anlyon-llamaindex

LlamaIndex integration for Anlyon. action_tools turns Anlyon actions into LlamaIndex tools.

Installation

pip install anlyon-llamaindex

Actions as tools

from anlyon import Client
from anlyon_llamaindex import action_tools

client = Client(api_key="anlyon_live_...")

# Declare once, from an operator key. This makes the action governed.
client.actions.declare(
    "send-email",
    impact={"dimension": "emails", "amount": "count(input.to)", "bound": "exact"},
    verify={"url": "https://api.example.com/v1/messages/{{response.id}}", "status": 200},
)

tools = action_tools(client)  # one FunctionTool per enabled action
send_email = next(tool for tool in tools if tool.metadata.name == "send-email")

print(send_email.metadata.description)
# Sends an email. Declared impact: emails. Each call counts toward any shared limit set for this environment.

output = send_email.call(to=["a@example.com"], subject="Hi")
print(output.raw_output["grade"])  # "confirmed", "acknowledged", "unknown", "failed", "refused", "denied" or "pending"

Each tool calls client.actions.invoke(). Anlyon holds the credential, evaluates policy and makes the call. A tool your own code calls directly is not routed through Anlyon and is not governed by it. The description carries the declared impact when the action declares one. It says what one call counts. It does not say a limit is configured. The raw output is the invocation as a dict. grade is the receipt grade of a governed action, and None for an action that is not governed. A gated action comes back with pendingApproval and an approvalId.

Pass names=[...] to keep a subset.

See the Anlyon docs for the full guide.

License

MIT

Earlier namespaces remain available through the API for existing workspaces. See the billing docs.