Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/DAMO-NLP-SG/CoI-Agent
Official code for paper: Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents
https://github.com/DAMO-NLP-SG/CoI-Agent
Last synced: about 2 months ago
JSON representation
Official code for paper: Chain of Ideas: Revolutionizing Research via Novel Idea Development with LLM Agents
- Host: GitHub
- URL: https://github.com/DAMO-NLP-SG/CoI-Agent
- Owner: DAMO-NLP-SG
- License: apache-2.0
- Created: 2024-10-10T09:06:43.000Z (3 months ago)
- Default Branch: main
- Last Pushed: 2024-11-18T03:47:49.000Z (about 2 months ago)
- Last Synced: 2024-11-22T01:06:18.085Z (about 2 months ago)
- Language: Python
- Homepage:
- Size: 576 KB
- Stars: 369
- Watchers: 4
- Forks: 19
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- StarryDivineSky - DAMO-NLP-SG/CoI-Agent - Agent是一个利用大型语言模型（LLM）代理来革新研究的新颖想法开发项目的代码库。该项目基于论文“Chain of Ideas: Revolutionizing Researchvia Novel Idea Development with LLM Agents”，并提供了一个在线演示。用户可以通过输入研究主题，利用CoI-Agent生成新的研究想法。该项目使用SciPDF Parser解析PDF文件，并利用LLM API进行语义搜索和生成。用户需要安装SciPDF Parser、Grobid和配置LLM API密钥才能使用该项目。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
README
Chain-of-Ideas Agent: Revolutionizing Research Via Novel Idea Development with LLM Agents
[[📖 arXiv Paper](https://arxiv.org/pdf/2410.13185)] [[📊 Online Demo](https://huggingface.co/spaces/DAMO-NLP-SG/CoI_Agent)]
## 🔥 News
* **[2024.10.12]** The first version of CoI Agent!
## 🛠️ Requirements and Installation
**Step 1**:
```bash
git clone https://github.com/DAMO-NLP-SG/CoI-Agent.git
cd CoI-Agent
pip install -r requirements.txt
```
**Step 2**:
Install [SciPDF Parser](https://github.com/titipata/scipdf_parser) for PDF parsing.
```bash
git clone https://github.com/titipata/scipdf_parser.git
pip install git+https://github.com/titipata/scipdf_parser
python -m spacy download en_core_web_sm
```
**Step 3**:
Install java for grobid
```bash
wget https://download.oracle.com/java/GA/jdk11/9/GPL/openjdk-11.0.2_linux-x64_bin.tar.gz
tar -zxvf openjdk-11.0.2_linux-x64_bin.tar.gz
export JAVA_HOME=Your_path/jdk-11.0.2
```
**Step 4**:
set config.yaml to use the LLM APIs.
```yaml
# Sementic scholor api, it should be filled
SEMENTIC_SEARCH_API_KEY: ""
is_azure : True # if false, it is openai
# set it if you set is_azure to True
AZURE_OPENAI_ENDPOINT : ""
AZURE_OPENAI_KEY : ""
AZURE_OPENAI_API_VERSION : ""
# set it if you set is_azure to False
OPENAI_API_KEY: ""
OPENAI_BASE_URL: ""
# if not set it will be set to the same as main llm
EMBEDDING_API_KEY: ""
EMBEDDING_API_ENDPOINT: ""
EMBEDDING_MODEL: ""
MAIN_LLM_MODEL: "" # "gpt-4o" or ...
CHEAP_LLM_MODEL: "" # "gpt-4o" or ...
```
## 🚀 Quick Start
**Step 1**: Run grobid
If you can successfully start grobid in [SciPDF Parser](https://github.com/titipata/scipdf_parser.git), run the following commands:
```bash
cd scipdf_parser
bash serve_grobid.sh
```
(Optional) Or, you can refer to the following process to install grobid if the previous commands fail:
```bash
git clone https://github.com/kermitt2/grobid.git
cd grobid
./gradlew clean install
./gradlew run
```
**Step 2**: Generate idea
```python
python main.py --topic {your research topic}
```
## :black_nib: Citation
If you find our work helpful for your research, please consider starring the repo and citing our work.
```bibtex
@article{li2024chain,
title={Chain of Ideas: Revolutionizing Research in Novel Idea Development with LLM Agents},
author={Li, Long and Xu, Weiwen and Guo, Jiayan and Zhao, Ruochen and Li, Xinxuan and Yuan,
Yuqian and Zhang, Boqiang and Jiang, Yuming and Xin, Yifei and Dang, Ronghao and
Rong, Yu and Zhao, Deli and Feng, Tian and Bing, Lidong},
journal={arXiv preprint arXiv:2410.13185},
year={2024},
url={https://arxiv.org/abs/2410.13185}
}
```