paper-qa

paper-qa copied to clipboard

This PR contains the following updates: | Update | Change | |---|---| | lockFileMaintenance | All locks refreshed | 🔧 This Pull Request updates lock files to use the latest...

renovate[bot]

model for llama.cpp

1

About your locally hosted example ``` 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://127.0.0.1:8080/", api_key="sk-no-key-required", temperature=0.1, frequency_penalty=1.5, max_tokens=512, ), ) ] ) answer =...

Pellarin

API issues

2

from paperqa import Settings, ask import os os.environ["OPENAI_API_KEY"] = "EMPTY" local_llm_config = { "model_list": [ { "model_name": "ollama/llama3", "litellm_params": { "model": "ollama/llama3", "api_base": } } ] } answer = ask(...

FahaxikiHoney

No module named 'paperqa.version'

4

Why show “ModuleNotFoundError: No module named 'paperqa.version' “

SURUIYUAN

See PR title

jamesbraza

Pinpoint raw evidence chunks

1

I want to be able to pinpoint the exact sentence(s) in a document where data was extracted from so that I can cross-check for accuracy. `answer.context()` gives summarized chunks (after...

athena-yao

Add rate limits for LLMs and Embedding Models

2

LiteLLM's rate limits weren't suitable for PaperQA in that we wanted rate limits that could span models. This PR adds them in with both an in-memory based rate limiter, as...

mskarlin

It's good to keep our configs DRY because it enables updated defaults to apply to all configs, without doing anything

jamesbraza

How to skip the semantic and corssfy api Request

4

hi there . i have question for you . due my country restriction i can't get semantic or crossfy api . is there way that in that i cant deactivated...

MrAlishr

Cannot use "mixtral-8x7b-instruct-v0.1.Q4_K_M" as local LLM

1

Hello, I'm trying to use paper-qa with a "mixtral-8x7b-instruct-v0.1.Q4_K_M" on a local network. The LLM executable llamafile is launched with "-cb -np 4 -a my-llm-model --embedding" options as described in...

Snikch63200