## What
#15240
Implements `GET /api/v1/mcp/servers` in the Go API server.
## Changes
- Added MCP server DAO list query with tenant scoping.
- Added MCP service response wrapper.
- Added MCP handler for list request parsing and response formatting.
- Wired `GET /api/v1/mcp/servers` under authenticated `/api/v1` routes.
- Initialized MCP service and handler in the Go server startup.
- update_time and update_date now both map to update_date
- create_time and create_date now both map to create_date
- default ordering now returns create_date
## API Behavior
Matches the Python endpoint behavior:
- Requires authenticated user.
- Lists MCP servers for the current user tenant.
- Supports `keywords`.
- Supports `mcp_id` and repeated/comma-separated `mcp_ids`.
- Supports `page`, `page_size`, `orderby`, and `desc`.
- Returns:
```json
{
"code": 0,
"message": "success",
"data": {
"mcp_servers": [],
"total": 0
}
}
```
## Summary
- Add custom `base_url` support to the Google Go model driver.
- Preserve Google URL suffix configuration when creating custom base URL
driver instances.
- Validate Google chat/stream request inputs before constructing the SDK
client.
- Cover Google model listing, connection checks, base URL resolution,
and request validation with focused tests.
## What changed
- `GoogleModel.NewInstance` now returns a Google driver configured with
the supplied base URL map.
- Google SDK client creation now resolves configured base URLs through
`genai.HTTPOptions.BaseURL`.
- Base URL lookup supports configured regions, empty-region keys, and
`default` fallback.
- Google chat, streaming chat, embeddings, and model listing now reject
blank API keys before creating SDK clients.
- Google chat and streaming chat now reject blank model names locally,
and streaming chat rejects a nil sender.
- Existing message handling, embeddings, pagination, and provider errors
are preserved.
## Why
Google custom model instances could not use configured base URLs because
`NewInstance` returned `nil` and the SDK client path ignored the driver
base URL map. The request validation keeps invalid Google calls from
reaching SDK client construction with blank credentials or incomplete
chat inputs.
### What problem does this PR solve?
Part of the Python → Go API server rewrite tracked in #15240 (Dataset
ingestion section). This PR implements the three dataset ingestion
endpoints in the Go API server, mirroring the existing Python
`dataset_api_service` behaviour:
- `GET /api/v1/datasets/<dataset_id>/ingestions/summary`
- `GET /api/v1/datasets/<dataset_id>/ingestions`
- `GET /api/v1/datasets/<dataset_id>/ingestions/<log_id>`
### Type of change
- [x] Refactoring
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: sxxtony <sxxtony@users.noreply.github.com>
### What problem does this PR solve?
The Go GPUStack driver returned a stub error for `Embed()` even though
GPUStack exposes OpenAI-compatible embeddings on the **v1-openai** route
(not `v1/embeddings`).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
As title
### 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?
This PR updates `SystemService.ListAPITokens` to lazily backfill missing
`beta` values for API tokens, matching the Python behavior of
`/api/v1/system/tokens`.
### Type of change
- When an API token has an empty `beta`, generate a new one.
- Persist the generated `beta` back to the `api_token` table.
- Keep the handler/routing unchanged.
- `GET /api/v1/system/tokens` now returns tokens with `beta` filled in
for older records that were missing it.
- This aligns Go behavior with the Python implementation.
## Summary
- Validate Hunyuan embedding model name and API key before building
requests.
- Reuse region-aware base URL validation for embedding requests.
- Replace the stale unsupported Embed test with happy-path and
validation coverage.
## What changed
- Added early Hunyuan Embed validation for missing model names and API
keys.
- Routed Embed through the same base URL region guard used by the other
Hunyuan methods.
- Updated Hunyuan tests to configure the embedding suffix and cover
Embed success plus invalid inputs.
## Why
Hunyuan Embed is implemented, but the existing test still expected it to
be unsupported and could panic before returning a normal validation
error. This keeps the implemented embedding path aligned with the
current driver behavior and prevents nil input panics.
Closes#15087
Refs #14736
### Summary
Closes#15381
Every provider in `internal/entity/models/` reads its streaming response
with `bufio.NewScanner(resp.Body)` and iterates over `scanner.Scan()`.
The default `bufio.Scanner` maximum token size is 64KB, so when an
upstream sends a single SSE `data:` line larger than 64KB (long content
deltas, large tool or function call argument blobs, bundled
`reasoning_content`, or providers that emit a whole message in one
event) `scanner.Scan()` returns `false` and `scanner.Err()` returns
`bufio.ErrTooLong`. Streaming chat then ends with an error partway
through the response.
This change adds `scanner.Buffer(make([]byte, 64*1024), 1024*1024)`
immediately after every SSE scanner that was still bare, raising the cap
to 1MB. 1MB is the value already used for streaming chat in `openai.go`,
`modelscope.go`, `groq.go`, `mistral.go`, `xai.go` and the other already
patched providers (the 8MB cap in the repo is reserved for TTS and
embedding paths), so this simply converges the remaining providers onto
the established pattern. Nothing else changes: line parsing, `data:`
prefix handling, `[DONE]` detection, JSON unmarshalling, error handling,
and the existing `scanner.Err()` checks all stay the same.
Providers covered (23 scanners across 22 files): 302ai, aliyun,
baichuan, baidu, cohere, deepinfra, deepseek, gitee, huggingface,
lmstudio, minimax (the chat scanner, whose TTS scanner was already
bumped), moonshot, nvidia, ollama, openrouter, orcarouter, paddleocr,
siliconflow, tokenhub, vllm, volcengine, xunfei, zhipu-ai. `jiekouai.go`
is excluded because it is covered by the in flight #15337.
A table driven regression test (`sse_scanner_buffer_test.go`) streams a
single 128KB `data:` content delta followed by `data: [DONE]` through an
`httptest` server and asserts that `ChatStreamlyWithSender` delivers the
full content with no error across a representative subset of providers.
Without the buffer fix the test fails with `bufio.Scanner: token too
long`.
This PR also removes three duplicate declarations of the package level
`roundTripperFunc` test helper that several recently merged provider PRs
each added independently, which had left the `internal/entity/models`
test package unable to compile. The helper now lives in a single place
and is shared.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fixes custom `base_url` resolution when a model instance has no
configured region.
Some drivers read custom base URLs from `BaseURL[""]` when
`apiConfig.Region` is empty, while others normalize empty region to
`"default"` and read `BaseURL["default"]`. This PR adds the `"default"`
alias only for empty-region custom base URLs while preserving the
existing empty-region key.
Closes#15042
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR fixes several behavior gaps in the Go implementation of the user
registration API.
### Type of change
- Make `nickname` required for user registration.
- Align registration error messages and response data with expected API
behavior.
- Handle password decryption errors for registration more consistently.
- Generate UUID v1-style IDs for new users, access tokens, tenants,
user-tenant records, and root files.
- Initialize default user fields during registration, including:
- language
- color schema
- timezone
- last login time
- Create user, tenant, user-tenant relation, tenant LLM records, and
root folder in a single DB transaction.
- Initialize default tenant LLM records from configured default models.
- Avoid partial registration data when one creation step fails.
- Use locale-based default language fallback for user profile responses.
### What problem does this PR solve?
Added 4 new models:
deepseek-ai/DeepSeek-V4-Pro
deepseek-ai/DeepSeek-V4-Flash
Pro/moonshotai/Kimi-K2.6
Pro/zai-org/GLM-5.1
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Python implementation of the Go-based model_provider API suite.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: bill <yibie_jingnian@163.com>
## Summary
- Harden `NewNovitaModel` to avoid panics when `http.DefaultTransport`
is a custom non-`*http.Transport` RoundTripper.
- Fallback to a safe transport (`ProxyFromEnvironment`) while preserving
existing pooling/timeout settings.
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Closes#15199.
The add-custom-model endpoint is routed through
`/api/v1/providers/:provider_name/instances/:instance_name/models`, but
the handler previously trusted `provider_name` and `instance_name` from
the JSON body instead of the path target. A request could therefore hit
one provider/instance URL while operating on a different body
provider/instance.
The same handler only rejected `model_types` when the slice was nil. An
empty array passed validation and reached
`ModelProviderService.AddCustomModel`, where `request.ModelTypes[0]`
could panic.
This PR makes the path provider/instance authoritative, rejects
mismatched body values, rejects missing or empty `model_types`, and adds
a service-level guard so direct service callers cannot hit the same
panic path.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
Ports the Python `tenant_api` team/member management endpoints to Go,
adding 4 endpoints under `/api/v1/tenants/:tenant_id/`:
- `GET /tenants/:tenant_id/users` — list non-owner members with user
details (owner only)
- `POST /tenants/:tenant_id/users` — invite a user by email; creates
invite-role join record (owner only)
- `DELETE /tenants/:tenant_id/users` — remove a member by `user_id`;
owner can remove anyone, members can remove themselves
- `PATCH /tenants/:tenant_id` — accept a pending invitation,
transitioning role `invite → normal`
Closes#15294
### What problem does this PR solve?
As title
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
## Summary
- Harden JieKouAI request validation before outbound provider calls
- Force non-streaming and streaming chat methods to use their expected
stream modes
- Make model listing use a bodyless GET and parse model responses
without panics
Closes#14736
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
Closes#15268.
The `UpdateMetadataSetting` handler at `internal/handler/kb.go:126`
retrieved the authenticated user via `GetUser(c)` but discarded the user
object (`_, errorCode, errorMessage := GetUser(c)`), then forwarded the
caller-supplied `kb_id` straight to the service layer with no ownership
check. Any authenticated user could mutate the `parser_config` /
metadata of any knowledge base in the system by guessing or harvesting a
`kb_id` — a classic IDOR (CWE-284, OWASP A01).
This is the only handler in `internal/handler/kb.go` missing the check;
every sibling (`ListTags`, `ListTagsFromKbs`, `RenameTag`,
`KnowledgeGraph`, `DeleteKnowledgeGraph`, `GetMeta`, `GetBasicInfo`)
already calls `h.kbService.Accessible(kbID, user.ID)`. The same
defensive check on the document preview endpoint was added in PR #14625
— this PR closes the matching gap on the KB metadata endpoint.
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- Harden `NewModelScopeModel` to avoid panics when
`http.DefaultTransport` is a custom non-`*http.Transport` RoundTripper.
- Fallback to a safe transport (`ProxyFromEnvironment`) while preserving
existing pooling/timeout settings.
- Add `TestModelScopeNewModelWithCustomDefaultTransport` regression
coverage.
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
Closes: #15328
- Implements `GET /api/v1/agents` — the agent/canvas listing endpoint
needed to complete the Home dashboard tile in `web/src/pages/home/`.
- Mirrors Python `api/apps/restful_apis/agent_api.py::list_agents`
exactly: tenant-join auth, optional `owner_ids` guard, keyword filter,
pagination, ordering, and `canvas_category` filter (default:
`agent_canvas`).
- **Scope:** read-only list only. Full agent CRUD and canvas runtime are
explicitly out of scope (separate slice of #15240).
## Summary
Ports the connector (data source) management endpoints that power
`web/src/pages/user-setting/data-source/` from Python
(`api/apps/restful_apis/connector_api.py`) to Go. Previously only `GET
/connectors` (list) was implemented in Go; this adds the rest of the
lifecycle.
Closes#15273 (subtask of #15240).
## Endpoints implemented
All under base path `/api/v1` (mirrors the Python routes):
| Method | Path | Description |
|--------|------|-------------|
| POST | `/connectors/{connector_id}/test` | Validate stored credentials
|
`GET /connectors` (list) was already present and is unchanged.
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- Harden `NewVoyageModel` to avoid panics when `http.DefaultTransport`
is a custom non-`*http.Transport` RoundTripper.
- Fallback to a safe transport (`ProxyFromEnvironment`) while preserving
existing pooling/timeout settings.
- Add `TestVoyageNewModelWithCustomDefaultTransport` regression
coverage.
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
- Harden `NewLongCatModel` to avoid panics when `http.DefaultTransport`
is a custom non-`*http.Transport` RoundTripper.
- Fallback to a safe transport (`ProxyFromEnvironment`) while preserving
existing pooling/timeout settings.
- Add `TestLongCatNewModelWithCustomDefaultTransport` regression
coverage.
Co-authored-by: Cursor <cursoragent@cursor.com>
### What problem does this PR solve?
implement delete, rebuild api for connector
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Summary
- Harden the 302.AI model driver request validation and response parsing
paths.
- Add focused tests for chat request mode, model listing, malformed
provider responses, and input validation.
## What changed
- Validate API keys, model names, rerank queries, ASR file paths, OCR
inputs, parse URLs, task IDs, and model-list IDs before use.
- Keep chat and streaming methods from accepting conflicting `stream`
values in request payloads.
- Send `ListModels` as a bodyless GET and parse the response with typed
JSON structs instead of unchecked assertions.
- Remove raw SSE event logging from stream handling.
## Why
The driver could panic or send inconsistent requests when optional
config fields were nil, empty, malformed, or contradicted the method
path. This keeps provider-driver behavior explicit while preserving the
existing supported 302.AI flows.
Closes#14736
### What problem does this PR solve?
Fixes the `/user/me` response so it returns the current user's model
settings correctly.
### Type of change
- Added model settings data to the `/user/me` response.
- Kept the response structure compatible with existing user profile
fields.
- Avoided changing unrelated user/session behavior.
## Summary
- Add Go REST support for `GET /api/v1/system/healthz`.
- Return Python-compatible `ok`/`nok` dependency fields for DB, Redis,
document engine, and storage.
- Return HTTP 200 only when all checks pass; otherwise return HTTP 500
with `_meta` failure details.
- Add focused service coverage for the unhealthy dependency response
when Go dependencies are not initialized.
## Scope
This is a small, isolated slice of #15240. It avoids current open
connector PRs (#15274, #15300, #15265, #15264), tenant/member PRs
(#15295, #15301, #15276), MCP PRs (#15281, #15253, #15254, #15260,
#15261, #15262), and the memory-message PR (#15256).
Refs #15240
### What problem does this PR solve?
- Add Go implementation parity for `PATCH /api/v1/users/me`.
- This updates the Go user settings endpoint to match the Python
behavior for updating the current user's profile settings.
### Changes
- Route `PATCH /api/v1/users/me` through the authenticated current user
from middleware.
- Add `password` and `new_password` support to `UpdateSettingsRequest`.
- Prevent `email` from being updated through this endpoint, matching the
Python blacklist behavior.
- Support updating:
- `nickname`
- `avatar`
- `language`
- `color_schema`
- `timezone`
- `password`
- Align password handling with Python:
- invalid plaintext password payload returns `CodeExceptionError`
- wrong old password returns `Password error!`
- successful update returns `{ code: 0, data: true, message: "success"
}`
### Test
Tested manually with Python and Go backends using the same request
bodies:
- `PATCH /api/v1/users/me` with nickname/timezone update
- plaintext password payload returns Python-compatible `Incorrect
padding`
- wrong old password returns `Password error!`
### What problem does this PR solve?
implement create_connector API
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Summary
- centralize TokenHub chat request validation for chat and streaming
calls
- reject blank TokenHub model names before sending provider requests
- send TokenHub model listing requests as bodyless GET requests
## What changed
- Added shared TokenHub chat request validation for API key, model name,
and messages.
- Updated `ListModels` to call `GET /models` without a request body.
- Added focused tests for blank model names and accidental GET request
bodies.
- Replaced an httptest handler callback `t.Fatalf` with `t.Errorf` plus
an HTTP error and return.
## Why
TokenHub chat requests should fail locally for invalid model names
instead of sending avoidable malformed requests upstream. Model listing
should also match normal GET semantics and avoid sending an empty JSON
body.
Closes#14736
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
As title
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Refactoring
## Summary
- Add Go REST support for `GET /api/v1/connectors/:connector_id`.
- Reuse the Python API behavior by returning the connector only when the
current user can access its tenant.
- Add focused handler coverage for success and unauthorized responses.
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
`ReplicateModel.Rerank` in `internal/entity/models/replicate.go` was a
`"replicate, no such method"` stub. The chat path landed in #14958 and
the embed path in #15073; rerank is the last major retrieval surface
still missing on this provider.
Until this PR, a tenant who selected a Replicate reranker model got the
sentinel error on every rerank 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?
This PR adds Qiniu provider integration for the Go model driver layer in
RAGFlow.
Supported capabilities:
- [X] Chat
- [X] Think Chat
- [X] Stream Chat
- [X] Stream Think Chat
- [X] Model listing
- [X] Provider configuration and factory registration
Verified examples from the CLI:
```
login user '***' password '***';
ADD PROVIDER 'qiniu';
CREATE PROVIDER 'qiniu' INSTANCE 'test' KEY '***';
chat with 'deepseek/deepseek-v3.1-terminus-thinking@test@qiniu' message
'hello';
think chat with 'deepseek/deepseek-v3.1-terminus-thinking@test@qiniu'
message 'hello';
stream chat with 'deepseek/deepseek-v3.1-terminus-thinking@test@qiniu'
message 'hello, what are you';
stream think chat with
'deepseek/deepseek-v3.1-terminus-thinking@test@qiniu' message 'hello,
what are you';
stream think chat with 'qwen3-max-2026-01-23@test@qiniu' message 'hello,
what are you';
LIST MODELS FROM 'qiniu' 'test';
```
### Type of change
- [X] New Feature
- [X] Provider integration
## Summary
- add the VolcEngine `models` URL suffix used by the existing Go
`ListModels` implementation
- return a clear error when the VolcEngine models suffix is missing
- add focused VolcEngine model-listing regression tests
## What changed
- Added `url_suffix.models` to `conf/models/volcengine.json`.
- Normalized the configured models suffix before building the request
URL.
- Covered config loading, successful model listing, upstream errors, and
missing suffix handling.
## Why
`VolcEngine.ListModels` already builds requests from `URLSuffix.Models`,
but the bundled VolcEngine config did not define that suffix. That left
the model-listing path unable to call the documented `/models` endpoint
from the existing provider config.
Fixes#14701
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- route hosted MinerU.Net and PaddleOCR.Net provider names to their
existing Go drivers
- add regression coverage for loading the hosted OCR provider configs
through ProviderManager
## What changed
- Added canonical provider-name aliases for the hosted OCR provider
display names.
- Covered both bundled configs with a focused provider-manager test.
## Why
The hosted provider configs use display names with `.Net`, while model
factory dispatch lowercases the provider name. Without aliases, those
configs fall through to `DummyModel` instead of using the existing
MinerU and PaddleOCR drivers.
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- Add LongCat model-list support through the documented
OpenAI-compatible models endpoint.
## What changed
- Add the LongCat `models` URL suffix for `/openai/v1/models`.
- Implement `ListModels` for the LongCat Go driver.
- Delegate `CheckConnection` to the lightweight model-list request.
- Add focused regression coverage for successful, malformed, oversized,
and missing-key responses.
## Why
LongCat documents a models endpoint under the OpenAI-compatible API
surface, but the Go driver still returned `no such method` for model
listing and connection checks.
## Validation
- `go test ./internal/entity/models -run TestLongCat -count=1`
- `go test -race ./internal/entity/models -run TestLongCat -count=1`
- `go test ./internal/entity -count=1`
- `git diff --check`
## Notes
- Related to the broader Go model provider tracking in #14736, but this
PR only handles LongCat model listing.
- `go test ./internal/entity/models -count=1` is currently blocked by an
unrelated Astraflow test panic outside this LongCat change.
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
- add the xAI `models` URL suffix used by the existing Go `ListModels`
implementation
- return a clear error when the xAI models suffix is missing
- add focused xAI model-listing and connection-check regression tests
## What changed
- Added `url_suffix.models` to `conf/models/xai.json`.
- Normalized the configured models suffix before building the request
URL.
- Covered config loading, successful model listing, upstream errors,
API-key validation, missing suffix handling, and `CheckConnection`
delegation.
## Why
`XAIModel.ListModels` already builds requests from `URLSuffix.Models`,
and `CheckConnection` delegates to that method. The bundled xAI config
did not define that suffix, which left the model-listing path unable to
call the provider `/models` endpoint from the existing provider config.
## Validation
- `go test ./internal/entity/models -run TestXAI -count=1`
- `go test ./internal/entity -count=1`
- `git diff HEAD~1..HEAD --check`
## Notes
- `go test ./internal/entity/models -count=1` currently fails in
unchanged Astraflow coverage: `TestAstraflowEmbedReturnsNoSuchMethod`
panics before reaching any xAI assertions.
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
implement provider `OrcaRouter`
**The following functionalities are now supported:**
**Cohere:**
- [x] Chat / Think Chat / Stream Chat / Stream Think Chat
- [x] Model listing
- [x] TTS
- [ ] Balance
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Closes#15040.
ModelScope was listed unchecked in the Go-rewrite tracker #14736 and
already had an llm_factories.json entry (tags: LLM) but no Go driver, so
the new Go API server could not route ModelScope instances. The Python
side has supported it through the OpenAI-compatible base at
rag/llm/chat_model.py:618 (ModelScopeChat), which requires a
user-supplied base URL and appends /v1.
This adds:
- internal/entity/models/modelscope.go: self-hosted OpenAI-compatible
driver with chat (sync + SSE stream with idle-timeout cancellation),
list_models, and check_connection. Auth header is optional, matching the
xinference pattern, so deployments without auth and auth-enabled
deployments both work. Base URL is normalized so users can configure
either the root endpoint or the /v1 endpoint.
- internal/entity/models/modelscope_test.go: 12 tests covering name, URL
normalization, factory routing, chat happy path / auth header /
reasoning_content extraction, stream happy path / stream=false rejection
/ idle cancellation, list_models + check_connection, missing-base-URL
clear error, and the no-such-method sentinels.
- conf/models/modelscope.json: shipped config (class: "local",
url_suffix v1/chat/completions and v1/models).
- internal/entity/models/factory.go: case "modelscope" →
ModelScopeModel.
- internal/service/llm.go: ModelScope added to the selfDeployed map
alongside Ollama, Xinference, LocalAI, LM-Studio, GPUStack — the Python
side requires user-supplied URL with no default, so the Go side
classifies it the same way.
Follow-on issues will add Embed and Rerank, in line with how Novita,
NVIDIA, TogetherAI, and other providers landed method-by-method.
---------
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
This PR adds HuaweiCloud provider integration in RAGFlow.
Supported capabilities:
- [x] Chat / Think Chat / Stream Chat / Stream Think Chat
- [x] Embedding
- [x] Rerank
- [x] Model listing
- [x] Provider connection checking
Verified examples from the CLI:
```
check instance 'test' from 'HuaweiCloud';
chat with 'deepseek-v4-flash@test@HuaweiCloud' message 'hello';
think chat with 'deepseek-v4-flash@test@HuaweiCloud' message 'hello';
stream chat with 'deepseek-v4-flash@test@HuaweiCloud' message 'hello';
stream think chat with 'deepseek-v4-flash@test@HuaweiCloud' message
'hello';
embed text 'what is rag' 'who are you' with 'bge-m3@test@HuaweiCloud'
dimension 1024;
rerank query 'what is rag' document 'rag is retrieval augmented
generation' 'rag need llm' 'famous rag
project includes ragflow' with 'bge-reranker-v2-m3@test@HuaweiCloud' top
3;
list supported models from 'HuaweiCloud' 'test';
LIST MODELS FROM 'HuaweiCloud' 'test';
```
### Type of change
- [x] New Feature
- [x] Provider integration
## Summary
- Wire the Go TokenHub provider through the model factory.
- Harden TokenHub request handling for chat, streaming, embeddings, and
model listing.
- Add focused TokenHub unit coverage for factory wiring and provider
behavior.
## Notes
- Refs #14736.
- Follows up #15159.
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
## Summary
Closes#15165.
Implements the AWS Bedrock model provider for the Go API server, tracked
under #14736. Adds Converse + Converse-Stream chat and foundation-model
listing, with SigV4 signing over a hand-rolled `net/http` path that
matches the established pattern in `internal/entity/models/` (no new
direct `go.mod` deps).
## Linked tracker
Tracked under #14736 (Implement model providers of RAGFlow API server in
Go). Closes#15165.
### What problem does this PR solve?
The Go DeepInfra driver returned a stub error for `Rerank()` even though
DeepInfra serves reranker models at `POST /v1/inference/{model}` with
`query`, `documents`, and a `scores[]` response.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Cursor <cursoragent@cursor.com>
### What problem does this PR solve?
Add a Go driver for **FuturMix** (https://futurmix.ai/docs), one of the
unchecked providers on the umbrella tracking issue #14736. FuturMix is
documented as an "OpenAI-compatible API" aggregator over Claude / GPT /
Gemini / DeepSeek (~22 models per their `/models` page).
Until this PR, a tenant who configured `futurmix` 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>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
