Replaced pypi.tuna.tsinghua.edu.cn with mirrors.aliyun.com/pypi (#5309)
### What problem does this PR solve?
Replaced pypi.tuna.tsinghua.edu.cn with mirrors.aliyun.com/pypi.
I notice aliyun.com sometimes is much faster than tsinghua.edu.
### Type of change
- [x] Refactoring
### What problem does this PR solve?
Feat: Render agent details #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: Render operator menu by category. #3221 (#5302)
### What problem does this PR solve?
Feat: Render operator menu by category. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Feat: Disable Max_token by default #5283
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: Add PageHeader to DatasetWrapper #3221 (#5284)
### What problem does this PR solve?
Feat: Add PageHeader to DatasetWrapper #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Refactor rerank model with dynamic batch processing and memory manage… (#5273)
…ment
### What problem does this PR solve?
Issue：https://github.com/infiniflow/ragflow/issues/5262
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
### What problem does this PR solve?
Partitions the upload of documents in parts of 20 to avoid the size
limit error. Allows uploading 100s of documents on a single interaction.
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
This pull request includes changes to the initialization logic of the
`ChatModel` and `EmbeddingModel` classes to enhance the handling of AWS
credentials.
Use cases:
- Use env variables for credentials instead of managing them on the DB
- Easy connection when deploying on an AWS machine
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
Add configuration to choose default llm models (#5245)
### What problem does this PR solve?
This pull request includes changes to the `api/settings.py` and
`docker/service_conf.yaml.template` files to add support for default
models in the LLM configuration (specially for LIGHTEN builds). The most
important changes include adding default model configurations and
updating the initialization settings to use these defaults.
For example:
With this configuration Bedrock will be enable by default with claude
and titan embeddings.
```
user_default_llm:
factory: 'Bedrock'
api_key: '{}'
base_url: ''
default_models:
chat_model: 'anthropic.claude-3-5-sonnet-20240620-v1:0'
embedding_model: 'amazon.titan-embed-text-v2:0'
rerank_model: ''
asr_model: ''
image2text_model: ''
```
### Type of change
- [X] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Support downloading models from ModelScope Community. (#5073)
This PR supports downloading models from ModelScope. The main
modifications are as follows:
-New Feature (non-breaking change which adds functionality)
-Documentation Update
---------
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
### What problem does this PR solve?
Feat: Add RAGFlowSelect component #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix session.ask return generator bug when stream=False on python sdk (#5209)
add non-stream mode support to session.ask function
### What problem does this PR solve?
same as title, I do not know why the stream=False is not work on the
server side also, when stream=False, the response in the
session._ask_chat is a fully connnected SSE string.
This is a quick fix on the sdk side to make the response format align
with API docs
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
Feat: Add AgentTemplates component. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Optimized Recognizer.sort_X_firstly and Recognizer.sort_Y_firstly (#5182)
### What problem does this PR solve?
Optimized Recognizer.sort_X_firstly and Recognizer.sort_Y_firstly
### Type of change
- [x] Performance Improvement
### What problem does this PR solve?
Feat: Add SearchPage component. #3221
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: Add reasoning item to chat configuration modal #5173 (#5177)
### What problem does this PR solve?
Feat: Add reasoning item to chat configuration modal #5173
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Fix: Normalize embedding model ID comparison across datasets (#5169)
Modify embedding model ID comparison to remove vendor suffixes, ensuring
consistent model identification when working with multiple knowledge
bases. This change affects dialog creation, chat operations, and
document retrieval test functions.
### What problem does this PR solve?
resolve this bug: https://github.com/infiniflow/ragflow/issues/5166
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Feat: Show formulas when answering, show reference labels in style, remove cursor flashing effect. #5173 (#5174)
### What problem does this PR solve?
Feat: Show formulas when answering, show reference labels in style,
remove cursor flashing effect. #5173
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### What problem does this PR solve?
Right now we cannot embed a chat in website when it has variables in the
begin component.
This PR tries to read the variables values from the query string via a
data_ prefixed variable.
#5016
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: gstrat88 <gstrat@innews.gr>
Fix: Improve message input handling with Shift+Enter support (#5129)
### What problem does this PR solve?
just resolve issue： [Improve message input handling with Shift+Enter
support](https://github.com/infiniflow/ragflow/issues/5116)
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Feat: Add insert variable icon in the header of prompt editor. #4764 (#5142)
### What problem does this PR solve?
Feat: Add insert variable icon in the header of prompt editor. #4764
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Docs: Add note about docker volume deletion in README files，will be more novice-friendly (#5133)
### What problem does this PR solve?
Docs: Add note about docker volume deletion in README files
refer to this question:
https://github.com/infiniflow/ragflow/issues/5132
### Type of change
- [x] Documentation Update
---------
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Co-authored-by: writinwaters <93570324+writinwaters@users.noreply.github.com>
### What problem does this PR solve?
Feat: Support preview of HTML files #5096
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: Allow the Rewrite operator to connect to the Generate operator #1739 (#5128)
### What problem does this PR solve?
Feat: Allow the Rewrite operator to connect to the Generate operator
#1739
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Feat: Add support for document meta fields update through api (#5120)
### What problem does this PR solve?
add support for update document meta data through api
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
Co-authored-by: wenju.li <wenju.li@deepctr.cn>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
Zhichang Yu
balibabu
writinwaters
Kevin Hu
liwenju0
Omar Leonardo Sanchez Granados
yrk111222
davidche
Vela-zz
gstrat88