### What problem does this PR solve?
The LM Studio Go driver shipped with a stub \`Encode\` method that
returned \`no such method\`, even though LM Studio is one of the most
common local LLM runners on macOS and Windows and exposes an
OpenAI-compatible embeddings endpoint at \`/v1/embeddings\`.
LM Studio users routinely load local embedding models such as
\`nomic-ai/nomic-embed-text-v1.5\`,
\`mixedbread-ai/mxbai-embed-large-v1\`, or \`BAAI/bge-m3\`. They run on
the same \`/v1\` namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not actually run an embedding
call.
This finishes the local-LLM trio: Ollama Encode (#14664) and vLLM Encode
(#14688) are already in flight, both using the
same OpenAI-compatible \`/embeddings\` shape.
### What this PR includes
- \`conf/models/lmstudio.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the driver can build the URL from config.
- \`internal/entity/models/lmstudio.go\`: replace the \`Encode\` stub
with a real implementation. Adds a small local response type that
matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local LM Studio,
so the Authorization header is only set when both \`apiConfig\` and
\`ApiKey\` are non-nil and non-empty, the same pattern the recently
merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) and the in-flight Ollama Encode (#14664) and vLLM
Encode (#14688) use.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`LmStudioModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647), the in-flight
Ollama Encode (#14664) and vLLM Encode (#14688), and the existing
SiliconFlow Encode.
Closes#14693
### What problem does this PR solve?
The NVIDIA Go driver in `internal/entity/models/nvidia.go` shipped with
a stub `Encode`
method that returned `no such method`. `conf/models/nvidia.json` already
lists
`nvidia/llama-3.2-nemoretriever-1b-vlm-embed-v1` as an embedding model,
but the conf had
no `embedding` URL suffix, so the picker had nothing wired even if
`Encode` worked.
A tenant who wanted to use NVIDIA NIM for chat (already working) and
embeddings from a
single provider could not, even though the upstream endpoint is public
at
`https://integrate.api.nvidia.com/v1/embeddings` and uses an
OpenAI-compatible request
body extended with the NVIDIA-specific `input_type` and `truncate`
fields. Several other
Go drivers already implement `Encode` (siliconflow, zhipu-ai, aliyun),
so the interface
and the pattern are well-established.
This PR fills the gap.
### What this PR includes
* `conf/models/nvidia.json`: declare the `embedding` URL suffix
alongside the existing
`chat` and `models` entries. The embedding model entry was already
present, so no
model addition is needed.
* `internal/entity/models/nvidia.go`: replace the `Encode` stub with a
real
implementation. Adds a small local response type that matches the
OpenAI-compatible
shape NVIDIA NIM returns.
No factory change. No interface change.
### How the driver works
* Validates `apiConfig` and the API key, validates the model name,
resolves the region
with a default fallback (matching the pattern the merged `ListModels`
and
`CheckConnection` paths in this driver already use), and builds the URL
from
`BaseURL[region] + URLSuffix.Embedding`.
* Sends all input texts in one request as the `input` array, with the
NVIDIA-specific `input_type: "query"`, `encoding_format: "float"`, and
`truncate: "END"`
fields, mirroring the Python `NvidiaEmbed` reference.
* Parses `data[*].embedding` and copies each slice into `[][]float64`
indexed by
`data[*].index` so the output order matches the input order even if the
API returns
items in a different order.
* Handles both `float64` and `float32` element types.
* Empty input returns `[][]float64{}` with no HTTP call.
* Non-200 responses propagate the upstream status line and body.
* A final pass checks every input slot got a vector and returns a clear
error if any
slot is still nil.
* Per-call 30s context deadline so a slow call cannot block forever.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
* `go build ./internal/entity/models/...` returns exit 0.
* `go vet ./internal/entity/models/...` is clean.
* `gofmt -l internal/entity/models/nvidia.go` is clean.
* The full method set on `NvidiaModel` still matches the `ModelDriver`
interface.
* Pattern parity with the just-merged Aliyun `Encode` (#14647).
Closes#14699
### What problem does this PR solve?
The Ollama Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though Ollama is one of the most common local
LLM runners and exposes an OpenAI-compatible embeddings endpoint at
\`/v1/embeddings\`.
Ollama users routinely run local embedding models such as
\`nomic-embed-text\`, \`mxbai-embed-large\`, or \`bge-m3\`.
Pulled with \`ollama pull <model>\` and served on the same \`/v1\`
namespace as chat. The existing \`ListModels\` already
discovers them, but because \`Encode\` was a stub, a tenant who picked
one of these models in the Go layer could not
actually run an embedding call.
### What this PR includes
- \`conf/models/ollama.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the
driver can build the URL from config.
- \`internal/entity/models/ollama.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for local Ollama, so
the Authorization header is only set when both
\`apiConfig\` and \`ApiKey\` are non-nil and non-empty, the same pattern
the recently merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) uses.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`OllamaModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the merged Aliyun Encode (#14647) and the existing
SiliconFlow Encode.
Closes#14662
### What problem does this PR solve?
The vLLM Go driver shipped with a stub \`Encode\` method that returned
\`not implemented\`, even though vLLM is one of the most common
production-grade self-hosted inference servers and exposes an
OpenAI-compatible embeddings endpoint at \`/v1/embeddings\`.
Users who self-host \`BAAI/bge-m3\`, \`Qwen3-Embedding-*\`,
\`NV-Embed-v2\`, or similar models on vLLM could not run an embedding
call through the Go layer. The existing \`ListModels\` already discovers
the loaded models, but the embedding path failed because \`Encode\` was
a stub.
### What this PR includes
- \`conf/models/vllm.json\`: add \`\"embedding\": \"embeddings\"\` under
\`url_suffix\` so the driver can build the URL from config.
- \`internal/entity/models/vllm.go\`: replace the \`Encode\` stub with a
real implementation. Adds a small local response
type that matches the OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate the model name. The API key is optional for self-hosted vLLM,
so the Authorization header is only set when both \`apiConfig\` and
\`ApiKey\` are non-nil and non-empty, the same pattern the recently
merged CheckConnection PR (#14614) uses.
- Resolve the region with a default fallback. Return a clear "missing
base URL" error when the user has not configured
the local access address yet.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, the same pattern the merged
Aliyun Encode (#14647) and in-flight Ollama Encode (#14664) use.
- Send \`{model, input: [texts]}\` in one request.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\`, so the output
order matches the input order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Length mismatch between input and result, out-of-range index, and any
missing slot all return clear errors instead
of silent zero vectors.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`VllmModel\` still matches the \`ModelDriver\`
interface.
- Pattern parity with the merged Aliyun Encode (#14647), the in-flight
Ollama Encode (#14664), and the existing
SiliconFlow Encode.
Closes#14687
### What problem does this PR solve?
The Gitee AI Go driver in `internal/entity/models/gitee.go` shipped with
a stub `Encode` method that returned `gitee, no such method`, even
though `conf/models/gitee.json` already wires the `embedding` URL
suffix. The conf also listed no embedding models, so the picker had
nothing to select.
This blocked any tenant who wanted to use Gitee AI for chat, rerank
(already working, see #14656), and embeddings from a single provider.
This PR fills the gap, mirroring the just-merged Aliyun `Encode`
(#14647):
- `internal/entity/models/gitee.go`: replace the `Encode` stub with a
real implementation.
Validates inputs, resolves the region with a default fallback, POSTs the
standard OpenAI-compatible `{"model", "input": [...]}` body to
`BaseURL[region] + URLSuffix.Embedding`, parses `data[*].embedding`
indexed by `data[*].index` so output order matches input order, handles
both `float64` and `float32` element types, and uses a 30s per-call
context deadline matching the merged `Rerank`.
- `conf/models/gitee.json`: add `BAAI/bge-m3` so the embedding picker
has something to select.
No factory change. No interface change. No URL suffix change.
Verified with `go build`, `go vet`, and `gofmt -l` : all clean.
Closes#14697
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
- Implements the `Encode` method in the Google Gemini driver, which was
previously a stub returning `not implemented`
- Uses the `google.golang.org/genai` SDK's `EmbedContent` API, which
routes to the `batchEmbedContents` endpoint internally — all texts are
sent in a single request
- Adds `text-embedding-004` (max 2048 tokens) to
`conf/models/google.json`
- Response values are `[]float32` from the SDK and are cast to
`[]float64` to satisfy the `ModelDriver` interface
## Files changed
- `internal/entity/models/google.go` — full `Encode` implementation
- `conf/models/google.json` — adds `text-embedding-004` embedding model
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The VolcEngine Go driver in `internal/entity/models/volcengine.go`
shipped with a
`ListModels` stub that returned `volcengine, no such method`.
`conf/models/volcengine.json`
also did not declare a `models` URL suffix, so the model picker had
nothing to call even
if the method body were filled in.
A tenant who configured Volcengine (Doubao / Ark) as a provider could
not see the list of
available endpoints from the RAGFlow UI. Several other Go drivers
already implement
`ListModels` against the OpenAI-compatible `/models` endpoint (deepseek,
gitee, nvidia,
openai, siliconflow), so the interface and pattern are well-established.
This PR fills the gap.
### What this PR includes
* `conf/models/volcengine.json`: declare the `models` URL suffix
alongside the existing
`chat`, `files`, and `embedding` entries. The Ark v3 API exposes
`https://ark.cn-beijing.volces.com/api/v3/models`, so the suffix is just
`models`.
* `internal/entity/models/volcengine.go`: replace the `ListModels` stub
with a real
implementation. Reuses the package-level `DSModelList` / `DSModel` types
that
DeepSeek, Gitee, and SiliconFlow already use to parse the
OpenAI-compatible models
response shape.
No factory change. No interface change.
### How the driver works
* Resolves the region with a default fallback, the same way the other
VolcEngine methods
in this driver already do.
* Builds the URL from `BaseURL[region] + URLSuffix.Models`, with
`strings.TrimSuffix` on
the base to keep the join robust.
* Issues a `GET` with optional `Authorization: Bearer <api_key>` (the
header is omitted
when no key is configured, mirroring the existing NVIDIA `ListModels`).
* Reads the response body once, surfaces a non-200 with the upstream
status line plus
body, and parses the JSON via the shared `DSModelList` type.
* Returns the model id list in input order. When the response includes
an `owned_by`
field, the entry is rendered as `id@owned_by`, matching the convention
used by the
other Go drivers.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
* `go build ./internal/entity/models/...` returns exit 0.
* `go vet ./internal/entity/models/...` is clean.
* `gofmt -l internal/entity/models/volcengine.go` is clean.
* The full method set on `VolcEngine` still matches the `ModelDriver`
interface.
* Endpoint reachability check: `GET
https://ark.cn-beijing.volces.com/api/v3/models`
returns `401 Unauthorized` without an API key, confirming the path
exists and accepts
Bearer authentication.
* Pattern parity with DeepSeek, Gitee, NVIDIA, and SiliconFlow
`ListModels`.
Fixes#14701
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
The OpenAI Go driver landed in #14605 with chat, list models, and check
connection. Encode was left as a stub that returns \`not implemented\`.
\`conf/models/openai.json\` already lists three embedding models out of
the box:
- text-embedding-ada-002
- text-embedding-3-small
- text-embedding-3-large
So a tenant who picked one of these in the Go layer could not actually
run an embedding call. This PR fills the gap.
### What this PR includes
- \`conf/models/openai.json\`: add \`\"embedding\": \"embeddings\"\`
under \`url_suffix\` so the driver can build the URL from config. This
matches the \`URLSuffix.Embedding\` field used by other drivers
(siliconflow, zhipu-ai).
- \`internal/entity/models/openai.go\`: replace the Encode stub with a
real implementation that POSTs to \`/v1/embeddings\`. Adds a small local
response type \`openaiEmbeddingResponse\`.
No factory change. No interface change.
### How the implementation works
- Validate \`apiConfig\` and the API key, validate 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 OpenAI API accepts the
\`input\` field as an array.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\` so the output order matches the input order
even if the API returns items in a different order.
- Handle both \`float64\` and \`float32\` element types, the way the
SiliconFlow driver does.
- An empty input slice returns \`[][]float64{}\` 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 nil, return a clear error so the caller does not silently use a
zero vector.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
(the go.mod minimum) returns exit 0.
- The full method set on \`OpenAIModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the existing SiliconFlow Encode implementation
(\`internal/entity/models/siliconflow.go\`).
Closes#14629
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
This PR completes the Baidu Qianfan provider integration in RAGFlow.
**The following functionalities are now supported:**
- [x] Chat / Think Chat / Stream Chat / Stream Think Chat
- [x] Embedding
- [x] Rerank
- [x] Model listing
- [x] Provider connection checking
- [ ] Balance
-----
**Verified examples from the CLI:**
```plaintext
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 'qwen3-reranker-4b@test@baidu' top 2;
+-------+---------------------+
| index | relevance_score |
+-------+---------------------+
| 0 | 0.974821150302887 |
| 1 | 0.14223189651966095 |
| 2 | 0.08632347732782364 |
+-------+---------------------+
RAGFlow(user)> think chat with 'deepseek-v3.2@test@baidu' message 'who r u'
Thinking: Hmm, the user is asking for a simple introduction. This is straightforward – no need for overcomplication.
I should give a clear, friendly response that covers my basic identity as an AI assistant, my purpose, and my capabilities. Keeping it concise but informative is key here.
Mentioning my creator Anthropic adds credibility, and ending with an offer to help invites further interaction. No need for technical details unless the user asks later.
Answer: Hello! I'm an AI assistant created by Anthropic, designed to help with a wide variety of tasks. You can think of me as a helpful digital companion—I can answer questions, assist with writing, help solve problems, provide explanations, and engage in conversation on many topics. I'm here to help with whatever you need! How can I assist you today?
Time: 8.103902
RAGFlow(user)> stream think chat with 'deepseek-v3.2@test@baidu' message 'who r u'
Thinking: mm, the user is asking "who r u" with casual spelling. This is a straightforward identity question. should give a clear, friendly introduction without overcomplicating it. Can start with my core function as an AI assistant, mention my creator, and briefly state my key capabilities. response should be welcoming and invite further interaction since this seems like an introductory question. Keeping it concise but covering the essentials: who I am, what I do, and how I can help.
Answer: ! I am DeepSeek, an AI assistant created by DeepSeek Company. I'm designed to help answer questions, provide information, assist with various tasks, and engage in conversations on a wide range of topics. I'm here to assist you with whatever you need - whether it's answering questions, helping with analysis, writing, coding, or just having a friendly chat!Is there anything specific I can help you with today? 😊
Time: 7.219703
RAGFlow(user)> list supported models from 'baidu' 'test'
+--------------------------------------+
| model_name |
+--------------------------------------+
| ernie-3.5-8k-preview |
| ernie-4.0-8k |
| ernie-4.0-turbo-8k-latest |
| ernie-4.0-turbo-8k-preview |
| ernie-4.0-8k-preview |
| ernie-speed-pro-128k |
| ernie-char-fiction-8k |
| ernie-3.5-8k |
| ernie-3.5-128k |
| ernie-lite-pro-128k |
| ernie-novel-8k |
| ernie-4.0-turbo-8k |
| ernie-4.0-turbo-128k |
| ernie-4.0-8k-latest |
| irag-1.0 |
| ........... |
| glm-5.1 |
| ernie-image-turbo |
| deepseek-v4-pro |
| deepseek-v4-flash |
| ernie-5.1 |
+--------------------------------------+
RAGFlow(user)> check instance 'test' from 'baidu'
SUCCESS
```
Additionally, this PR fixes an incorrect error message typo:
Before:
```go
fmt.Errorf("API requestssss failed with status %d: %s : %s", ...)
```
After:
```go
fmt.Errorf("API request failed with status %d: %s", ...)
```
This PR mainly improves provider compatibility, API completeness, and
runtime stability.
### Type of change
* [x] Bug Fix (non-breaking change which fixes an issue)
* [x] New Feature (non-breaking change which adds functionality)
* [x] Refactoring
### 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>
### What problem does this PR solve?
Update mapping.json to treat id as a keyword.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Implement `HuggingFace` provider
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The Aliyun Go driver has a stub `Rerank` method that always returns
`"Aliyun, Rerank not implemented"`. DashScope exposes an
OpenAI-compatible rerank endpoint (`compatible-mode/v1/rerank`) and
hosts dedicated bilingual rerankers (`gte-rerank-v2`, `gte-rerank`) that
are a natural pairing with the embedding models already in
`aliyun.json`. Without this, Aliyun users cannot use reranking within
RAGFlow.
Closes#14675
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
1. **Fix Global State Pollution in Local Providers (Critical Bug):** -
Resolved a severe concurrency and architecture issue in
`model_service.go`. Previously, `ListSupportedModels` would permanently
overwrite the global provider singleton with a localized URL instance
(`driver.NewInstance`). This caused cross-request contamination in
multi-tenant environments.
- Fixed `CheckProviderConnection` for local models (LM Studio, vLLM,
Ollama). It now properly creates a localized driver copy and injects the
`base_url` before testing the connection, entirely eliminating the
false-positive `missing base URL` error without polluting the global
state.
2. **Implement `VolcEngine` Embeddings:** - Fully implemented the
`Encode` method for the `volcengine` provider, enabling text embedding
capabilities for VolcEngine models.
3. **Enhance Region Validation in `SiliconFlow`:** - Added a strict
empty string check (`*apiConfig.Region != ""`) alongside the existing
`nil` check when parsing regions. This ensures that if an empty string
is passed, the system safely falls back to the `"default"` region,
preventing malformed URL requests and `unsupported protocol scheme`
errors.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The Aliyun Go driver shipped with a stub \`Encode\` method that returned
\`no such method\`, even though \`conf/models/aliyun.json\` already
wires the OpenAI-compatible embeddings URL suffix at
\`compatible-mode/v1/embeddings\`. The same config also did not list any
embedding models, so the picker had nothing to select.
So an Aliyun tenant who wanted to use Tongyi text-embedding-v3 or v4 in
the Go layer could not, even though the upstream endpoint is public and
uses the standard \`POST /v1/embeddings\` shape that the SiliconFlow and
ZhipuAI
drivers already support.
This PR fills the gap.
### What this PR includes
- \`conf/models/aliyun.json\`: add \`text-embedding-v4\` and
\`text-embedding-v3\` to the \`models\` array.
- \`internal/entity/models/aliyun.go\`: replace the \`Encode\` stub with
a real implementation. Adds a small local response type that matches the
OpenAI-compatible shape.
No factory change. No interface change.
### How the driver works
- Validate \`apiConfig\` and the API key, validate the model name,
resolve the region with a default fallback, build the
URL from \`BaseURL[region] + URLSuffix.Embedding\`.
- Send all input texts in one request as the \`input\` array, the same
OpenAI-compatible shape the SiliconFlow \`Encode\`
uses.
- Parse \`data[*].embedding\` and copy each slice into a \`[][]float64\`
indexed by \`data[*].index\` so the output order matches the input order
even if the API returns items in a different order.
- Handle both \`float64\` and \`float32\` element types.
- Empty input returns \`[][]float64{}\` with no HTTP call.
- Non-200 responses propagate the upstream status line and body.
- A final pass checks every input slot got a vector and returns a clear
error if any slot is still nil.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`AliyunModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the existing SiliconFlow Encode implementation.
Closes#14646
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
1. implement `rerank`, `embedding`, `balance`, `checkConnet` method for
`OpenRouter`
2. delete `chat` method in `internal/entity/models/volcengine.go`
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
The Gitee AI Go driver shipped with a stub \`Rerank\` method that
returned \`Rerank not implemented\`, even though
\`conf/models/gitee.json\` already wires the rerank URL suffix at
\`\"rerank\": \"rerank\"\`. The same config did not list any
rerank model, so the picker had nothing to select.
So a Gitee tenant could not use BAAI/bge-reranker-v2-m3 as a reranker
through the Go layer today, even though the
infrastructure was one config entry and one method body away.
### What this PR includes
- \`conf/models/gitee.json\`: add \`BAAI/bge-reranker-v2-m3\` to the
\`models\` array.
- \`internal/entity/models/gitee.go\`: replace the \`Rerank\` stub with
a real implementation. Adds two small local types
that match the OpenAI-compatible \`/rerank\` shape already used by the
SiliconFlow and ZhipuAI drivers.
No factory change. No interface change.
### How the driver works
- Validate \`apiConfig\` and the API key, validate the model name,
resolve the region with a default fallback, build the
URL from \`BaseURL[region] + URLSuffix.Rerank\`.
- Use a per-call \`context.WithTimeout(30s)\` and
\`http.NewRequestWithContext\`, matching the pattern the
recently merged Aliyun Encode and the OpenAI driver already use.
- Send \`{model, query, documents, top_n, return_documents:false}\` in
the body.
- Parse \`results[*].relevance_score\` and copy each score into the
output slice indexed by \`results[*].index\`, so the
output order matches the input order even if the API returns items in a
different order.
- Empty input returns \`[]float64{}\` with no HTTP call.
- An out-of-range result index returns a clear error rather than
silently skipping the entry.
- Non-200 responses propagate the upstream status line and body.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`GiteeModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the existing SiliconFlow Rerank and the recently
merged ZhipuAI Rerank (#14608).
Closes#14655
Closes#14631
### What problem does this PR solve?
The DeepSeek Go driver shipped with a stub \`Balance\` method that
returned \`no such method\`, even though DeepSeek exposes a public \`GET
/user/balance\` endpoint that works with the same Bearer token used for
chat.
So the "Balance" panel in the model provider UI always shows an error
for DeepSeek tenants, while it already works for Moonshot and Gitee.
This PR fills the gap.
### What this PR includes
- \`conf/models/deepseek.json\`: add \`\"balance\": \"user/balance\"\`
under \`url_suffix\` so the driver can build the URL from config the
same way the other endpoints do.
- \`internal/entity/models/deepseek.go\`: replace the \`Balance\` stub
with a real implementation. Adds a small local response type
\`deepseekBalanceResponse\` that matches the upstream shape.
No factory change. No interface change.
### How the driver works
- Validate \`apiConfig\` and the API key, resolve the region (with a
\`default\` fallback), and build the URL from \`BaseURL[region] +
URLSuffix.Balance\`.
- GET the URL with \`Authorization: Bearer <api_key>\`.
- Parse the upstream response:
\`\`\`json
{
\"is_available\": true,
\"balance_infos\": [
{\"currency\": \"USD\", \"total_balance\": \"10.00\", ...},
{\"currency\": \"CNY\", \"total_balance\": \"70.00\", ...}
]
}
\`\`\`
\`total_balance\` is a string in the upstream API, so the driver parses
it with \`strconv.ParseFloat\`.
- Return the first balance entry as \`{\"balance\": <float>,
\"currency\": <string>}\`, the same shape the Moonshot driver returns.
The UI can render it with no provider-specific code.
### Edge cases
- Missing or empty API key returns a clear local error before any HTTP
call.
- Empty \`balance_infos\` returns a clear \"no balance info in
response\" error rather than a zero-value silent success.
- Non-numeric \`total_balance\` returns a clear parse error.
- Non-200 responses propagate the upstream status line and body so the
user can see why the call failed.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
(the go.mod minimum) returns exit 0.
- The full method set on \`DeepSeekModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the existing Moonshot and Gitee Balance
implementations.
### What problem does this PR solve?
1. **Implement `OpenRouter` Provider:** Fully support OpenRouter AI
models (e.g., `gemma`, `minimax`). Includes robust handling of
Server-Sent Events (SSE) streams, error event interception, and proper
parsing of both `reasoning_content` and standard `content`.
2. **Fix BaseURL Resolution Bug:** Fixed a critical edge case in region
configuration parsing. Added a strict empty string check
(`*apiConfig.Region != ""`) alongside the `nil` check. This ensures that
if the UI passes an empty string, the system correctly falls back to the
`"default"` region, preventing `unsupported protocol scheme ""` errors
during HTTP requests.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
The SiliconFlow Go driver shipped with a stub \`Balance\` method that
returned \`no such method\`, even though SiliconFlow exposes a public
\`GET /v1/user/info\` endpoint that returns the account balance per
currency.
So the "Balance" panel in the model provider UI always shows an error
for SiliconFlow tenants, while it already works for
Moonshot and Gitee. This PR fills the gap.
### What this PR includes
- \`conf/models/siliconflow.json\`: add \`\"balance\": \"user/info\"\`
under \`url_suffix\` so the driver builds the URL from config.
- \`internal/entity/models/siliconflow.go\`: replace the \`Balance\`
stub with a real implementation. Adds a small local response type that
matches the upstream shape.
No factory change. No interface change.
### How the driver works
- Validate \`apiConfig\` and the API key, resolve the region with a
default fallback, and build the URL from \`BaseURL[region] +
URLSuffix.Balance\`.
- GET the URL with \`Authorization: Bearer <api_key>\`.
- Parse the upstream response. SiliconFlow returns balance fields as
strings, so the driver parses them with \`strconv.ParseFloat\`. It
prefers \`totalBalance\` over \`balance\` when both are present.
- Return \`{\"balance\": <float>, \"currency\": \"CNY\"}\`, the same
shape the Moonshot driver returns. The UI can render it
with no provider-specific code.
### Edge cases
- Missing or empty API key returns a clear local error before any HTTP
call.
- An unknown region falls back to the default base URL.
- Empty \`balance\` and \`totalBalance\` returns a clear "no balance
info in response" error rather than a zero-value silent success.
- Non-numeric balance string returns a clear parse error.
- Non-200 responses propagate the upstream status line and body.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- \`go build ./internal/entity/models/...\` in a clean go 1.25 image
returns exit 0.
- The full method set on \`SiliconflowModel\` still matches the
\`ModelDriver\` interface.
- Pattern parity with the existing Moonshot and Gitee Balance
implementations.
Closes#14642
### What problem does this PR solve?
Feat: support local provider for code exec component & remove some
outdated models
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
1. **Implement `Nvidia` Provider:** Fully support NVIDIA NIM APIs with
robust parameter handling (including the `thinking` parameter) and safe
URL merging in `NewInstance`.
2. **Fix Misleading CLI Errors:** Corrected a bug in `common_command.go`
where failed chat requests inaccurately reported `failed to list
instance models`.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add a Go driver for OpenAI (GPT models).
The config file conf/models/openai.json has been in the repo for a while
with the full GPT-5 model list, but
internal/entity/models/factory.go had no case for "openai". So any
tenant that configured OpenAI as a model provider in the Go layer fell
through to the default branch and got the dummy driver. Chat, list
models, and check connection all returned dummy responses instead of
reaching the API.
OpenAI is the most commonly requested provider and the JSON config
already ships with the repo, so this gap is high impact even though the
JSON has been there for some time.
### What this PR includes
- New file internal/entity/models/openai.go with an OpenAIModel that
implements the ModelDriver interface.
- factory.go: route the "openai" provider name to NewOpenAIModel.
- conf/models/openai.json: add "models": "models" under url_suffix so
ListModels can hit /v1/models with no hardcoded fallback.
### How the driver works
- OpenAI exposes the canonical OpenAI-compatible API at
https://api.openai.com/v1.
- ChatWithMessages and ChatStreamlyWithSender post to /chat/completions
in the same shape the moonshot, vllm, and xai drivers use.
- ListModels and CheckConnection call /models to list available ids and
confirm the API key works.
- reasoning_content is passed through for the o-series and other
reasoning models, in both the non-stream and stream paths.
- Encode (embeddings) is left as "not implemented" for now, the same way
the other recent provider drivers do it. Rerank and Balance are not part
of OpenAI's public API surface in this layer and return a clear "not
implemented" or "no such method" error.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### How was this tested?
- go build ./internal/entity/models/... in a clean go 1.25 image (the
go.mod minimum) returns exit 0 with no errors.
- Method set of OpenAIModel matches the ModelDriver interface:
NewInstance, Name, ChatWithMessages, ChatStreamlyWithSender, Encode,
Rerank, ListModels, Balance, CheckConnection.
- Pattern parity with the merged moonshot (#14433), volcengine (#14460),
minimax (#14478), vllm (#14532), xai (#14550), and lm-studio (#14586)
PRs.
Closes#14604
### What problem does this PR solve?
implement `lm-studio` provider
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
implement `Ollama` provider
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
implement MiniMax provider
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
### 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>
### What problem does this PR solve?
implement `volcengine` provider
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
1. Refactor server_main
2. Add volcengine
### Type of change
- [x] Refactoring
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### 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>
### 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>
## Summary
RAPTOR's recursive clustering builds a `layers` list tracking
`(start_idx, end_idx)` boundaries per level, but currently discards this
information — only the flat `chunks` list is returned. This makes it
impossible to distinguish leaf-level summaries from top-level ones.
This PR:
- Returns `(chunks, layers)` tuple from `raptor.py`'s `__call__`
- Annotates each RAPTOR summary chunk with `raptor_layer_int` (1 = first
summary level, 2 = summary-of-summaries, etc.)
- Adds `raptor_layer_int` to `infinity_mapping.json` (Elasticsearch
handles it via existing `*_int` dynamic template)
### Why this matters
Downstream features need to know which RAPTOR layer a summary belongs
to:
- **Retrieving the top-level document summary** for entity extraction,
search snippets, or document comparison
- **Filtering by abstraction level** — users may want only high-level
summaries or only leaf-level cluster summaries
- **RAPTOR recall quality** — #10951 reports summaries not being
recalled for definition queries; layer metadata enables targeted
retrieval
### Changes
| File | Change | LOC |
|------|--------|-----|
| `rag/raptor.py` | Return `(chunks, layers)` tuple | ~3 |
| `rag/svr/task_executor.py` | Build `chunk_layer` mapping, set
`raptor_layer_int` | ~12 |
| `conf/infinity_mapping.json` | Add `raptor_layer_int` integer field |
~1 |
### Backward compatibility
- **Additive only** — no existing fields or behavior changed
- Existing RAPTOR chunks continue to work (they'll have
`raptor_layer_int = 0` by default)
- New RAPTOR chunks get layer metadata automatically
## Test plan
- [ ] Parse a document with RAPTOR enabled, verify `raptor_layer_int` is
set on indexed chunks
- [ ] Verify `raptor_layer_int` values increase with abstraction level
(layer 1 < layer 2 < ...)
- [ ] Verify existing RAPTOR deletion (`delete by raptor_kwd`) still
works
- [ ] Verify Infinity backend accepts the new field
Fixes#7488
Related: #4104, #11191, #10951🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: yuch85 <yuch85.1@gmail.com>
Co-authored-by: Wang Qi <wangq8@outlook.com>
### 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>
### 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>
### 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>
## Add Astraflow Provider Support
This PR integrates [Astraflow](https://astraflow.ucloud.cn/) (by UCloud
/ 优刻得) as a new AI model provider in RAGFlow, with support for both
global and China endpoints.
### About Astraflow
Astraflow is an OpenAI-compatible AI model aggregation platform
supporting 200+ models from major providers including DeepSeek, Qwen,
GPT, Claude, Gemini, Llama, Mistral, and more.
| Variant | Factory Name | Endpoint | Env Var |
|---------|-------------|----------|---------|
| Global | `Astraflow` | `https://api-us-ca.umodelverse.ai/v1` |
`ASTRAFLOW_API_KEY` |
| China | `Astraflow-CN` | `https://api.modelverse.cn/v1` |
`ASTRAFLOW_CN_API_KEY` |
- **API key signup**: https://astraflow.ucloud.cn/
---
### Files Changed
| File | Change |
|------|--------|
| `rag/llm/__init__.py` | Register `Astraflow` and `Astraflow-CN` in
`SupportedLiteLLMProvider` enum, `FACTORY_DEFAULT_BASE_URL`, and
`LITELLM_PROVIDER_PREFIX` |
| `rag/llm/chat_model.py` | Add `AstraflowChat` and `AstraflowCNChat`
(OpenAI-compatible `Base` subclass) |
| `rag/llm/embedding_model.py` | Add `AstraflowEmbed` and
`AstraflowCNEmbed` (subclasses of `OpenAIEmbed`) |
| `rag/llm/rerank_model.py` | Add `AstraflowRerank` and
`AstraflowCNRerank` (subclasses of `OpenAI_APIRerank`) |
| `rag/llm/cv_model.py` | Add `AstraflowCV` and `AstraflowCNCV`
(subclasses of `GptV4`) |
| `rag/llm/tts_model.py` | Add `AstraflowTTS` and `AstraflowCNTTS`
(subclasses of `OpenAITTS`) |
| `rag/llm/sequence2txt_model.py` | Add `AstraflowSeq2txt` and
`AstraflowCNSeq2txt` (subclasses of `GPTSeq2txt`) |
| `conf/llm_factories.json` | Register `Astraflow` and `Astraflow-CN`
factories with a curated list of popular models |
---
### Supported Model Types
- ✅ **Chat / LLM** — DeepSeek-V3/R1, Qwen3, GPT-4o/4.1, Claude 3.5/3.7,
Gemini 2.0/2.5 Flash, Llama 3.3/4, Mistral, and 200+ more
- ✅ **Text Embedding** — text-embedding-3-small/large
- ✅ **Image / Vision (IMAGE2TEXT)** — GPT-4o, GPT-4.1, Claude, Gemini,
Llama-4, etc.
- ✅ **Text Re-Rank**
- ✅ **TTS** — tts-1
- ✅ **Speech-to-Text (SPEECH2TEXT)** — whisper-1
### Implementation Notes
- Uses the `openai/` LiteLLM prefix — consistent with other
OpenAI-compatible aggregation platforms (SILICONFLOW, DeerAPI, CometAPI,
OpenRouter, n1n, Avian, etc.)
- `Astraflow` (global, rank 250) and `Astraflow-CN` (China, rank 249)
are separate factory entries, allowing users to choose the optimal
endpoint based on their region.
- All model classes cleanly subclass existing base classes (`Base`,
`OpenAIEmbed`, `OpenAI_APIRerank`, `GptV4`, `OpenAITTS`, `GPTSeq2txt`)
with no custom logic needed — the provider is fully OpenAI-compatible.
---------
Co-authored-by: user <user@xzaaaMacBook-Air.local>
### 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>
### 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>
https://bailian.console.aliyun.com/cn-beijing?tab=api#/api/?type=model&url=2780056
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Other (please describe): add gte-rerank-v2、qwen3-rerank
### What problem does this PR solve?
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
---------
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
### 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>
