Welcome to RECAPS, a cutting-edge research copilot designed to revolutionize the way researchers approach complex questions and collaborate on projects. Our goal is to streamline the research process by leveraging Large Language Models, advanced algorithms/prompting techniques, and natural language processing techniques to generate a comprehensive and intuitive representation of research findings.
-
Recursive Question Subdivision: RECAPS intelligently breaks down research questions into smaller, manageable sub-questions, allowing for a more focused and efficient exploration of the problem space.
-
Candidate Solution Proposal: By analyzing the sub-questions, RECAPS proposes potential solutions, helping researchers identify promising avenues for further investigation.
-
Directed Acyclic Graph (DAG) Representation: The system organizes the propositions into a DAG, where each node represents an answer to a sub-research question. This visual representation provides a clear overview of the research landscape and helps identify connections between different aspects of the problem.
-
Bidirectional Graph Building: RECAPS can construct the DAG from both ends, either by recursively subdividing the research question or by cumulatively building propositions from the ground up. This flexibility allows researchers to approach the problem from multiple angles and gain a comprehensive understanding of the subject matter.
-
Document-Based Proposition Synthesis: Given a set of documents relevant to the research question, RECAPS can extract and synthesize information to generate propositions. This feature enables researchers to leverage existing knowledge and incorporate it seamlessly into their research.
-
Collaborative Research Platform: The DAG representation serves as a foundation for effective collaboration among researchers. By sharing and contributing to the same project, team members can work together to refine propositions, identify gaps in knowledge, and ultimately reach a well-supported conclusion.
To get started with RECAPS, follow these steps:
- Clone the repository:
git clone https://github.com/ReLink-Inc/RECAPS.git - Install the required dependencies:
pip install -r requirements.txt - Prepare your research documents and organize them in the designated folder.
- Run the main script:
python main.py - Interact with the RECAPS interface to input your research question and explore the generated propositions and DAG.
For detailed usage instructions and API documentation, please refer to the wiki.
We welcome contributions from the research community to enhance RECAPS and make it an even more powerful tool for research exploration and collaboration. If you'd like to contribute, please follow our contribution guidelines and submit a pull request.
RECAPS is released under the MIT License.
If you have any questions, suggestions, or feedback, please feel free to reach out to us at [email protected] or open an issue on the GitHub repository.
Join us in revolutionizing the way we conduct research and collaborate with RECAPS!