### What problem does this PR solve?
Feat: When exporting the agent DSL, the tailkey, password, and history
fields need to be cleared. #13281
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
### What problem does this PR solve?
test_doc_sdk_routes_unit had two flaky/incorrect branch assumptions:
1. parse/stop_parsing production logic gates on doc.run, but tests used
progress, causing branch mismatch and unintended fallthrough into
mutation/DB paths.
2. stop_parsing invalid-state test asserted an outdated message
fragment, making the contract brittle.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Update for Admin UI:
- Update file picker input in **Registration whitelist** > **Import from
Excel** modal
- Modify DOM structure of **Sandbox Settings** and move several
hardcoded texts into translation files
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Necessary ids for implementing the new testing suite with playwright for
UI
### Type of change
- [x] Other (please describe): Testing IDs
Co-authored-by: Liu An <asiro@qq.com>
### What problem does this PR solve?
Properly close detached PIL image on JPEG save failure in encode_image.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
When the original code terminates the parsing task halfway, the progress
may not be 0 or 1, which will result in the inability to call the
interface to parse again
-Change the document parsing progress check to task status check, and
use TaskStatus.RUNNING.value to judge
-Update the condition judgment for stopping parsing documents, and check
whether the task is running instead
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This pull request refactors the chat session creation and deletion logic
in both the parser and client code to use unique session IDs instead of
session names. It also updates the corresponding command syntax and
payloads, ensuring more robust and unambiguous session management.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
1. Create / Drop / List chat sessions
2. Chat with LLM and datasets
### 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 pull request makes a small but important fix to how streaming
requests are handled in the `completion` endpoint of
`conversation_app.py`. The main change ensures that the `stream`
argument is not passed twice, which could cause errors.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
**Summary**
This PR tackles a significant memory bottleneck when processing
image-heavy Word documents. Previously, our pipeline eagerly decoded
DOCX images into `PIL.Image` objects, which caused high peak memory
usage. To solve this, I've introduced a **lazy-loading approach**:
images are now stored as raw blobs and only decoded exactly when and
where they are consumed.
This successfully reduces the memory footprint while keeping the parsing
output completely identical to before.
**What's Changed**
Instead of a dry file-by-file list, here is the logical breakdown of the
updates:
* **The Core Abstraction (`lazy_image.py`)**: Introduced `LazyDocxImage`
along with helper APIs to handle lazy decoding, image-type checks, and
NumPy compatibility. It also supports `.close()` and detached PIL access
to ensure safe lifecycle management and prevent memory leaks.
* **Pipeline Integration (`naive.py`, `figure_parser.py`, etc.)**:
Updated the general DOCX picture extraction to return these new lazy
images. Downstream consumers (like the figure/VLM flow and base64
encoding paths) now decode images right at the use site using detached
PIL instances, avoiding shared-instance side effects.
* **Compatibility Hooks (`operators.py`, `book.py`, etc.)**: Added
necessary compatibility conversions so these lazy images flow smoothly
through existing merging, filtering, and presentation steps without
breaking.
**Scope & What is Intentionally Left Out**
To keep this PR focused, I have restricted these changes strictly to the
**general Word pipeline** and its downstream consumers.
The `QA` and `manual` Word parsing pipelines are explicitly **not
modified** in this PR. They can be safely migrated to this new lazy-load
model in a subsequent, standalone PR.
**Design Considerations**
I briefly considered adding image compression during processing, but
decided against it to avoid any potential quality degradation in the
derived outputs. I also held off on a massive pipeline re-architecture
to avoid overly invasive changes right now.
**Validation & Testing**
I've tested this to ensure no regressions:
* Compared identical DOCX inputs before and after this branch: chunk
counts, extracted text, table HTML, and image descriptions match
perfectly.
* **Confirmed a noticeable drop in peak memory usage when processing
image-dense documents.** For a 30MB Word document containing 243 1080p
screenshots, memory consumption is reduced by approximately 1.5GB.
**Breaking Changes**
None.
### What problem does this PR solve?
Added the option to delete models individually from providers.
For additional context, see
[issue-13184](https://github.com/infiniflow/ragflow/issues/13184)
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Note: when deleting a selected model, it leaves the full model name as
text as seen here:
<img width="676" height="90" alt="image"
src="https://github.com/user-attachments/assets/c11c7c1b-3f2a-4119-b20c-bb8148a8ad16"
/>
If attempting to use ragflow with that deleted model, ragflow will throw
an unauthorized model error as expected.
I left it like that on purpose, so it's easier for the user to
understand what he deleted and that he needs to replace it with another
model.
Co-authored-by: Shahar Flumin <shahar@Shahars-MacBook-Air.local>
### What problem does this PR solve?
The SeaFile connector currently synchronises the entire account — every
library
visible to the authenticated user. This is impractical for users who
only need
a subset of their data indexed, especially on large SeaFile instances
with many
shared libraries.
This PR introduces granular sync scope support, allowing users to choose
between
syncing their entire account, a single library, or a specific directory
within a
library. It also adds support for SeaFile library-scoped API tokens
(`/api/v2.1/via-repo-token/` endpoints), enabling tighter access control
without
exposing account-level credentials.
### 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):
### Test
```
from seafile_connector import SeaFileConnector
import logging
import os
logging.basicConfig(level=logging.DEBUG)
URL = os.environ.get("SEAFILE_URL", "https://seafile.example.com")
TOKEN = os.environ.get("SEAFILE_TOKEN", "")
REPO_ID = os.environ.get("SEAFILE_REPO_ID", "")
SYNC_PATH = os.environ.get("SEAFILE_SYNC_PATH", "/Documents")
REPO_TOKEN = os.environ.get("SEAFILE_REPO_TOKEN", "")
def _test_scope(scope, repo_id=None, sync_path=None):
print(f"\n{'='*50}")
print(f"Testing scope: {scope}")
print(f"{'='*50}")
creds = {"seafile_token": TOKEN} if TOKEN else {}
if REPO_TOKEN and scope in ("library", "directory"):
creds["repo_token"] = REPO_TOKEN
connector = SeaFileConnector(
seafile_url=URL,
batch_size=5,
sync_scope=scope,
include_shared = False,
repo_id=repo_id,
sync_path=sync_path,
)
connector.load_credentials(creds)
connector.validate_connector_settings()
count = 0
for batch in connector.load_from_state():
for doc in batch:
count += 1
print(f" [{count}] {doc.semantic_identifier} "
f"({doc.size_bytes} bytes, {doc.extension})")
print(f"\n-> {scope} scope: {count} document(s) found.\n")
# 1. Account scope
if TOKEN:
_test_scope("account")
else:
print("\nSkipping account scope (set SEAFILE_TOKEN)")
# 2. Library scope
if REPO_ID and (TOKEN or REPO_TOKEN):
_test_scope("library", repo_id=REPO_ID)
else:
print("\nSkipping library scope (set SEAFILE_REPO_ID + token)")
# 3. Directory scope
if REPO_ID and SYNC_PATH and (TOKEN or REPO_TOKEN):
_test_scope("directory", repo_id=REPO_ID, sync_path=SYNC_PATH)
else:
print("\nSkipping directory scope (set SEAFILE_REPO_ID + SEAFILE_SYNC_PATH + token)")
```
### What problem does this PR solve?
Update **Chat** UI:
- Align to the design.
- Update `<AudioButton>` visualizer logic.
- Fix keyboard navigation issue.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
The _transfer_to_sections method was throwing a type hint violation
because it occasionally returns 3-item tuples instead of 2. Adjusted to
list[tuple[str, ...]] to prevent runtime crashes.
Error:
20:53:21 Page(1~10): [ERROR]Internal server error while chunking:
Method[1m[35m
deepdoc.parser.docling_parser.DoclingParser._transfer_to_sections()[0m
return [1m[31m[(1. JIRA Nasıl Kullanılır?, text,
@@1\t70.8\t194.9\t70.9\t85.5##), (1.1. Proje O...##)][0m violates type
hint [1m[32mlist[tuple[str, str]][0m, as [1m[33mlist [0mindex
[1m[33m15[0m item tuple [1m[33mtuple [0m[1m[31m(Gelen ekran
üzerinden alanları isterlerine göre doldurduğunuz taktirde Create
düğmesi i...##)[0m length 3 != 2.
20:53:21 [ERROR][Exception]: Method[1m[35m
deepdoc.parser.docling_parser.DoclingParser._transfer_to_sections()[0m
return [1m[31m[('1. JIRA Nasıl Kullanılır?', 'text',
'@@1\t70.8\t194.9\t70.9\t85.5##'), ('1.1. Proje O...##')][0m violates
type hint [1m[32mlist[tuple[str, str]][0m, as [1m[33mlist [0mindex
[1m[33m15[0m item tuple [1m[33mtuple [0m[1m[31m('Gelen ekran
üzerinden alanları isterlerine göre doldurduğunuz taktirde Create
düğmesi i...##')[0m length 3 != 2.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Enes Delibalta <enes.delibalta@pentanom.com>
### What problem does this PR solve?
Refer to issue: #13236
The base url for GPUStack chat model requires `/v1` suffix. For the
other model type like `Embedding` or `Rerank`, the `/v1` suffix is not
required and will be appended in code.
So keep the same logic for chat model as other model type.
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This PR fixes 2 bugs related to RAGFlow's init superuser functionality.
#### Bug 1
When the RAGFlow server was started with the `--init-superuser` option
it would always create a new admin user even if it already exists
resulting in duplicate users.
To fix this, I added an additional check before create the superuser and
added the *unique* constraint to the email column of the database, to
mitigate potential TOCTOU race conditions. Since existing databases
could contain duplicate emails I added email de-duplication to the
database migration.
#### Bug 2
When the RAGFlow server was started with the `--init-superuser` option
but without configured default LLM and embedding models it would fail to
start because the `init_superuser` function would always make test
request to the models even if they were not set.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Fix: The output content of the multi-model comparison will disappear.
#13227
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Make the embedded page of chat compatible with mobile devices.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR adds [Avian](https://avian.io) as a new LLM provider to RAGFlow.
Avian provides an OpenAI-compatible API with competitive pricing,
offering access to models like DeepSeek V3.2, Kimi K2.5, GLM-5, and
MiniMax M2.5.
**Provider details:**
- API Base URL: `https://api.avian.io/v1`
- Auth: Bearer token via API key
- OpenAI-compatible (chat completions, streaming, function calling)
- Models:
- `deepseek/deepseek-v3.2` — 164K context, $0.26/$0.38 per 1M tokens
- `moonshotai/kimi-k2.5` — 131K context, $0.45/$2.20 per 1M tokens
- `z-ai/glm-5` — 131K context, $0.30/$2.55 per 1M tokens
- `minimax/minimax-m2.5` — 1M context, $0.30/$1.10 per 1M tokens
**Changes:**
- `rag/llm/chat_model.py` — Add `AvianChat` class extending `Base`
- `rag/llm/__init__.py` — Register in `SupportedLiteLLMProvider`,
`FACTORY_DEFAULT_BASE_URL`, `LITELLM_PROVIDER_PREFIX`
- `conf/llm_factories.json` — Add Avian factory with model definitions
- `web/src/constants/llm.ts` — Add to `LLMFactory` enum, `IconMap`,
`APIMapUrl`
- `web/src/components/svg-icon.tsx` — Register SVG icon
- `web/src/assets/svg/llm/avian.svg` — Provider icon
- `docs/references/supported_models.mdx` — Add to supported models table
This follows the same pattern as other OpenAI-compatible providers
(e.g., n1n #12680, TokenPony).
cc @KevinHuSh @JinHai-CN
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
### What problem does this PR solve?
Fix [#13210](https://github.com/infiniflow/ragflow/issues/13210)
Remove limit in _search_metadata, use pagination in _search_metadata.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This pull request makes a minor update to the English locale strings for
the Table of Contents toggle buttons, changing the labels from "Show
TOC"/"Hide TOC" to "Show content"/"Hide content" for improved clarity.
### Type of change
- [x] Refactoring
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Codecov’s coverage report shows that several RAGFlow code paths are
currently untested or under-tested. This makes it easier for regressions
to slip in during refactors and feature work.
This PR adds targeted automated tests to cover the files and branches
highlighted by Codecov, improving confidence in core behavior while
keeping runtime functionality unchanged.
### Type of change
- [x] Other (please describe): Test coverage improvement (adds/extends
unit and integration tests to address Codecov-reported gaps)
…ff publishing this guide.
### What problem does this PR solve?
Removed failsure mode checklist per your request. @JinHai-CN
### Type of change
- [x] Documentation Update
### What problem does this PR solve?
Fix: The agent is embedded in the webpage; interrupting its operation
will redirect to the login page. #12697
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Summary
Fixes the initial enabled/disabled state of chat variable checkboxes by
correcting a helper function that previously always returned .
## Problem
in had two statements:
Because of the early , the function always returned , so all chat
variable checkboxes were initially disabled regardless of the field.
This also made the helper inconsistent with , which enables all fields
by default except .
## Fix
Update to use the same condition as :
This ensures:
- All chat variable checkboxes are enabled by default
- remains the only field disabled by default
- Behavior is consistent between the helper and the checkbox map
initialization in .
No API or backend changes are involved; this is a small, isolated
frontend bugfix.
### What problem does this PR solve?
Feat: optimize ingestion pipeline with preprocess
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This PR adds a new guide: **"RAG failure modes checklist"**.
RAG systems often fail in ways that are not immediately visible from a
single metric like accuracy or latency. In practice, debugging
production RAG applications requires identifying recurring failure
patterns across retrieval, routing, evaluation, and deployment stages.
This guide introduces a structured, pattern-based checklist (P01–P12) to
help users interpret traces, evaluation results, and dataset behavior
within RAGFlow. The goal is to provide a practical way to classify
incidents (e.g., retrieval hallucination, chunking issues, index
staleness, routing misalignment) and reason about minimal structural
fixes rather than ad-hoc prompt changes.
The change is documentation-only and does not modify any code or
configuration.
Refs #13138
### Type of change
- [ ] Bug Fix (non-breaking change which fixes an issue)
- [ ] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
- [ ] Refactoring
- [ ] Performance Improvement
- [ ] Other (please describe):
### What problem does this PR solve?
Codecov’s coverage report shows that several RAGFlow code paths are
currently untested or under-tested. This makes it easier for regressions
to slip in during refactors and feature work.
This PR adds targeted automated tests to cover the files and branches
highlighted by Codecov, improving confidence in core behavior while
keeping runtime functionality unchanged.
### Type of change
- [x] Other (please describe): Test coverage improvement (adds/extends
unit and integration tests to address Codecov-reported gaps)
### What problem does this PR solve?
Fix: Note component text area does not resize with component #13065
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
User experience enhancement for variable picker in prompt editor:
- Add case-insensitive string search for variables.
- Add basic keyboard navigation in variable picker:
- Hit <kbd>UpArrow</kbd> and <kbd>DownArrow</kbd> for navigating.
- Hit <kbd>Tab</kbd> or <kbd>Enter</kbd> for selecting focused item into
editor.
- Fix unexpectedly inserting invalid variable into editor by hitting
<kbd>Tab</kbd>.
_Note: you still need to pick variables inside secondary menu (agent
structured output, etc.) by using your pointing device. May finish these
later._
### Type of change
- [x] Refactoring
Actual behavior
When using OceanBase as storage, the list_chunk sorting is abnormal. The
following is the SQL statement.
SELECT id, content_with_weight, important_kwd, question_kwd, img_id,
available_int, position_int, doc_type_kwd, create_timestamp_flt,
create_time, array_to_string(page_num_int, ',') AS page_num_int_sort,
array_to_string(top_int, ',') AS top_int_sort FROM
rag_store_284250730805059584 WHERE doc_id = '' AND kb_id IN ('') ORDER
BY page_num_int_sort ASC, top_int_sort ASC, create_timestamp_flt DESC
LIMIT 0, 20
<img width="1610" height="740" alt="image"
src="https://github.com/user-attachments/assets/84e14c30-a97f-4e8f-8c8c-6ccac915d97d"
/>
Co-authored-by: Aron.Yao <yaowei@yaoweideMacBook-Pro.local>
### What problem does this PR solve?
When users start RAGFlow with `docker compose -p <alias>`, Docker
creates volumes prefixed with the alias (e.g., `myproject_mysql_data`).
The migration script (`docker/migration.sh`) previously hardcoded the
`docker_` prefix in volume names, causing backup/restore to silently
skip all volumes for any non-default project name.
This PR adds a `-p <project_name>` option so the script correctly
targets volumes regardless of the Docker Compose project name used.
### 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
- Add `-p <project_name>` flag (default: `docker`) for specifying Docker
Compose project name
- Build volume names dynamically: `${project_name}_${base_name}`
- Update help text with new option documentation and examples
- Show project-aware `docker compose` commands in error messages
- Fix deprecated `docker-compose` to `docker compose` in hints
- Use dynamic step count instead of hardcoded `4`
- Fully backward compatible — existing usage without `-p` works
unchanged
### Usage
```bash
# Existing usage (unchanged)
./migration.sh backup
./migration.sh restore my_backup
# New: custom project name
./migration.sh -p myproject backup
./migration.sh -p myproject restore my_backup
```
### What problem does this PR solve?
Fix authorization bypass (IDOR) in `/v1/document/web_crawl` allows
Cross-Tenant Dataset Modification.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
The RDBMS (MySQL/PostgreSQL) connector generates document filenames
using the first 100 characters of the content column
(semantic_identifier). When the content contains newline characters
(\n), the resulting filename includes those newlines — for example:
Category: غير صحيح كليًا\nTitle: تفنيد حقائق....txt
RAGFlow's filename_type() function uses re.match(r".*\.txt$", filename)
to detect file types, but .* does not match newline characters by
default in Python regex. This causes the regex to fail, returning
FileType.OTHER, which triggers:
pythonraise RuntimeError("This type of file has not been supported
yet!")
As a result, all documents synced via the MySQL/PostgreSQL connector are
silently discarded. The sync logs report success (e.g., "399 docs
synchronized"), but zero documents actually appear in the dataset. This
is the root cause of issue #13001.
Root cause trace:
rdbms_connector.py → _row_to_document() sets semantic_identifier from
raw content (may contain \n)
connector_service.py → duplicate_and_parse() uses semantic_identifier as
the filename
file_service.py → upload_document() calls filename_type(filename)
file_utils.py → filename_type() regex .*\.txt$ fails on newlines →
returns FileType.OTHER
upload_document() raises "This type of file has not been supported yet!"
Fix: Sanitize the semantic_identifier in _row_to_document() by replacing
newlines and carriage returns with spaces before truncating to 100
characters.
Relates to: #13001, #12817
Type of change
Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Ahmad Intisar <ahmadintisar@Ahmads-MacBook-M4-Pro.local>
