paper-qa icon indicating copy to clipboard operation
paper-qa copied to clipboard

High accuracy RAG for answering questions from scientific documents with citations

Results 248 paper-qa issues
Sort by recently updated
recently updated
newest added

Hi! Thanks for a great project! Would it be possible to add an example to the README of how to use a separate vector database? Thanks!

documentation

Looking at how to convert the langchain Document object to the paper-qa Docs object. Currently, my solution is below. splitter = splitter_type(chunk_size=chunk_size, chunk_overlap=chunk_overlap) docs_split = splitter.split_documents(docs) # docs is langchain...

When I run the huggingface demo locally, I encounter the following problem. `Traceback (most recent call last): File "/Users/mac/miniconda3/lib/python3.11/site-packages/gradio/queueing.py", line 407, in call_prediction output = await route_utils.call_process_api( ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/Users/mac/miniconda3/lib/python3.11/site-packages/gradio/route_utils.py",...

Thank you for your wonderful work. It seems that the current system uses OpenAI's embedding models for dense retrieval, which might be sub-optimal (and costly). We have a biomedical embedding...

https://github.com/whitead/paper-qa/blob/97a99b7f55e88a6c14c1461bf5b7d12f951abf91/paperqa/types.py#L149

When I use Ollama via Langchain I get the error: ``` /paper_searching/env/lib/python3.11/site-packages/langchain/llms/ollama.py:185: RuntimeWarning: coroutine 'AsyncCallbackManagerForLLMRun.on_llm_new_token' was never awaited run_manager.on_llm_new_token( RuntimeWarning: Enable tracemalloc to get the object allocation traceback Traceback (most...

- **My operator sysytem**: Windows 11 -**My code**: ``` from paperqa import Docs path1 = "D:\\testqa.pdf" citation1 = "Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press."...

I just encountered this error on the Hugging Face demo (https://huggingface.co/spaces/whitead/paper-qa) **Runtime error** Space failed. Exit code: 1. Reason: Traceback (most recent call last): File "app.py", line 2, in import...

bug

Hi all, Good day to everyone. One of my students will like to generate output texts and their supporting/accompanying images. Not only the texts or OCR images Also is it...

enhancement

Currently, each document uploaded requires an API call to get embeddings. Due to API rate-limits, this really slows the document adding process for large corpus. This process could be parallelized...