Archives
/
langchain-hub
mirror of https://github.com/hwchase17/langchain-hub
2
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
master
harrison/tracing-docs
harrison/hello-world
readme-update
harrison/update-readmes
prompts
harrison/add-usage-readmes
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from 'master'
${ noResults }
langchain-hub/prompts/qa/refine
History
Anonymous 48989e6a0c update readmes 1 year ago
..
README.md update readmes 1 year ago
basic.json Added more prompts 1 year ago

README.md

Description of QA Refine Prompts

Prompts designed to be used to refine original answers during question answering chains using the refine method.

Inputs

This is a description of the inputs that the prompt expects.

  1. question: Original question to be answered.
  2. existing_answer: Existing answer from previous documents.
  3. context_str: New piece of context to use to refine the existing answer.

Usage

Below is a code snippet for how to use the prompt.

from langchain.prompts import load_prompt
from langchain.chains.question_answering import load_qa_chain

llm = ...
prompt = load_prompt('lc://prompts/qa/refine/<file-name>')
chain = load_qa_chain(llm, chain_type="refine", refine_prompt=prompt)