oimwiodev/ChatMock
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
Game_Time
2025-08-16 01:03:45 +05:00
committed by GitHub
parent 50eccac1e2
commit 39536725a7
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -17,14 +17,14 @@ ChatMock runs a local server that creates an OpenAI compatible API, and requests
1. Sign in with your ChatGPT account and follow the prompts 1. Sign in with your ChatGPT account and follow the prompts
```bash ```bash
python chatgpt_local.py login python chatmock.py login
``` ```
You can make sure this worked by running `python chatgpt_local.py info` You can make sure this worked by running `python chatmock.py info`
2. After the login completes successfully, you can just simply start the local server 2. After the login completes successfully, you can just simply start the local server
```bash ```bash
python chatgpt_local.py serve python chatmock.py serve
``` ```
- Then, you can simply use the address and port as the baseURL as you require (http://127.0.0.1:8000 by default) - Then, you can simply use the address and port as the baseURL as you require (http://127.0.0.1:8000 by default)
@@ -92,7 +92,7 @@ Models like GPT-5 do not return raw thinking content, but instead return thinkin
## Notes ## Notes
If you wish to have the fastest responses, I'd recommend setting `--reasoning-effort` to low, and `--reasoning-summary` to none. If you wish to have the fastest responses, I'd recommend setting `--reasoning-effort` to low, and `--reasoning-summary` to none.
All parameters and choices can be seen by sending `python chatgpt_local.py serve --h` All parameters and choices can be seen by sending `python chatmock.py serve --h`
**When the model returns a thinking summary, the model will send back thinking tags to make it compatible with chat apps. If you don't like this behavior, you can instead set `--reasoning-compat` to legacy, and reasoning will be set in the reasoning tag instead of being returned in the actual response text.** **When the model returns a thinking summary, the model will send back thinking tags to make it compatible with chat apps. If you don't like this behavior, you can instead set `--reasoning-compat` to legacy, and reasoning will be set in the reasoning tag instead of being returned in the actual response text.**