aichat Tools README
aichat --model name
--file file_or_url
--role %code% # %shell% or custom role.
--info # Print config
--macro my_macro
--rag aichat-wiki # Start or use RAG
--list-models # List models, roles, sessions, rags, macros
# query in command line args
aichat 4 * 6 # gives output as 24
# Read stdin or file as input
cat data.json | aichat convert json to yaml
aichat -f https://example.com explain
aichat -f "input-guide.pdf" explain
For use with in REPL :
.file dir1/ data.txt -- explain
# Generate code
aichat -c echo server in node.js
# Use roles (built-in roles and define your own)
aichat --role %code% Hello World
# REPL Mode
aichat
> .model openai:gpt-4o
> .role %code%
%code%> print "hello world" in js
# Shell assistant
aichat -e list ts files
find . -type '*.ts'
> execute | revise | cancel
# Use Predefined functions as role
aichat -r %functions% what is weather today in India ?
aichat -r %code% Hello world
# Sessions
> .session
temp) list 1 to 5, odd only
# Macro -- Alias for sequence of REPL commands
> .macro get-weather-in-India-USA
>> .role %fuctions% what is the weather in Paris and Sanfrancisco?
# Define Your own Custom RAG
>.rag aichat-wiki
> Select embedding model: openai:...
> Set chunk size: 3000
> Set chunk overlay: 150
> Add documents: https://github.com/sigodeon/aichat/wiki/**
...
Saved Rag to ~/.config/aichat/args/aichat-wiki.yaml
# Allow predefined functions to search web or execute local command or such ..
aichat -r %functions% what is latest version of node.js
AI Agent = Instructions (Prompt) + Tools (Function Callings) + Documents (RAG).
> .agent todo
....
$ aichat --serve
Chat Completions API: http://127.0.0.1:8000/v1/chat/completions
Embeddings API: http://127.0.0.1:8000/v1/embeddings
Rerank API: http://127.0.0.1:8000/v1/rerank
LLM Playground: http://127.0.0.1:8000/playground
LLM Arena: http://127.0.0.1:8000/arena?num=2