ChatResearch is a tool that uses OpenAI's GPT-3 to accelerate your research. It provides several features such as generating summary papers, fetching and summarizing papers from arxiv and bioarxiv, generating responses for review comments, and more.
There have been countless projects and research initiatives in the field of ChatGPT, but none have fulfilled my particular needs. Consequently, I have made the decision to develop my own project. I am committed to continuously refining and improving this project. Your support and ratings are greatly appreciated, so please do not hesitate to leave a star. I also welcome any suggestions, proposals, and pull requests.
- Multi thread and Asynchronous support has been added.
- GIFs have been added for documentation.
- Config can now be used to set key.
- Output for Latex and PDF is now supported.
- Multi thread and Asynchronous support
- Add GIF for document
- Use config to set key
- Support output for Latex and PDF
- Fine-tune prompt
- Generate Image
- Add RSS support for multiple journal
- Revise help message
- add classic paper as examples
- Chat Config: Generate
chatre.toml
in current working directory or set environment variableOPENAI_API_KEY
. - Chat Paper: Fetch or summary paper from local or arxiv with specified query, research fields, and language.
- Chat Biorxiv: Fetch and summary paper from bioarxiv with specified category, filter keys, and language.
- Chat Reviewer: Generate summary paper with specified research fields and language.
- Chat Response: Generate response for review comment with specified language.
- Markdown, PDF, and Latex
pip install chat-research
❯ chatre config
It will generate chatre.toml
in current working directory. Otherwise,
setting environment variable OPENAI_API_KEY
is another way to config API KEY.
Also, chatre config set OPENAI_API_KEY=sk-key
will create configuration file
in current file directory and set your key as sk-key
.
[OpenAI]
OPENAI_API_KEYS = [ "sk-key1", "sk-key2",]
[Gitee]
api = "your_gitee_api"
owner = "your_gitee_name"
repo = "your_repo_name"
path = "files_name_in_your_repo"
> chatre reviewer -h
usage: chatre reviewer [-h] --paper-path [--file-format] [--review-format] [--research-fields] [--language]
optional arguments:
-h, --help show this help message and exit
--paper-path path of papers
--file-format output file format (default: txt)
--review-format review format
--research-fields the research fields of paper (default: computer science, artificial intelligence and reinforcement learning)
--language output language, en or zh (default: en)
This project is licensed under the MIT License - see the LICENSE file for details.
- Yangyang Li