primeqa
The prime repository for state-of-the-art Multilingual Question Answering research and development.
APACHE-2.0 License
Published by bhavani105 over 1 year ago
DocumentCollection Util
Bug fix reranker component
https://pypi.org/project/primeqa/0.14.5/
Commit: 31f78de
https://pypi.org/project/primeqa/0.14.2/
Generative Readers
Reranker component
UDAPDR
Published by bhavani105 over 1 year ago
Updated default reader model in extractive reader component
"PrimeQA/nq_tydi_sq1-reader-xlmr_large-20221110"
Published by bhavani105 almost 2 years ago
1 Add MRQA preprocessor
2. Simplified run_ir arguments
3. Supporting annotate EM
4. Updates to README to. install faiss from conda
4 Updates to services/README on how to finetune with feedback data
Published by bhavani105 almost 2 years ago
This release adds support for:
- Dense Passage Retrieval (DPR)
- Pipelines and components interface
- gRPC and REST service layer
- Containerize PrimeQA (cpu and gpu)
- MRC training with custom data and feedback data
- Automate documentation build
- Updated PrimeQA logo
Published by bhavani105 almost 2 years ago
This tags the version from which primeqa container is built and made available on docker hub https://hub.docker.com/r/primeqa/services/tags
Published by bhavani105 about 2 years ago
This version includes the following:
- IR via primeqa/ir/run_ir.py script supports dense and sparse retrieval
- MRC via primeqa/mrc/run_mrc.py supports TyDI, SQUAD, MLQA
- TyDIQA support for Boolean Questions
- Question Generation over table and text
- Continuous Integration with GitHub Actions
