wangzhihong comments

Results 19 comments of


                                            wangzhihong

PIP Error

1. Check your python version（3.9-3.11） 2. Check your pip source 3. Otherwise, you can install lazyllm by: ``` git clone https://github.com/LazyAGI/LazyLLM.git cd LazyLLM pip3 install -r requirements.txt export PYTHONPATH=$PWD:$PYTHONPATH ```

RAG Enhancement

can use https://github.com/fsspec/filesystem_spec to support 2

[Bug] When there are duplicate modules in the pipeline, parameter binding will fail.

when auto-capture is enable, parameter binding will fail too

Optimize Model Path Management

add documents

Couldn‘t find the base_model of "Qwen2.5-VL-3B-Instruct"

https://github.com/LazyAGI/LazyLLM/pull/499

The result data obtained from embedding is 1024-dimensional, and in certain scenarios, ast.literal_eval(result) throws an error. This PR fixes the issue.

pr的标题要改成英文，这样在合并之后，commit message中看起来不会很奇怪

The result data obtained from embedding is 1024-dimensional, and in certain scenarios, ast.literal_eval(result) throws an error. This PR fixes the issue.

execute `python -m flake8` fix these errors: ./lazyllm/tools/rag/doc_impl.py:42:122: E501 line too long (124 > 121 characters) ./lazyllm/tools/rag/doc_impl.py:46:26: E261 at least two spaces before inline comment ./lazyllm/tools/rag/doc_impl.py:47:39: E261 at least two...

The result data obtained from embedding is 1024-dimensional, and in certain scenarios, ast.literal_eval(result) throws an error. This PR fixes the issue.

Error occurs after restarting milvus

Milvus-lite and Milvus do not support using HDDs for storage; only SSDs can be used for mounting.

About milvus: the data type

will be resolved by https://github.com/LazyAGI/LazyLLM/pull/603