astra-assistants

What it is and what it does

Astra Assistants is a Python library that patches the OpenAI SDK to act as a drop-in replacement for OpenAI's Assistants API. It extends the standard API with support for AstraDB vector stores and adds a credential abstraction layer that lets you route requests to alternative LLM providers—including Groq, Anthropic, Gemini, Perplexity, Cohere, AWS Bedrock, Vertex AI, and many others—by setting environment variables. The library wraps litellm under the hood to handle provider-specific authentication and API translation.

You install it alongside the OpenAI SDK, import the patch function, and apply it to an OpenAI client instance. From that point forward, your existing OpenAI Assistants code works unchanged, but now backed by AstraDB for vector storage and able to use any LLM provider litellm supports. It includes support for streaming and the full Assistants v2 API surface. The package carries 12 runtime dependencies covering HTTP clients, language server protocol support, code parsing, and linting.

Use it for:

• Build an assistant that uses AstraDB for semantic search and retrieval without rewriting OpenAI integration code.
• Route assistant requests to multiple LLM providers (Anthropic, Groq, etc.) by changing environment variables instead of code.
• Add vector store capabilities to an existing OpenAI Assistants application with minimal refactoring.
• Prototype multi-provider LLM workflows where you can swap backends without touching business logic.
• Stream assistant responses from non-OpenAI providers using the same Assistants v2 API surface.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Wraps OpenAI's Assistants API as a drop-in replacement, adding support for AstraDB vector stores and enabling credential pass-through to alternative LLM providers via litellm.

Yes, if you are already using OpenAI Assistants and want to add AstraDB vector storage or experiment with alternative LLM providers without rewriting integration code. The low install friction and broad provider support make it a practical bridge. However, the aging maintenance status (482 days since last release) and unclear license terms are cautions—verify license compliance and test compatibility with your current OpenAI SDK version before committing to production use.

Install

astra-assistants on PyPI

pip install astra-assistants

uv add astra-assistants

poetry add astra-assistants

Installing astra-assistants

Before you install

Low install friction with a pure-Python wheel. Maintenance status is aging—last release was 482 days ago—so expect slower response to issues or compatibility updates with newer OpenAI SDK versions.

License in practice

License treatment is unclear; no SPDX identifier or raw license text is published. Verify the actual license terms before using in proprietary or commercial contexts.

Quickstart

pip install astra-assistants

from openai import OpenAI
from astra_assistants import patch

client = patch(OpenAI())

Requires Python 3.10 or later. API keys for AstraDB and at least one LLM provider must be set as environment variables.

Verify before relying

• Whether the aging maintenance status (482 days since last release) affects compatibility with current OpenAI SDK versions.
• Exact license terms and any restrictions on commercial use or redistribution.
• Support status for the full Assistants v2 API surface, including all recent OpenAI additions.

Package facts

Evidence: astra_assistants-2.5.5-py3-none-any.whl

Tags

More Artificial Intelligence packages

Further reading