Hz_
0de8f3e127
feat: add missing qwen models to all_models.json ( #16379 )
...
Add 19 missing qwen models and 3 aliases to all_models.json.
Models added: qwen-image-2.0-pro (2026-06-22, 2026-04-22), qwen3.5-ocr,
qwen3.7-max-2026-05-17, qwen3.5-livetranslate-flash-realtime,
qwen3.5-omni-plus/flash-realtime, qwen-deep-research-2025-12-15,
qwen-flash-character-2026-02-26, qwen-plus-2025-11-05,
qwen-deep-search-planning, qwen3-s2s-flash-realtime-2025-09-22,
qwen-max-1201/longcontext/0107, qwen-1.8b-longcontext-chat
Aliases: qwen3.5-plus-2026-04-20, qwen-turbo-0919, qwen-1.8b-chat
2026-06-26 15:35:30 +08:00
Jin Hai
65afaa1292
Model config: add tools ( #16371 )
...
### What problem does this PR solve?
```
{
"name": "glm-4-flash",
"max_tokens": 128000,
"model_types": [
"chat"
],
"tools": {
"support": true
}
}
```
```
RAGFlow(admin)> list provider 'zhipu-ai' models;
+------------+---------------+------------+---------------+----------------+-----------+-----------+
| dimensions | max_dimension | max_tokens | model_type | name | thinking | tools |
+------------+---------------+------------+---------------+----------------+-----------+-----------+
| | | 204800 | [chat] | glm-5 | supported | supported |
| | | 204800 | [chat] | glm-5-turbo | supported | supported |
```
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com >
2026-06-26 11:37:51 +08:00
Jin Hai
7214a23614
Go: fix duplicate models ( #16197 )
...
### What problem does this PR solve?
1. Remove unused file
2. Remove duplicate models
3. Resort the function order
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com >
2026-06-19 09:57:58 +08:00
Haruko386
b53b5bf12c
Json add paddleOCR models ( #16156 )
...
close #15853
### What problem does this PR solve?
As title
### Type of change
- [x] Other (add models):
2026-06-18 17:57:41 +08:00
Hz_
8047857de0
fix(go): all_models.json ( #16075 )
...
### What problem does this PR solve?
This PR fixes Go admin server startup failure caused by duplicate model
aliases in conf/all_models.json.
The model provider loader builds a global lookup table from both model
name and alias values. Some aliases duplicated another model's name or
another
alias, for example amazon.titan-embed-text-v1, which caused startup to
fail with a duplicate alias error. This PR removes conflicting duplicate
aliases
while keeping all model definitions intact.
2026-06-16 15:31:17 +08:00
Hz_
4a33455a20
feat(go-models): add more providers ( #16017 )
...
### What problem does this PR solve?
add more providers.
2026-06-16 12:54:19 +08:00
Haruko386
cafd8a1125
Json: add many models to all_models.json ( #16013 )
...
### What problem does this PR solve?
As title
### Type of change
- [x] Other (please describe): add some models
2026-06-15 15:25:49 +08:00
Hz_
eb6ea284a8
feat(go-models): Add google models to all_models.json ( #16007 )
...
### What problem does this PR solve?
Add google models to all_models.json
2026-06-15 11:37:56 +08:00
Haruko386
4115282c5f
Json[model-provider] add nvidia, moonshot, minimax, claude, GPT models ( #15970 )
...
### What problem does this PR solve?
As title
### Type of change
- [x] Other (please describe): add models
2026-06-12 19:16:10 +08:00
Hz_
30724140d2
feat(go): Add Z.ai model entries to all_models.json Add missing Qwen commercial models and provider aliases ( #15929 )
...
### What problem does this PR solve?
- Add Z.ai model definitions to `conf/all_models.json`.
- Add missing Qwen / DashScope commercial API-only models, including:
- Qwen3.7 / Qwen3.6 / Qwen3.5 Max, Plus, Flash families
- Qwen Coder and Math commercial models
- Qwen VL, OCR, Omni, ASR, TTS, translation, image generation, and image
editing models
- Add verified provider-specific aliases for supported Qwen models:
- DashScope / Alibaba Cloud Model Studio model IDs
- OpenRouter `qwen/...` aliases
- Amazon Bedrock `qwen.qwen3-*` model IDs
- Add `thinking` metadata for Qwen models that officially support
thinking mode.
- Remove aliases that exactly duplicate their own canonical `name`.
2026-06-12 14:33:01 +08:00
Haruko386
e3be39d0de
Json: add some models ( #15947 )
...
### What problem does this PR solve?
As title
### Type of change
- [x] Other (please describe): add models
2026-06-12 14:32:21 +08:00
Hz_
515acf4f60
fix(go): Fix case-insensitive model alias lookup ( #15911 )
...
## Summary
- Normalize model alias index keys to lowercase
- Detect lowercase alias collisions during provider manager
initialization
- Fix ListModels metadata mapping for mixed-case provider aliases
2026-06-10 20:36:43 +08:00
Hz_
38755c705a
feat(go): Add DeepSeek models and Gitee alias metadata tests ( #15885 )
...
This PR expands conf/all_models.json with DeepSeek model entries and
provider aliases.
Changes:
- Added DeepSeek model entries across `V4`, `V3.2`, `V3.1`, `V3`, `R1`,
`Coder`, `Math`, `VL`, `OCR`, `Prover`, `MoE`, and `LLM` series.
- Normalized model name values to lowercase canonical IDs.
- Added alias values for official DeepSeek/Hugging Face names and
provider-specific names from OpenRouter, VolcEngine, SiliconFlow,
HuaweiCloud, and QiniuCloud.
- Preserved model metadata such as max_tokens, model_types, and thinking
where applicable.
- Added Gitee ListModels tests to verify DeepSeek aliases map back to
model metadata from all_models.json.
- Added an optional Gitee integration test gated by
GITEE_LIST_MODELS_INTEGRATION=1.
Test:
/usr/local/go/bin/go clean -cache
/usr/local/go/bin/go test ./internal/entity/models -run
'TestGiteeListModels(MapsAllDeepSeekAliasesToModelMetadata|KeepsOwnedBySuffixAfterAliasMetadataLookup|
Integration)'
2026-06-10 13:59:23 +08:00
Jin Hai
55abf4f565
Go: new CLI command, list all models and show model ( #15786 )
...
### What problem does this PR solve?
```
RAGFlow(user)> list models;
+---------------------------+------------+-------------+--------------------+---------------------------------------------+
| alias | max_tokens | model_types | name | thinking |
+---------------------------+------------+-------------+--------------------+---------------------------------------------+
| | 1048576 | [chat] | deepseek-v4-flash | map[clear_thinking:true default_value:true] |
| | 1048576 | [chat] | deepseek-v4-pro | map[clear_thinking:true default_value:true] |
| | 1024000 | [chat] | minimax-m3 | map[clear_thinking:true default_value:true] |
| | 64000 | [vision] | glm-4.5v | map[clear_thinking:true default_value:true] |
| [baai/bge-m3] | 8192 | [embedding] | bge-m3 | |
| [baai/bge-reranker-v2-m3] | 1024 | [rerank] | bge-reranker-v2-m3 | |
| | | [tts] | step-audio-tts-3b | |
| [qwen/qwen3-asr-1.7b] | | [asr] | qwen3-asr-1.7b | |
| [paddleocr-vl-1.5] | | [ocr] | paddleocr-vl-0.9b | |
+---------------------------+------------+-------------+--------------------+---------------------------------------------+
RAGFlow(user)> show model 'minimax-m3';
+--------------+---------------------------------------------+
| field | value |
+--------------+---------------------------------------------+
| name | minimax-m3 |
| max_tokens | 1024000 |
| model_types | [chat] |
| thinking | map[clear_thinking:true default_value:true] |
| class | |
| alias | |
| ModelTypeMap | |
+--------------+---------------------------------------------+
RAGFlow(user)> show model 'baai/bge-m3';
+--------------+---------------+
| field | value |
+--------------+---------------+
| model_types | [embedding] |
| thinking | |
| class | |
| alias | [baai/bge-m3] |
| ModelTypeMap | |
| name | bge-m3 |
| max_tokens | 8192 |
+--------------+---------------+
```
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com >
2026-06-08 21:38:15 +08:00
