youngkingdom/ragflow
1
0
Fork 0
mirror of https://github.com/infiniflow/ragflow.git synced 2026-06-08 08:07:21 +08:00
Code Issues Packages Projects Releases Wiki Activity
6,012 Commits 3 Branches 48 Tags
89961962c0281560fbe9daeb4d00ef6ea4161c8a
Commit Graph

11 Commits

Author SHA1 Message Date
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
f670913bb4 Refactor model type to model class (#14426) 
### What problem does this PR solve?

As title

### Type of change

- [x] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-04-28 16:05:15 +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
c3eac4103a Go: aliyun model provider (#14379) 
### 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 14:53:33 +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
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
f269ee9739 Go: add thinking features to zhipu-ai (#14234) 
### What problem does this PR solve?

```
RAGFlow(user)> list models from 'zhipu-ai';
+------------+------------+---------------+----------------+
| features   | max_tokens | model_types   | name           |
+------------+------------+---------------+----------------+
| [thinking] | 128000     | [chat]        | glm-4.7        |
| [thinking] | 128000     | [chat]        | glm-4.5        |
| [thinking] | 128000     | [chat vision] | glm-4.6v-Flash |
| [thinking] | 128000     | [chat]        | glm-4.5-x      |
| [thinking] | 128000     | [chat]        | glm-4.5-air    |
| [thinking] | 128000     | [chat]        | glm-4.5-airx   |
| [thinking] | 128000     | [chat]        | glm-4.5-flash  |
| [thinking] | 64000      | [vision]      | glm-4.5v       |
|            | 128000     | [chat]        | glm-4-plus     |
|            | 128000     | [chat]        | glm-4-0520     |
|            | 128000     | [chat]        | glm-4          |
|            | 8000       | [chat]        | glm-4-airx     |
|            | 128000     | [chat]        | glm-4-air      |
|            | 128000     | [chat]        | glm-4-flash    |
|            | 128000     | [chat]        | glm-4-flashx   |
|            | 1000000    | [chat]        | glm-4-long     |
|            | 128000     | [chat]        | glm-3-turbo    |
|            | 2000       | [vision]      | glm-4v         |
|            | 8192       | [chat]        | glm-4-9b       |
|            | 512        | [embedding]   | embedding-2    |
|            | 512        | [embedding]   | embedding-3    |
|            | 4096       | [asr]         | glm-asr        |
|            | 0          | [tts]         | glm-tts        |
|            | 0          | [ocr]         | glm-ocr        |
|            | 0          | [rerank]      | glm-rerank     |
+------------+------------+---------------+----------------+
```

### Type of change

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

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-04-20 21:53:27 +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
94106646e7 Go: set and list default models (#14191) 
### What problem does this PR solve?

```
RAGFlow(user)> set default vlm "zhipu-ai" "ccc" "glm-4.6v-flash";
SUCCESS
RAGFlow(user)> list default models;
+--------+----------------+----------------+----------------+------------+
| enable | model_instance | model_name     | model_provider | model_type |
+--------+----------------+----------------+----------------+------------+
| true   | ccc            | glm-4.6v-flash | zhipu-ai       | llm        |
| true   | ccc            | glm-4.6v-flash | zhipu-ai       | image2text |
+--------+----------------+----------------+----------------+------------+
```

### Type of change

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

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
 2026-04-17 18:05:33 +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
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