Simplify using LLMs in code

Rigging is a lightweight LLM framework built on Pydantic XML. The goal is to make leveraging language models in production code as simple and effictive as possible. Here are the highlights:

• Structured Pydantic models can be used interchangably with unstructured text output.
• LiteLLM as the default generator giving you instant access to a huge array of models.
• Simple tool calling abilities for models which don't natively support it.
• Store different models and configs as simple connection strings just like databases.
• Chat templating, forking, continuations, generation parameter overloads, stripping segments, etc.
• Async batching and fast iterations for large scale generation.
• Metadata, callbacks, and data format conversions.
• Modern python with type hints, async support, pydantic validation, serialization, etc.

import rigging as rg
from rigging.model import CommaDelimitedAnswer as Answer

chat = rg.get_generator('gpt-4') \
    .chat(f"Give me 3 famous authors between {Answer.xml_tags()} tags.") \
    .until_parsed_as(Answer) \
    .run()

answer = chat.last.parse(Answer)
print(answer.items)

# ['J. R. R. Tolkien', 'Stephen King', 'George Orwell']

Rigging is built by dreadnode where we use it daily.

Installation

We publish every version to Pypi:

pip install rigging

If you want to build from source:

cd rigging/
poetry install

Supported LLMs

Rigging will run just about any language model:

• Any model from LiteLLM
• Any model from vLLM
• Any model from transformers

API Keys

Pass the api_key in an generator id or use standard environment variables.

rg.get_generator("gpt-4-turbo,api_key=...")

export OPENAI_API_KEY=...
export MISTRAL_API_KEY=...
export ANTHROPIC_API_KEY=...
...

Check out the docs for more.

Getting Started

Check out the guide in the docs

1. Get a generator using a connection string.
2. Build a chat or completion pipeline
3. Run the pipeline and get the output.

import rigging as rg 

# 1 - Get a generator
generator = rg.get_generator("claude-3-sonnet-20240229")

# 2 - Build a chat pipeline
pending = generator.chat([
    {"role": "system", "content": "Talk like a pirate."},
    {"role": "user", "content": "Say hello!"},
])

# 3 - Run the pipeline
chat = pending.run()
print(chat.conversation)

# [system]: Talk like a pirate.
# [user]: Say hello!
# [assistant]: Ahoy, matey! Here be the salty sea dog ready to trade greetings wit' ye. Arrr!

Want more?

• Use structured pydantic parsing
• Check out raw completions
• Give the LLM access to tools
• Play with generation params
• Use callbacks in the pipeline
• Scale up with async and batching
• Save your work with serialization

Examples

• OverTheWire Bandit Agent: bandit.py
• Damn Vulnerable Restaurant Agent: dvra.py
• RAG Pipeline: rag.py (from kyleavery)

Documentation

rigging.dreadnode.io has everything you need.

Star History