Skip to main content

Modular Python framework for LLM workflows, tools, memory, and data.

Project description

griptape

PyPI Version Docs License

griptape is a modular Python framework for LLM workflows, tools, memory, and data.

With griptape, you can:

  1. 🚰 Build sequential LLM pipelines and sprawling DAG workflows for complex use cases.
  2. 🧰️ Augment LLMs with chain of thought capabilities and integrate external tools, such as calculators, web search, spreadsheet editors, and API connectors.
  3. 💾 Add memory to AI pipelines for context preservation and summarization.

griptape consists of several core packages:

  • griptape-flow: build LLM workflows and pipelines with memory, rules, and chain of thought reasoning.
  • griptape-core: integrate other services and functionality into LLMs as tools; run tools in any environment (local, containerized, cloud, etc.); convert tools into underlying middleware abstractions, such as ChatGPT Plugins, LangChain tools, and Fixie.ai agents.
  • griptape-tools: official Griptape tools registry.

griptape is in early development and its APIs and documentation are subject to change. Until we stabilize the API and release version 1.0.0, we will use minor versions (i.e., x.Y.z) to introduce breaking features and patch versions (i.e., x.y.Z) for bug fixes.

Documentation

Please refer to Griptape Docs for:

  • Getting started guides.
  • Core concepts and design overviews.
  • Examples.
  • Contribution guidelines.

Quick Start

First, install griptape that includes all core modules:

pip install griptape

Second, configure an OpenAI client by getting an API key and adding it to your environment as OPENAI_API_KEY. griptape uses OpenAI Completions API to execute LLM prompts and to work with LlamaIndex data structures.

With griptape, you can create structures, such as Pipelines and Workflows, that are composed of different types of steps. You can also define structures as JSON objects and load them into griptape dynamically. Let's define a simple two-step pipeline that uses tools:

from decouple import config
from griptape.tools import WebScraper, Calculator
from griptape.flow import utils
from griptape.flow.memory import PipelineMemory
from griptape.flow.steps import PromptStep, ToolkitStep
from griptape.flow.structures import Pipeline
from griptape.flow.utils import ToolLoader


scraper = WebScraper(
    openai_api_key=config("OPENAI_API_KEY")
)
calculator = Calculator()

pipeline = Pipeline(
    memory=PipelineMemory(),
    tool_loader=ToolLoader(
        tools=[calculator, scraper]
    )
)

pipeline.add_steps(
    ToolkitStep(
        tool_names=[calculator.name, scraper.name]
    ),
    PromptStep(
        "Say the following like a pirate: {{ input }}"
    )
)

pipeline.run("Give me a summary of https://en.wikipedia.org/wiki/Large_language_model")

print(utils.Conversation(pipeline.memory).to_string())

Boom! Our first multistep LLM pipeline with memory that used tools generated a conversation:

Q: Give me a summary of https://en.wikipedia.org/wiki/Large_language_model
A: Arr, me hearties! Large language models have been developed and set sail since 2018, includin' BERT, GPT-2, GPT-3 [...]

Contributing

Contributions in the form of bug reports, feature ideas, or pull requests are super welcome! Take a look at the current issues and if you'd like to help please submit a pull request with some tests.

License

griptape is available under the Apache 2.0 License.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

griptape-0.1.0.tar.gz (2.8 kB view hashes)

Uploaded Source

Built Distribution

griptape-0.1.0-py3-none-any.whl (3.0 kB view hashes)

Uploaded Python 3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page