Commit Graph

8 Commits

Author SHA1 Message Date
JPette1783
daa3811165 feat(models): add shared HTTP client, SSE parser, and stub helpers for Go model drivers (#15821)
### What problem does this PR solve?

The Go model-driver layer () has ~38,700 lines across 109 files. Roughly
74% of that is boilerplate duplicated into every driver: identical HTTP
client setup, the same 65-line SSE scanner loop, and 10-11 one-line "not
supported" stub methods per driver. Any fix must be manually propagated
to every file. Closes #15820.

This PR establishes the three shared utility files that form the
foundation for incremental driver migration:

---

### Type of change

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

---------

Co-authored-by: Haruko386 <tryeverypossible@163.com>
2026-06-11 19:20:12 +08:00
Haruko386
84edf539e7 Go: Refactor list-models func (#15900)
### What problem does this PR solve?

As title
Issue: #15853 

### Type of change

- [x] Refactoring
2026-06-11 13:32:50 +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
baeb0c0431 Refactor[Go Model Provider]: refactor baseURL and modelConfig (#15627)
### What problem does this PR solve?

As Title

### Type of change

- [x] Refactoring
2026-06-04 17:50:22 +08:00
Jin Hai
dbebc66ba8 Go: refactor provider code (#15564)
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2026-06-03 14:09:07 +08:00
oktofeesh
be28177955 fix(go-models): harden Hunyuan embedding validation (#15249)
## Summary
- Validate Hunyuan embedding model name and API key before building
requests.
- Reuse region-aware base URL validation for embedding requests.
- Replace the stale unsupported Embed test with happy-path and
validation coverage.

## What changed
- Added early Hunyuan Embed validation for missing model names and API
keys.
- Routed Embed through the same base URL region guard used by the other
Hunyuan methods.
- Updated Hunyuan tests to configure the embedding suffix and cover
Embed success plus invalid inputs.

## Why
Hunyuan Embed is implemented, but the existing test still expected it to
be unsupported and could panic before returning a normal validation
error. This keeps the implemented embedding path aligned with the
current driver behavior and prevents nil input panics.

Closes #15087
Refs #14736
2026-05-29 19:50:01 +08:00
Haruko386
69f301b84a Go: implement embed for Tencent Hunyuan (#15207)
### What problem does this PR solve?

Implement embed for Tencent Hunyuan

**Verified from CLI**
```
RAGFlow(user)> embed text 'what is rag' 'who are you' with 'hunyuan-embedding@test1@hunyuan' dimension 16;
+-----------+-------+
| dimension | index |
+-----------+-------+
| 1024      | 0     |
| 1024      | 1     |
+-----------+-------+
```

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
2026-05-25 16:04:17 +08:00
dripsmvcp
8d8ea71877 Go: implement provider: Tencent Hunyuan (#15092)
## Summary
- Adds a `Hunyuan` Go driver so the new API server can route Tencent
Hunyuan chat instances (registered in `conf/llm_factories.json:3830` as
`Tencent Hunyuan`). Follows the same SaaS-driver shape used for
Astraflow, Avian, Novita, TogetherAI, Replicate, DeepInfra, Upstage, and
LongCat.

Closes #15087

---------

Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-25 11:04:39 +08:00