This PR modularizes the **Extractor** component configuration with dedicated feature subtabs, adds independent system prompt configuration, fixes multi-node execution determinism and parameter persistence across save and page refresh, and ensures backward compatibility with legacy flat fields.
Ports dataset knowledge compilation (wiki/graph/tree/mindmap) to the Go
scheduler with a status contract, aligns wiki storage/retrieval with
Python, sizes prompts by content_length, and resolves embedding batch
size from provider capability.
Ports the dataset knowledge compilation (wiki/graph/tree/mindmap) to the
Go scheduler with a status contract, aligns wiki storage/retrieval with
Python, and sizes prompts by content_length.
## Summary
Six sites used to read the same `parser_config.delimiter` field with
divergent grammars:
- `rag.nlp.get_delimiters` (PDF/DOCX/HTML/EPUB/JSON/CSV/XLSX/email/book)
- `rag.nlp.naive_merge` (custom-delimiter branch)
- `rag.nlp.naive_merge_with_images`
- `rag.nlp._build_cks`
- `deepdoc.parser.txt_parser.parser_txt` (.txt, code)
-
`deepdoc.parser.markdown_parser.MarkdownElementExtractor.get_delimiters`
The six implementations disagreed on bare-vs-wrapped chars, dedupe, sort
order, CRLF normalization, and `re.I` (#17384). The shipped default ``
`\n!?;。；！？` `` was a no-op for `.md` because the markdown path only
matched backtick-wrapped tokens.
## Changes
- **new:** `rag/nlp/delim.py` with `parse_delimiter_field` and
`compile_delimiter_pattern`. Single source of truth. CRLF normalization
at the top; longest-first stable sort; insertion-ordered dedupe; no
`re.I`.
- **refactor:** all six call sites delegate to the helper.
- `rag/nlp/__init__.py::get_delimiters` becomes a thin shim.
- `deepdoc/parser/txt_parser.py::parser_txt` drops the
`[encode/decode/unicode_escape]` round-trip.
- `deepdoc/parser/markdown_parser.py::get_delimiters` honors bare chars
(fixes [1]).
- **tests:** `test/unit_test/rag/test_delim.py` (85 tests) — helper,
acceptance table, frontend parity, static guard against re-inlining.
- **tests:** `test/unit_test/rag/test_delimiter_case_sensitive.py` (from
#17386) updated to retarget the static check at the new helper +
AST-based broader scan.
## Acceptance criteria
- All six sites produce the same regex pattern for the same input.
- Shipped default keeps working for `.txt` / `.pdf` / `.docx`.
- Shipped default for `.md` now splits (was a silent no-op).
- Tooltip example `` `\n##;` `` produces three effective delimiters
regardless of file type.
- Bare whitespace inputs split on every occurrence.
- Backtick-wrapped whitespace splits only on the exact N-char sequence.
- CRLF-line-ending documents split identically to LF-line-ending
documents.
- 123 tests pass (85 new + 38 existing).
## Rebase protocol
As #17385 and #17386 evolve, this branch will be rebased on top. The
only overlap between this PR's diff and the other two is
`test_delimiter_case_sensitive.py`, where #17383 modifies the static
check to point at the new helper location.
---------
Co-authored-by: kiloconnect[bot] <240665456+kiloconnect[bot]@users.noreply.github.com>
## Summary
Improve the UX of the **"Delimiter for text"** field on the dataset
configuration page. The field is a single string with a backtick-based
mini-syntax, but both the tooltip and the surrounding UI failed to
surface what delimiters the backend would actually derive from a given
value — leaving users to discover by trial-and-error that the same
string produces different splits depending on file type (see #7436,
#4704, #9680).
### Summary
This PR adds **aimlapi.com** as a model provider, so a RAGFlow user can
enter one API key in the model settings and use AIMLAPI's models across
the app. AIMLAPI ([aimlapi.com](https://aimlapi.com)) is an
OpenAI-compatible aggregator that serves 700+ models (LLM, embedding,
vision, TTS, ASR) from many providers behind a single API.
The change mirrors the repo's existing "add provider" pattern (e.g.
FuturMix / OpenRouter): provider logic lives in the same files those
providers use, and shared / UI files get only registration entries.
**Backend**
- `conf/llm_factories.json` — the `aimlapi.com` factory entry.
- `rag/llm/__init__.py`, `rag/llm/{chat,embedding,cv}_model.py` —
LiteLLM adapters (chat, embedding, image2text) with a production base
URL, overridable via `AIMLAPI_API_URL`.
- `rag/llm/model_meta.py` — an `AIMLAPI` model-meta so the provider
lists its full `/v1/models` catalog dynamically (classified by the
endpoint `type`), the same way OpenRouter does.
- `api/apps/restful_apis/aimlapi_api.py` — an optional "Get API key"
flow using AIMLAPI's agent-authorization (OAuth 2.0 Device Authorization
Grant, RFC 8628). The device code is kept server-side (Redis); only the
issued key reaches the browser.
**Frontend (`web/`)**
- Provider registration (constant, icon allowlist, brand logo), the
model picker (`LIST_MODEL_PROVIDERS` + a `buildLocalConfig` entry), and
the "Get API key" button in the provider dialog. Locales added to `en`
and `zh`.
**Configuration** — production defaults are compiled in; endpoints and
the partner id are overridable through `AIMLAPI_*` environment
variables, so the same build works across environments.
**Testing** — the `web` build passes; chat, embedding and dynamic model
listing were smoke-tested against the live API.
Follow-up to #16468.
PR #16468 fixed the Python
(`api/db/joint_services/tenant_model_service.py
split_model_name`) and Go (`internal/service/model_service.go
parseModelName`)
parsers to right-anchor the '@'-split on the composite
"model_name@instance@provider" key, but the matching helper in the
front-end
(`web/src/utils/llm-util.ts parseModelValue`) was missed.
parseModelValue used `split('@')` (anchored on the first '@'), which
silently
mangles composite keys whose model_name itself contains '@' (e.g. LM
Studio
embedding IDs like `text-embedding-nomic-embed-text-v1.5@q8_0`):
text-embedding-nomic-embed-text-v1.5@q8_0@lmstudio@LM-Studio
became
model_name: text-embedding-nomic-embed-text-v1.5
model_instance: q8_0@lmstudio
model_provider: LM-Studio
`PATCH /api/v1/models/default` then sent those to the server, which
returned
HTTP 200 with body `{"code": 102, "message": "Instance 'q8_0@lmstudio'
not
found for provider 'LM-Studio'"}`. The UI swallowed the body-level error
code, so the failure was silent: no toast, the Embedding field stayed
empty.
This change makes parseModelValue do a right-anchored split that mirrors
the
Python `split_model_name` `rsplit('@', 2)` exactly:
- 3-part form: model_name@instance@provider -> same three fields.
- 2-part form: model_name@provider -> model_instance defaults to
"default"
(matching Python).
- 4+-part form (embedded '@' in model name): last two fields are
anchored
as instance and provider, everything to the left is the bare model name.
`parseModelUuid` is updated to the same right-anchored split so the
factoryId portion of `model_name@factory_id[#instance]` keeps the last
'@'
as the separator even when the model name itself contains '@'.
Adds jest cases under `web/src/utils/tests/llm-util.test.ts` (12 total)
covering the plain 3-part, 2-part, 4-part, multi-'@' name,
buildModelValue
round-trip and parseModelUuid variants.
Note for reviewers: the front-end is bundled into the published docker
image, so a release containing this fix will need `docker compose build
--no-cache ragflow-cpu` (or equivalent) for it to be visible to end
users.
Refs #16468, #16467
Both backends serve GET /api/v1/language. Frontend calls it once and
caches. By this way, front end can know the backend is go or python and
thus can determine which part of logic to load.
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
Fixes#14985 — clicking the **Thinking** button in a shared/embedded
chat returns 401 and bounces the user to the login page, even though
the same share page can chat with the agent just fine.
## Root cause
In shared chat, `useGetSharedChatSearchParams` binds `conversationId`
to the URL's `shared_id` query param — which is the **beta APIToken**,
not the real agent id. That `conversationId` propagates through the
component tree:
```tsx
<WorkFlowTimeline canvasId={conversationId}>
→ useFetchMessageTrace(canvasId)
→ GET /api/v1/agents/<sharedId>/logs/<messageId>
```
But `/agents/<agent_id>/logs/<message_id>` is decorated with
`@login_required` (`api/apps/restful_apis/agent_api.py:842-846`).
The share page only holds the beta token — there is no session JWT
— so the request 401s and quart-auth redirects to the login page.
The reporter's server log matches exactly:
```
load_user from jwt got exception No b'.' found in value
load_user: No APIToken found for token=ULG10SWG3E...
Unauthorized request (quart_auth)
GET /api/v1/agents/394013f8d42211f0bad6123fa55e8ed9/logs/96fd72e2-... 1.1 401
```
The `394013f8...` segment in the URL is the `shared_id` (beta
token), not an actual agent id. `_load_user` already accepts the
regular `APIToken.token` field, but not `APIToken.beta`, by design
— beta is a much weaker share-link credential than a personal API
key.
The sibling endpoints `/agentbots/<id>/completions` and
`/agentbots/<id>/inputs` already use the right auth pattern for
this scope (beta-token via `_get_sdk_authorization_token` →
`APIToken.query(beta=token)`). Trace just didn't have a parallel.
## Fix
### Backend (`api/apps/restful_apis/bot_api.py`)
Added a beta-token sibling endpoint:
```
GET /api/v1/agentbots/<shared_id>/logs/<message_id>
```
- Same auth shape as the existing `agentbots` endpoints.
- The `<shared_id>` path segment is a client-supplied label only.
The real `agent_id` used to build the Redis key
(`<agent_id>-<message_id>-logs`) is taken from
`APIToken.dialog_id` on the looked-up token, so the endpoint
never trusts client-supplied identifiers for the data lookup.
- Returns the same `{data: ...}` shape as the existing
`/agents/<id>/logs/<message_id>` endpoint, so the frontend
doesn't need to reshape the response.
### Frontend
- `web/src/utils/api.ts`: added `sharedTrace(sharedId, messageId)`
URL builder.
- `web/src/services/agent-service.ts`: added
`fetchSharedTrace({ shared_id, message_id })`.
- `web/src/hooks/use-agent-request.ts`: `useFetchMessageTrace`
takes an optional `isShare` argument. When set, it calls
`fetchSharedTrace`; `isShare` is also folded into the
`queryKey` so the two modes never share cached results.
- `web/src/pages/agent/log-sheet/workflow-timeline.tsx`:
forwards the already-existing `isShare` prop into the hook.
All other existing call sites of `useFetchMessageTrace` (webhook
timeline, pipeline log, dataflow result) pass no `isShare`
argument → undefined → falsy → unchanged behavior.
## Test plan
- [ ] In the regular Agent UI (logged-in user): open the trace /
log sheet for any message and click into "Thinking" — the
timeline should still load via `/agents/<id>/logs/<msg>`,
same as before.
- [ ] From the Agent page, click **Chat in new tab** to open
`/chat/share?shared_id=<token>&from=agent`. Send a message,
wait for a response, then click **Thinking** on the
assistant turn. The trace panel should load instead of
redirecting to the login page.
- [ ] Same flow but with the agent embedded in an iframe ("Embed
into webpage") — confirm there is no login redirect.
- [ ] In DevTools → Network, confirm the share-chat trace request
goes to `/api/v1/agentbots/<sharedId>/logs/<msgId>` and
returns 200 with the same JSON shape as the logged-in path.
- [ ] Confirm the chat completions, inputs, and upload flows in
the share page still work — they were not touched.
- [ ] Send a bogus / expired beta token to the new endpoint and
confirm it returns the standard "Authentication error: API
key is invalid!" response (no traceback, no 500).
- [ ] Run `uv run pytest` to make sure no existing tests regress.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
---------
Co-authored-by: Zhichang Yu <yuzhichang@gmail.com>
### What problem does this PR solve?
This PR follows up on
[#15863](https://github.com/infiniflow/ragflow/pull/15863) (Korean i18n)
with translation refinements and i18n coverage for hardcoded strings
found in the UI.
- Refine awkward Korean phrasing (e.g. 'Chunk 만들기' → 'Chunk 생성', '유형' →
'타입', etc.)
- Apply i18n to hardcoded strings in `message-item`,
`next-message-item`, `multi-select`, `chat-prompt-engine`, and various
filter hooks
- Rename `use-selelct-filters.ts` → `use-select-filters.ts` (typo fix)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
