paper-qa
paper-qa copied to clipboard
Future-House
High accuracy RAG for answering questions from scientific documents with citations
Hello, Sometimes, documents that contains images are not recognized as text documents. For this issue, paperqa recommands to disable document checking. `Could not read Auchy les mines (62) - Haisnes-lez-la...
Hi, I've encountered an error when trying to set the 'k' parameter in AnswerSettings. Here's the code I'm using: ```python from paperqa import Settings settings = Settings() settings.answer.answer_max_sources = 3...
Hello, Is there a way to create an embedding model object (with `LiteLLMEmbeddingModel()` i guess) from a locally served embedding model. For more precision I run in parallel : -...
Hello, I wonder why my Doc().query request often achieve random and often poor quality answers i term of relevance. Papers are sometimes relevant sometimes not... Citations are, most of time,...
I am trying to use paper-qa with a locally-hosted model. However, the provided example: ```python from paperqa import Settings, ask local_llm_config = dict( model_list=[ dict( model_name="my_llm_model", litellm_params=dict( model="my-llm-model", api_base="http://localhost:8080/v1", api_key="sk-no-key-required",...
The agent makes decisions based on a pretty sparse state, which has no access to which specific papers are relevant or found. We should try including this in the agent...
Hello, What is the difference between 'ask' function and 'doc.query' function from behavior point of view? Best regards. @dosa.
Hello, I use paperQA with "mixtral-8x7b-instruct-v0.1.Q4_K_M" served locally. This LLM understands French, German, Spanish, Italian, and English. I tested it via browser, it wors well in french. When I use...
When using the `get_doc_details_from_crossref` -- using a title search, even when limited to rows=1 (as is hard coded) will not deterministically return the same DOI for titles with multiple DOIs....
I wanted to confirm the source DOIs can actually be found in an index
Metadata
Owner
Metadata
High accuracy RAG for answering questions from scientific documents with citations