AutoGPT, babyAGI, ... and now LocalAGI!
LocalAGI is a small π€ virtual assistant that you can run locally, made by the LocalAI author and powered by it.
The goal is:
Note: Be warned! It was hacked in a weekend, and it's just an experiment to see what can be done with local LLMs.
Search on internet (interactive mode)
https://github.com/mudler/LocalAGI/assets/2420543/23199ca3-7380-4efc-9fac-a6bc2b52bdb3
Plan a road trip (batch mode)
https://github.com/mudler/LocalAGI/assets/2420543/9ba43b82-dec5-432a-bdb9-8318e7db59a4
Note: The demo is with a GPU and
30b
models size
No frills, just run docker-compose and start chatting with your virtual assistant:
# Modify the configuration
# vim .env
# first run (and pulling the container)
docker-compose up
# next runs
docker-compose run -i --rm localagi
By default localagi starts in interactive mode
Road trip planner by limiting searching to internet to 3 results only:
docker-compose run -i --rm localagi \
--skip-avatar \
--subtask-context \
--postprocess \
--search-results 3 \
--prompt "prepare a plan for my roadtrip to san francisco"
Limit results of planning to 3 steps:
docker-compose run -i --rm localagi \
--skip-avatar \
--subtask-context \
--postprocess \
--search-results 1 \
--prompt "do a plan for my roadtrip to san francisco" \
--plan-message "The assistant replies with a plan of 3 steps to answer the request with a list of subtasks with logical steps. The reasoning includes a self-contained, detailed and descriptive instruction to fullfill the task."
localagi has several options in the CLI to tweak the experience:
--system-prompt
is the system prompt to use. If not specified, it will use none.--prompt
is the prompt to use for batch mode. If not specified, it will default to interactive mode.--interactive
is the interactive mode. When used with --prompt
will drop you in an interactive session after the first prompt is evaluated.--skip-avatar
will skip avatar creation. Useful if you want to run it in a headless environment.--re-evaluate
will re-evaluate if another action is needed or we have completed the user request.--postprocess
will postprocess the reasoning for analysis.--subtask-context
will include context in subtasks.--search-results
is the number of search results to use.--plan-message
is the message to use during planning. You can override the message for example to force a plan to have a different message.--tts-api-base
is the TTS API base. Defaults to http://api:8080
.--localai-api-base
is the LocalAI API base. Defaults to http://api:8080
.--images-api-base
is the Images API base. Defaults to http://api:8080
.--embeddings-api-base
is the Embeddings API base. Defaults to http://api:8080
.--functions-model
is the functions model to use. Defaults to functions
.--embeddings-model
is the embeddings model to use. Defaults to all-MiniLM-L6-v2
.--llm-model
is the LLM model to use. Defaults to gpt-4
.--tts-model
is the TTS model to use. Defaults to en-us-kathleen-low.onnx
.--stablediffusion-model
is the Stable Diffusion model to use. Defaults to stablediffusion
.--stablediffusion-prompt
is the Stable Diffusion prompt to use. Defaults to DEFAULT_PROMPT
.--force-action
will force a specific action.--debug
will enable debug mode.To use a different model, you can see the examples in the config
folder.
To select a model, modify the .env
file and change the PRELOAD_MODELS_CONFIG
variable to use a different configuration file.
The "goodness" of a model has a big impact on how LocalAGI works. Currently 13b
models are powerful enough to actually able to perform multi-step tasks or do more actions. However, it is quite slow when running on CPU (no big surprise here).
The context size is a limitation - you can find in the config
examples to run with superhot 8k context size, but the quality is not good enough to perform complex tasks.
It is a dead simple experiment to show how to tie the various LocalAI functionalities to create a virtual assistant that can do tasks. It is simple on purpose, trying to be minimalistic and easy to understand and customize for everyone.
It is different from babyAGI or AutoGPT as it uses LocalAI functions - it is a from scratch attempt built on purpose to run locally with LocalAI (no API keys needed!) instead of expensive, cloud services. It sets apart from other projects as it strives to be small, and easy to fork on.
LocalAGI
just does the minimal around LocalAI functions to create a virtual assistant that can do generic tasks. It works by an endless loop of intent detection
, function invocation
, self-evaluation
and reply generation
(if it decides to reply! :)). The agent is capable of planning complex tasks by invoking multiple functions, and remember things from the conversation.
In a nutshell, it goes like this:
Under the hood LocalAI converts functions to llama.cpp BNF grammars. While OpenAI fine-tuned a model to reply to functions, LocalAI constrains the LLM to follow grammars. This is a much more efficient way to do it, and it is also more flexible as you can define your own functions and grammars. For learning more about this, check out the LocalAI documentation and my tweet that explains how it works under the hoods: https://twitter.com/mudler_it/status/1675524071457533953.
The intention of this project is to keep the agent minimal, so can be built on top of it or forked. The agent is capable of doing the following functions:
Run docker-compose with main.py checked-out:
docker-compose run -v main.py:/app/main.py -i --rm localagi
--postprocess
some times helps, but not always7b
models to perform good, and 13b
models perform better but on CPU are quite slow.