paper-qa
paper-qa copied to clipboard
Future-House
High accuracy RAG for answering questions from scientific documents with citations
system prompts now have format called on them, which means if there are curly braces, like for explaining json, they can inadvertently be formatted. We don't really expect system prompts...
Hello, I wondered what is recommended way to use local markdown files with paperqa. Looking at [readers.py](https://github.com/Future-House/paper-qa/blob/HEAD/paperqa/readers.py#L287) it seems markdown is threated as code, so one would have to generate...
Hi there, I've just installed Paper-QA2 and tried to test it with CLI. By asking a simple question I run into UnicodeDecodeError. The same error happened when I tried to...
Paper QA2 for clinical trials does not revert any answers for questions like this : What are the major adverse events observed in case of wegovy drug?
The line `text = page.get_text("text", sort=True)` in `readers.py` doesn't respect multiple columns. For example, applied to pasa.pdf (in tests/stub_data), the first line of text is extracted as "We introduce PaSa,...
In readers.py, the text extracted from multi-column pdf documents doesn't respect columns, i.e., the text continues across columns. To fix this, the following line: ```python text = page.get_text("text", sort=True) ```...
``I got 800 papers and I want the paperqa can read most of them to give me a answer. But the paperqa usually answer that with less than 30 paper...
Seen in [this CI run](https://github.com/Future-House/paper-qa/actions/runs/14201198722/job/39788349395?pr=930): ```none [INFO] Installing environment for https://github.com/renovatebot/pre-commit-hooks. [INFO] Once installed this environment will be reused. [INFO] This may take a few minutes... An unexpected error has...
At present, paper-qa seems to create indices indexed by file path. For example, renaming the root document directory for `papers` to `papers2` causes paper-qa to treat all files inside as...
Hi, Thanks for putting together this very compelling tooling. I was hoping to ask a few specific questions about what is going on to make sure that everything is working...
Metadata
Owner
Metadata
High accuracy RAG for answering questions from scientific documents with citations