github/opencommit
1
1
Fork 0
mirror of https://github.com/di-sukharev/opencommit.git synced 2026-04-20 03:02:51 -04:00
Code Issues Packages Projects Releases Wiki Activity

Feat: Update OCO_MODEL to Latest Version and Remove Legacy GPT-3.5 Turbo Models (#299)

Browse Source 
* fix(config.ts): improve code formatting for better readability
feat(config.ts): add additional supported models for OCO_MODEL configuration
feat(config.ts): update default OCO_MODEL value to 'gpt-3.5-turbo' for better compatibility

* docs(README.md): update OCO_MODEL options to include new GPT-4 models and remove
mention of 'gpt-3.5-turbo-16k' model
docs(README.md): update default OCO_MODEL to 'gpt-3.5-turbo' and provide
instructions for switching to GPT-4 models, specifically 'gpt-4-0125-preview'
and 'gpt-4-turbo-preview'
docs(README.md): update OCO_MODEL configuration in CI/CD pipeline to 'gpt-3.5-turbo'
docs(README.md): update cost information related to default and GPT-4 models in
OpenCommit
This commit is contained in:
Kuma Taro
2024-03-06 23:00:35 +09:00
committed by GitHub
parent 401be04b4d
commit 744bb9b11d
2 changed files with 19 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@@ -72,16 +72,18 @@ AI_PROVIDER='ollama' opencommit
```
### Flags
There are multiple optional flags that can be used with the `oco` command:
#### Use Full GitMoji Specification
This flag can only be used if the `OCO_EMOJI` configuration item is set to `true`. This flag allows users to use all emojis in the GitMoji specification, By default, the GitMoji full specification is set to `false`, which only includes 10 emojis (🐛✨📝🚀✅♻️⬆️🔧🌐💡).
This is due to limit the number of tokens sent in each request. However, if you would like to use the full GitMoji specification, you can use the `--fgm` flag.
```
oco --fgm
```
## Configuration
### Local per repo configuration
@@ -95,7 +97,7 @@ OCO_TOKENS_MAX_OUTPUT=<max response tokens (default: 500)>
OCO_OPENAI_BASE_PATH=<may be used to set proxy path to OpenAI api>
OCO_DESCRIPTION=<postface a message with ~3 sentences description of the changes>
OCO_EMOJI=<boolean, add GitMoji>
OCO_MODEL=<either 'gpt-4', 'gpt-3.5-turbo-16k' (default), 'gpt-3.5-turbo-0613' or 'gpt-3.5-turbo'>
OCO_MODEL=<either 'gpt-4', 'gpt-3.5-turbo' (default), 'gpt-3.5-turbo-0125', 'gpt-4-1106-preview', 'gpt-4-turbo-preview' or 'gpt-4-0125-preview'>
OCO_LANGUAGE=<locale, scroll to the bottom to see options>
OCO_MESSAGE_TEMPLATE_PLACEHOLDER=<message template placeholder, default: '$msg'>
OCO_PROMPT_MODULE=<either conventional-commit or @commitlint, default: conventional-commit>
@@ -125,7 +127,7 @@ oco config set OCO_EMOJI=false
### Switch to GPT-4 or other models
By default, OpenCommit uses `gpt-3.5-turbo-16k` model.
By default, OpenCommit uses `gpt-3.5-turbo` model.
You may switch to GPT-4 which performs better, but costs ~x15 times more 🤠
@@ -142,7 +144,7 @@ oco config set OCO_MODEL=gpt-3.5-turbo
or for GPT-4 Turbo (Preview) which is more capable, has knowledge of world events up to April 2023, a 128k context window and 2-3x cheaper vs GPT-4:
```sh
oco config set OCO_MODEL=gpt-4-1106-preview
oco config set OCO_MODEL=gpt-4-0125-preview
```
Make sure that you spell it `gpt-4` (lowercase) and that you have API access to the 4th model. Even if you have ChatGPT+, that doesn't necessarily mean that you have API access to GPT-4.
@@ -348,7 +350,7 @@ jobs:
OCO_OPENAI_BASE_PATH: ''
OCO_DESCRIPTION: false
OCO_EMOJI: false
OCO_MODEL: gpt-3.5-turbo-16k
OCO_MODEL: gpt-3.5-turbo
OCO_LANGUAGE: en
OCO_PROMPT_MODULE: conventional-commit
```
@@ -365,6 +367,6 @@ You pay for your requests to OpenAI API on your own.
OpenCommit stores your key locally.
OpenCommit by default uses 3.5-turbo-16k model, it should not exceed $0.10 per casual working day.
OpenCommit by default uses 3.5-turbo model, it should not exceed $0.10 per casual working day.
You may switch to gpt-4, it's better, but more expensive.

17
src/commands/config.ts
View File

@@ -54,7 +54,11 @@ const validateConfig = (
export const configValidators = {
[CONFIG_KEYS.OCO_OPENAI_API_KEY](value: any, config: any = {}) {
//need api key unless running locally with ollama
validateConfig('API_KEY', value || config.OCO_AI_PROVIDER == 'ollama', 'You need to provide an API key');
validateConfig(
'API_KEY',
value || config.OCO_AI_PROVIDER == 'ollama',
'You need to provide an API key'
);
validateConfig(
CONFIG_KEYS.OCO_OPENAI_API_KEY,
value.startsWith('sk-'),
@@ -150,12 +154,13 @@ export const configValidators = {
CONFIG_KEYS.OCO_MODEL,
[
'gpt-3.5-turbo',
'gpt-3.5-turbo-0125',
'gpt-4',
'gpt-3.5-turbo-16k',
'gpt-3.5-turbo-0613',
'gpt-4-1106-preview'
'gpt-4-1106-preview',
'gpt-4-turbo-preview',
'gpt-4-0125-preview'
].includes(value),
`${value} is not supported yet, use 'gpt-4', 'gpt-3.5-turbo-16k' (default), 'gpt-3.5-turbo-0613', 'gpt-3.5-turbo' or 'gpt-4-1106-preview'`
`${value} is not supported yet, use 'gpt-4', 'gpt-3.5-turbo' (default), 'gpt-3.5-turbo-0125', 'gpt-4-1106-preview', 'gpt-4-turbo-preview' or 'gpt-4-0125-preview'`
);
return value;
},
@@ -210,7 +215,7 @@ export const getConfig = (): ConfigType | null => {
OCO_OPENAI_BASE_PATH: process.env.OCO_OPENAI_BASE_PATH,
OCO_DESCRIPTION: process.env.OCO_DESCRIPTION === 'true' ? true : false,
OCO_EMOJI: process.env.OCO_EMOJI === 'true' ? true : false,
OCO_MODEL: process.env.OCO_MODEL || 'gpt-3.5-turbo-16k',
OCO_MODEL: process.env.OCO_MODEL || 'gpt-3.5-turbo',
OCO_LANGUAGE: process.env.OCO_LANGUAGE || 'en',
OCO_MESSAGE_TEMPLATE_PLACEHOLDER:
process.env.OCO_MESSAGE_TEMPLATE_PLACEHOLDER || '$msg',