### What problem does this PR solve?
This PR implements ASR and TTS support for the ZhipuAI Go driver.
The ZhipuAI model config already advertises `glm-asr-2512` as an ASR
model, but the Go driver returned `zhipu, no such method` from
`TranscribeAudio`. This adds the documented audio transcription endpoint
suffix and sends multipart transcription requests with `model`,
`stream=false`, and `file` fields.
Per maintainer review, this also adds the ZhipuAI TTS endpoint suffix
and implements `AudioSpeech` / `AudioSpeechWithSender` for `glm-tts`.
Closes#15133
### 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?
Closes#15089.
Adds PPIO support to the Go model-provider layer so PPIO instances can
be routed through the Go API server with the same OpenAI-compatible
chat, streaming, model listing, and connection-check flow used by other
SaaS providers.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Summary
- Added a PPIO Go model driver.
- Added the PPIO provider catalog and default OpenAI-compatible API URL.
- Registered PPIO in the model factory.
- Added focused provider and provider-manager tests.
## What changed
- Implemented chat completions, SSE streaming, ListModels, and
CheckConnection for PPIO.
- Covered request shape, stream termination, reasoning fallback, model
listing, custom base URLs, safe transport setup, unsupported methods,
and provider config loading.
- Kept the provider catalog aligned with the existing RAGFlow PPIO
factory model set.
- Cleaned up pre-existing Go model package validation blockers so the
scoped provider tests can run normally with vet enabled.
## Why
The existing Python/provider catalog path includes PPIO, but the Go
model-provider layer did not have a PPIO driver, so the Go API server
could not instantiate or use PPIO as requested in #15089.
### What problem does this PR solve?
implement rerank, asr, tts for TogetherAI
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
implement ASR and TTS for Xinference
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
`UpstageModel.ChatStreamlyWithSender` (in the driver merged via #14819)
only extracted `delta.content` from each SSE event. For the `solar-pro3`
reasoning family (and any future Upstage model that follows the same
wire shape), the chain-of-thought is streamed in a **separate
`delta.reasoning` field**, and the driver was silently dropping all of
it.
The non-streaming path already extracts `message.reasoning` into
`ChatResponse.ReasonContent` (added earlier in this PR's history), so
the same model produced **inconsistent behavior** between streaming and
non-streaming: a tenant calling `solar-pro3` with `reasoning_effort:
high` would see the reasoning trace if they used `ChatWithMessages` but
not if they used `ChatStreamlyWithSender`.
### Live evidence
Probed against `api.upstage.ai/v1/chat/completions` with `solar-pro3` +
`reasoning_effort: high` + `stream: true` (8000-token budget so the
reasoning has room to finish):
```
$ curl -sN -H "Authorization: Bearer <key>" -H "Content-Type: application/json" \
-X POST https://api.upstage.ai/v1/chat/completions \
-d '{"model":"solar-pro3","messages":[{"role":"user","content":"Compute 15% of 80."}],
"max_tokens":8000,"stream":true,"reasoning_effort":"high"}'
# across 168 SSE events:
# delta keys seen: [content reasoning role]
# delta.content total len: 121 chars (the visible answer)
# delta.reasoning total len: 159 chars (the chain-of-thought) <- driver dropped this
```
A representative event showing both fields side by side:
```json
data: {"choices":[{"index":0,"delta":{"reasoning":"15% = 0.15."}}]}
data: {"choices":[{"index":0,"delta":{"content":"15% of 80 is "}}]}
```
The 159 chars of reasoning were arriving on the wire and being thrown
away. `solar-pro2` was also probed (625 events); it does **not** emit
`delta.reasoning` — its reasoning is inlined into `delta.content` — so
this change is a no-op for it and for `solar-mini`.
### What this PR includes
- `internal/entity/models/upstage.go`: in the SSE scanner loop, extract
`delta.reasoning` before `delta.content` and forward each non-empty
chunk via the sender's second arg (the existing `reasonContent` channel
the non-stream path already populates).
The ordering contract is documented inline: reasoning chunks within a
single SSE event are emitted before content chunks, so a UI that pipes
both sees the chain-of-thought start before the answer for that token,
matching the wire order Upstage emits.
- `internal/entity/models/upstage_test.go`: three new tests pinning the
new behavior:
- `TestUpstageStreamExtractsReasoningDelta` — reasoning + content
forwarded to the right sender args; one-of invariant per call
- `TestUpstageStreamReasoningChunksArriveBeforeContent` — ordering
pinned within a single SSE event that carries both fields
- `TestUpstageStreamWithoutReasoningStillWorks` — regression net:
non-reasoning models (`solar-mini`, `solar-pro2`) continue to work; the
reason callback never fires
No interface change. No factory change. No config change.
### How was this tested?
```
$ go test -vet=off -run TestUpstage -count=1 -v ./internal/entity/models/...
... (existing tests 1..9 still pass) ...
=== RUN TestUpstageStreamExtractsReasoningDelta
--- PASS: TestUpstageStreamExtractsReasoningDelta (0.01s)
=== RUN TestUpstageStreamReasoningChunksArriveBeforeContent
--- PASS: TestUpstageStreamReasoningChunksArriveBeforeContent (0.01s)
=== RUN TestUpstageStreamWithoutReasoningStillWorks
--- PASS: TestUpstageStreamWithoutReasoningStillWorks (0.00s)
PASS
ok ragflow/internal/entity/models 0.034s
```
12/12 Upstage tests pass on go 1.25. `go build
./internal/entity/models/...` exits 0.
**Live integration test** (smoke test not committed) — the patched
driver was run directly against `api.upstage.ai/v1` with the same prompt
that produced the curl evidence above:
```
=== RUN TestUpstageStreamReasoningLiveSmoke
[OK] visible content: 50 chunks, 84 chars
[OK] reasoning: 39 chunks, 90 chars
content head 200: "\\(15\\% = \\frac{15}{100}=0.15\\).\n\n\\[\n0.15 \\times 80 = 12.\n\\]\n\n**15 % of 80 is 12.**"
reasoning head 200: "We need to compute 15% of 80. That's 0.15 * 80 = 12. So answer is 12. Provide explanation."
UPSTAGE STREAM REASONING SMOKE PASSED
--- PASS: TestUpstageStreamReasoningLiveSmoke (1.97s)
```
Before this fix, the same call would have produced **0 reasoning
chunks**. The 90 chars of reasoning that the patched driver now surfaces
are the chain-of-thought solar-pro3 emits when reasoning_effort is high.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
`MistralModel.ChatWithMessages` (in the driver merged via #14807)
assumes that `choices[0].message.content` from `/v1/chat/completions` is
always a string and falls through to `return nil, fmt.Errorf("invalid
content format")` on anything else.
That assumption breaks for the **magistral reasoning family**
(`magistral-small-*`, `magistral-medium-*`). When the model needs a
chain-of-thought to answer, Mistral returns `content` as a **structured
array of typed parts**:
```json
"content": [
{"type": "thinking",
"thinking": [{"type": "text", "text": "Combined speed is 150 mph. 300 / 150 = 2 hours."}],
"closed": true},
{"type": "text", "text": "They will meet after **2 hours**."}
]
```
Concretely, this is what the live API returns today (probed against
`api.mistral.ai/v1`):
```
$ curl -H "Authorization: Bearer <key>" -H "Content-Type: application/json" \
-X POST https://api.mistral.ai/v1/chat/completions \
-d '{"model":"magistral-medium-latest",
"messages":[{"role":"user","content":"two trains 60mph and 90mph, 300mi apart, when do they meet? step by step."}],
"max_tokens":1024}'
HTTP 200
{ "choices":[{"message":{
"role":"assistant",
"content":[
{"type":"thinking","thinking":[{"type":"text","text":"Okay, let's see..."}],"closed":true},
{"type":"text","text":"To determine when the two trains meet..."}
]}}] }
```
With the current driver, every call like that returns the generic
`"invalid content format"` error. Trivial prompts that happen to fit in
a string answer still succeed, so the breakage is **non-deterministic
from the tenant's POV**: same model, same provider, sometimes works,
sometimes 500s with no useful error.
A secondary issue: `conf/models/mistral.json` does not include any
magistral model. The picker hid the broken path, which is why this
wasn't caught during #14807's review.
### What this PR includes
- New helper `extractMistralContent(raw interface{}) (answer,
reasonContent string, err error)` in
`internal/entity/models/mistral.go`, which normalizes both shapes
Mistral can return:
- `string` → historical path. `Answer = content`, `ReasonContent = ""`.
Preserves behavior for every non-reasoning model (`mistral-large-*`,
`mistral-small-*`, `ministral-*`, `codestral-*`, `pixtral-*`,
`open-mistral-nemo`).
- `[]interface{}` → walk the parts. Concatenate every `{"type":"text",
"text":...}` part into `Answer`; concatenate the inner text inside every
`{"type":"thinking", "thinking":[...]}` part into `ReasonContent`.
- `ChatWithMessages` now calls the helper instead of doing the raw
`.(string)` cast.
- Unknown part types are **skipped, not failed**. Mistral has been
adding new content variants quickly (audio chunks, citations, etc.);
this driver should not 500 every call when a new part type appears.
- `conf/models/mistral.json`: add `magistral-medium-latest` and
`magistral-small-latest`. Both are visible in `/v1/models` today.
No interface change. No factory change. No new dependencies.
### How was this tested?
**Unit tests** — 5 new tests in `internal/entity/models/mistral_test.go`
on top of the 27 already shipped via #14807:
- `TestMistralChatHandlesStringContent` — regression net for the
historical path
- `TestMistralChatExtractsReasoningFromStructuredContent` — the fixture
body is a trimmed copy of the actual `magistral-medium-latest` response
captured above; asserts both `Answer` and `ReasonContent` are populated
correctly
- `TestMistralChatHandlesStructuredContentWithoutThinking` —
`magistral-*` with a trivial answer returns a structured shape that has
only a `text` part; `ReasonContent` must stay empty
- `TestMistralChatIgnoresUnknownContentPartTypes` — `audio_url` and
`future_part_type` parts are skipped, `text` parts still flow through
- `TestExtractMistralContent` — table-driven unit coverage of the helper
for string, empty string, nil, empty array, text-only, thinking+text,
unsupported root type
```
$ go test -vet=off -run "TestMistral|TestExtractMistralContent" -count=1 -v ./internal/entity/models/...
=== RUN TestMistralChatHandlesStringContent
--- PASS: TestMistralChatHandlesStringContent (0.00s)
=== RUN TestMistralChatExtractsReasoningFromStructuredContent
--- PASS: TestMistralChatExtractsReasoningFromStructuredContent (0.00s)
=== RUN TestMistralChatHandlesStructuredContentWithoutThinking
--- PASS: TestMistralChatHandlesStructuredContentWithoutThinking (0.00s)
=== RUN TestMistralChatIgnoresUnknownContentPartTypes
--- PASS: TestMistralChatIgnoresUnknownContentPartTypes (0.00s)
=== RUN TestExtractMistralContent
=== RUN TestExtractMistralContent/plain_string
=== RUN TestExtractMistralContent/empty_string
=== RUN TestExtractMistralContent/nil
=== RUN TestExtractMistralContent/empty_array
=== RUN TestExtractMistralContent/text_only
=== RUN TestExtractMistralContent/thinking_then_text
=== RUN TestExtractMistralContent/unknown_root_type
--- PASS: TestExtractMistralContent (0.00s)
PASS
ok ragflow/internal/entity/models 0.046s
```
All 32 Mistral tests pass on go 1.25. `go build
./internal/entity/models/...` exits 0.
**Live integration test** — driver exercised against `api.mistral.ai/v1`
with the patched code:
```
=== RUN TestMistralMagistralSmoke
[OK] "magistral-small-latest" present upstream
[OK] "magistral-medium-latest" present upstream
[OK trivial] Answer="7" ReasonContent=""
[OK reasoning] Answer len=797 head="To determine when the two trains meet, we can follow these steps:\n\n1. **Identify..."
ReasonContent len=1069 head="Okay, let's see. There are two trains, one going 60 mph and the other going 90 mph. They're moving towards each other, s..."
MAGISTRAL SMOKE PASSED
--- PASS: TestMistralMagistralSmoke (18.09s)
PASS
ok ragflow/internal/entity/models 18.112s
```
What the live run proves on the wire:
- `magistral-small-latest` with a trivial prompt still uses the
string-content shape; the regression-net path is exercised against the
real server, not just the mock.
- `magistral-medium-latest` with a reasoning prompt uses the
structured-array shape; the new code path extracts a 1069-character
reasoning trace into `ChatResponse.ReasonContent` and a 797-character
visible answer into `ChatResponse.Answer`. Before this fix, the same
call returned `"invalid content format"` and the caller saw nothing.
The smoke-test file itself is not committed (live tests live outside the
PR diff, same convention used for prior provider PRs).
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Problem
The Go server build pipeline (`build.sh` + CMake + CGO bindings) was
tested on Ubuntu only. On macOS arm64 with Homebrew it fails in five
orthogonal places. None of these require platform-specific code paths —
the same source builds on both Linux and Darwin after these fixes.
## Reproduction (before)
```
$ uname -a
Darwin … 25.4.0 arm64
$ brew install cmake pcre2 simde
$ bash build.sh
…
error: 'simde/x86/sse4.1.h' file not found
error: implicit instantiation of undefined template 'std::basic_istringstream<char>'
error: no matching function for call to 'Join'
…
clang: error: no such file or directory: '/usr/local/lib/libpcre2-8.a'
```
## Fix (5 small, orthogonal changes)
### 1. `internal/cpp/CMakeLists.txt` — find Homebrew + libpcre2-8
portably
- Detect Apple platforms via `if(APPLE)`, call `brew --prefix` once, add
`${HOMEBREW_PREFIX}/include` and `${HOMEBREW_PREFIX}/lib`. No effect on
Linux.
- Replace the literal `libpcre2-8.a` link token (which only the Linux
linker finds in `/usr/local/lib` by default) with
`find_library(PCRE2_LIB NAMES pcre2-8 REQUIRED)`. Works on
`/usr/lib/x86_64-linux-gnu` (Debian/Ubuntu), `/usr/local/lib` (Intel Mac
& legacy Linux), `/opt/homebrew/lib` (Apple Silicon).
### 2. `internal/cpp/wordnet_lemmatizer.cpp` +
`internal/cpp/rag_analyzer.cpp` — explicit `#include <sstream>`
libstdc++ (Linux) pulls `<sstream>` in transitively via `<fstream>`;
libc++ (Apple Clang) doesn't, so the existing `std::istringstream` /
`std::ostringstream` uses fail to compile on macOS. One-line include in
each file.
### 3. `internal/cpp/rag_analyzer.cpp` — `Join` template overload fix
`Join(tokens, start, tokens.size(), delim)` at line 146 passes `size_t`
to an `int` parameter. C++23 strict mode in Apple Clang refuses the
implicit narrowing and reports the 4-arg overload as a substitution
failure, leaving the call ambiguous between the 3-arg and 4-arg
templates. Fix: explicit `static_cast<int>(tokens.size())`. Behaviour
identical on libstdc++ — the narrowing was always intentional.
### 4. `internal/binding/rag_analyzer.go` — split darwin CGO LDFLAGS
The existing `#cgo darwin LDFLAGS: ... /usr/local/lib/libpcre2-8.a` only
matches Intel Macs. Apple Silicon Homebrew installs to `/opt/homebrew`.
Split into `darwin,arm64` and `darwin,amd64` build constraints with the
right absolute path on each.
### 5. `build.sh` — accept Homebrew path in the pcre2 sanity check
The sanity check looked at two Linux paths only and then fell through to
`sudo apt -y install libpcre2-dev` on failure. Added
`/opt/homebrew/lib/libpcre2-8.a`, and on Darwin failure now exits
cleanly with the right `brew install pcre2` hint instead of trying
`apt`.
## Verified
- `bash build.sh` now completes on macOS arm64 (Apple Silicon, brew 4.x,
cmake 4.x, Apple Clang 17, Go 1.25, pcre2 10.x, simde 0.8.x).
- Produced binaries: `bin/server_main`, `bin/admin_server`,
`bin/ragflow_cli`.
- `bin/server_main` boots, connects MySQL, runs migrations, loads the 64
model provider configs cleanly.
- Still builds on Linux — the CMake additions are inside an `if(APPLE)`
guard, the `find_library` call matches Linux paths too, the build.sh
check still tries `apt` when not on Darwin.
## Out of scope
The Go server itself currently fails at runtime when not pointing at
Elasticsearch (`Failed to initialize doc engine: failed to ping
Elasticsearch`), but that's the placeholder Infinity engine documented
in `internal/engine/README.md` — unrelated to this build patchset.
---
Happy to split this into smaller PRs if you'd prefer (one per file). The
five changes are independent.
## What
- Add Perplexity as a chat and embedding provider backed by its
OpenAI-compatible `/chat/completions` and `/v1/embeddings` APIs
- Register Perplexity in the Go model factory and provider config
- Support non-streaming chat, SSE streaming chat, embeddings, model
listing, and connection checks
Refs #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
- Adds an `Astraflow` Go driver so the new API server can route
Astraflow (UCloud ModelVerse) chat instances, matching the existing
Python `AstraflowChat` (`rag/llm/chat_model.py:1237`). Follows the same
SaaS-driver shape used for Avian, Novita, TogetherAI, Replicate,
DeepInfra, Upstage, and LongCat.
Closes#15062
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Closes#15044.
Avian was listed unchecked in the Go-rewrite tracker #14736 and already
had an llm_factories.json entry with 4 preconfigured chat models
(deepseek-v3.2, kimi-k2.5, glm-5, minimax-m2.5), but the Go API server
had no driver to route them. The Python side has supported Avian at
rag/llm/chat_model.py:1220 (AvianChat) via the LiteLLM openai/ provider
with default base https://api.avian.io/v1.
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
`ReplicateModel.Embed` in `internal/entity/models/replicate.go` was a
`"replicate, no such method"` stub. Tracking issue #14736 lists
Replicate's embedding surface as not implemented. This PR wires it up
against Replicate's documented embedding schema.
Until this PR, a tenant who selected a Replicate embedding model got the
sentinel error on every embed call.
Co-authored-by: sxxtony <sxxtony@users.noreply.github.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## What problem does this PR solve?
Closes#15021.
The Go model-provider layer had no support for **Azure OpenAI**. Azure
OpenAI is *not* a drop-in base-URL swap of the OpenAI driver — it
differs in authentication, endpoint structure, and how models are listed
— so it needs its own `ModelDriver` implementation.
## Type of change
- [x] New feature (non-breaking change which adds functionality)
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fixes#15023
GPUStack is listed as unchecked in the Go-rewrite tracker #14736, and
`internal/service/llm.go:171` already classifies it as a self-deployed
provider alongside Ollama, Xinference, LocalAI, and LM Studio — but
`internal/entity/models/` had no `gpustack.go` driver, so the new Go API
server could not route GPUStack instances. This PR adds the chat surface
for GPUStack so it lines up with the existing self-hosted Go drivers.
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- Replaces the `"no such method"` stub on `XinferenceModel.Embed`
(`internal/entity/models/xinference.go`) with a real implementation
against Xinference's OpenAI-compatible `/v1/embeddings` endpoint.
- Adds the `"embedding": "v1/embeddings"` URL suffix to
`conf/models/xinference.json`.
- Mirrors the Python `XinferenceEmbed` class in
`rag/llm/embedding_model.py:407` for payload shape (OpenAI-compatible
`model + input` → `data[*].index + data[*].embedding`) and tolerates the
same no-auth default Xinference deployments use. Authorization is only
sent when a non-empty API key is configured, via the existing
`setXinferenceAuth` helper.
- Reuses the existing `normalizeXinferenceBaseURL` + `baseURLForRegion`
helpers so both `http://127.0.0.1:9997` and `http://127.0.0.1:9997/v1`
resolve to the same `/v1/embeddings` target without doubled `/v1`.
- Validates response indices — duplicate, missing, or out-of-range
`data[*].index` values fail with a clear error rather than silently
producing misaligned vectors.
- Returns `[]EmbeddingData` in original input order (placed by `Index`)
so downstream callers can index positionally without re-sorting.
- Forwards `EmbeddingConfig.Dimension` as `dimensions` when `> 0`,
matching the OpenAI cluster pattern.
Closes#14810
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fixes#15012
The Novita Go driver landed in #14850 and shipped a stub `Rerank` method
that returned `"novita, no such method"`, so Novita could not be used as
a rerank provider in RAGFlow. This PR fills that gap, in the same way
#14895 filled the Embed gap on the same driver.
Novita exposes a public rerank endpoint at `POST
https://api.novita.ai/openai/v1/rerank` that accepts the
Cohere-compatible request shape (`{model, query, documents, top_n}`)
with `Authorization: Bearer <api_key>`. `baai/bge-reranker-v2-m3` is
documented in Novita's model library with a 1024-token limit.
### What problem does this PR solve?
Fixes#14816
The Xinference Go driver landed chat in #14938 and Embed is in review in
#14932, but `Rerank` shipped as a stub that returns `"xinference, no
such method"`. Tenants who launch a rerank model with `--model-type
rerank` on their Xinference instance cannot route it through the Go API
server. This PR fills the gap.
Xinference exposes an OpenAI-compatible REST API. The rerank endpoint is
at `POST <base>/v1/rerank` and accepts the Cohere-shaped body `{model,
query, documents, top_n}`, returning `{results: [{index,
relevance_score}]}` — the same wire shape used by the merged NVIDIA
(#14778), Aliyun (#14676), Gitee (#14656), ZhipuAI (#14608), Novita
(#15014), and LocalAI (#14813) Rerank implementations. Documented in
[Xinference rerank
docs](https://inference.readthedocs.io/en/v1.6.1/models/model_abilities/rerank.html);
the [builtin rerank model
catalog](https://inference.readthedocs.io/en/stable/models/builtin/rerank/)
lists `bge-reranker-base`, `bge-reranker-large`, `bge-reranker-v2-m3`,
and others.
### What problem does this PR solve?
Add a Go driver for **n1n.ai** (https://docs.n1n.ai), one of the
unchecked providers on the umbrella tracking issue #14736. n1n.ai is an
OpenAI-compatible aggregator hosting a 450+ model catalog (GPT, Claude,
Gemini, DeepSeek, Kimi, Qwen, embedding + reranker families) under
`https://api.n1n.ai/v1`.
Until this PR, a tenant who configured `n1n` as a model provider in the
Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
---------
Co-authored-by: sxxtony <sxxtony@users.noreply.github.com>
### What problem does this PR solve?
Fixes#15015
The TogetherAI Go driver in `internal/entity/models/togetherai.go`
shipped a stub `Embed` method that returned `"TogetherAI, no such
method"`, so TogetherAI could not be used as an embedding provider in
RAGFlow. This PR fills that gap.
TogetherAI exposes a public OpenAI-compatible embeddings endpoint at
`POST https://api.together.ai/v1/embeddings` that accepts the standard
`{model, input}` shape with `Authorization: Bearer <api_key>` (confirmed
in TogetherAI's official docs:
https://docs.together.ai/docs/embeddings-overview). Documented embedding
models include `intfloat/multilingual-e5-large-instruct`,
`BAAI/bge-large-en-v1.5`, and `BAAI/bge-base-en-v1.5`.
### Changes
- `internal/entity/models/togetherai.go`: implement
`TogetherAIModel.Embed`.
- Validate inputs (api key, model name) and short-circuit on empty
texts.
- Resolve region with the existing `baseURLForRegion` helper.
- Build URL from `URLSuffix.Embedding`.
- Send `{model, input}` POST body, add `dimensions` when
`embeddingConfig.Dimension > 0` (matches the pattern in #14735).
- Bearer auth + JSON content type, mirroring the chat path.
- Parse `{data: [{embedding, index}]}` and reorder by `index`, rejecting
out-of-range indices, duplicates, and missing entries so the output
always lines up with the input. Same shape as the merged Mistral,
Upstage, and Novita Embed implementations.
- `conf/models/togetherai.json`:
- Add `"embedding": "embeddings"` to `url_suffix`.
- Add default embedding model entries for
`intfloat/multilingual-e5-large-instruct`, `BAAI/bge-large-en-v1.5`, and
`BAAI/bge-base-en-v1.5`.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
1. Add model types when add model
---
```
RAGFlow(user)> add model 'pipeline' to provider 'mineru_local' instance 'test' with tokens 131072 doc_parse;
SUCCESS
```
2. implement provider: MinerU_Local
---
**Verified from CLI**
```
RAGFlow(user)> parse with 'pipeline@test@mineru_local' file './internal/test.pdf'
+--------------------------------------+
| task_id |
+--------------------------------------+
| c7260e31-b6e2-4b36-955d-e9c60510c669 |
+--------------------------------------+
RAGFlow(user)> show 'test@mineru_local' task 'c7260e31-b6e2-4b36-955d-e9c60510c669'
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+
| content | index |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+
| # Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Bingxin Ke Anton Obukhov Shengyu Huang Nando Metzger Rodrigo Caye Daudt Konrad Schindler Photogrammetry and Remote Sensing, ETH Zurich ¨
### What problem does this PR solve?
Closes#15029.
Some custom `base_url` paths in `ModelProviderService` call
`NewInstance(newURL)` and then immediately invoke methods on the
returned driver. Several real Go model drivers still return `nil` from
`NewInstance`, so those paths can panic instead of returning a normal
error.
This PR:
- centralizes custom base URL driver creation in `model_service.go`
- skips request-local driver creation when `base_url` is blank or
whitespace
- preserves the existing region key behavior when building the
request-local base URL map
- returns a clear error when the provider driver is missing or
`NewInstance` returns `nil`
- routes list/check/task and active model paths through the guarded
helper
- adds focused unit coverage for empty-region preservation, regional
base URLs, blank base URLs, nil drivers, and nil `NewInstance` results
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Test plan
- [x] `git diff --check upstream/main...HEAD`
- [x] `/root/go/bin/gofmt -w internal/service/model_service.go
internal/service/model_service_test.go`
- [x] `GOPATH=/root/gopath GOTOOLCHAIN=local /root/go/bin/go test
./internal/service -run TestNewModelDriverForBaseURL -count=1 -vet=off`
- [x] `GOPATH=/root/gopath GOTOOLCHAIN=local /root/go/bin/go build
./internal/service/... ./internal/entity/models/...`
Note: the same targeted `go test` command without `-vet=off` is
currently blocked by an existing unrelated vet finding in
`internal/service/llm.go:355` (`non-constant format string in call to
fmt.Errorf`).
### What problem does this PR solve?
This PR implement implement provider 302.AI and JieKouAI
**The following functionalities are now supported:**
**302.ai**
- [x] chat / think chat / stream chat / stream think chat
- [x] Embedding
- [x] ASR
- [x] ListModels
- [x] Provider connection checking
- [x] Balance
- [x] Rerank
- [x] OCR
- [x] Doc Parse
- [x] Show task
- [ ] ~~List Tasks!~~
- [ ] TTS
**JieKouAI**
- [x] chat / think chat / stream chat / stream think chat
- [x] Embedding
- [x] Rerank
- [x] ListModels
**Verified examples from the CLI:**
```palintext
# jiekouAI
RAGFlow(user)> stream think chat with 'zai-org/glm-4.5@test@jiekouai' message 'Hi'
Thinking: Let me think about how to respond to this simple greeting. The user just said "Hi", which is a basic and friendly way to start a conversation. I should respond in a similarly warm and welcoming manner.First, I need to acknowledge their greeting and reciprocate with enthusiasm. Something like "Hello!" or "Hi there!" would work well to create a positive atmosphere right from the start.Next, I should make it clear that I'm ready to help. Since they haven't asked anything specific yet, I'll keep it open-ended and inviting. Perhaps offering assistance with a question or task would encourage them to engage further.I should also maintain a professional yet approachable tone. Being an AI assistant, I want to convey that I'm knowledgeable and capable, but also friendly and easy to talk to.Let me put this all together into a concise response. I'll start with a cheerful greeting, express my readiness to help, and finish with an open invitation for them to share what's on their mind. This should create a welcoming environment for whatever they want to discuss next.
Answer: ! I'm Claude, an AI assistant created by Anthropic. I'm here to help you with information, answer questions, or assist you with tasks. What can I help you with today?
RAGFlow(user)> think chat with 'zai-org/glm-4.5@test@jiekouai' message 'Hi'
Thinking: Let me consider how to respond to this greeting. The user initiated with a simple "Hi," so a friendly and open response would be most appropriate to encourage further conversation. I should maintain a welcoming tone while offering assistance.
The response should accomplish a few key things: return the greeting warmly, show openness to conversation, and offer specific ways I can help. This approach demonstrates both approachability and usefulness.
I'll start with a greeting in return, then express my availability to help, and finish by suggesting some areas where I can provide assistance. This creates a natural flow from acknowledgment to support.
It's important to keep the response concise but inviting. Since the user hasn't specified their needs yet, I'll present a few broad categories of assistance to spark their thinking about what they might want to discuss or ask about.
The response should end with an encouraging note that prompts them to share what's on their mind, keeping the conversational ball in their court while making it clear I'm ready to engage with whatever they need.
Answer: Hello! How can I help you today? Whether you have questions, need information, or just want to chat, I'm here to assist.
RAGFlow(user)> embed text 'walkerwhat' 'jumperwho' with 'text-embedding-3-large@test@jiekouai' dimension 16
+-----------+-------+
| dimension | index |
+-----------+-------+
| 3072 | 0 |
| 3072 | 1 |
+-----------+-------+
RAGFlow(user)> rerank query 'what is rag' document 'rag is retrieval augment generation' 'rag need llm' 'famous rag project includes ragflow' with 'baai/bge-reranker-v2-m3@test@jiekouai' top 3
+-------+-----------------+
| index | relevance_score |
+-------+-----------------+
| 0 | 0.9830034 |
| 2 | 0.06399203 |
| 1 | 0.04665664 |
+-------+-----------------+
# 302.ai
RAGFlow(user)> think chat with 'kimi-k2.6@test@302.ai' message 'who r u'
Thinking: The user is asking "who r u" which is a casual way of asking "who are you." I need to identify myself as an AI assistant created by Moonshot AI. I should be friendly, concise, and helpful.
Key points to include:
- I am Kimi, an AI assistant made by Moonshot AI
- I can help with various tasks like answering questions, writing, analysis, coding, etc.
- Keep it casual but informative since the user used "r u" (text speak)
I should not:
- Pretend to be human
- Claim to have personal experiences or emotions
- Be overly formal or robotic
Simple, friendly response is best.
Answer: I'm Kimi, an AI assistant made by Moonshot AI. I can help you with answering questions, writing, coding, analysis, or just chatting. What can I do for you?
Time: 17.687750
RAGFlow(user)> stream think chat with 'kimi-k2.6@test@302.ai' message 'who r u'
Thinking: user asked "who r u" which is a casual way of asking "who are you." I should introduce myself as Kimi, an AI assistant developed by Moonshot AI. I need to be friendly, concise, and accurate. I should mention my capabilities briefly and keep the tone helpful. Since the user used casual text speak ("r u"), I can match that energy with a friendly but still informative tone.Key points:- I'm Kimi, an AI assistant made by Moonshot AI- I can help with various tasks like answering questions, writing, coding, analysis, etc.- Keep it brief but warm- Don't claim to be human- Don't over-explainDraft:"I'm Kimi, an AI assistant created by Moonshot AI. I can help with answering questions, writing, coding, analysis, brainstorming, and lots of other tasks. What can I do for you?"This is good - direct, accurate, and inviting.
Answer: Kimi, an AI assistant made by Moonshot AI. I can help with answering questions, writing, coding, analysis, brainstorming, and lots of other stuff. What can I do for you?
Time: 14.912576
RAGFlow(user)> asr with 'whisper-v3-turbo@test@302.ai' audio './internal/test.wav' param ''
+---------------------------------------------------------------------------------------------------------------------+
| text |
+---------------------------------------------------------------------------------------------------------------------+
| The examination and testimony of the experts enabled the Commission to conclude that five shots may have been fired |
+---------------------------------------------------------------------------------------------------------------------+
RAGFlow(user)> ocr with 'mistral-ocr-latest@test@302.ai' file './internal/test.pdf'
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| text |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| # Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Bingxin Ke
Nando Metzger
Anton Obukhov
Rodrigo Caye Daudt
Shengyu Huang
Konrad Schindler
Photogrammetry and Remote Sensing, ETH Zürich
Figur... |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
RAGFlow(user)> parse with 'vlm@test@302.ai' file 'https://arxiv.org/pdf/2505.09358'
+--------------------------------------+
| task_id |
+--------------------------------------+
| 6de6eae6-c122-4b67-91e8-b061a0b8c087 |
+--------------------------------------+
RAGFlow(user)> show 'test@302.ai' task '6de6eae6-c122-4b67-91e8-b061a0b8c087'
+----------------------------------------------------------------------------+-------+
| content | index |
+----------------------------------------------------------------------------+-------+
| https://file.302.ai/gpt/imgs/20260519/b340fdff4774699c287fe4ee4658b317.zip | 0 |
+----------------------------------------------------------------------------+-------+
RAGFlow(user)> embed text 'walkerwhat' 'jumperwho' with 'jina-embeddings-v3@test@302.ai' dimension 16
+-----------+-------+
| dimension | index |
+-----------+-------+
| 1024 | 0 |
| 1024 | 1 |
+-----------+-------+
RAGFlow(user)> rerank query 'what is rag' document 'rag is retrieval augment generation' 'rag need llm' 'famous rag project includes ragflow' with 'jina-reranker-v2-base-multilingual@test@302.ai' top 3;
+-------+-----------------+
| index | relevance_score |
+-------+-----------------+
| 0 | 0.74167407 |
| 2 | 0.18832397 |
| 1 | 0.15713684 |
+-------+-----------------+
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
## What
- Add TogetherAI as a chat provider backed by its OpenAI-compatible
`/v1/chat/completions` API
- Register TogetherAI in the Go model factory and provider config
- Support non-streaming chat, SSE streaming chat, model listing, and
connection checks
## Notes
- Uses the current TogetherAI OpenAI-compatible base URL
`https://api.together.ai/v1`
- Forwards documented chat parameters from `ChatConfig`: `max_tokens`,
`temperature`, `top_p`, `stop`, and GPT-OSS `reasoning_effort`
- Routes Together reasoning traces from `reasoning` /
`reasoning_content` into `ReasonContent`
## Tests
- `go test -vet=off -run TestTogetherAI -count=1
./internal/entity/models`
- `go test -vet=off -count=1 ./internal/entity/models`
Refs #14736
### What problem does this PR solve?
Closes#14808.
Adds a Go model driver for Xinference so self-hosted Xinference chat
models can be used through the Go provider layer instead of falling
through to the dummy driver. Xinference exposes an OpenAI-compatible API
under `/v1`; the driver accepts either a root endpoint such as
`http://127.0.0.1:9997` or an OpenAI-compatible endpoint such as
`http://127.0.0.1:9997/v1` and normalizes it before calling chat or
model-listing routes.
### What is changed?
- Add `internal/entity/models/xinference.go` implementing `ModelDriver`
for Xinference chat.
- Route provider name `xinference` in
`internal/entity/models/factory.go`.
- Add `conf/models/xinference.json` as a local provider config.
- Add focused unit tests in `internal/entity/models/xinference_test.go`.
Initial method coverage:
- `ChatWithMessages`: POST `/v1/chat/completions`.
- `ChatStreamlyWithSender`: SSE streaming from `/v1/chat/completions`.
- `ListModels`: GET `/v1/models`.
- `CheckConnection`: lightweight `ListModels` probe.
- Optional auth: send `Authorization: Bearer <api_key>` only when a
non-empty key is configured, matching Xinference no-auth and
auth-enabled deployments.
- `Balance`, `Embed`, `Rerank`, ASR, TTS, and OCR return `no such
method` for this initial chat-provider PR.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Bug Fix (non-breaking change which fixes an issue)
### Tests
- `go test -vet=off -run TestXinference -count=1
./internal/entity/models/...`
- `go test -vet=off -count=1 ./internal/entity/models/...`
### References
- Xinference docs:
https://inference.readthedocs.io/zh-cn/latest/index.html
- OpenAI-compatible chat usage:
https://inference.readthedocs.io/zh-cn/latest/getting_started/using_xinference.html
- API key auth:
https://inference.readthedocs.io/zh-cn/latest/user_guide/auth_system.html
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
Fix critical severity security issue in
`internal/cpp/opencc/dictionary/text.c`.
## Vulnerability
| Field | Value |
|-------|-------|
| **ID** | V-001 |
| **Severity** | CRITICAL |
| **Scanner** | multi_agent_ai |
| **Rule** | `V-001` |
| **File** | `internal/cpp/opencc/dictionary/text.c:107` |
**Description**: The OpenCC C library uses fgets() to read dictionary
and configuration files without proper bounds validation on subsequent
buffer operations. While fgets() itself is bounds-checked, the sprintf()
call at config_reader.c:174 constructs file paths by concatenating
home_path and filename without verifying the result fits in pkg_filename
buffer. An attacker providing malformed OpenCC configuration files with
excessively long path components can overflow the fixed-size buffer,
overwriting adjacent memory including return addresses and function
pointers.
## Changes
- `internal/cpp/opencc/config_reader.c`
- `internal/cpp/opencc/dictionary/text.c`
- `internal/cpp/opencc/utils.c`
## Verification
- [x] Build passes
- [x] Scanner re-scan confirms fix
- [x] LLM code review passed
---
*Automated security fix by [OrbisAI Security](https://orbisappsec.com)*
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Bug Fixes**
* Improved error detection and handling for malformed configuration and
dictionary entries during file parsing.
* Enhanced memory cleanup in error recovery paths to prevent potential
issues.
* Strengthened robustness of string operations and buffer handling
throughout the library.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
Co-authored-by: Ubuntu <ubuntu@ip-172-31-32-15.us-west-2.compute.internal>
## What
- Add Replicate as a chat provider backed by the documented predictions
API
- Register Replicate in the Go model factory and provider config
- Support non-streaming chat through sync predictions, polling fallback,
streaming through `urls.stream`, model listing, and connection checks
## Notes
- Uses `POST /v1/predictions` with Replicate model identifiers in
`version`, which supports official and community model identifiers
- Maps RAGFlow messages into Replicate prompt-shaped inputs (`prompt`,
optional `system_prompt`) and forwards common documented LLM inputs:
`max_new_tokens`, `temperature`, `top_p`
- Preserves whitespace in SSE output chunks and emits RAGFlow `[DONE]`
at stream completion
## Tests
- `go test -vet=off -run TestReplicate -count=1
./internal/entity/models`
- `go test -vet=off -count=1 ./internal/entity/models`
Refs #14736
### What problem does this PR solve?
fix forgetting policy validation and fix memory update diff checks
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Adds the Go model provider driver for CometAPI, which is listed as
unchecked in the Go provider tracking issue #14736 and requested in
#14804. Without this, the Go layer falls back to the dummy driver for
the `cometapi` provider.
Fixes#14804
### What this PR includes
- New `internal/entity/models/cometapi.go` implementing `ModelDriver`
for CometAPI.
- New `conf/models/cometapi.json` with CometAPI base URLs and
representative chat / embedding models from the public catalog.
- `factory.go`: route `"cometapi"` to `NewCometAPIModel`.
- Unit tests in `internal/entity/models/cometapi_test.go`.
### Method coverage
- `ChatWithMessages`: `POST /v1/chat/completions`.
- `ChatStreamlyWithSender`: SSE streaming on the same endpoint.
- `Embed`: `POST /v1/embeddings`, including optional `dimensions`.
- `ListModels`: `GET /api/models` public catalog.
- `Balance`: `GET https://query.cometapi.com/user/quota?key=...`.
- `CheckConnection`: delegates to the quota query to verify the key.
- `Rerank`, ASR, TTS, OCR: return `no such method` for now.
No ModelDriver interface change. No new dependencies.
### How was this tested?
```bash
go test -vet=off -run TestCometAPI -count=1 ./internal/entity/models/...
go test -vet=off -count=1 ./internal/entity/models/...
```
---------
Signed-off-by: dependabot[bot] <support@github.com>
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
Signed-off-by: majiayu000 <1835304752@qq.com>
Co-authored-by: 加帆 <Jiafan@users.noreply.github.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: bulexu <baiheng527@gmail.com>
Co-authored-by: xubh <xubh@wikiflyer.cn>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Carve_ <75568342+Rynzie02@users.noreply.github.com>
Co-authored-by: Paul Y Hui <paulhui@seismic.com>
Co-authored-by: LIRUI YU <128563231+LiruiYu33@users.noreply.github.com>
Co-authored-by: yun.kou <koopking@gmail.com>
Co-authored-by: Yun.kou <yunkou@deepglint.com>
Co-authored-by: Ahmad Intisar <168020872+ahmadintisar@users.noreply.github.com>
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
Co-authored-by: chanx <1243304602@qq.com>
Co-authored-by: Syed Shahmeer Ali <syedshahmeerali196@gmail.com>
Co-authored-by: Octopus <liyuan851277048@icloud.com>
Co-authored-by: lif <1835304752@qq.com>
### What problem does this PR solve?
Adds the missing Anthropic provider implementation for the Go model
provider layer.
Closes#14939
### What changed
- Add `conf/models/anthropic.json` with Anthropic Claude chat/vision
models and API endpoints.
- Add `internal/entity/models/anthropic.go` implementing non-streaming
Messages API chat, model listing, and connection checking.
- Register `anthropic` in the Go model factory.
- Add httptest coverage for headers, payload mapping, response parsing,
validation errors, provider errors, model listing, connection checking,
factory registration, and unsupported methods.
### Notes
Streaming chat is left as an explicit `no such method` follow-up because
this initial provider focuses on non-streaming chat and connection
checking.
### Tests
- `docker run --rm -v
/home/ubuntu/Documents/gitTensor_repos/carlos/ragflow:/work -v
/tmp/ragflow-go-cache:/go/pkg/mod -v
/tmp/ragflow-go-build:/root/.cache/go-build -w /work golang:1.25 go test
-vet=off ./internal/entity/models -run Anthropic -count=1 -v`
- `docker run --rm -v
/home/ubuntu/Documents/gitTensor_repos/carlos/ragflow:/work -v
/tmp/ragflow-go-cache:/go/pkg/mod -v
/tmp/ragflow-go-build:/root/.cache/go-build -w /work golang:1.25 go test
-vet=off ./internal/entity -count=1`
- `git diff --check`
- `jq . conf/models/anthropic.json >/dev/null`
Plain `go test ./internal/entity/models` currently hits pre-existing
unrelated vet findings in other provider files (`baidu.go`, `cohere.go`,
`fishaudio.go`, `openrouter.go`).
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
This PR adds non-streaming chat support for the Jina Go model provider.
The Jina provider was added with embedding, rerank, model listing, and
connection checking, but `ChatWithMessages` still returned a
not-implemented error even though Jina exposes an OpenAI-compatible
`/v1/chat/completions` endpoint.
Closes#14933
**The following functionalities are now supported:**
### **Jina:**
- [x] Chat
- [ ] Stream Chat
- [x] Embedding
- [x] Rerank
- [x] Model listing
- [x] Provider connection checking
- [ ] Balance
### **Implementation details:**
- Implements `JinaModel.ChatWithMessages`
- Sends `Authorization: Bearer <api-key>` and JSON chat completion
requests
- Validates API key, model name, messages, and configured region before
making requests
- Forwards supported chat config fields: `max_tokens`, `temperature`,
`top_p`, and `stop`
- Parses the first chat completion choice into `ChatResponse.Answer`
- Adds `jina-ai/jina-vlm` as a chat-capable model in
`conf/models/jina.json`
- Adds focused unit tests for request construction, auth, response
parsing, validation errors, provider errors, and region handling
**Verification:**
```plaintext
docker run --rm -v $PWD:/repo -w /repo golang:1.25 sh -c '/usr/local/go/bin/gofmt -w internal/entity/models/jina.go internal/entity/models/jina_test.go && /usr/local/go/bin/go test -vet=off ./internal/entity/models -run TestJina -count=1'
ok ragflow/internal/entity/models 0.037s
```
Note: `go test ./internal/entity/models -run TestJina -count=1`
currently hits unrelated existing vet findings in other provider files,
so the focused Jina tests were run with `-vet=off`.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fixes#14893
The Novita Go driver landed in #14850 and shipped a stub `Embed` method
that returned `"novita, no such method"`, so Novita could not be used as
an embedding provider in RAGFlow. This PR fills that gap.
Novita exposes a public embeddings endpoint at `POST
https://api.novita.ai/v3/embeddings` that accepts the standard
OpenAI-compatible request shape (`{model, input}`) with `Authorization:
Bearer <api_key>`. Two embedding models are documented in Novita's model
library: `baai/bge-m3` (multilingual, 8192 tokens) and
`baai/bge-large-en-v1.5`.
### Changes
- `internal/entity/models/novita.go`: implement `NovitaModel.Embed`.
- Validate inputs (api key, model name) and short-circuit on empty
texts.
- Resolve region with the existing `baseURLForRegion` helper.
- Build URL from `URLSuffix.Embedding` (the embeddings path lives under
`/v3/`, separate from the chat path under `/openai/v1/`).
- Send `{model, input}` POST body, add `dimensions` when
`embeddingConfig.Dimension > 0` (matches the pattern in #14735).
- Bearer auth + JSON content type, mirroring the chat path.
- Parse `{data: [{embedding, index}]}` and reorder by `index`, rejecting
out-of-range indices, duplicates, and missing entries so the output
always lines up with the input. Same shape as the merged Mistral and
Upstage Embed implementations.
- `conf/models/novita.json`:
- Add `"embedding": "v3/embeddings"` to `url_suffix`.
- Add default embedding model entries for `baai/bge-m3` and
`baai/bge-large-en-v1.5` so they appear in the model picker.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
This PR implement implement OCR for Baidu and Mistral, implement
PaddleOCR provider and implement ASR for CoHere
**Verified examples from the CLI:**
```
RAGFlow(user)> ocr with 'mistral-ocr-2512@test@mistral' file './internal/text.jpg'
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| text |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Parallel to these organizational innovations there were significant complementary technical innovations (e.g., improved methods of manufacturing cast-iron pipe and of coating interiors for pressure maintenance, and newer paving and construction material... |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
RAGFlow(user)> ocr with 'paddleocr-vl-0.9b@test@baidu' file './internal/text.jpg'
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| text |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Parallel to these organizational innovations there were significant complementary technical innovations (e.g., improved methods of manufacturing cast-iron pipe and of coating interiors for pressure maintenance, and newer paving and construction material... |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
# PaddleOCR
RAGFlow(user)> ocr with 'PaddleOCR-VL-1.5@test@paddleocr' file './internal/test.pdf'
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| text |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| # Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Bingxin Ke
Nando Metzger
Photogra
Anton Obukhov
Rodrigo Caye Daudt
netry and Remote Sensing,
Shengyu Huang
Konrad Schindler
ETH Zürich
<div style="text-align: c... |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
# Cohere
RAGFlow(user)> asr with 'cohere-transcribe-03-2026@test@cohere' audio './internal/test.wav' param '{"language": "en"}'
+-----------------------------------------------------------------------------------------------------------------------+
| text |
+-----------------------------------------------------------------------------------------------------------------------+
| The examination and testimony of the experts enabled the Commission to conclude that five shots may have been fired. |
+-----------------------------------------------------------------------------------------------------------------------+
```
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
### What problem does this PR solve?
This PRimplement TTS, ASR for Siliconflow and TTs for StepFun
**The following functionalities are now supported:**
**SiliConFlow:**
- [x] Text To Speech
- [x] Audio To Text
- [x] Stream Audio To Text
**StrepFun:**
- [x] Audio To Text
- [x] Stream Audio To Text
**Verified examples from the CLI:**
```plaintext
# SiliconFlow
RAGFlow(user)> tts with 'FunAudioLLM/CosyVoice2-0.5B@test@Siliconflow' text 'hello? show yourself' play format 'wav' param '{"voice": "fnlp/MOSS-TTSD-v0.5:alex"}'
SUCCESS
RAGFlow(user)> asr with 'FunAudioLLM/SenseVoiceSmall@test@siliconflow' audio './internal/test.wav' param ''
+----------------------------------------------------------------------------------------------------------------------+
| text |
+----------------------------------------------------------------------------------------------------------------------+
| The examination and testimony of the experts enabled the commission to conclude that five shots may have been fired. |
+----------------------------------------------------------------------------------------------------------------------+
RAGFlow(user)> stream asr with 'FunAudioLLM/SenseVoiceSmall@test@siliconflow' audio './internal/test.wav' param ''
+----------------------------------------------------------------------------------------------------------------------+
| text |
+----------------------------------------------------------------------------------------------------------------------+
| The examination and testimony of the experts enabled the commission to conclude that five shots may have been fired. |
+----------------------------------------------------------------------------------------------------------------------+
```
### 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?
```
+---------------------+----------------------------------+-------------+-----------------+---------+--------+------+
| created_at | id | meta_fields | name | size | status | type |
+---------------------+----------------------------------+-------------+-----------------+---------+--------+------+
| 2026-05-08 19:35:08 | f6aa38bb4ad111f1ba6338a74640adcc | map[] | abc.pdf | 3387987 | 1 | pdf |
+---------------------+----------------------------------+-------------+-----------------+---------+--------+------+
```
### 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?
Closes#14878.
`VllmModel.Rerank()` in
[internal/entity/models/vllm.go:551](internal/entity/models/vllm.go#L551)
is currently a stub returning `nil, fmt.Errorf("%s, Rerank not
implemented", z.Name())`, and
[conf/models/vllm.json](conf/models/vllm.json) is missing a `rerank`
entry in `url_suffix`. Chat (long-standing) and embeddings (#14688)
already work, so rerank is the last missing leg of the retrieval
pipeline for operators running everything on a single self-hosted vLLM
server — today they have to point rerank at a different provider, which
defeats the point of a fully local deployment.
Upstream vLLM has supported a Jina/Cohere-compatible `POST /v1/rerank`
endpoint since v0.7
([vllm-project/vllm#12376](https://github.com/vllm-project/vllm/pull/12376)).
The request/response shape is essentially identical to the NVIDIA driver
landed in #14778, so this PR mirrors that structure with two
vLLM-specific adjustments.
This PR replaces the stub with a real implementation against vLLM's
`/v1/rerank`:
- `POST {baseURL}/rerank`
- Request body: `{"model": "<modelName>", "query": "<query>",
"documents": [...], "top_n": <int>}` — documents are a flat `[]string`,
**not** wrapped as `{text: "..."}` like NVIDIA's `/ranking`.
- Response body: `{"results": [{"index": int, "relevance_score": float},
...]}` (Jina-compatible; the optional `document` field is ignored since
callers reconstruct text via `Index`).
- `Authorization: Bearer <ApiKey>` is set **only when `APIConfig.ApiKey`
is non-empty**, matching the existing `Embed`/`ListModels` behaviour in
this file. vLLM is a local driver and can be deployed without an API
key.
The return shape matches the existing `*RerankResponse` contract used by
the NVIDIA ([nvidia.go:461](internal/entity/models/nvidia.go#L461)),
Aliyun ([aliyun.go:507](internal/entity/models/aliyun.go#L507)), and
ZhipuAI ([zhipu-ai.go:554](internal/entity/models/zhipu-ai.go#L554))
drivers, i.e. `Data []RerankResult` carrying `{Index, RelevanceScore}`
in the API's ranking order. Callers that need original-input order sort
by `Index`.
Behaviour requirements from the issue, all covered:
1. Empty `documents` → returns `&RerankResponse{}` without an HTTP call.
2. Missing `modelName` → `"model name is required"` validation error.
3. `rerankConfig.TopN` honored when `0 < TopN < len(documents)`;
otherwise `top_n` defaults to `len(documents)` so callers get a score
per input.
4. Non-200 responses return an error including upstream status and body
(`"vLLM rerank API error: <status>, body: <body>"`).
5. Response `index` values are bounds-checked against `len(documents)`.
**Scope:**
- [internal/entity/models/vllm.go](internal/entity/models/vllm.go) —
replaces the `Rerank` stub at line 551 with a real implementation; adds
`vllmRerankRequest`/`vllmRerankResponse` types for the slim subset of
the payload we need. Region/baseURL resolution, 30s context timeout,
conditional bearer header, and error wrapping all follow the existing
patterns in this file.
- [conf/models/vllm.json](conf/models/vllm.json) — adds `"rerank":
"rerank"` to `url_suffix`, joined to the operator-configured vLLM base
URL the same way the NVIDIA driver joins at
[nvidia.go:485](internal/entity/models/nvidia.go#L485).
-
[internal/entity/models/vllm_rerank_test.go](internal/entity/models/vllm_rerank_test.go)
— adds 7 `httptest`-backed tests mirroring `nvidia_rerank_test.go`:
happy path (out-of-order ranking → Index preservation), `top_n` clamp to
`RerankConfig.TopN`, empty-documents short-circuit, missing-model-name
validation, HTTP error propagation, out-of-range index rejection, and a
vLLM-specific `TestVllmRerankWithoutAPIKey` locking in the optional-auth
behaviour that distinguishes this driver from NVIDIA.
**Out of scope:** no interface change, no DDL, no frontend change. Chat,
embeddings, and balance paths are untouched. No new user-facing docs
required beyond the existing rerank model setup page — vLLM joins the
list of providers whose rerank model can be selected once `/v1/rerank`
is exposed by the server.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
```
RAGFlow(user)> ocr with 'hunyuanocr@test@gitee' file './picture.png'
+----------------------------------------------------------+
| text |
+----------------------------------------------------------+
| 生活不是等待风暴过去，而是学会在雨中翩翩起舞。
——佚名 |
+----------------------------------------------------------+
RAGFlow(user)> list 'test@gitee' tasks;
+---------+----------------------------------+
| status | task_id |
+---------+----------------------------------+
| success | C3FX4MQNKY5MGC6ZFMIXIAMJKHCEBQB5 |
+---------+----------------------------------+
RAGFlow(user)> show 'test@gitee' task 'C3FX4MQNKY5MGC6ZFMIXIAMJKHCEBQB5';
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+
| content | index |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+
| # PDF 1: Purpose of RAGFlow
RAGFlow is an open source Retrieval-Augmented Generation (RAG) engine designed to turn raw documents into reliable context for large language models.Its purpose is to make it practical to build an Al assistant that can ans... | 1 |
+------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+-------+
```
### 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?
This PR implement TTS for FishAudio and MiniMax provider and ASR for
FishAudio
**The following functionalities are now supported:**
**FishAudio:**
- [x] Text To Speech
- [x] Stream Text To Speech
- [x] Audio To Text
**OpenRouter:**
- [x] Text To Speech
**Verified examples from the CLI:**
```plaintext
**FishAudio**
RAGFlow(user)> tts with 's1@test@fishaudio' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"reference_id": "90e65eaaf50e4470b8e6d43ee6afd7d5", "temperature": 0.7, "top_p": 0.7, "prosody": {"speed": 1, "volume": 0, "normalize_loudness": true}, "chunk_length": 300, "normalize": true, "sample_rate": 44100, "mp3_bitrate": 128, "latency": "normal", "max_new_tokens": 1024, "repetition_penalty": 1.2, "min_chunk_length": 50, "condition_on_previous_chunks": true, "early_stop_threshold": 1}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/s1_output.wav
SUCCESS
RAGFlow(user)> stream tts with 's1@test@fishaudio' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"reference_id": "90e65eaaf50e4470b8e6d43ee6afd7d5", "temperature": 0.7, "top_p": 0.7, "prosody": {"speed": 1, "volume": 0, "normalize_loudness": true}, "chunk_length": 300, "normalize": true, "sample_rate": 44100, "mp3_bitrate": 128, "latency": "normal", "max_new_tokens": 1024, "repetition_penalty": 1.2, "min_chunk_length": 50, "condition_on_previous_chunks": true, "early_stop_threshold": 1}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/s1_output.wav
SUCCESS
RAGFlow(user)> asr with 'transcribe-1@test@fishaudio' audio './internal/test.wav' param '{"language": "en", "ignore_timestamps": true}'
+----------------------------------------------------------------------------------------------------------------------+
| text |
+----------------------------------------------------------------------------------------------------------------------+
| The examination and testimony of the experts enabled the commission to conclude that five shots may have been fired. |
+----------------------------------------------------------------------------------------------------------------------+
```
### 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?
This PR implement TTS for MiniMax provider and CLI testing for TTS
**The following functionalities are now supported:**
**MiniMax:**
- [x] Chat / Stream Chat
- [x] Embedding
- [x] Rerank
- [x] Model listing
- [x] Provider connection checking
- [x] Text To Speech
- [ ] OCRFile
- [ ] ~~Audio To Text~~
- [ ] ~~Balance~~
**Verified examples from the CLI:**
```plaintext
RAGFlow(user)> tts with 'speech-2.8-hd@test@minimax' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"voice_setting": {"voice_id": "English_radiant_girl", "speed": 1, "vol": 1, "pitch": 0}, "audio_setting": {"sample_rate": 32000, "bitrate": 128000, "format": "wav", "channel": 1}, "output_format": "hex"}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/speech-2.8-hd_output.wav
SUCCESS
RAGFlow(user)> stream tts with 'speech-2.8-hd@test@minimax' text 'He who desires but acts not, breeds pestilence.' play format 'wav' save './internal' param '{"voice_setting": {"voice_id": "English_radiant_girl", "speed": 1, "vol": 1, "pitch": 0}, "audio_setting": {"sample_rate": 32000, "bitrate": 128000, "format": "wav", "channel": 1}, "output_format": "hex"}'
Saved to directory: /home/infiniflow/Documents/development/ragflow/internal/speech-2.8-hd_output.wav
SUCCESS
```
Set `Play` to play audio in CLI
Set `Save` `PATH_TO_SAVE` to save file
Set `format` to save file in wav or mp3
Set `Param` align with official request body
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Add a Go driver for Voyage AI (https://voyageai.com), one of the
unchecked providers on the umbrella tracking issue #14736. Voyage AI is
**embed + rerank only** — no chat, no streaming, no `/v1/models`
endpoint. It's the first provider in the Go layer of this shape.
Until this PR, a tenant who configured `voyage` as a model provider in
the Go layer fell through to the default branch of
`internal/entity/models/factory.go` and got the dummy driver.
### What this PR includes
- New `internal/entity/models/voyage.go` with a `VoyageModel`
implementing the `ModelDriver` interface.
- New `conf/models/voyage.json` with 6 embedding models (`voyage-3.5`,
`voyage-3.5-lite`, `voyage-3-large`, `voyage-code-3`, `voyage-law-2`,
`voyage-finance-2`) and 2 rerank models (`rerank-2`, `rerank-2-lite`).
- `factory.go`: route `"voyage"` to `NewVoyageModel`.
- `internal/entity/models/voyage_test.go`: 19 unit tests.
### How the driver works
- **Embed**: `POST /v1/embeddings`. Response is OpenAI-shaped (`{data:
[{embedding, index, object, text}], model, usage}`). Driver reorders by
`index`, rejects duplicate / out-of-range / missing slots, and
short-circuits empty input without an HTTP call.
- **Rerank**: `POST /v1/rerank`. Voyage uses **`top_k`** as the request
param name (not `top_n` like Aliyun/SiliconFlow); the driver translates
`RerankConfig.TopN` → `top_k`. Response is Cohere-shaped (`{data:
[{relevance_score, index}], model}`), so the existing
`RerankResponse{Data: []RerankResult{Index, RelevanceScore}}` shape fits
cleanly.
- **`ListModels`**: returns a hardcoded list of `voyageKnownModels`.
Voyage does **not** expose `/v1/models` (probed live, returns 404), so
the driver synthesizes the list from the same set the config ships. New
upstream models are added by extending one slice.
- **`CheckConnection`**: pings a 1-input embed call against
`voyage-3.5`. Without `/v1/models`, this is the cheapest way to verify
the API key + network path before a tenant tries a real workload.
- **`ChatWithMessages` / `ChatStreamlyWithSender` / `Balance` /
`TranscribeAudio` / `AudioSpeech` / `OCRFile`**: all return `"no such
method"`. Voyage does not host any of these surfaces.
No interface change. No new dependencies.
### How was this tested?
**19 unit tests** in `internal/entity/models/voyage_test.go` — all pass
on go 1.25:
```
$ go test -vet=off -run TestVoyage -count=1 ./internal/entity/models/...
ok ragflow/internal/entity/models 0.036s
```
Coverage: Name; Embed (happy path, reorder, empty-input, missing
key/model, duplicate index, out-of-range index, missing slot); Rerank
(happy path with `top_k` assertion, default-to-len-documents, empty
documents, out-of-range index); ListModels (static list, missing key);
CheckConnection (happy, 401); chat methods sentinels; Balance sentinel;
audio/OCR sentinels.
`go build ./internal/entity/models/...` exits 0.
**Live integration test** against `api.voyageai.com`:
```
=== RUN TestVoyageLiveSmoke
[OK] Name() = "voyage"
[OK] ListModels (static): 8 models -> [voyage-3.5 voyage-3.5-lite voyage-3-large voyage-code-3 voyage-law-2 voyage-finance-2 rerank-2 rerank-2-lite]
[OK] CheckConnection
[OK] Embed vectors=3 dim=1024 indices=[0 1 2]
[OK] Embed(empty) -> 0 vectors
[OK] Rerank results=3 scores=[0.8125 0.59765625 0.39453125]
[OK] ChatWithMessages returns voyage, no such method
[OK] Balance returns voyage, no such method
VOYAGE LIVE SMOKE PASSED
--- PASS: TestVoyageLiveSmoke (0.81s)
```
What the live run proves on the wire:
- Auth (`Bearer <key>`) accepted by `api.voyageai.com`.
- Embed `voyage-3.5` on 3 inputs returns 3 vectors at dim 1024 with
`index` field preserved as `[0, 1, 2]` — the reorder-by-index code is
exercised on real data.
- Empty input short-circuits without an HTTP call (mock server would
have been hit if it did).
- Rerank `rerank-2` on 3 docs returns 3 real `relevance_score` floats
`[0.8125, 0.598, 0.395]`. The `top_k` translation works on the live
wire.
- All sentinel methods return the documented `"no such method"` strings.
### Note on PR history
This branch was previously named for LocalAI Embed work which is now
consolidated into PR #14813. The branch was reset to `upstream/main` and
rebuilt for Voyage. Diff against `main` is a clean +838 lines across 4
files.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Tracking: #14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
