Aleph Alpha | Respan Docs

Aleph Alpha is a European AI company offering the Luminous family of large language models. Their API provides text generation, semantic embeddings, and multimodal capabilities with a focus on enterprise use cases and data sovereignty. Respan gives you full observability over every Luminous call, prompt, and completion — and gateway routing through the OpenAI-compatible Respan endpoint.

Set up Respan

Create an account at platform.respan.ai and grab an API key. For gateway, also add credits or a provider key.

Run npx @respan/cli setup to set up with your coding agent.

Example projects

Python examples

Tracing

Gateway

Setup

Install packages

$ pip install respan-ai opentelemetry-instrumentation-alephalpha aleph-alpha-client

Set environment variables

$ export ALEPH_ALPHA_API_KEY="YOUR_ALEPH_ALPHA_API_KEY"
$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

ALEPH_ALPHA_API_KEY is used for Luminous requests. RESPAN_API_KEY is used to export traces to Respan.

Initialize and run

1 import os
2 from aleph_alpha_client import Client, CompletionRequest, Prompt
3 from respan import Respan
4 from opentelemetry.instrumentation.alephalpha import AlephAlphaInstrumentor
5 
6 respan = Respan(instrumentations=[AlephAlphaInstrumentor()])
7 
8 client = Client(token=os.environ["ALEPH_ALPHA_API_KEY"])
9 
10 request = CompletionRequest(
11     prompt=Prompt.from_text("Say hello in three languages:"),
12     maximum_tokens=100,
13 )
14 response = client.complete(request, model="luminous-base")
15 print(response.completions[0].completion)
16 respan.flush()

View your trace

Open the Traces page to see your auto-instrumented Luminous spans with prompts, tokens, and latency.

Configuration

Parameter	Type	Default	Description
`api_key`	`str \| None`	`None`	Falls back to `RESPAN_API_KEY` env var.
`base_url`	`str \| None`	`None`	Falls back to `RESPAN_BASE_URL` env var.
`instrumentations`	`list`	`[]`	Plugin instrumentations to activate (e.g. `AlephAlphaInstrumentor()`).
`customer_identifier`	`str \| None`	`None`	Default customer identifier for all spans.
`metadata`	`dict \| None`	`None`	Default metadata attached to all spans.
`environment`	`str \| None`	`None`	Environment tag (e.g. `"production"`).

Attributes

In Respan()

1 from respan import Respan
2 from opentelemetry.instrumentation.alephalpha import AlephAlphaInstrumentor
3 
4 respan = Respan(
5     instrumentations=[AlephAlphaInstrumentor()],
6     customer_identifier="user_123",
7     metadata={"service": "luminous-api", "version": "1.0.0"},
8 )

With propagate_attributes

1 from respan import Respan, propagate_attributes
2 from opentelemetry.instrumentation.alephalpha import AlephAlphaInstrumentor
3 
4 respan = Respan(instrumentations=[AlephAlphaInstrumentor()])
5 
6 def handle_request(user_id: str, prompt: str):
7     with propagate_attributes(
8         customer_identifier=user_id,
9         thread_identifier="conv_abc_123",
10         metadata={"plan": "pro"},
11     ):
12         response = client.complete(
13             CompletionRequest(prompt=Prompt.from_text(prompt), maximum_tokens=100),
14             model="luminous-base",
15         )
16         print(response.completions[0].completion)

Attribute	Type	Description
`customer_identifier`	`str`	Identifies the end user in Respan analytics.
`thread_identifier`	`str`	Groups related messages into a conversation.
`metadata`	`dict`	Custom key-value pairs. Merged with default metadata.