Add test for document (#3548)

Ensure LIGHTEN work (#3542)

Fix bugs (#3535)

New: a new interpretor based on Andrew Ng theory. (#3532)

Fix: authorization issue (#3530)

Removed beartype (#3528)

Warning instead of exception on type mismatch (#3523)

Fix: potential risk (#3515)

fix: keyerror issue (#3512)

add input variables to begin component (#3498)

Add api for sessions and add max_tokens for tenant_llm (#3472)

Fix logs. Use dict.pop instead of del. Close #3473 (#3484)

Introduced beartype (#3460)

Added LocalAI support for rerank models (#3446)

Remove unused code (#3448)

Adjusted heartbeat format (#3459)

enlarge the default token length of RAPTOR summarization (#3454)

handle_task catch all exception (#3441)

Move settings initialization after module init phase (#3438)

refine the message of queuing a task (#3437)

Enlarge the term weight difference (#3435)

Rework task executor heartbeat (#3430)

Remove unused settings (#3427)

Print configs when startup RAGFlow server (#3414)

Update version display on web UI (#3405)

Use consistent log file names, introduced initLogger (#3403)

Updates on parsing progress, including more detailed time cost inform… (#3402)

Print version when RAGFlow server startup (#3393)

fix: standardize property name from 'chat' to 'chat_id' (#3383)

resolve halt while starting up (#3397)

fix bug about fetching knowledge graph (#3394)

Add enviroment validation at server startup phase (#3388)

adapt to lower case cohere (#3392)

Added doc for switching elasticsearch to infinity (#3370)

set DLA active for KG (#3386)

refine the error message (#3382)

mv service_conf.yaml to conf/ and fix: add 'answer' as a parameter to 'generate' (#3379)

Turn the relative date in question to absolute date (#3372)

Refine english synonym (#3371)

Rework logging (#3358)

Fix bugs in api and add examples (#3353)

Integration with Infinity (#2894)

Miscellaneous edits to RAGFlow's UI (#3337)

trival (#3325)

Fix typo (#3319)

Fix:#3230 When parsing a docx file using the Book parsing method, to_page is always -1, resulting in a block count of 0 even if parsing is successful (#3249)

Update authorization for team (#3262)

fix: improve embedding model validation logic for dataset operations (#3235)

add inputs to display to every components (#3242)

Add sdk for Agent API (#3220)