Add READMEs for 5 utility chains (#27)

pull/36/head
Rahul Behal 1 year ago committed by GitHub
parent a10dd86647
commit ec48310da4
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -0,0 +1,13 @@
# BashChain
## Description
The LLMBashChain takes in a task to perform and generates a series of bash commands that will perform the task.
## Chain type
LLMBashChain
## Input Variables
question: a question about how to perform a task in bash.

@ -0,0 +1,13 @@
# LLMCheckerChain
## Description
The LLMCheckerChain is designed to generate better answers to factual questions. The chain works by first generating a draft answer based on the question. The model is then asked to list its assumptions for this statement. The model is then asked to determine whether each assertion is true or false, and explain why if it is false. Finally, the model is prompted to revise their answer based on the above checks and assertions.
## Chain type
LLMCheckerChain
## Input Variables
question: the question to answer

@ -0,0 +1,14 @@
# LLM Math
## Description
A LLMMathChain that uses LLMs and the Python REPL to do complex word math problems.
## Chain type
LLMMathChain
## Input Variables
question: math problem to be solved.

@ -0,0 +1,14 @@
# LLMRequestsChain
## Description
The LLMRequestsChain extracts answers from HTML results from a URL. Given a URL, and a query to extract information from the results, the chain will extract the answer to the query from the text of the results or return "not found" if the information is not contained in the results text.
## Chain type
LLMRequestsChain
## Input Variables
url: URL
query: query to extract information from search results.

@ -0,0 +1,13 @@
# PAL Math Chain
## Description
The PALChain mplements Program-Aided Language Models, as in https://arxiv.org/pdf/2211.10435.pdf. Gives the model examples of math questions sent as text and answers written in Python, then provides the input question to do the same.
## Chain type
PALChain
## Input Variables
question: a math problem in plain text
Loading…
Cancel
Save