### What problem does this PR solve?
Fix: the input length exceeds the context length #10750
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
This commit removes the Youdao and BAAI entries from the LLM factories
configuration as they are no longer needed or supported.
### Type of change
- [x] Config update
### What problem does this PR solve?
Allow initialize Redis without password.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
- Add time utilities and unit tests
### Type of change
- [x] Refactoring
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
- rename rmSpace to remove_redundant_spaces
- move clean_markdown_block to common module
- add unit tests for remove_redundant_spaces and clean_markdown_block
### Type of change
- [x] Refactoring
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fixed the bug that the "dataset_ids" field will not be updated if an
empty array is passed when updating the assistant
### Type of change
- [*] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Introduced gpu profile in .env
Added Dockerfile_tei
fix datrie
Removed LIGHTEN flag
### Type of change
- [x] Documentation Update
- [x] Refactoring
### What problem does this PR solve?
Fix: can't upload image in ollama model #10447
### Type of change
- [X] Bug Fix (non-breaking change which fixes an issue)
### Change all `image=[]` to `image = None`
Changing `image=[]` to `images=None` avoids Python’s mutable default
parameter issue.
If you keep `images=[]`, all calls share the same list, so modifying it
(e.g., images.append()) will affect later calls.
Using images=None and creating a new list inside the function ensures
each call is independent.
This change does not affect current behavior — it simply makes the code
safer and more predictable.
把 `images=[]` 改成 `images=None` 是为了避免 Python 默认参数的可变对象问题。
如果保留 `images=[]`，所有调用都会共用同一个列表，一旦修改就会影响后续调用。
改成 None 并在函数内部重新创建列表，可以确保每次调用都是独立的。
这个修改不会影响现有运行结果，只是让代码更安全、更可控。
### What problem does this PR solve?
Feat: Make knowledge base renaming automatically reflected in agent
discussions, solved #10597
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Support attribute filtering #8703
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
Co-authored-by: writinwaters <cai.keith@gmail.com>
### What problem does this PR solve?
Fix: Remove pdf embed support, update based on #10635
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
File: Now parsing support all types of embedded documents, solved #10059
Fix: Incomplete words in chat #10530
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: add forgot password reset (update naming style), solve #8547
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
## What problem does this PR solve?
Fixes the PostgreSQL connection error that prevents RAGFlow from
starting:
peewee.ProgrammingError: invalid dsn: invalid connection option
"max_retries"
## Problem Analysis
The `BaseDataBase` class in `api/db/db_models.py` adds `max_retries` and
`retry_delay` to the database configuration dict before passing it to
the database connection constructor.
- **MySQL**: Has `RetryingPooledMySQLDatabase` class that properly
extracts these custom parameters using `kwargs.pop()` before calling the
parent constructor
- **PostgreSQL**: Was using the base `PooledPostgresqlDatabase` class
which passes all parameters directly to `psycopg2.connect()`, which
doesn't recognize `max_retries` as a valid connection option
## Solution
Created `RetryingPooledPostgresqlDatabase` class that:
- Extracts `max_retries` and `retry_delay` parameters before
initialization
- Implements retry logic with exponential backoff for connection
failures
- Handles PostgreSQL-specific connection errors (connection refused,
server closed, etc.)
- Mirrors the existing `RetryingPooledMySQLDatabase` implementation
Updated the `PooledDatabase` enum to use the new retrying class for
PostgreSQL.
## Benefits
✅ Prevents invalid connection parameters from being passed to psycopg2
✅ Adds automatic retry logic for PostgreSQL connection failures
✅ Provides better error logging for PostgreSQL-specific issues
✅ Maintains consistency between MySQL and PostgreSQL database handling
## Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
## Testing
Tested with PostgreSQL database configuration and verified:
- Server starts without the "invalid dsn" error
- Database connections are established successfully
- Retry logic works correctly on connection failures
Co-authored-by: Andrea Bugeja <andrea.bugeja@gig.com>
### What problem does this PR solve?
Feat: add forgot password reset, solve #8547
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
issue:
[#5787](https://github.com/infiniflow/ragflow/issues/5787)
change:
Support Specifying OpenRouter Model Provider
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Improve file management. #10287.
Passed tests:
1. Create folder `A` and `B`.
2. Upload a file inside `A`, called `file`.
3. Create a KB, called `K`.
3. Link `file` to `K`.
4. Parse `file` inside of `K`. (OK)
5. Move `file` from `A` to `B`.
6. Parse `file` inside of `K`. (OK)
7. Move `file` from `B` to `A`.
8. Parse `file` inside of `K`. (OK)
9. Move entire folder `A` into `B`. (B -> A -> file)
10. Parse `file` inside of `K`. (OK)
11. Delete folder `B`.
12. All clear. (There is no document inside of `K`)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
issue:
[#10296](https://github.com/infiniflow/ragflow/issues/10296)
change:
- ExeSQL: support connecting to Trino.
- Validation: password can be empty only when db_type === "trino";
all other database types keep the existing requirement (non-empty).
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Maintain backward compatibility for KB tasks
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Google Cloud model does not work correctly with gemini-2.5 models
Close#10408
### 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?
Fix: Fixed the issue where swagger apidocs could not be opened
properly(#9522)
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: virgilwong <hyhvirgil@gmail.com>
### What problem does this PR solve?
Feat: add total in List dataset API, solved #10360
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
- Admin service support SHOW SERVICE <id>.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
issue: #10241
### What problem does this PR solve?
Unexpected operation of document management.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
- Admin client support drop user.
Issue: #10241
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
