Flow Chart
- 2023.12.18 Support download retrieval model from modelscope.
- 2023.12.15 Support api server. tag:#3
- 2023.12.14 Change
model.generate()
tomodel.chat()
. tag:#6 - 2023.12.14 Optimize ECHARTS_PROMPT to improve the success rate of chart rendering. tag:#5
- Support api server #3
Place the retrieval model in the retriever/retriever_model directory. The retrieval model used to train this search engine agent is based on the code from the ToolBench repository. If you are interested in the dataset and training code, you can refer to the source repository. ToolBench/Training Retriever
Model | Download |
---|---|
MrBun/ToolRetrieval_IR_bert_based_chinese | 🤗HuggingFace / ModelScope |
git clone https://github.com/mMrBun/Chat2BI.git
conda create -n Chat2BI python=3.10
conda activate Chat2BI
cd Chat2BI
pip install -r requirements.txt
python web_demo.py
view the web demo at http://127.0.0.1:7860
python api_demo.py
callable api address at http://127.0.0.1:7861