https://github.com/curtlab/qretrievalaugmentedgeneration
Userinterface for LLM question-answering on PDF documents
Science Score: 13.0%
This score indicates how likely this project is to be science-related based on various indicators:
-
○CITATION.cff file
-
✓codemeta.json file
Found codemeta.json file -
○.zenodo.json file
-
○DOI references
-
○Academic publication links
-
○Academic email domains
-
○Institutional organization owner
-
○JOSS paper metadata
-
○Scientific vocabulary similarity
Low similarity (9.9%) to scientific vocabulary
Repository
Userinterface for LLM question-answering on PDF documents
Basic Info
- Host: GitHub
- Owner: CURTLab
- License: mit
- Language: C++
- Default Branch: main
- Size: 58.6 KB
Statistics
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
- Releases: 1
Metadata Files
README.md
QRetrievalAugmentedGeneration
Userinterface for LLM question-answering on PDF documents
Overview
QRetrievalAugmentedGeneration is a Qt/C++ project designed to facilitate question-answering tasks on PDF documents. Leveraging the power of language models, particularly Mistral, and retrieval augmented generation techniques, it provides a interface for querying PDF content and references the used sources including page numbers.
Features
- PDF Parsing: The project includes functionality to parse PDF documents stored in the designated data folder.
- Question Generation: Users can prompt questions through the interface.
- Retrieval Augmented Generation: The system utilizes retrieval augmented generation techniques with embedding database to provide context-aware prompts to the language model.
- Language Model Integration: LLM, powered by Ollama, serves as the language model for generating responses with context from the PDFs.
Dependencies
- Qt: The project is built using the Qt framework.
- Ollama: The language model integration is facilitated by Ollama.
- LLMs:
Mistral: Runollama pull mistralandnomic-embed-text: Runollama pull nomic-embed-textin the console
Contributing
Contributions to QRetrievalAugmentedGeneration are welcome! If you have ideas for new features, improvements, or bug fixes, feel free to open an issue or submit a pull request.
License
This project is licensed under the MIT License.
Acknowledgments
The code in this project is inspired by the youtube video: Python RAG Tutorial (with Local LLMs): AI For Your PDFs from pixegami
Owner
- Login: CURTLab
- Kind: user
- Location: Linz, Austria
- Repositories: 3
- Profile: https://github.com/CURTLab