85 Commits

Author SHA1 Message Date
Kevin Hu
6e8d0e3177
Fix: rank feat issue. (#6225)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-18 16:07:29 +08:00
Kevin Hu
1333d3c02a
Fix: float transfer exception. (#6197)
### What problem does this PR solve?

#6177

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-18 11:13:44 +08:00
Kevin Hu
fabc5e9259
Refa: fix re-rank scope. (#6152)
### What problem does this PR solve?

#6140

### Type of change


- [x] Refactoring
2025-03-17 13:26:29 +08:00
Kevin Hu
e5a8b23684
Fix: empty tag field issue. (#6103)
### What problem does this PR solve?

#6102

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-03-14 17:35:57 +08:00
Kevin Hu
7b3d700d5f
Apply agentic searching. (#5196)
### What problem does this PR solve?

#5173

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-02-20 17:41:01 +08:00
ubbg
29a59ed7e2
Fix: Use self.dataStore.indexExist in all_tags method of Dealer (#5108)
### What problem does this PR solve?

This PR fixes an AttributeError in the all_tags method of the Dealer
class. Previously, the method incorrectly called
self.docStoreConn.indexExist instead of self.dataStore.indexExist. Since
self.docStoreConn was never set (and self.dataStore is already
initialized in init), this resulted in an error when attempting to check
if the index exists. This change ensures that the proper connector is
used for the index existence check, thereby resolving the issue._

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-19 11:50:57 +08:00
Kevin Hu
9ff825f39d
Ignore exceptions when no index ahead. (#5047)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2025-02-18 09:09:22 +08:00
Mathias Panzenböck
9bcccadebd
Remove use of eval() from search.py (#4887)
Use `json.loads()` instead.

### What problem does this PR solve?

Using `eval()` can lead to code injections. I think this loads a JSON
field, right? If yes, why is this done via `eval()` and not
`json.loads()`?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-12 13:15:38 +08:00
Kevin Hu
448fa1c4d4
Robust for abnormal response from LLMs. (#4747)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-02-06 17:34:53 +08:00
Kevin Hu
4011c8f68c
Fix potential error. (#4650)
### What problem does this PR solve?
#4622

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-26 12:38:32 +08:00
Kevin Hu
86892959a0
Rebuild graph when it's out of time. (#4607)
### What problem does this PR solve?

#4543

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] Refactoring
2025-01-23 17:26:20 +08:00
Kevin Hu
dd0ebbea35
Light GraphRAG (#4585)
### What problem does this PR solve?

#4543

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-22 19:43:14 +08:00
Kevin Hu
c5da3cdd97
Tagging (#4426)
### What problem does this PR solve?

#4367

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2025-01-09 17:07:21 +08:00
Kevin Hu
d9a4e4cc3b
Fix page size error. (#4401)
### What problem does this PR solve?

#4400

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2025-01-07 19:06:31 +08:00
Bo Liu
321e9f3719
fix: stop rerank by model when search result is empty (#4203)
### What problem does this PR solve?


stop rerank by model when search result is empty, otherwise rerank may
raise an error (qwen).

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)

Co-authored-by: 刘博 <liubo@ynby.cn>
2024-12-24 14:33:46 +08:00
Kevin Hu
c373dba0bc
Fix raptor bug. (#4192)
### What problem does this PR solve?


### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-12-23 18:59:48 +08:00
Kevin Hu
31d67c850e
Fetch chunk by batches. (#4177)
### What problem does this PR solve?

#4173

### Type of change

- [x] Performance Improvement
2024-12-23 12:12:15 +08:00
Kevin Hu
000cd6d615
Fix position lost issue. (#4068)
### What problem does this PR solve?

#4040

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-12-17 16:31:58 +08:00
Zhichang Yu
03f00c9e6f
Rename page_num_list, top_list, position_list (#3940)
### What problem does this PR solve?

Rename page_num_list, top_list, position_list to page_num_int, top_int,
position_int

### Type of change

- [x] Refactoring
2024-12-10 16:32:58 +08:00
Kevin Hu
56f473b680
Feat: Add question parameter to edit chunk modal (#3875)
### What problem does this PR solve?

Close #3873

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-12-05 14:51:19 +08:00
Kevin Hu
74b28ef1b0
Add pagerank to KB. (#3809)
### What problem does this PR solve?

#3794

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-12-03 14:30:35 +08:00
Kevin Hu
0f08b0f053
Weight up title and keywords for chunks in terms of retrieval (#3750)
### What problem does this PR solve?


### Type of change

- [x] Performance Improvement
2024-11-29 16:39:55 +08:00
Zhichang Yu
43e367f2ea
Detect shape error of embedding (#3710)
### What problem does this PR solve?

Detect shape error of embedding. Close #2997

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-11-28 14:10:22 +08:00
Zhichang Yu
bc701d7b4c
Edit chunk shall update instead of insert it (#3709)
### What problem does this PR solve?

Edit chunk shall update instead of insert it. Close #3679 

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-11-28 13:00:38 +08:00
Kevin Hu
9f3141804f
Fix chunk enable/disable issue (#3579)
### What problem does this PR solve?

#3576

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-11-22 12:25:42 +08:00
Kung Quang
568322aeaf
fix(rag): fix error in viewing document chunk and cannot start task_executor server (#3481)
### What problem does this PR solve?

1. Fix error in viewing document chunk

<img width="1677" alt="Pasted Graphic"
src="https://github.com/user-attachments/assets/acd84cde-f38c-4190-b135-5e5139ae2613">

Viewing document chunk details in a BeartypeCallHintParamViolation
error.

Traceback (most recent call last):
File "ragflow/.venv/lib/python3.12/site-packages/flask/app.py", line
880, in full_dispatch_request
    rv = self.dispatch_request()
         ^^^^^^^^^^^^^^^^^^^^^^^
File "ragflow/.venv/lib/python3.12/site-packages/flask/app.py", line
865, in dispatch_request
return self.ensure_sync(self.view_functions[rule.endpoint])(**view_args)
# type: ignore[no-any-return]
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "ragflow/.venv/lib/python3.12/site-packages/flask_login/utils.py",
line 290, in decorated_view
    return current_app.ensure_sync(func)(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "ragflow/api/apps/chunk_app.py", line 311, in knowledge_graph
sres = settings.retrievaler.search(req, search.index_name(tenant_id),
kb_ids)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "<@beartype(rag.nlp.search.Dealer.search) at 0x3381fd800>", line
39, in search
beartype.roar.BeartypeCallHintParamViolation: Method
rag.nlp.search.Dealer.search() parameter
idx_names='ragflow_0e1e67f431d711ef98fc00155d29195d' violates type hint
list[str], as str 'ragflow_0e1e67f431d711ef98fc00155d29195d' not
instance of list.
2024-11-19 11:30:29,817 ERROR 91013 Method
rag.nlp.search.Dealer.search() parameter
idx_names='ragflow_0e1e67f431d711ef98fc00155d29195d' violates type hint
list[str], as str 'ragflow_0e1e67f431d711ef98fc00155d29195d' not
instance of list.
Traceback (most recent call last):
  File "ragflow/api/apps/chunk_app.py", line 60, in list_chunk
sres = settings.retrievaler.search(query, search.index_name(tenant_id),
kb_ids, highlight=True)

^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "<@beartype(rag.nlp.search.Dealer.search) at 0x3381fd800>", line
39, in search
beartype.roar.BeartypeCallHintParamViolation: Method
rag.nlp.search.Dealer.search() parameter
idx_names='ragflow_0e1e67f431d711ef98fc00155d29195d' violates type hint
list[str], as str 'ragflow_0e1e67f431d711ef98fc00155d29195d' not
instance of list.


because in nlp/search.py,the idx_names is only list

<img width="1098" alt="Pasted Graphic 2"
src="https://github.com/user-attachments/assets/4998cb1e-94bc-470b-b2f4-41ecb5b08f8a">

but the DocStoreConnection.search method accept list or str
<img width="1175" alt="Pasted Graphic 3"
src="https://github.com/user-attachments/assets/ee918b4a-87a5-42c9-a6d2-d0db0884b875">


and his implements also list and str
es_conn.py

<img width="1121" alt="Pasted Graphic 4"
src="https://github.com/user-attachments/assets/3e6dc030-0a0d-416c-8fd4-0b4cfd576f8c">

infinity_conn.py

<img width="1221" alt="Pasted Graphic 5"
src="https://github.com/user-attachments/assets/44edac2b-6b81-45b0-a3fc-cb1c63219015">

2. Fix cannot star task_executor server with Unresolved reference
'Mapping'
<img width="1283" alt="Pasted Graphic 6"
src="https://github.com/user-attachments/assets/421f17b8-d0a5-46d3-bc4d-d05dc9dfc934">

### 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):
2024-11-19 14:36:10 +08:00
Zhichang Yu
dec9b3e540
Fix logs. Use dict.pop instead of del. Close #3473 (#3484)
### What problem does this PR solve?

Fix logs. Use dict.pop instead of del.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-11-19 14:15:25 +08:00
Zhichang Yu
4413683898
Introduced beartype (#3460)
### What problem does this PR solve?

Introduced [beartype](https://github.com/beartype/beartype) for runtime
type-checking.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-11-18 17:38:17 +08:00
Zhichang Yu
30f6421760
Use consistent log file names, introduced initLogger (#3403)
### What problem does this PR solve?

Use consistent log file names, introduced initLogger

### Type of change

- [ ] 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):
2024-11-14 17:13:48 +08:00
Zhichang Yu
a2a5631da4
Rework logging (#3358)
Unified all log files into one.

### What problem does this PR solve?

Unified all log files into one.

### Type of change

- [x] Refactoring
2024-11-12 17:35:13 +08:00
Zhichang Yu
f4c52371ab
Integration with Infinity (#2894)
### What problem does this PR solve?

Integration with Infinity

- Replaced ELASTICSEARCH with dataStoreConn
- Renamed deleteByQuery with delete
- Renamed bulk to upsertBulk
- getHighlight, getAggregation
- Fix KGSearch.search
- Moved Dealer.sql_retrieval to es_conn.py


### Type of change

- [x] Refactoring
2024-11-12 14:59:41 +08:00
Kevin Hu
004487cca0
fix term weight issue (#3306)
### What problem does this PR solve?

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-11-08 18:25:23 +08:00
Kevin Hu
2d1fbefdb5
search between multiple indiices for team function (#3079)
### What problem does this PR solve?

#2834 
### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-10-29 13:19:01 +08:00
Kevin Hu
04ff9cda7c
expand rerank range (#2746)
### What problem does this PR solve?


### Type of change

- [x] Performance Improvement
2024-10-08 16:34:33 +08:00
Kevin Hu
ecf441c830
refine using rerank model (#2553)
### What problem does this PR solve?

#2552

### Type of change

- [x] Performance Improvement
2024-09-24 12:38:18 +08:00
Kevin Hu
54342ae0a2
boost highlight performace (#2419)
### What problem does this PR solve?

#2415

### Type of change

- [x] Performance Improvement
2024-09-13 18:10:32 +08:00
Kevin Hu
9d4bb5767c
make highlight friendly to English (#2417)
### What problem does this PR solve?

#2415

### Type of change

- [x] Performance Improvement
2024-09-13 17:03:51 +08:00
Kevin Hu
4730145696
debug backend API for TAB 'search' (#2389)
### What problem does this PR solve?
#2247

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-09-12 17:51:20 +08:00
Kevin Hu
333608a1d4
add search TAB backend api (#2375)
### What problem does this PR solve?
 #2247

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-09-11 19:49:18 +08:00
Kevin Hu
78ed8fe9a5
add doc ids to chat (#1944)
### What problem does this PR solve?

### Type of change

- [x] Performance Improvement
2024-08-14 16:31:49 +08:00
Kevin Hu
43199c45c3
refine loginfo about graprag progress (#1823)
### What problem does this PR solve?



### Type of change

- [x] Refactoring
2024-08-06 16:01:43 +08:00
Kevin Hu
152072f900
Add graphrag (#1793)
### What problem does this PR solve?

#1594

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-08-02 18:51:14 +08:00
KevinHuSh
e35f7610e7
fix too long query exception (#1195)
### What problem does this PR solve?

#1161 
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-06-18 09:50:59 +08:00
Jin Hai
9ed0e50f6b
Update info (#1005)
### 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] Refactoring

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2024-05-31 09:53:04 +08:00
KevinHuSh
614defec21
add rerank model (#969)
### What problem does this PR solve?

feat: add rerank models to the project #724 #162

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-29 16:50:02 +08:00
GYH
be13429d05
Add api/list_kb_docs function and modify api/list_chunks (#874)
### What problem does this PR solve?
#717 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-05-22 14:58:56 +08:00
KevinHuSh
648a2baaa9
fix disabled doc is still retreivalable (#695)
### What problem does this PR solve?

Fix that disabled doc is still retreivalable

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-05-09 15:32:24 +08:00
KevinHuSh
8c07992b6c
refine code (#595)
### What problem does this PR solve?

### Type of change

- [x] Refactoring
2024-04-28 19:13:33 +08:00
KevinHuSh
ed6081845a
Fit a lot of encodings for text file. (#458)
### What problem does this PR solve?

#384

### Type of change

- [x] Performance Improvement
2024-04-19 18:02:53 +08:00
KevinHuSh
d4e0bfc8a5
fix gb2312 encoding issue (#394)
### What problem does this PR solve?

Issue link:#384
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-04-16 19:45:14 +08:00