aichat.git - Docker container specifically designed to be used for coding with aichat

Age	Commit message (Collapse)	Author	Lines
2023-11-02	refactor: improve code quanity (#197)	sigoden	-52/+0
	- move model_info.rs/message.rs to clients/ - rename SharedConfig to GlobalConfig
2023-11-01	refactor: improve code quanity (#194)	sigoden	-12/+7
	- extends ModelInfo for tokens calculating - refactor config/session.rs, improve export, render, getter/setter - modify main.rs, allow --model override session.model
2023-11-01	refactor: clients/* and config.rs (#193)	sigoden	-1/+8
	- add register_clients macro to make it easier to add a new client - no create_client_config, just add const PROMPTS - move ModelInfo from clients/ to config/ - model's max_tokens are optional - improve code quanity on config/mod.rs - add/use macro config_get_fn
2023-10-30	chore: remove unnecessary clippy macros	sigoden	-1/+0

2023-07-10	fix: minor code cleanup and pedantic lints (#134)	Anthony Rubick	-1/+2

2023-03-20	feat: check token usage in dry_run mode (#82)	sigoden	-9/+0

2023-03-16	feat: support multiple models (#71)	sigoden	-4/+2

2023-03-10	chore: opitmize code, move MAX_TOKENS related to config/message.rs	sigoden	-1/+12

2023-03-09	refactor: optimize counting tokens (#53)	sigoden	-7/+23

2023-03-09	feat: support two types of role prompts (#52)	sigoden	-0/+34
	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. ```