[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[nongnu] elpa/gptel 50a2498259 126/273: README: Tweak instructions for l
From: |
ELPA Syncer |
Subject: |
[nongnu] elpa/gptel 50a2498259 126/273: README: Tweak instructions for local LLMs, mention #120 |
Date: |
Wed, 1 May 2024 10:02:12 -0400 (EDT) |
branch: elpa/gptel
commit 50a2498259ebc4cfbd4da918bc28f7ac7786617c
Author: Karthik Chikmagalur <karthikchikmagalur@gmail.com>
Commit: Karthik Chikmagalur <karthikchikmagalur@gmail.com>
README: Tweak instructions for local LLMs, mention #120
---
README.org | 43 +++++++++++++++++++++++++++++--------------
1 file changed, 29 insertions(+), 14 deletions(-)
diff --git a/README.org b/README.org
index dffe773a65..636e63fc45 100644
--- a/README.org
+++ b/README.org
@@ -4,14 +4,14 @@
GPTel is a simple Large Language Model chat client for Emacs, with support for
multiple models/backends.
-| LLM Backend | Supports | Requires |
-|-------------+----------+------------------------|
-| ChatGPT | ✓ | [[https://platform.openai.com/account/api-keys][API
key]] |
-| Azure | ✓ | Deployment and API key |
-| Ollama | ✓ | An LLM running locally |
-| GPT4All | ✓ | An LLM running locally |
-| PrivateGPT | Planned | - |
-| Llama.cpp | Planned | - |
+| LLM Backend | Supports | Requires |
+|-------------+----------+-------------------------|
+| ChatGPT | ✓ | [[https://platform.openai.com/account/api-keys][API
key]] |
+| Azure | ✓ | Deployment and API key |
+| Ollama | ✓ | [[https://ollama.ai/][Ollama running locally]] |
+| GPT4All | ✓ | [[https://gpt4all.io/index.html][GPT4All running
locally]] |
+| PrivateGPT | Planned | - |
+| Llama.cpp | Planned | - |
*General usage*:
@@ -59,6 +59,8 @@ GPTel uses Curl if available, but falls back to url-retrieve
to work without ext
** Breaking Changes
+- Possible breakage, see #120: If streaming responses stop working for you
after upgrading to v0.5, try reinstalling gptel and deleting its native comp
eln cache in =native-comp-eln-load-path=.
+
- The user option =gptel-host= is deprecated. If the defaults don't work for
you, use =gptel-make-openai= (which see) to customize server settings.
- =gptel-api-key-from-auth-source= now searches for the API key using the host
address for the active LLM backend, /i.e./ "api.openai.com" when using ChatGPT.
You may need to update your =~/.authinfo=.
@@ -162,7 +164,14 @@ Register a backend with
#+end_src
These are the required parameters, refer to the documentation of
=gptel-make-gpt4all= for more.
-You can pick this backend from the transient menu when using gptel (see
usage), or set this as the default value of =gptel-backend=.
+You can pick this backend from the transient menu when using gptel (see
usage), or set this as the default value of =gptel-backend=. Additionally you
may want to increase the response token size since GPT4All uses very short
(often truncated) responses by default:
+
+#+begin_src emacs-lisp
+;; OPTIONAL configuration
+(setq-default gptel-model "mistral-7b-openorca.Q4_0.gguf" ;Pick your default
model
+ gptel-backend (gptel-make-gpt4all "GPT4All" :protocol ...))
+(setq-default gptel-max-tokens 500)
+#+end_src
#+html: </details>
@@ -178,19 +187,25 @@ Register a backend with
:models '("mistral:latest") ;Installed models
:stream t) ;Stream responses
#+end_src
-These are the required parameters, refer to the documentation of
=gptel-make-gpt4all= for more.
+These are the required parameters, refer to the documentation of
=gptel-make-ollama= for more.
+
+You can pick this backend from the transient menu when using gptel (see
Usage), or set this as the default value of =gptel-backend=:
-You can pick this backend from the transient menu when using gptel (see
usage), or set this as the default value of =gptel-backend=.
+#+begin_src emacs-lisp
+;; OPTIONAL configuration
+(setq-default gptel-model "mistral:latest" ;Pick your default model
+ gptel-backend (gptel-make-ollama "Ollama" :host ...))
+#+end_src
#+html: </details>
** Usage
|-------------------+-------------------------------------------------------------------------|
-| *Commands* | Description
|
+| *Command* | Description
|
|-------------------+-------------------------------------------------------------------------|
-| =gptel= | Create a new dedicated chat buffer. Not required,
gptel works anywhere. |
-| =gptel-send= | Send selection, or conversation up to =(point)=. Works
anywhere in Emacs. |
+| =gptel= | Create a new dedicated chat buffer. (Not required,
gptel works anywhere.) |
+| =gptel-send= | Send selection, or conversation up to =(point)=.
(Works anywhere in Emacs.) |
| =C-u= =gptel-send= | Transient menu for preferenes, input/output
redirection etc. |
| =gptel-menu= | /(Same)/
|
|-------------------+-------------------------------------------------------------------------|
- [nongnu] elpa/gptel 075609544a 085/273: README: Update instructions for setting key (#46), (continued)
- [nongnu] elpa/gptel 075609544a 085/273: README: Update instructions for setting key (#46), ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel a7207a3835 097/273: README: Add TOC, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel f218388d4d 082/273: gptel-transient: Fix bug when sending in existing session, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 30700cc88a 096/273: README: Mention extensions, gptel-proxy, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 09729ee718 089/273: gptel: Create customization group, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel ac754ceb2a 086/273: gptel: Handle read-only gptel-buffers, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel cc6c5e7321 104/273: gptel: saving and restoring state, and limiting context, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 24add64455 114/273: gptel: Adjust how gptel--system-message is set, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 17a58d38e7 135/273: gptel: Fix bug in url-retrieve setup, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 61c0df5e19 119/273: gptel, gptel-curl: Make the gptel text-property non-sticky, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 50a2498259 126/273: README: Tweak instructions for local LLMs, mention #120,
ELPA Syncer <=
- [nongnu] elpa/gptel ec0e461b35 128/273: gptel-curl: Increased curl timeout (#127), ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel d5949ef428 140/273: gptel-curl: handle large Curl payloads with a temp file (#137), ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 0ea3c7fb15 143/273: gptel-transient: Improve suffix message editor, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel ce75072f9d 152/273: gptel: Bump version, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 3af2650342 170/273: gptel-transient: save window state when ediff, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel e67ed41e31 173/273: README: Specify: no key needed for llama backend, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 1fcb4606a2 184/273: Fix compilation warning in gptel-openai.el, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel b3d028d074 185/273: Add .gitignore, ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 5465271541 207/273: gptel: Add gpt-4-0125-preview to model list (Fix #215), ELPA Syncer, 2024/05/01
- [nongnu] elpa/gptel 43f625ecb9 209/273: gptel-openai: curl-args slot in gptel-backend (#221), ELPA Syncer, 2024/05/01