tristan/gptel
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

gptel: Update docstrings for prompt/response prefixes

Browse source 
README: Mention `gptel-response-prefix-alist`

gptel.el (gptel-prompt-prefix-alist, gptel-response-prefix-alist):
Improve docstring.
This commit is contained in:
Karthik Chikmagalur 2023-12-15 09:42:37 -08:00
parent 644e341244
commit e105a52541
2 changed files with 16 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

15
README.org
View file

@ -305,13 +305,14 @@ These are packages that depend on GPTel to provide additional functionality
| =gptel-temperature= | Randomness in response text, 0 to 2. |
|---------------------------+---------------------------------------------------------------------|
|---------------------------+---------------------------------------------------------------------|
| *Chat UI options* | |
|---------------------------+---------------------------------------------------------------------|
| =gptel-default-mode= | Major mode for dedicated chat buffers. |
| =gptel-prompt-prefix-alist= | Text demarcating queries and replies. |
|---------------------------+---------------------------------------------------------------------|
|-----------------------------+----------------------------------------|
| *Chat UI options* | |
|-----------------------------+----------------------------------------|
| =gptel-default-mode= | Major mode for dedicated chat buffers. |
| =gptel-prompt-prefix-alist= | Text inserted before queries. |
| =gptel-response-prefix-alist= | Text inserted before responses. |
|-----------------------------+----------------------------------------|
** Why another LLM client?
Other Emacs clients for LLMs prescribe the format of the interaction (a comint shell, org-babel blocks, etc). I wanted:

10
gptel.el
View file

@ -228,7 +228,10 @@ defaults to `text-mode'."
'((markdown-mode . "### ")
(org-mode . "*** ")
(text-mode . "### "))
"String inserted after the response from ChatGPT.
"String used as a prefix to the query being sent to the LLM.
This is meant for the user to distinguish between queries and
responses, and is removed from the query before it is sent.
This is an alist mapping major modes to the prefix strings. This
is only inserted in dedicated gptel buffers."
@ -239,7 +242,10 @@ is only inserted in dedicated gptel buffers."
'((markdown-mode . "")
(org-mode . "")
(text-mode . ""))
"String inserted after the response from ChatGPT.
"String inserted before the response from the LLM.
This is meant for the user to distinguish between queries and
responses.
This is an alist mapping major modes to the reply prefix strings. This
is only inserted in dedicated gptel buffers before the AI's response."