-
### Is there an existing issue for this?
- [ ] I have searched the existing issues
- [ ] I have checked [#657](https://github.com/microsoft/graphrag/issues/657) to validate if my issue is covered by …
-
**Describe the bug**
When cloning this repository on Windows using Git on Windows instead of Git Bash, you'll encounter build errors related to line endings being corrupted in Bash scripts. This prev…
-
When choosing "global", it works well. However, when choosing "local" for any query, it gets below error:
Error: Traceback (most recent call last):
File "/usr/local/conda3/lib/python3.10/runpy.py…
-
### Describe the issue
```
如题：假如我有1w条数据，我这次初始化1w条，下次新增了100条，我要把这批数据重新追加到之前的初始化数据里面做成增量形式。poutut/artifacts 目录目前是一样的路径，测试效果发现，200条会覆盖之前1w条的parquet文件中的内容，想请教下大家，有木有什么方式可以让数据做成增量的形式
```
### Additi…
-
win10
Traceback (most recent call last):
File "E:\Code\Python_Code\chatweb\condaenv\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File …
-
### Describe the bug
- Try to use local model(include qwen2:1.5b and phi3) by ollama instead of GPT4
- Command:`python -m graphrag.index --root ./ragtest`
- When executing `create_final_entities` p…
-
### can not load the txt correctly. need help
I have an right .txt file in the input, but it filtered, why?
File "C:\Users\maoxi\github\miniconda3\envs\finance_bot\Lib\site-packages\graphrag\ind…
-
### Describe the issue
A single api or model can provide just around 100 token/sec max, still too slow if indexing a lot of files. Is it possible we use multiple api to have parallel indexing to spee…
K2559 updated
3 months ago
-
### Is there an existing issue for this?
- [X] I have searched the existing issues
- [ ] I have checked [#657](https://github.com/microsoft/graphrag/issues/657) to validate if my issue is covered by …
-
### What is the issue?
I use the bge-m3 model in graphrag with the following parameters
```
embeddings:
## parallelization: override the global parallelization settings for embeddings
async…