Commit Graph

36 Commits

Author SHA1 Message Date
Jin Hai
dec2ce4a60 Go CLI: admin model framework (#16252) 2026-06-23 16:57:05 +08:00
Jin Hai
b661e9c19e Go CLI: admin list providers (#16243)
### What problem does this PR solve?

```
RAGFlow(admin)> list providers;
+----------------------+-------------------------------------------------------------+
| command              | error                                                       |
+----------------------+-------------------------------------------------------------+
| list_model_providers | 'list model providers' is implemented in enterprise edition |
+----------------------+-------------------------------------------------------------+

RAGFlow(admin)> add provider 'zhipu-ai';
+-------------+-----------------------------------------------------------+
| field       | value                                                     |
+-------------+-----------------------------------------------------------+
| command     | add_model_provider                                        |
| error       | 'add model provider' is implemented in enterprise edition |
| provider_id | admin                                                     |
| user_id     | zhipu-ai                                                  |
+-------------+-----------------------------------------------------------+

RAGFlow(admin)> delete provider 'zhipu-ai';
+-------------+--------------------------------------------------------------+
| field       | value                                                        |
+-------------+--------------------------------------------------------------+
| command     | delete_model_provider                                        |
| error       | 'delete model provider' is implemented in enterprise edition |
| provider_id | admin                                                        |
| user_id     | zhipu-ai                                                     |
+-------------+--------------------------------------------------------------+

RAGFlow(admin)> add provider 'zhipu-ai' instance 'instance1';
+---------------+-----------------------------------------------------------+
| field         | value                                                     |
+---------------+-----------------------------------------------------------+
| command       | add_model_instance                                        |
| error         | 'add model instance' is implemented in enterprise edition |
| instance_name | instance1                                                 |
| provider_id   | zhipu-ai                                                  |
| user_id       | admin                                                     |
+---------------+-----------------------------------------------------------+

RAGFlow(admin)> delete provider 'zhipu-ai' instance 'test'
+-------------+--------------------------------------------------------------+
| field       | value                                                        |
+-------------+--------------------------------------------------------------+
| instances   | [test]                                                       |
| provider_id | zhipu-ai                                                     |
| user_id     | admin                                                        |
| command     | delete_model_provider                                        |
| error       | 'delete model instance' is implemented in enterprise edition |
+-------------+--------------------------------------------------------------+

RAGFlow(admin)> add provider 'zhipu-ai' instance 'instance1' model 'xxx';
+---------------+--------------------------------------------------+
| field         | value                                            |
+---------------+--------------------------------------------------+
| command       | add_model                                        |
| error         | 'add model' is implemented in enterprise edition |
| instance_name | instance1                                        |
| model_names   | [xxx]                                            |
| provider_id   | zhipu-ai                                         |
| user_id       | admin                                            |
+---------------+--------------------------------------------------+

RAGFlow(admin)> delete provider 'zhipu-ai' instance 'test' model 'xxx';
+---------------+------------------------------------------------------+
| field         | value                                                |
+---------------+------------------------------------------------------+
| command       | delete_model_provider                                |
| error         | 'delete models' is implemented in enterprise edition |
| instance_name | test                                                 |
| models        | [xxx]                                                |
| provider_id   | zhipu-ai                                             |
| user_id       | admin                                                |
+---------------+------------------------------------------------------+

```

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-06-23 10:26:31 +08:00
Haruko386
6beae949d8 feat[Go]: add modelID for delete_model and update_status (#16025)
### What problem does this PR solve?

1. add modelID for delete_model and update_status
2. fix the bug when update-status delete model

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
2026-06-18 17:56:51 +08:00
Haruko386
27d723e13a fix: fix some bugs in check_conn and drop_inst (#16180)
### What problem does this PR solve?

As title:

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2026-06-18 14:19:46 +08:00
Jin Hai
32d5c0039b Go: refactor model API to accept model id (#15999)
### What problem does this PR solve?

Not not only model_name@instance_name@provider_name is acceptable, but
also model_id is acceptable.

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-06-15 10:10:14 +08:00
Zhichang Yu
3fa15c0e2f feat(agent): Go port — canvas engine, 22 components, DSL v2, 13 endpoints (#15952)
Ports the agent canvas subsystem from Python to Go.

## What's included

### Canvas Engine (Phase 0/1)
- State engine, scheduler, variable resolver, Redis checkpoint store,
cancel protocol
- **209 tests** across canvas / component / io packages

### 22 Components (P0–P4)
| Tier | Components |
|---|---|
| P0 T1+T2+T3 | LLM, Agent, ExitLoop, Switch, Categorize, Begin,
Message, Invoke |
| P1 T3 | VariableAggregator, VariableAssigner, StringTransform,
ListOperations, DataOperations |
| P2 T3 | Iteration, IterationItem, Loop, LoopItem |
| P3 T3 | UserFillUp, Fillup |
| P4 T5 | Browser, ExcelProcessor, DocsGenerator |

### DSL v2 Schema (Phase 2.5)
- Typed v2 in-memory model with v1-to-v2 auto-detect converter
- v1 legacy field stripping per plan §2.11.7

### HTTP Endpoints & Bug Fixes (Plans PR1–PR3)
- **DELETE SQL bug fix**: gorm v2 `Where("id = ?", id).Delete(...)`
pattern
- **CreateAgent validation**: title/DSL required, duplicate check, 103
envelope
- **13 new endpoints**: templates, prompts, tags, sessions CRUD,
chat/completions (SSE + non-stream stubs), rerun, test_db_connection,
logs, webhook/logs
- **756 Go unit tests** (745 → 756, +18)
- **17 → 0 Python integration test failures** (test_agents.py +
test_session_management/)

### Tools
21 eino tools: HTTPHelper, search tools, financial/data tools, mandatory
stubs

### Infrastructure
OTel observability, NATS message queue, DeepDoc gRPC client, SSRF
guards, IDOR mitigation
2026-06-12 22:58:28 +08:00
bitloi
cafa0f2e4f fix: SSE write timeout (#15852)
### What problem does this PR solve?

Fixes #15840.

The Go HTTP server sets `WriteTimeout: 120s`, which also applies to
long-lived SSE responses. Existing Go streaming handlers did not clear
the per-response write deadline, so streams that run longer than the
server timeout can be terminated mid-response.

This PR adds a small handler helper that clears the response write
deadline for SSE requests and calls it only in existing Go streaming
branches:

- conversation completion streaming
- provider chat streaming
- provider transcription streaming
- provider speech streaming

The global server `WriteTimeout` remains unchanged for non-streaming
requests.

### Type of change

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

### Test plan

- `/root/go/bin/go test ./internal/handler -run
TestDisableWriteDeadlineForSSEAllowsLongLivedStream -count=1`
- `/root/go/bin/go test ./internal/handler -count=1`
2026-06-12 20:49:34 +08:00
Jin Hai
719ce15c95 Go CLI: update list supported models (#15845)
### What problem does this PR solve?

Now list supported models will show more info.

```
RAGFlow(api/default)> list supported models from 'gitee' 'test';
+-----------+------------+-------------+----------------------------------------------------------+---------------------------------------------+
| dimension | max_tokens | model_types | name                                                     | thinking                                    |
+-----------+------------+-------------+----------------------------------------------------------+---------------------------------------------+
|           |            |             | Wan2.7                                                   |                                             |
|           |            |             | HappyHorse-1.0                                           |                                             |
|           |            |             | Qwen3.6-27B@Qwen                                         |                                             |
|           |            |             | Qwen3.6-35B-A3B@Qwen                                     |                                             |
|           | 1048576    | [chat]      | DeepSeek-V4-Flash@deepseek-ai                            | map[clear_thinking:true default_value:true] |
|           | 1048576    | [chat]      | DeepSeek-V4-Pro@deepseek-ai                              | map[clear_thinking:true default_value:true] |
+-----------+------------+-------------+----------------------------------------------------------+---------------------------------------------+
```

### Type of change

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

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-06-09 19:01:00 +08:00
Haruko386
473d06d1ad feat[Go]: implement add multi_models (#15563) 2026-06-03 15:26:46 +08:00
Haruko386
9f969feb89 feat[Go] implement check connection by using apikey and region (#15475)
### What problem does this PR solve?

**Verified from PostMan**


GET http://127.0.0.1:9384/api/v1/providers/gitee/connection
```json
body: 

{
    "api_key": "XXXXXXXXXXXXXXXXXXXXXXXXXXXX",
    "region": "default"

}

resp: 
{
    "code": 0,
    "message": "success"
}
```

GET http://127.0.0.1:9384/api/v1/providers/gitee/connection
```json
body: 

{
    "api_key": "XXXXXXXXXXXXXXXXXXXXXXXXXXXX",
    "region": "deprecated"

}

resp: 
{
    "code": 0,
    "message": "success"
}
```

GET http://127.0.0.1:9384/api/v1/providers/gitee/connection
```json
body: 

{
    "api_key": "XXXXXXXXXXXXXXXXXXXXXXXXXXXX",
    "region": "china"

}

resp: 
{
    "code": 0,
    "message": "success"
}

```

GET http://127.0.0.1:9384/api/v1/providers/lmstudio/connection
```json
body: 

{
    "api_key": "",
    "region": "test"

}

resp: 
{
    "code": 0,
    "message": "success"
}
```


### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2026-06-02 19:32:41 +08:00
bitloi
ea3a5dba11 fix: validate custom model inputs (#15200)
### What problem does this PR solve?

Closes #15199.

The add-custom-model endpoint is routed through
`/api/v1/providers/:provider_name/instances/:instance_name/models`, but
the handler previously trusted `provider_name` and `instance_name` from
the JSON body instead of the path target. A request could therefore hit
one provider/instance URL while operating on a different body
provider/instance.

The same handler only rejected `model_types` when the slice was nil. An
empty array passed validation and reached
`ModelProviderService.AddCustomModel`, where `request.ModelTypes[0]`
could panic.

This PR makes the path provider/instance authoritative, rejects
mismatched body values, rejects missing or empty `model_types`, and adds
a service-level guard so direct service callers cannot hit the same
panic path.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2026-05-29 10:15:01 +08:00
Jin Hai
3a5df08c76 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>
2026-05-15 12:29:52 +08:00
Haruko386
106f4b777e Go: implement TTS for fishaudio, openrouter and asr for fishaudio (#14926)
### What problem does this PR solve?

This PR implement TTS for FishAudio and MiniMax provider and ASR for
FishAudio

**The following functionalities are now supported:**

**FishAudio:**
- [x] Text To Speech
- [x] Stream Text To Speech
- [x] Audio To Text

**OpenRouter:**

- [x] Text To Speech

**Verified examples from the CLI:**
```plaintext

**FishAudio**

RAGFlow(user)> tts with 's1@test@fishaudio' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"reference_id": "90e65eaaf50e4470b8e6d43ee6afd7d5", "temperature": 0.7, "top_p": 0.7, "prosody": {"speed": 1, "volume": 0, "normalize_loudness": true}, "chunk_length": 300, "normalize": true, "sample_rate": 44100, "mp3_bitrate": 128, "latency": "normal", "max_new_tokens": 1024, "repetition_penalty": 1.2, "min_chunk_length": 50, "condition_on_previous_chunks": true, "early_stop_threshold": 1}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/s1_output.wav
SUCCESS

RAGFlow(user)> stream tts with 's1@test@fishaudio' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"reference_id": "90e65eaaf50e4470b8e6d43ee6afd7d5", "temperature": 0.7, "top_p": 0.7, "prosody": {"speed": 1, "volume": 0, "normalize_loudness": true}, "chunk_length": 300, "normalize": true, "sample_rate": 44100, "mp3_bitrate": 128, "latency": "normal", "max_new_tokens": 1024, "repetition_penalty": 1.2, "min_chunk_length": 50, "condition_on_previous_chunks": true, "early_stop_threshold": 1}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/s1_output.wav
SUCCESS

RAGFlow(user)> asr with 'transcribe-1@test@fishaudio' audio './internal/test.wav' param '{"language": "en", "ignore_timestamps": true}'
+----------------------------------------------------------------------------------------------------------------------+
| text                                                                                                                 |
+----------------------------------------------------------------------------------------------------------------------+
| The examination and testimony of the experts enabled the commission to conclude that five shots may have been fired. |
+----------------------------------------------------------------------------------------------------------------------+

```

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
2026-05-14 18:58:00 +08:00
Haruko386
ef46005ef1 Go: implement TTS for MiniMax provider and CLI testing for TTS (#14911)
### What problem does this PR solve?

This PR implement TTS for MiniMax provider and CLI testing for TTS

**The following functionalities are now supported:**

**MiniMax:**
- [x] Chat / Stream Chat 
- [x] Embedding
- [x] Rerank
- [x] Model listing
- [x] Provider connection checking
- [x] Text To Speech
- [ ] OCRFile
- [ ] ~~Audio To Text~~
- [ ] ~~Balance~~

**Verified examples from the CLI:**

```plaintext
RAGFlow(user)> tts with 'speech-2.8-hd@test@minimax' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"voice_setting": {"voice_id": "English_radiant_girl", "speed": 1, "vol": 1, "pitch": 0}, "audio_setting": {"sample_rate": 32000, "bitrate": 128000, "format": "wav", "channel": 1}, "output_format": "hex"}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/speech-2.8-hd_output.wav
SUCCESS

RAGFlow(user)> stream tts with 'speech-2.8-hd@test@minimax' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"voice_setting": {"voice_id": "English_radiant_girl", "speed": 1, "vol": 1, "pitch": 0}, "audio_setting": {"sample_rate": 32000, "bitrate": 128000, "format": "wav", "channel": 1}, "output_format": "hex"}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/speech-2.8-hd_output.wav
SUCCESS
```
Set `Play` to play audio in CLI
Set `Save` `PATH_TO_SAVE` to save file
Set `format` to save file in wav or mp3
Set `Param` align with official request body

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2026-05-14 13:19:31 +08:00
Jin Hai
b18640d228 Go: fix OCR command (#14891)
### 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>
2026-05-13 17:29:53 +08:00
Jin Hai
d08bf02d9b Go: add ASR, TTS, OCR command (#14836)
### What problem does this PR solve?

```
RAGFlow(user)> asr with 'glm-asr-2512@test@zhipu-ai' audio './speech.wav';
CLI error: zhipu, no such method
RAGFlow(user)> stream asr with 'glm-asr-2512@test@zhipu-ai' audio './speech.wav';
CLI error: zhipu, no such method

RAGFlow(user)> tts with 'glm-tts@test@zhipu-ai' text 'how are you';
CLI error: zhipu, no such method

RAGFlow(user)> stream tts with 'glm-tts@test@zhipu-ai' text 'how are you';
CLI error: zhipu, no such method

RAGFlow(user)> ocr with 'glm-ocr@test@zhipu-ai' file './test.log';
CLI error: zhipu, no such method
```

### Type of change

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

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 17:17:44 +08:00
Jin Hai
c55e23e7e2 Go: refactor embedding interface (#14757)
### What problem does this PR solve?

Provide embedding index according to the input text

### Type of change

- [x] Refactoring

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-05-11 14:45:30 +08:00
Jin Hai
17d71e5d79 Go CLI: embed and rerank (#14735)
### What problem does this PR solve?

```
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'embedding-3@test@zhipu-ai' dimension 16;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 16        | 0     |
| 16        | 1     |
+-----------+-------+

RAGFlow(user)> rerank query 'what is rag' document 'rag is retrieval augment generation' 'rag need llm' 'famous rag project includes ragflow' with 'rerank@test@zhipu-ai' top 2;
+-------+-----------------+
| index | relevance_score |
+-------+-----------------+
| 0     | 1               |
| 2     | 0.99999976      |
+-------+-----------------+
```

### Type of change

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

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-05-09 17:41:54 +08:00
qinling0210
7335916868 Use GetChatModel, remove duplicate functions in model_service.go (#14546)
### What problem does this PR solve?

Use GetChatModel, remove duplicate functions in model_service.go

### Type of change

- [x] Refactoring

Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-06 11:33:32 +08:00
qinling0210
12af73f2ca Support stream for multimodal chat (#14537)
### What problem does this PR solve?

Support stream for multimodal chat

### Type of change

- [x] Refactoring
2026-04-30 19:33:57 +08:00
qinling0210
265f92c83e Simplify chat and support multimodal chat (#14523)
### What problem does this PR solve?

Simplify chat and support multimodal chat

### Type of change

- [x] Refactoring
2026-04-30 15:25:01 +08:00
Jin Hai
261be81127 Go: add drop instance models (#14485)
### What problem does this PR solve?

1. drop instance model
2. Fix issue of drop instance but not drop models.

### Type of change

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

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-29 19:18:49 +08:00
Jin Hai
bb05a8bd7e Update create model instance command (#14441)
### What problem does this PR solve?

1. support command:

```
RAGFlow(user)> create provider 'vllm' instance 'test' key 'test-key' url 'base-url' region 'abc';
SUCCESS
RAGFlow(user)> list instances from 'vllm';
+----------+----------------------------------------+----------------------------------+--------------+----------------------------------+--------+
| apiKey   | extra                                  | id                               | instanceName | providerID                       | status |
+----------+----------------------------------------+----------------------------------+--------------+----------------------------------+--------+
| test-key | {"base_url":"base-url","region":"abc"} | 40213c89430311f1a7cf38a74640adcc | test         | b4d40e6142d311f1a4f938a74640adcc | enable |
+----------+----------------------------------------+----------------------------------+--------------+----------------------------------+--------+
```
2. support add vllm model
```
RAGFlow(user)> add model 'Qwen/Qwen2-0.5B' to provider 'vllm' instance 'test' with tokens 131072 chat;
SUCCESS
```
3. add vllm chat

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-29 17:05:08 +08:00
Jin Hai
b493a33316 Go: update chat URL (#14453)
### What problem does this PR solve?

Update the URL to: /api/v1/chat/completions

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-29 11:45:06 +08:00
qinling0210
effc84a042 Refactor model in GO (#14398)
### What problem does this PR solve?

Refactor model in GO

### Type of change

- [x] Refactoring
2026-04-28 12:59:01 +08:00
Jin Hai
965717c4fb Go: add new provider: google (#14395)
### What problem does this PR solve?

As title.

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-27 20:35:47 +08:00
Jin Hai
1c244df90d Go: add gitee and siliconflow as model provider (#14336)
### What problem does this PR solve?

As title

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-24 20:59:30 +08:00
Jin Hai
2b029882d7 Go: add new provider minimax (#14296)
### What problem does this PR solve?

1. Add new provider minimax
2. Add new command: CHECK INSTANCE 'instance_name' FROM 'provider_name';
```
RAGFlow(user)> check instance 'test' from 'minimax';
SUCCESS
```

### Type of change

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

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-23 10:16:20 +08:00
Jin Hai
74b44e1aa3 Go: add balance command (#14262)
### What problem does this PR solve?

```
RAGFlow(user)> list supported models from 'moonshot' 'test';
+---------------------------------+
| model_name                      |
+---------------------------------+
| moonshot-v1-32k-vision-preview  |
| kimi-k2.6                       |
| moonshot-v1-8k                  |
| moonshot-v1-auto                |
| moonshot-v1-128k                |
| moonshot-v1-32k                 |
| kimi-k2.5                       |
| moonshot-v1-8k-vision-preview   |
| moonshot-v1-128k-vision-preview |
+---------------------------------+
RAGFlow(user)> show balance from 'moonshot' 'test';
+---------+----------+
| balance | currency |
+---------+----------+
| 0       | CNY      |
+---------+----------+
```

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-21 21:31:50 +08:00
Jin Hai
e48d75987c Go: add stream / think chat (#14242)
### What problem does this PR solve?

1. Supports stream and non-stream chat
2. Supports think and non-think chat
3. List supported models from DeepSeek service. (This command can be
used to verify the API validity)

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-21 16:52:32 +08:00
Jin Hai
af2ed416a7 Add extra field to model instance (#14203)
### What problem does this PR solve?

Now each model support region with different URL

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-20 15:31:12 +08:00
Jin Hai
e03212fd7a Fix go cli models command and api (#14166)
### What problem does this PR solve?

```
RAGFlow(user)> list providers;
+--------------------------------------+----------+-------------------------------------------+--------------+
| base_url                             | name     | tags                                      | total_models |
+--------------------------------------+----------+-------------------------------------------+--------------+
| https://open.bigmodel.cn/api/paas/v4 | ZHIPU-AI | LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION | 21           |
| https://api.x.ai/v1                  | xAI      | LLM                                       | 6            |
+--------------------------------------+----------+-------------------------------------------+--------------+
RAGFlow(user)> show provider 'zhipu-ai';
+--------------------------------------+----------+-------------------------------------------+--------------+
| base_url                             | name     | tags                                      | total_models |
+--------------------------------------+----------+-------------------------------------------+--------------+
| https://open.bigmodel.cn/api/paas/v4 | ZHIPU-AI | LLM,TEXT EMBEDDING,SPEECH2TEXT,MODERATION | 21           |
+--------------------------------------+----------+-------------------------------------------+--------------+
RAGFlow(user)> delete provider 'zhipu-ai';
SUCCESS
RAGFlow(user)> add provider 'zhipu-ai';
SUCCESS
RAGFlow(user)> create provider 'zhipu-ai' instance 'ccc' 'ccxxccxx';
SUCCESS
RAGFlow(user)> list instances from 'zhipu-ai';
+---------------------------------------------------+----------------------------------+--------------+----------------------------------+--------+
| apiKey                                            | id                               | instanceName | providerID                       | status |
+---------------------------------------------------+----------------------------------+--------------+----------------------------------+--------+
| ccxxccxx | 640dd7ee398711f1bdd838a74640adcc | ccc          | d1d59de5398411f1bdd838a74640adcc | active |
+---------------------------------------------------+----------------------------------+--------------+----------------------------------+--------+
RAGFlow(user)> list models from 'zhipu-ai';
+----------+------------+---------------+---------------+
| features | max_tokens | model_types   | name          |
+----------+------------+---------------+---------------+
| map[]    | 128000     | [chat]        | glm-4.7       |
| map[]    | 128000     | [chat]        | glm-4.5       |
| map[]    | 128000     | [chat]        | glm-4.5-x     |
| map[]    | 128000     | [chat]        | glm-4.5-air   |
| map[]    | 128000     | [chat]        | glm-4.5-airx  |
| map[]    | 128000     | [chat]        | glm-4.5-flash |
| map[]    | 64000      | [image2text]  | glm-4.5v      |
| map[]    | 128000     | [chat]        | glm-4-plus    |
| map[]    | 128000     | [chat]        | glm-4-0520    |
| map[]    | 128000     | [chat]        | glm-4         |
| map[]    | 8000       | [chat]        | glm-4-airx    |
| map[]    | 128000     | [chat]        | glm-4-air     |
| map[]    | 128000     | [chat]        | glm-4-flash   |
| map[]    | 128000     | [chat]        | glm-4-flashx  |
| map[]    | 1000000    | [chat]        | glm-4-long    |
| map[]    | 128000     | [chat]        | glm-3-turbo   |
| map[]    | 2000       | [image2text]  | glm-4v        |
| map[]    | 8192       | [chat]        | glm-4-9b      |
| map[]    | 512        | [embedding]   | embedding-2   |
| map[]    | 512        | [embedding]   | embedding-3   |
| map[]    | 4096       | [speech2text] | glm-asr       |
+----------+------------+---------------+---------------+
RAGFlow(user)> disable model 'glm-4.5-flash' from 'zhipu-ai' 'ccc';
SUCCESS
RAGFlow(user)> drop instance 'ccc' from 'zhipu-ai';
SUCCESS
RAGFlow(user)> list instances from 'zhipu-ai';
No data to print
```

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-17 09:55:25 +08:00
Jin Hai
6d9430a125 Add think chat to CLI (#13922)
### What problem does this PR solve?

Now user can use 'think mode' to chat with LLM

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-03 18:11:23 +08:00
Jin Hai
6c29128de1 Refactor model provider and command (#13887)
### What problem does this PR solve?

Introduce 5 new tables, including model groups and provider instance.

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-04-02 20:20:35 +08:00
Jin Hai
efd6ecc3e5 New provider and models API and CLI (#13865)
### What problem does this PR solve?

As title.

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-03-31 18:42:12 +08:00
Jin Hai
e20cf39735 Refactor Go server model provider reading and access (#13831)
### What problem does this PR solve?

1. Refactor model provider json file format
2. Use memory data structure to replace database
3. Add CLI command to access

```
RAGFlow(user)> list pool models from 'xai';
+-------------------------------------------------------------------------------------+------------+-------------+-----------------------+
| features                                                                            | max_tokens | model_types | name                  |
+-------------------------------------------------------------------------------------+------------+-------------+-----------------------+
| map[]                                                                               | 256000     | [llm]       | grok-4                |
| map[]                                                                               | 131072     | [llm]       | grok-3                |
| map[]                                                                               | 131072     | [llm]       | grok-3-fast           |
| map[]                                                                               | 131072     | [llm]       | grok-3-mini           |
| map[]                                                                               | 131072     | [llm]       | grok-3-mini-mini-fast |
| map[multimodal:map[enabled:true input_modalities:[image] output_modalities:[text]]] | 32768      | [vlm]       | grok-2-vision         |
+-------------------------------------------------------------------------------------+------------+-------------+-----------------------+
RAGFlow(user)> show pool model 'grok-2-vision' from 'xai';
+-------------------------------------------------------------------------------------+------------+-------------+---------------+
| features                                                                            | max_tokens | model_types | name          |
+-------------------------------------------------------------------------------------+------------+-------------+---------------+
| map[multimodal:map[enabled:true input_modalities:[image] output_modalities:[text]]] | 32768      | [vlm]       | grok-2-vision |
+-------------------------------------------------------------------------------------+------------+-------------+---------------+
RAGFlow(user)> list pool providers;
+--------+------------------------------------------------------------+---------------------------+
| name   | tags                                                       | url                       |
+--------+------------------------------------------------------------+---------------------------+
| OpenAI | LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION | https://api.openai.com/v1 |
| xAI    | LLM                                                        | https://api.x.ai/v1       |
+--------+------------------------------------------------------------+---------------------------+
RAGFlow(user)> show pool provider 'openai';
+---------------------------+--------+------------------------------------------------------------+--------------+
| base_url                  | name   | tags                                                       | total_models |
+---------------------------+--------+------------------------------------------------------------+--------------+
| https://api.openai.com/v1 | OpenAI | LLM,TEXT EMBEDDING,TTS,TEXT RE-RANK,SPEECH2TEXT,MODERATION | 27           |
+---------------------------+--------+------------------------------------------------------------+--------------+
```

### Type of change

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

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-03-30 12:00:49 +08:00