branch: externals/llm
commit 3919b77383324173dcff352c506112fee903a646
Author: Andrew Hyatt <[email protected]>
Commit: Andrew Hyatt <[email protected]>
Implement confusion and typos in README.org
This fixes the problems noted in https://github.com/ahyatt/llm/pull/1 by
https://github.com/tvraman.
---
README.org | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/README.org b/README.org
index ee764e5d80..dea73f1a66 100644
--- a/README.org
+++ b/README.org
@@ -1,8 +1,8 @@
#+TITLE: llm package for emacs
-This is a library for interfacing with Large Language Models. It allows elisp
code to use LLMs, but gives the user an option to choose which LLM they would
prefer. This is especially useful for LLMs, since there are various
high-quality ones that in which API access costs money, as well as locally
installed ones that are free, but of medium quality. Applications using LLMs
can use this library to make sure their application works regardless of whether
the user has a local LLM or is p [...]
+This is a library for interfacing with Large Language Models. It allows elisp
code to use LLMs, but allows gives the end-user an option to choose which LLM
they would prefer. This is especially useful for LLMs, since there are various
high-quality ones that in which API access costs money, as well as locally
installed ones that are free, but of medium quality. Applications using LLMs
can use this library to make sure their application works regardless of whether
the user has a local [...]
-The functionality supported by LLMs is not completely consistent, nor are
their APIs. In this library we attempt to abstract functionality to a higher
level, because sometimes those higher level concepts are supported by an API,
and othertimes they must be put in more low-level concepts. Examples are an
example of this; the GCloud Vertex API has an explicit API for examples, but
for Open AI's API, examples must be specified by modifying the sytem prompt.
And Open AI has the concept of [...]
+The functionality supported by LLMs is not completely consistent, nor are
their APIs. In this library we attempt to abstract functionality to a higher
level, because sometimes those higher level concepts are supported by an API,
and othertimes they must be put in more low-level concepts. One such
higher-level concept is "examples" where the client can show example
interactions to demonstrate a pattern for the LLM. The GCloud Vertex API has
an explicit API for examples, but for Open AI [...]
Some functionality may not be supported by LLMs. Any unsupported
functionality with throw a ='not-implemented= signal.