20 Commits

Author SHA1 Message Date
Kevin Hu
297b2d0ac9
force eml file to be parsed by EMAIL (#2615)
### What problem does this PR solve?
#2613
### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-09-27 10:29:30 +08:00
Fachuan Bai
422c229e52
Storage: Rename all the variables about get file to storage from minio. (#2497)
https://github.com/infiniflow/ragflow/issues/2496

### 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

- [ ] 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):
2024-09-19 19:19:27 +08:00
Fachuan Bai
8dd3adc443
Storage: Support the s3, azure blob as the object storage of ragflow. (#2278)
### What problem does this PR solve?

issue: https://github.com/infiniflow/ragflow/issues/2277

_Briefly describe what this PR aims to solve. Include background context
that will help reviewers understand the purpose of the PR._

### 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):

Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-09-09 09:41:14 +08:00
黄腾
ede733e130
add support for eml file parser (#1768)
### What problem does this PR solve?

add support for eml file parser
#1363

### Type of change

- [x] New Feature (non-breaking change which adds functionality)

---------

Co-authored-by: Zhedong Cen <cenzhedong2@126.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
2024-08-06 16:42:14 +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
H
ac7a0d4fbf
Add ParsertType Audio (#1637)
### What problem does this PR solve?

#1514 

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-22 19:17:30 +08:00
cecilia-uu
4df75ca84e
API: Stop parsing (#1556)
### What problem does this PR solve?

Aims to stop the process of parsing.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-17 17:07:33 +08:00
cecilia-uu
9e1421b77c
API Documentation (#1526)
### What problem does this PR solve?

Adds the doc for the newly added API method.

### Type of change


- [x] Documentation Update
2024-07-16 18:07:17 +08:00
cecilia-uu
1a6bd437f5
API: show status of parsing (#1504)
### What problem does this PR solve?

show status of parsing.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-15 17:18:44 +08:00
cecilia-uu
2c2b2e0779
API: start parsing (#1377)
### What problem does this PR solve?

Make the document start parsing.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-11 18:19:18 +08:00
cecilia-uu
306108fe0e
API: Download doc api (#1354)
### What problem does this PR solve?

Adds download_document api

### Type of change


- [x] New Feature (non-breaking change which adds functionality)
2024-07-04 16:33:55 +08:00
cecilia-uu
1defc83506
API: create update_doc method (#1341)
### What problem does this PR solve?

Adds the API method of updating documents.


### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-03 15:14:34 +08:00
cecilia-uu
b5389f487c
API: created list_doc (#1327)
### What problem does this PR solve?

Adds the api of listing documentation.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-07-01 18:15:00 +08:00
cecilia-uu
f6ae8fcb71
API: upload document api (#1264)
### What problem does this PR solve?

API: Adds the feature of uploading document.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-06-25 12:16:28 +08:00
cecilia-uu
5ec19b5f53
created get_dataset, update_dataset API and fixed: delete (#1201)
### What problem does this PR solve?

Added get_dataset and update_dataset API.
Fixed delete_dataset.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
2024-06-19 18:01:38 +08:00
cecilia-uu
8d667d5abd
fixed: duplicate name (#1202)
### What problem does this PR solve?

Duplicate method name.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
2024-06-18 16:28:46 +08:00
cecilia-uu
d9a9be4b4c
added documentation for api and fixed: duplicate get_dataset() (#1190)
### What problem does this PR solve?

Added the documentation for api and fixed duplicate get_dataset()
methods.

### Type of change

- [x] Bug Fix (non-breaking change which fixes an issue)
- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update
2024-06-17 17:54:06 +08:00
cecilia-uu
6be3626372
delete_dataset method and tests created (#1186)
### What problem does this PR solve?

This PR have completed both HTTP API and Python SDK for
'delete_dataset". In addition, there are tests for it.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-06-17 15:10:05 +08:00
cecilia-uu
1eb4caf02a
create list_dataset api and tests (#1138)
### What problem does this PR solve?

This PR have completed both HTTP API and Python SDK for 'list_dataset".
In addition, there are tests for it.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
2024-06-17 12:19:05 +08:00
Jin Hai
cf2f6592dd
API: create dataset (#1106)
### What problem does this PR solve?

This PR have finished 'create dataset' of both HTTP API and Python SDK.
HTTP API:
```
curl --request POST --url http://<HOST_ADDRESS>/api/v1/dataset   --header 'Content-Type: application/json' --header 'Authorization: <ACCESS_KEY>' --data-binary '{
  "name": "<DATASET_NAME>"
}'
```

Python SDK:
```
from ragflow.ragflow import RAGFLow
ragflow = RAGFLow('<ACCESS_KEY>', 'http://127.0.0.1:9380')
ragflow.create_dataset("dataset1")

```

TODO: 
- ACCESS_KEY is the login_token when user login RAGFlow, currently.
RAGFlow should have the function that user can add/delete access_key.

### Type of change

- [x] New Feature (non-breaking change which adds functionality)
- [x] Documentation Update

---------

Signed-off-by: Jin Hai <haijin.chn@gmail.com>
2024-06-11 11:16:37 +08:00