Swarmauri Cloudflare Workers AI LLM

swarmauri_llm_cloudflare connects Swarmauri conversations and toolkits to Cloudflare Workers AI's account-scoped REST API.

Features

• OpenAI-compatible chat completions through CloudflareWorkersAIModel.
• Tool calling through CloudflareWorkersAIToolModel for models that advertise tool support.
• Synchronous, asynchronous, incremental streaming, and batch workflows.
• Optional discovery from Cloudflare's model-search endpoint.
• Explicit account ID and API-token configuration.
• Persistent, injectable Swarmauri HTTP clients with conservative rate-limit retries.

Installation

uv add swarmauri_llm_cloudflare

pip install swarmauri_llm_cloudflare

Usage

import os

from swarmauri_llm_cloudflare import CloudflareWorkersAIModel
from swarmauri_standard.conversations.Conversation import Conversation
from swarmauri_standard.messages.HumanMessage import HumanMessage

conversation = Conversation(messages=[HumanMessage(content="Explain edge inference.")])
model = CloudflareWorkersAIModel(
    account_id=os.environ["CLOUDFLARE_ACCOUNT_ID"],
    api_key=os.environ["CLOUDFLARE_API_TOKEN"],
    name="@cf/meta/llama-3.3-70b-instruct-fp8-fast",
)
model.predict(conversation)
print(conversation.get_last().content)

Set discover_models=True to query the current Workers AI model catalog. For tools, instantiate CloudflareWorkersAIToolModel with a tool-capable model and pass a Swarmauri Toolkit.

Pass an IHttpClient as http_client to integrate a custom transport or to test without network access. Pass an IHttpRetryPolicy as retry_policy to replace the default policy, which retries safe reads and rate-limited chat submissions without replaying failed POST requests for generic server errors.

See the Cloudflare Workers AI REST guide and model-search API for account setup and current model details.