Files
ragflow/internal/entity/models/factory.go
tmimmanuel eaa2e46b1e Go: implement Embed (embeddings) in Upstage driver (#14819)
### What problem does this PR solve?

The Upstage Go driver landed in #14817 with chat, list models, and check
connection. `Embed` was left as a stub that returns `"not implemented"`.
This PR fills the gap.

Upstage exposes an OpenAI-compatible embeddings endpoint at
`https://api.upstage.ai/v1/solar/embeddings` via the
`solar-embedding-1-large` family (`solar-embedding-1-large-query` for
queries, `solar-embedding-1-large-passage` for passages), and the Python
side has had `UpstageEmbed(OpenAIEmbed)` in `rag/llm/embedding_model.py`
for a long time targeting this same path. The existing
`conf/models/upstage.json` did not list any embedding model out of the
box, so a tenant who wanted to use Upstage end to end could not run an
embedding call. This PR fills the gap.

### What this PR includes

- `conf/models/upstage.json`: add `"embedding": "embeddings"` under
`url_suffix` so the driver can build the URL from config (matches the
`URLSuffix.Embedding` field already used by openai, mistral,
siliconflow, zhipu-ai), and add `solar-embedding-1-large-query` and
`solar-embedding-1-large-passage` entries under `models`.
- `internal/entity/models/upstage.go`: replace the `Embed` stub with a
real implementation that POSTs to `/v1/solar/embeddings`. Adds local
response types `upstageEmbeddingData` and `upstageEmbeddingResponse`.

No factory change. No interface change.

### How the implementation works

- Validate `apiConfig`, the API key, and the model name. Use the
existing `baseURLForRegion` helper so an unknown region fails fast with
a clear error.
- Wrap the request with `context.WithTimeout(nonStreamCallTimeout)` so
the call has a clear deadline. Same pattern as `ChatWithMessages` and
`ListModels` already use in this file.
- Send all input texts in one request. The Upstage API accepts the
`input` field as an array.
- Parse `data[*].embedding` and copy each slice into a `[]EmbeddingData`
indexed by `data[*].index` so the output order matches the input order
even if the API returns items in a different order.
- An empty input slice returns `[]EmbeddingData{}` with no HTTP call.
- Non-200 responses propagate the upstream status line and body.
- A final pass checks that every input slot got a vector. If any slot is
still empty, return a clear error so the caller does not silently use a
zero vector.

### Note on stacking

This PR builds on #14817 (the Upstage driver). Until #14817 merges, this
PR's diff on GitHub will include both that PR's commits and this one.
After #14817 lands on `main`, GitHub will auto-reduce this PR to only
the `Embed` changes (one commit, ~119 line diff in `upstage.go` plus ~15
lines in `upstage.json`).

### Type of change

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

### How was this tested?

- `go build ./internal/entity/models/...` returns exit 0 on go 1.25 (the
`go.mod` minimum).
- The full method set on `UpstageModel` still matches the `ModelDriver`
interface.
- Pattern parity with the existing Mistral Embed
(`internal/entity/models/mistral.go`) and OpenAI Embed
(`internal/entity/models/openai.go`) implementations.

Closes #14818
Depends on #14817
Tracking: #14736

---------

Co-authored-by: Jin Hai <haijin.chn@gmail.com>
2026-05-12 16:11:06 +08:00

86 lines
2.7 KiB
Go

//
// Copyright 2026 The InfiniFlow Authors. All Rights Reserved.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
//
package models
import (
"strings"
)
// ModelFactory creates ModelDriver instances based on provider name
type ModelFactory struct {
}
// NewModelFactory creates a new ModelFactory
func NewModelFactory() *ModelFactory {
return &ModelFactory{}
}
// CreateModelDriver creates a ModelDriver for the given provider and model
func (f *ModelFactory) CreateModelDriver(providerName string, baseURL map[string]string, urlSuffix URLSuffix) (ModelDriver, error) {
providerLower := strings.ToLower(providerName)
switch providerLower {
case "zhipu-ai":
return NewZhipuAIModel(baseURL, urlSuffix), nil
case "deepseek":
return NewDeepSeekModel(baseURL, urlSuffix), nil
case "moonshot":
return NewMoonshotModel(baseURL, urlSuffix), nil
case "minimax":
return NewMinimaxModel(baseURL, urlSuffix), nil
case "gitee":
return NewGiteeModel(baseURL, urlSuffix), nil
case "siliconflow":
return NewSiliconflowModel(baseURL, urlSuffix), nil
case "google":
return NewGoogleModel(baseURL, urlSuffix), nil
case "aliyun":
return NewAliyunModel(baseURL, urlSuffix), nil
case "volcengine":
return NewVolcEngine(baseURL, urlSuffix), nil
case "vllm":
return NewVllmModel(baseURL, urlSuffix), nil
case "xai":
return NewXAIModel(baseURL, urlSuffix), nil
case "lmstudio":
return NewLmStudioModel(baseURL, urlSuffix), nil
case "ollama":
return NewOllamaModel(baseURL, urlSuffix), nil
case "openai":
return NewOpenAIModel(baseURL, urlSuffix), nil
case "nvidia":
return NewNvidiaModel(baseURL, urlSuffix), nil
case "openrouter":
return NewOpenRouterModel(baseURL, urlSuffix), nil
case "huggingface":
return NewHuggingFaceModel(baseURL, urlSuffix), nil
case "baidu":
return NewBaiduModel(baseURL, urlSuffix), nil
case "cohere":
return NewCoHereModel(baseURL, urlSuffix), nil
case "fishaudio":
return NewFishAudioModel(baseURL, urlSuffix), nil
case "upstage":
return NewUpstageModel(baseURL, urlSuffix), nil
case "stepfun":
return NewStepFunModel(baseURL, urlSuffix), nil
case "baichuan":
return NewBaichuanModel(baseURL, urlSuffix), nil
default:
return NewDummyModel(baseURL, urlSuffix), nil
}
}