### What problem does this PR solve?
Refine the stream parsing for `<think>` / `</think>` so MiniMax and
DeepSeek-style chunking both flush in the right order without mixing
think and answer buffers.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This fixes duplicated post-think text in streamed chat responses. When
the model emits text immediately after `</think>`, the stream state now
advances its cursor correctly so the same visible prefix is not emitted
twice.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### 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>
### What problem does this PR solve?
Remove duplicate function definitions in
`api/db/services/dialog_service.py`.
**Problem:** Two helper functions were defined twice in the same file,
but with different parameter orders:
- First definition (line 57):
`_resolve_reference_metadata(request_payload=None, config=None)`
- Second definition (line 136): `_resolve_reference_metadata(config,
request_payload=None)`
**Solution:** Keep the second definition (which is actually used by
other modules) and remove the first one to avoid confusion.
Additionally, remove duplicate `_enrich_chunks_with_document_metadata`
definition (keep line 140 version).
<img width="1584" height="313" alt="image"
src="https://github.com/user-attachments/assets/7daee832-244f-4bb2-8488-e3b65012a3f9"
/>
<img width="1672" height="359" alt="image"
src="https://github.com/user-attachments/assets/4fd2f523-273c-4b20-a7c9-ab35740b7834"
/>
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [x] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Closes#15025
Langfuse-enabled `dialog_service.async_chat()` regressed to
`langfuse_tracer.start_generation(...)` after the earlier Langfuse v4
migration. Langfuse v4 uses `start_observation(as_type="generation")`,
so the remaining `start_generation` call can fail when chat tracing is
enabled.
This restores the migrated `start_observation(as_type="generation")`
call for chat observations while preserving the existing trace context,
model, input payload, and update/end flow. It also adds a regression
test with a fake Langfuse v4-style client that exposes
`start_observation()` but not `start_generation()`.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### Tests
- `.venv/bin/pytest
test/unit_test/api/db/services/test_dialog_service_final_answer.py -q`
- `.venv/bin/ruff check api/db/services/dialog_service.py
test/unit_test/api/db/services/test_dialog_service_final_answer.py`
## What problem does this PR solve?
Closes#12017.
TTS output is deterministic for a given `(model, text)` pair, so
re-running the same text through the same TTS model produces the same
bytes — yet `Canvas.tts` and `dialog_service.tts` re-synthesized on
every request. That's slow and wastes provider quota whenever the same
assistant response is replayed, shared across users, or repeated within
a session.
### Change
New helper `rag/utils/tts_cache.py` with `synthesize_with_cache(tts_mdl,
cleaned_text)`:
- **Key:** `tts:cache:{model_id}:{sha256(text)}` — separate namespace
per model, identical cleaned text reuses a single entry across both call
sites.
- **Value:** the hex-encoded audio blob both call sites already
returned. No format change for downstream consumers.
- **TTL:** 7 days by default, configurable via
`RAGFLOW_TTS_CACHE_TTL_SECONDS`.
- **Failure modes:** a Redis hiccup falls back to direct synthesis; a
failed synthesis still returns `None` (existing contract preserved).
[`Canvas.tts`](https://github.com/infiniflow/ragflow/blob/main/agent/canvas.py#L683-L724)
and
[`dialog_service.tts`](https://github.com/infiniflow/ragflow/blob/main/api/db/services/dialog_service.py#L1367-L1380)
now route through the helper; the per-file bytes-accumulation/hex-encode
loop has been removed in favor of one shared implementation.
## Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Test plan
- [ ] **Cache hit, chat path:** Configure a dialog with TTS enabled, ask
the same question twice with `stream=false`. Verify the second response
returns the same `audio_binary` and that the second invocation doesn't
hit the TTS provider (e.g., observe provider-side logs / usage counters;
check no `LLMBundle.tts can't update token usage` log line on the second
run).
- [ ] **Cache hit, agent path:** Same exercise via a Conversational
Agent that includes a Message component playing back the answer.
- [ ] **Cache isolation per model:** Switch tenant's `tts_id` between
two models, run the same text against each — confirm the second model's
first synthesis still happens (no cross-model hits).
- [ ] **TTL override:** Set `RAGFLOW_TTS_CACHE_TTL_SECONDS=120`, confirm
the entry expires after 2 minutes.
- [ ] **Redis unavailable:** Stop Redis (or break the connection).
Verify the TTS endpoint still works — synthesis falls back to direct
calls, with a `TTS cache lookup failed` / `TTS cache store failed`
warning logged.
- [ ] **Failure path:** Configure a TTS model with an invalid API key,
ensure the response still returns successfully with `audio_binary=None`
(no regression vs. current behavior).
## Summary
- Stop pulling chunk vectors (`q_*_vec`) back from Elasticsearch in the
main retrieval path. ES already knows them; shipping them was pure
bandwidth/memory overhead.
- Recover the per-chunk cosine similarity via a second KNN-only ES call
filtered by the candidate chunk ids. The new `_score` is merged with
locally computed term similarity using the user-configured
`vector_similarity_weight`.
- Lazily fetch the chunk embedding only for the chunks
`insert_citations` actually needs.
## Details
**`rag/nlp/search.py`**
- `Dealer.search`: no longer appends `q_*_vec` to the ES select list.
OceanBase still gets it (its rerank path is unchanged).
- New `Dealer._knn_scores(sres, idx_names, kb_ids)`: a `MatchDenseExpr`
over the cached query vector filtered by `id IN sres.ids`, returning
`{chunk_id: cosine_score}` via ES `_score`.
- New `Dealer.rerank_with_knn(...)`: term similarity from
`qryr.token_similarity` plus the ES-supplied KNN score, combined with
`tkweight`/`vtweight` and the existing rank-feature bonus.
- New `Dealer.fetch_chunk_vectors(chunk_ids, tenant_ids, kb_ids, dim)`:
on-demand vector fetch for citation use.
- `Dealer.retrieval` routes Infinity → unchanged, OceanBase → existing
local `rerank`, ES → new KNN-score path.
**`common/doc_store/es_conn_base.py`**
- New `get_scores(res)` helper returning `{_id: _score}` directly from
hit headers (ES doesn't surface `_score` through `get_fields`).
**`api/db/services/dialog_service.py`**
- New top-level `_hydrate_chunk_vectors(...)` helper. On ES it
back-fills `ck["vector"]` from `fetch_chunk_vectors` right before
`insert_citations`. No-op on Infinity / OB (their chunks already carry
vectors).
- Both `decorate_answer` closures became `async` and are `await`-ed at
all call sites in `async_chat` and `async_ask`.
## Backend behavior
| Backend | Returns chunk vec in main search | Sim source | Vectors for
citations |
|---|---|---|---|
| ES | No | second KNN call (`_score`) merged with term sim | fetched on
demand |
| Infinity | No (unchanged) | normalized `_score` | already on chunks |
| OceanBase | Yes (kept) | local hybrid rerank | already on chunks |
## Test plan
### What problem does this PR solve?
Closes#9837
The Langfuse integration currently only sends the output text to
`langfuse_generation.update()` without including token usage
information. This means Langfuse cannot track input/output token
consumption for cost analysis and monitoring.
### Solution
Add the `usage` parameter to `langfuse_generation.update()` with:
- `input`: approximate input token count from `message_fit_in()`
- `output`: approximate output token count from
`num_tokens_from_string(answer)`
- `total`: sum of input and output
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
The use_sql() function in dialog_service.py constructed SQL WHERE
clauses and Infinity table names by directly interpolating kb_id values
using Python f-strings, with no validation of the input values. A
malformed or maliciously crafted kb_id (introduced via a compromised
admin account or a separate injection vector) could alter the structure
of the generated SQL query, potentially leading to unauthorized data
access or data manipulation.
This PR adds strict UUID format validation for all kb_id values before
they are interpolated into any SQL string, causing requests with invalid
IDs to fail fast with a ValueError rather than executing a tampered
query.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
## Summary
- **Collapsible thinking**: Replace `<section>` with `<details>` for
`<think>` content, so model thinking output is collapsed by default
(click to expand). Works for all models that output `<think>` tags
(Qwen3, DeepSeek, Gemini, Claude, etc.).
- **Fix double thinking tags**: When reasoning/deep research mode is
enabled in knowledge base chat, both the retrieval progress and model
thinking were wrapped in `<think>` tags, producing two "Thinking..."
blocks. Now retrieval progress uses a dedicated `<retrieving>` tag
rendered as a separate "Retrieving..." collapsible with a distinct green
accent.
### Before
- Thinking content displayed as flat gray-bordered `<section>`,
occupying significant screen space
- Deep research + model thinking both use `<think>` → two identical
"Thinking..." blocks
### After
- Thinking content collapsed by default in a `<details>` element, click
"Thinking..." to expand
- Deep research shows "Retrieving..." (green border), model thinking
shows "Thinking..." (gray border)
## Changes
**Backend (`api/db/services/dialog_service.py`)**
- Deep research callback: replace `start_to_think`/`end_to_think` marker
flags with direct `<retrieving>`/`</retrieving>` answer text
**Frontend**
- `web/src/utils/chat.ts`: `replaceThinkToSection()` now uses
`<details>` instead of `<section>`; add new
`replaceRetrievingToSection()`
- 4 tsx files: import and pipe `replaceRetrievingToSection`, whitelist
`details`, `summary`, `retrieving` in DOMPurify `ADD_TAGS`
- 4 less files: `section.think` → `details.think` with `<summary>`
styles; add `details.retrieving` with green accent; dark mode and RTL
variants
## Test plan
- [ ] Open a chat WITHOUT knowledge base, ask a question to a model with
thinking (e.g. Qwen3) → thinking content should be collapsed by default,
click "Thinking..." to expand
- [ ] Open a chat WITH knowledge base and reasoning enabled, ask a
question → "Retrieving..." (green) shows retrieval progress,
"Thinking..." (gray) shows model thinking, each independently
collapsible
- [ ] Verify dark mode renders correctly for both collapsible blocks
- [ ] Verify RTL layout renders correctly
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: wanghualoong <wanghualoong@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
### What problem does this PR solve?
Fixes#14412.
`common.metadata_utils.meta_filter` evaluates user-defined metadata
conditions in Python after `DocMetadataService.get_flatted_meta_by_kbs`
loads the entire `meta_fields` table into memory. Past a few thousand
documents per knowledge base this becomes a memory bottleneck and a
wasted ES round-trip — every filter request currently fetches up to
10000 metadata rows even when the resulting `doc_ids` list is tiny.
This PR adds an ES push-down path that translates the same filter
language into a `bool` query and returns just the matching document IDs.
**Changes**
- `common/metadata_es_filter.py` *(new)*: pure-Python translator from
the RAGflow filter list to ES DSL. Covers every operator the in-memory
path supports (`=`, `≠`, `>`, `<`, `≥`, `≤`, `in`, `not in`, `contains`,
`not contains`, `start with`, `end with`, `empty`, `not empty`) with
`case_insensitive: true` on `prefix` and `wildcard` for parity with the
existing lower-cased Python comparisons. User wildcard metacharacters
are escaped before being injected into `wildcard` patterns. Negative
operators (`≠`, `not in`, `not contains`, ranges) are wrapped with an
`exists` guard so they do not accidentally match documents missing the
key, matching the legacy `if k not in metas` behaviour.
- `api/db/services/doc_metadata_service.py`: new
`DocMetadataService.filter_doc_ids_by_meta_pushdown(kb_ids, filters,
logic)` that returns the doc IDs ES matched, or `None` to signal the
caller should fall back to the in-memory path. Returns `None` when the
active doc store is Infinity (`meta_fields` is a JSON column, not a
dotted-object mapping), when any filter cannot be expressed in DSL
(`UnsupportedMetaFilter`), or when the ES request or metadata index
lookup errors.
- `common/metadata_utils.py`: `apply_meta_data_filter` accepts an
optional `kb_ids` argument. When supplied, conditions go through
push-down first via a new `_try_meta_pushdown` helper; on `None` the
function falls back to the original `meta_filter` call. Default
behaviour is unchanged for callers that don't pass `kb_ids`.
- Updated all four callers (`agent/tools/retrieval.py`,
`api/db/services/dialog_service.py` ×2,
`api/apps/services/dataset_api_service.py`, `api/apps/sdk/session.py`)
to forward `kb_ids` so the push-down path is exercised in production.
- `test/unit_test/common/test_metadata_es_filter.py` *(new)*: 35 unit
tests covering every operator's DSL shape, value coercion
(`ast.literal_eval`, lowercasing, ISO-date pass-through), wildcard
escaping, OR-logic wrapping that protects negative clauses, and the
doc-ID extractor.
**Behaviour preserved**
- The in-memory `meta_filter` is untouched and still services every
fallback case (Infinity backend, unknown operators, ES outages).
- The eligibility / credibility / issue-multiplier semantics described
in the LLM-driven `auto` and `semi_auto` modes still hand the LLM the
full in-memory `metas` dict to choose conditions from. Only the
*evaluation* of those generated conditions is pushed down.
- Existing tests in
`test/unit_test/common/test_metadata_filter_operators.py` continue to
pass (14/14).
**Test plan**
- `pytest test/unit_test/common/test_metadata_es_filter.py` — 35 passed.
- `pytest test/unit_test/common/test_metadata_filter_operators.py` — 14
passed.
- `ruff check` clean on every modified file.
- Reviewer please validate the ES query shapes against a live cluster —
particularly `case_insensitive` on `wildcard` and `prefix` (requires ES
7.10+) and the `exists` + `must_not` pairing for `≠`.
**Notes**
- The first cut caps each push-down request at 10000 results, matching
the existing `get_flatted_meta_by_kbs` limit, and logs a warning when
the cap is hit. A `search_after` follow-up would let us drop the cap
entirely once the push-down path is validated.
- Operator parity with the in-memory path is exact for the canonical
unicode operators (`≥`, `≤`, `≠`) used internally; the ASCII aliases
(`>=`, `<=`, `!=`) are normalised by `convert_conditions` before they
reach the translator.
### Type of change
- [x] Performance Improvement
---------
Co-authored-by: sxxtony <sxxtony@users.noreply.github.com>
### What problem does this PR solve?
Currently, RAGFlow's Search and Chat interfaces display only raw
vectorized text chunks during retrieval, without contextual information
about their source documents. Users cannot see document titles, page
numbers, upload dates, or custom metadata fields that would help them
understand and trust the retrieved results.
This PR introduces an **optional metadata display feature** that
enriches retrieved chunks with document-level metadata in both the
Search tab and Chatbot interface.
**Key improvements:**
- **Search results**: Display document metadata as styled badges beneath
chunk snippets
- **Chat citations**: Show metadata in citation popovers and reference
lists for better source context
- **LLM context**: Metadata is injected into the LLM prompt to enable
more accurate, citation-aware responses
- **External API support**: Applications using RAGFlow's SDK retrieval
endpoints (`/v1/retrieval`, `/v1/searchbots/retrieval_test`) can opt-in
via request parameters
- **User control**: Multi-select dropdown UI allows users to choose
which metadata fields to display
**Implementation approach:**
- ✅ Reuses existing `DocMetadataService` infrastructure (no new database
tables or indices)
- ✅ Settings stored in existing JSON configuration fields
(`search_config.reference_metadata`, `prompt_config.reference_metadata`)
- ✅ No database migrations required
- ✅ Disabled by default (fully opt-in and backward-compatible)
- ✅ Dynamic metadata field selection populated from actual document
metadata keys
- ✅ Fixed critical bug where Python's builtin `set()` was shadowed by a
route handler function
**Modified endpoints (all backward-compatible):**
- `POST /v1/retrieval` (Public SDK)
- `POST /v1/searchbots/retrieval_test` (Searchbots)
- `POST /v1/chunk/retrieval_test` (UI/Internal)
- Chat completions endpoints (via `extra_body.reference_metadata` or
`prompt_config`)
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
###Images
-
<img width="879" height="1275" alt="image"
src="https://github.com/user-attachments/assets/95b2d731-31ae-45a1-b081-bf5893f52aeb"
/>
<br><br>
<br><br>
<img width="1532" height="362" alt="image"
src="https://github.com/user-attachments/assets/9cebc65b-b7a7-459f-b25e-3b13fa9b638e"
/>
<br><br>
<br><br>
<img width="2586" height="1320" alt="image"
src="https://github.com/user-attachments/assets/2153d493-d899-461f-a7a9-041391e07776"
/>
---------
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Attili-sys <Attili-sys@users.noreply.github.com>
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
The Langfuse Python SDK v3+ removed `start_generation()` method.
RagFlow's code called this non-existent method, causing AttributeError
when Langfuse tracing is enabled.
Replace all `start_generation()` calls with
`start_observation(as_type="generation")` which is the correct v4 SDK
API.
Affected files:
- api/db/services/llm_service.py (12 occurrences)
- api/db/services/dialog_service.py (1 occurrence)
Fixes#14204
Related to #9243
### What problem does this PR solve?
_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
### What problem does this PR solve?
normalize think tags in final chat answer
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Resolve#14115 .
## Problem
On the shared chat link page (`/chats/share?shared_id=...`), querying
the knowledge base returns "no relevant information was found", while
the same query works correctly on the editor chat page.
## Root Cause
Knowledge base retrieval in `async_chat()` is gated by the check `if
"knowledge" in param_keys` (line 598), where `param_keys` is derived
from `prompt_config["parameters"]`. If `parameters` is empty or missing
the `{"key": "knowledge", "optional": false}` entry, retrieval is
entirely skipped.
This can happen because `_apply_prompt_defaults()` — which ensures
`parameters` contains the `knowledge` entry — is only called in the
`create` (POST) and `update_chat` (PUT) handlers, but **not** in
`patch_chat` (PATCH). If a chat's `prompt_config` was updated via PATCH
without including `parameters`, the `knowledge` entry would be absent.
Additionally, `prompt_config["parameters"]` would raise a `KeyError` if
the key was missing entirely.
## Fix
Added a defensive safety net in `async_chat()`
(`api/db/services/dialog_service.py`) that auto-injects the `knowledge`
parameter when:
- `dialog.kb_ids` is set (knowledge bases are configured)
- `"knowledge"` is not already in `param_keys`
- `{knowledge}` placeholder exists in the system prompt
Also changed `prompt_config["parameters"]` to
`prompt_config.get("parameters", [])` to prevent `KeyError` when the key
is absent.
## Files Changed
- `api/db/services/dialog_service.py` — added auto-injection of
`knowledge` parameter and safe `.get()` access for `parameters`
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: noob <yixiao121314@outlook.com>
## What's the problem
Both `async_chat()` and `async_ask()` call `decorate_answer()` to build
the final SSE payload — it inserts citation markers (`##N$$`) into the
answer text and prunes `doc_aggs` to only the cited documents.
Immediately after, both functions overwrite `final["answer"]` with `""`:
```python
# async_chat(), line ~774 (issue #13828)
final = decorate_answer(thought + full_answer)
final["final"] = True
final["audio_binary"] = None
final["answer"] = "" # discards decorated text
yield final
# async_ask(), line ~1444 (same bug, different path)
final = decorate_answer(full_answer)
final["final"] = True
final["answer"] = "" # discards decorated text
yield final
```
The client receives filtered references (built for a citation-decorated
answer it never sees) while displaying the raw, undecorated streaming
text. Citations can never match.
## Root cause
`final["answer"] = ""` was left over from an earlier design where
clients were meant to reconstruct the full answer purely from delta
events. Once `decorate_answer()` started placing citation markers, this
blank-out broke the contract: the final event is where the decorated
answer should land.
## Fix
Remove the two blank-override lines — one in `async_chat()`, one in
`async_ask()`:
```diff
- final["answer"] = ""
```
`decorate_answer()` already sets `final["answer"]` to the correct
decorated string; there is nothing to override.
## Relation to #13828
Issue #13828 and PR #13835 identify the bug in `async_chat()`. This PR
absorbs that fix and also corrects the identical pattern in
`async_ask()` (used by the `/retrieval` route in `chat_api.py`), which
PR #13835 does not touch.
## Regression test
Added
`test/unit_test/api/db/services/test_dialog_service_final_answer.py`
with three tests:
| Test | Purpose |
|------|---------|
| `test_buggy_pattern_drops_answer` | Documents the old behaviour:
blank-override empties the final answer |
| `test_fixed_pattern_preserves_decorated_answer` | Core invariant:
final event carries the decorated text from `decorate_answer()` |
| `test_final_event_reference_matches_decorated_result` | Citation
markers in the answer must match the pruned `doc_aggs` in the same event
|
Local run result:
```
test_dialog_service_final_answer.py::test_buggy_pattern_drops_answer PASSED
test_dialog_service_final_answer.py::test_fixed_pattern_preserves_decorated_answer PASSED
test_dialog_service_final_answer.py::test_final_event_reference_matches_decorated_result PASSED
3 passed in 0.04s
```
`ruff check` passes with no issues on all changed files.
---------
Co-authored-by: edenfunf <edenfunf@gmail.com>
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Fixes#14051.
The chat UI already sends an `internet` flag with each request, but the
backend previously triggered Tavily web retrieval whenever
`prompt_config.tavily_api_key` was configured. As a result, web search
could still run even when the internet toggle was off.
This PR makes web search an explicit opt-in at request time:
- `tavily_api_key` only indicates that web search is available
- Tavily retrieval runs only when `internet` is explicitly enabled
- the same behavior now applies to both the normal retrieval path and
the deep-research / reasoning path
This also fixes the no-KB fallback case so chats without KBs fall back
to normal solo chat when `internet` is off.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
fixes issue #13799 where team members get model not authorized when
running RAG on an admin-shared knowledge base after the admin changes
the KB embedding model (for example to bge-m3).
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
Fix knowledge-base chat retrieval when no individual document IDs are
selected.
## Root Cause
`async_chat()` initialized `doc_ids` as an empty list when the request
did not explicitly select documents. That empty list was then forwarded
into retrieval as an active `doc_id` filter, effectively becoming
`doc_id IN []` and suppressing all chunk matches.
## Changes
- treat missing selected document IDs as `None` instead of `[]`
- keep explicit document filtering when IDs are actually provided
- add regression coverage for the shared chat retrieval path
## Validation
- `python3 -m py_compile api/db/services/dialog_service.py
test/unit_test/api/db/services/test_dialog_service_use_sql_source_columns.py`
- `.venv/bin/python -m pytest
test/unit_test/api/db/services/test_dialog_service_use_sql_source_columns.py`
- manually verified that chat completions again inject retrieved
knowledge into the prompt
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
Add id for table tenant_llm and apply in LLMBundle.
### Type of change
- [x] Refactoring
---------
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
this pr adds new tests, for the full configuration tab in datasests
### Type of change
- [x] Other (please describe): new tests
### What problem does this PR solve?
This PR adds comprehensive **Right-to-Left (RTL) language support**,
primarily targeting Arabic and other RTL scripts (Hebrew, Persian, Urdu,
etc.).
Previously, RTL content had multiple rendering issues:
- Incorrect sentence splitting for Arabic punctuation in citation logic
- Misaligned text in chat messages and markdown components
- Improper positioning of blockquotes and “think” sections
- Incorrect table alignment
- Citation placement ambiguity in RTL prompts
- UI layout inconsistencies when mixing LTR and RTL text
This PR introduces backend and frontend improvements to properly detect,
render, and style RTL content while preserving existing LTR behavior.
#### Backend
- Updated sentence boundary regex in `rag/nlp/search.py` to include
Arabic punctuation:
- `،` (comma)
- `؛` (semicolon)
- `؟` (question mark)
- `۔` (Arabic full stop)
- Ensures citation insertion works correctly in RTL sentences.
- Updated citation prompt instructions to clarify citation placement
rules for RTL languages.
#### Frontend
- Introduced a new utility: `text-direction.ts`
- Detects text direction based on Unicode ranges.
- Supports Arabic, Hebrew, Syriac, Thaana, and related scripts.
- Provides `getDirAttribute()` for automatic `dir` assignment.
- Applied dynamic `dir` attributes across:
- Markdown rendering
- Chat messages
- Search results
- Tables
- Hover cards and reference popovers
- Added proper RTL styling in LESS:
- Text alignment adjustments
- Blockquote border flipping
- Section indentation correction
- Table direction switching
- Use of `<bdi>` for figure labels to prevent bidirectional conflicts
#### DevOps / Environment
- Added Windows backend launch script with retry handling.
- Updated dependency metadata.
- Adjusted development-only React debugging behavior.
---
### Type of change
- [x] Bug Fix (non-breaking change which fixes RTL rendering and
citation issues)
- [x] New Feature (non-breaking change which adds RTL detection and
dynamic direction handling)
---------
Co-authored-by: 6ba3i <isbaaoui09@gmail.com>
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
Co-authored-by: Ahmad Intisar <168020872+ahmadintisar@users.noreply.github.com>
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Adjust highlight parsing, add row-count SQL override, tweak retrieval
thresholding, and update tests with engine-aware skips/utilities.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
close#12770
This PR adds OceanBase as a storage backend for the Table Parser. It
enables dynamic table schema storage via JSON and implements OceanBase
SQL execution for text-to-SQL retrieval.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [ ] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### Changes
- Table Parser stores row data into `chunk_data` when doc engine is
OceanBase. (table.py)
- OceanBase table schema adds `chunk_data` JSON column and migrates if
needed.
- Implemented OceanBase `sql()` to execute text-to-SQL results.
(ob_conn.py)
- Add `DOC_ENGINE_OCEANBASE` flag for engine detection (setting.py)
### Test
1. Set `DOC_ENGINE=oceanbase` (e.g. in `docker/.env`)
<img width="1290" height="783" alt="doc_engine_ob"
src="https://github.com/user-attachments/assets/7d1c609f-7bf2-4b2e-b4cc-4243e72ad4f1"
/>
2. Upload an Excel file to Knowledge Base.(for test, we use as below)
<img width="786" height="930" alt="excel"
src="https://github.com/user-attachments/assets/bedf82f2-cd00-426b-8f4d-6978a151231a"
/>
3. Choose **Table** as parsing method.
<img width="2550" height="1134" alt="parse_excel"
src="https://github.com/user-attachments/assets/aba11769-02be-4905-97e1-e24485e24cd0"
/>
4.Ask a natural language query in chat.
<img width="2550" height="1134" alt="query"
src="https://github.com/user-attachments/assets/26a910a6-e503-4ac7-b66a-f5754bbb0e91"
/>
### What problem does this PR solve?
Put document metadata in ES/Infinity.
Index name of meta data: ragflow_doc_meta_{tenant_id}
### Type of change
- [x] Refactoring
### What problem does this PR solve?
1) Create dataset using table parser for infinity
2) Answer questions in chat using SQL
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
## Description
Fixes connection error handling when langfuse service is unavailable.
The application now gracefully handles connection failures instead of
crashing.
## Changes
- Wrapped `langfuse.auth_check()` calls in try-except blocks in:
- `api/db/services/dialog_service.py`
- `api/db/services/tenant_llm_service.py`
## Problem
When langfuse service is unavailable or connection is refused,
`langfuse.auth_check()` throws `httpx.ConnectError: [Errno 111]
Connection refused`, causing the application to crash during document
parsing or dialog operations.
## Solution
Added try-except blocks around `langfuse.auth_check()` calls to catch
connection errors and gracefully skip langfuse tracing instead of
crashing. The application continues functioning normally even when
langfuse is unavailable.
## Related Issue
Fixes#12621
---
Contribution by Gittensor, see my contribution statistics at
https://gittensor.io/miners/details?githubId=158349177
### What problem does this PR solve?
change:
Enhance delta streaming in chat functions for improved reasoning and
content handling
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Refactor metadata filter.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Retrieval metadata filtering adds semi-automatic mode, and users can
manually check the metadata key that participates in LLM to generate
filter conditions.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Fix RuntimeError when calling mindmap endpoint by converting
`gen_mindmap()` to async function and using `await` instead of
`asyncio.run()`.
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Cleanup synchronous functions in chat_model and implement
synchronization for conversation and dialog chats.
### Type of change
- [x] Refactoring
- [x] Performance Improvement
