### What problem does this PR solve?
Add GPUStack as a new model provider.
[GPUStack](https://github.com/gpustack/gpustack) is an open-source GPU
cluster manager for running LLMs. Currently, locally deployed models in
GPUStack cannot integrate well with RAGFlow. GPUStack provides both
OpenAI compatible APIs (Models / Chat Completions / Embeddings /
Speech2Text / TTS) and other APIs like Rerank. We would like to use
GPUStack as a model provider in ragflow.
[GPUStack Docs](https://docs.gpustack.ai/latest/quickstart/)
Related issue: https://github.com/infiniflow/ragflow/issues/4064.
### Type of change
- [x] New Feature (non-breaking change which adds functionality)
### Testing Instructions
1. Install GPUStack and deploy the `llama-3.2-1b-instruct` llm, `bge-m3`
text embedding model, `bge-reranker-v2-m3` rerank model,
`faster-whisper-medium` Speech-to-Text model, `cosyvoice-300m-sft` in
GPUStack.
2. Add provider in ragflow settings.
3. Testing in ragflow.
### What problem does this PR solve?
1. Update error message
2. Remove space characters
### Type of change
- [x] Refactoring
---------
Signed-off-by: Jin Hai <haijin.chn@gmail.com>
### What problem does this PR solve?
- Bring `STORAGE_IMPL` back in `rag/svr/cache_file_svr.py`
- Simplify storage connection when working with AWS S3
### Type of change
- [x] Refactoring
Fix some bugs in text2sql.(#4279)(#4281)
### What problem does this PR solve?
- The incorrect results in parsing CSV files of the QA knowledge base in
the text2sql scenario. Process CSV files using the csv library. Decouple
CSV parsing from TXT parsing
- Most llm return results in markdown format ```sql query ```, Fix
execution error caused by LLM output SQLmarkdown format.### Type of
change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
1. Refactor error message
2. Fix knowledges are created on ES and can't be found in Infinity. The
document chunk fetch error.
### Type of change
- [x] Fix bug
- [x] Refactoring
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
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>
### What problem does this PR solve?
Ignore the millisecond and microsecond value.
### Type of change
- [x] Refactoring
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
as title
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
1. Change embedding model of knowledge base won't change the default
embedding model.
2. Retrieval test bug
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
As title
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Signed-off-by: jinhai <haijin.chn@gmail.com>
### What problem does this PR solve?
Fix the issue when retrieving AWS credentials from the S3 configuration
from the settings module instead of getting from the environment
variables.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>
fix chunk method "Table" losing content when the Excel file has multi… (#4123)
…ple sheets
### What problem does this PR solve?
discussed in https://github.com/infiniflow/ragflow/pull/4102
- In excel_parser.py, `total` means the total number of rows in Excel,
but it return in the first iterate, that lead to the wrong `to_page`
- In table.py, it when Excel file has multiple sheets, it will be
divided into multiple parts, every part size is 3000, `data` may be
empty, because it has recorded in the last iterate.
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Fixed infinity exception SCORE() / SCORE_FACTORS() requires Fusion or MATCH TEXT or MATCH TENSOR (#4110)
### What problem does this PR solve?
Fixed infinity exception SCORE() / SCORE_FACTORS() requires Fusion or
MATCH TEXT or MATCH TENSOR. Close #4109
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
### What problem does this PR solve?
1. Fix initial build and load trie
2. Update comment
### Type of change
- [x] Refactoring
Signed-off-by: jinhai <haijin.chn@gmail.com>
Fix rerank_model bug in chat and markdown bug (#4061)
### What problem does this PR solve?
Fix rerank_model bug in chat and markdown bug
#4000#3992
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
---------
Co-authored-by: liuhua <10215101452@stu.ecun.edu.cn>
Kevin Hu
Jin Hai
Alex Chen
Kenny Dizi
Yingfeng
TeslaZY
Zhichang Yu
Bo Liu
ly0303521
liuhua