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)
### What problem does this PR solve?
ERROR: 'Stream' object has no attribute 'iter_lines' with reference to
Claude/Anthropic chat streams
### Type of change
- [x] Bug Fix (non-breaking change which fixes an issue)
Co-authored-by: Kyle Olmstead <k.olmstead@offensive-security.com>
### 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>
### 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>
