.Sprintf("Success to chunk %s", filename)
return &result, nil
}