paper-qa

paper-qa copied to clipboard

How to disable model cost computation?

3

Hi, I am running paper-qa with a local LLM served by ollama server, following configuration described in #582. I get several message `Could not find cost for model ollama/llama3.2` which...

gdurif

Using paper-qa with GROQ LLMs ?

2

I would like to use paper-qa with GROQ LLMs. Is this possible and if so, how exactly to do that? For reference see: https://console.groq.com/docs/models Etc. Also for Python code examples...

jbdatascience

How adding papers to index manually

8

Hi, A code snippet is provided in PaperQA' documentation to create a reusable documents index : ``` import os from paperqa import Settings from paperqa.agents.main import agent_query from paperqa.agents.models import...

Snikch63200

Efficiency difference between 'Agentic' and 'Manual' querying

1

Hello, I tried querying the same set of documents with Agentic (https://github.com/Future-House/paper-qa?tab=readme-ov-file#agentic-addingquerying-documents) and Manual (https://github.com/Future-House/paper-qa?tab=readme-ov-file#manual-no-agent-addingquerying-documents) methods. In this issue (https://github.com/Future-House/paper-qa/issues/549) i asked about methods algorithmic behavioural, i understood 'manual' one...

Snikch63200

errors in reading tabular data in PDF breaking qa

1

First, amazing effort. Really appreciate the hard work and making a greatly useful tool. I have a very large PDF (1600 pages) consisting mainly of a table with ~7000 rows...

bgriffen

Using external vector DBs

4

One of my struggle when using PaperQA is the inference time every time I do queries. Is there a means I could do to import external vector DBs rather than...

markokow

As of `paper-qa==5.10.2` we expose the `citation` LLM prompt as a setting in `Settings.parsing.citation_prompt`/`structured_citation_prompt`, but then we hardcode the citation processing for MLA parenthetical in-text citation style: https://github.com/Future-House/paper-qa/blob/v5.10.2/paperqa/docs.py#L296-L326 It would...

jamesbraza

save and import embeddings for faster answer generation

10

Hello, Thank you for the fantastic work on PaperQA. I’ve been able to use it to ask questions by providing over 100 papers as input, and I’ve been using only...

n400peanuts

Our LLM response --> `Context` logic is a bit fragile: - https://github.com/Future-House/paper-qa/issues/747 shows the LLM responding with a float relevance score. - https://github.com/Future-House/paper-qa/issues/736 shows the LLM failing to respond with...

jamesbraza

Fixing the parsing of scientific notation and non-ASCII characters

2

Because PDF encodings are a mess, parsing often leads to poor results with non-ASCII text of all kinds. For example, scientific notation in the form 10^3 is typically parsed as...

loesinghaus