Metadata-Version: 2.1
Name: openssa
Version: 0.24.6.8
Summary: OpenSSA: Small Specialist Agents for Industrial AI
Home-page: https://openssa.org
License: Apache-2.0
Keywords: Artificial Intelligence,A.I.,AI,industrial,specialist,specialized,domain,expertise,knowledge
Author: Aitomatic, Inc.
Author-email: engineering@aitomatic.com
Maintainer: Aitomatic, Inc.
Maintainer-email: engineering@aitomatic.com
Requires-Python: >=3.12,<3.13
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.12
Provides-Extra: contrib
Provides-Extra: llama-index-callbacks
Requires-Dist: adlfs (>=2024.4)
Requires-Dist: click (>=8.1)
Requires-Dist: docx2txt (>=0.8)
Requires-Dist: fsspec (>=2024.6)
Requires-Dist: gcsfs (>=2024.6)
Requires-Dist: google-api-python-client (>=2.132)
Requires-Dist: httpx (>=0.27)
Requires-Dist: llama-index (>=0.10)
Requires-Dist: llama-index-callbacks-arize-phoenix (>=0.1) ; extra == "llama-index-callbacks"
Requires-Dist: llama-index-callbacks-deepeval (>=0.1) ; extra == "llama-index-callbacks"
Requires-Dist: llama-index-callbacks-honeyhive (>=0.1) ; extra == "llama-index-callbacks"
Requires-Dist: llama-index-callbacks-langfuse (>=0.1) ; extra == "llama-index-callbacks"
Requires-Dist: llama-index-callbacks-openinference (>=0.1) ; extra == "llama-index-callbacks"
Requires-Dist: llama-index-callbacks-promptlayer (>=0.1) ; extra == "llama-index-callbacks"
Requires-Dist: llama-index-callbacks-wandb (>=0.1) ; extra == "llama-index-callbacks"
Requires-Dist: llama-index-embeddings-azure-openai (>=0.1)
Requires-Dist: llama-index-llms-azure-openai (>=0.1)
Requires-Dist: llama-index-readers-web (>=0.1)
Requires-Dist: llamaapi (>=0.1)
Requires-Dist: loguru (>=0.7)
Requires-Dist: openai (>=1.33)
Requires-Dist: pycryptodome (>=3.20)
Requires-Dist: pydantic (>=2.7)
Requires-Dist: pypdf (>=4.2)
Requires-Dist: python-dotenv (>=1.0)
Requires-Dist: s3fs (>=2024.6)
Requires-Dist: streamlit (>=1.35) ; extra == "contrib"
Requires-Dist: streamlit-extras (>=0.4) ; extra == "contrib"
Requires-Dist: streamlit-mic-recorder (>=0.0.8) ; extra == "contrib"
Requires-Dist: torch (>=2.2,<2.3)
Requires-Dist: tqdm (>=4.66)
Project-URL: Documentation, https://aitomatic.github.io/openssa
Project-URL: Repository, https://github.com/aitomatic/openssa
Description-Content-Type: text/markdown

<!-- markdownlint-disable MD013 MD043 -->

# `OpenSSA`: Small Specialist Agents for Problem-Solving

`OpenSSA` is an agentic AI framework for solving complex problems in real-world industry domains,
overcoming the limitations of LLMs and RAG in such settings.

## Level-2 Intelligence with Planning, Reasoning, domain-specific Knowledge and diverse Informational Resources

`OpenSSA` agents, built with powerful Hierarchical Task Planning (HTP) and Observe-Orient-Decide-Act Reasoning (OODAR),
go far beyond the Level-1 pattern-matching intelligence performed by LLMs and RAG and achieve superior outcomes
in complex multi-faceted, multi-step tasks. See our [comparative study](https://arxiv.org/abs/2404.11792).

`OpenSSA` agents can also be armed with domain-specific Knowledge, connected to diverse Informational Resources
(files, databases, web sources, etc.), and/or be guided by specialized industry experts
to maximize the accuracy and comprehensiveness in their planning, reasoning and deliberative/iterative problem-solving.

## Open and Extensible Architecture

Committed to promoting and supporting open development in generative AI,
`OpenSSA` would strive to integrate with a diverse array of LLM backends, especially open-source LLMs.
If you would like certain LLMs to be supported, please suggest through a GitHub issue, or, even better, submit your PRs.

Additionally, `OpenSSA`'s key Planning, Reasoning, Knowledge and Resource interfaces
are designed with customizability and extensibility as first-class concerns,
in order to enable developers to effectively solve problems in their specific industries and specialized domains.

## Small and Resource-Efficient Agents for Practical Real-World Deployment

Specialized, Level-2 intelligence allows `OpenSSA` agents to work well in many applications
using significantly smaller component models, thereby greatly economizing computing resources.

## Getting Started

Install by `pip install openssa` (on Python 3.12 only).

- for bleeding-edge latest capabilities: `pip install https://github.com/aitomatic/openssa/archive/main.zip`

Explore the `examples/` directory and developer guides and tutorials on our [documentation site](https://aitomatic.github.io/openssa).

## [API Documentation](https://aitomatic.github.io/openssa/modules)

## Contributing

We welcome contributions from the community!

- Join the discussion on our [Community Forum](https://github.com/aitomatic/openssa/discussions)
- Submit pull requests for bug fixes, enhancements, or new features

For more information, see our [Contribution Guide](CONTRIBUTING.md).

