| Age | Commit message (Collapse) | Author | Lines | |
|---|---|---|---|---|
| 2023-03-16 | feat: support multiple models (#71) | sigoden | -5/+1 | |
| 2023-03-10 | chore: opitmize code, move MAX_TOKENS related to config/message.rs | sigoden | -2/+1 | |
| 2023-03-10 | fix: forbid .clear role in middle of conversation | sigoden | -0/+7 | |
| 2023-03-09 | feat: add config.conversation_first (#55) | sigoden | -2/+16 | |
| If set true, start a conversation immediately upon repl. | ||||
| 2023-03-09 | refactor: optimize counting tokens (#53) | sigoden | -14/+7 | |
| 2023-03-09 | feat: support two types of role prompts (#52) | sigoden | -60/+48 | |
| 1. embeded prompt use __INPUT__ placeholder will generate one user message when send to gpt ``` - name: shell prompt: > I want you to act as a linux shell expert. Q: How to unzip a file A: unzip file.zip Q: __INPUT__ A: ``` 2. system prompt no __INPUT__ placeholder will generate on system message and one user message when send to gpt ``` - name: shell prompt: | I want you to act as a linux shell expert. I want you to answer only with bash code. Do not write explanations. ``` | ||||
| 2023-03-09 | feat: add remain tokens indicator and max tokens guard (#50) | sigoden | -3/+13 | |
| 2023-03-09 | feat: support conversation (#48) | sigoden | -0/+83 | |
 |
index : aichat.git | |
| Docker container specifically designed to be used for coding with aichat |
| summaryrefslogtreecommitdiffstats |