Skip to main content
  1. Sign up — Create an account at platform.respan.ai
  2. Create an API key — Generate one on the API keys page
  3. Add credits or a provider key — Add credits on the Credits page or connect your own provider key on the Integrations page
Add the Docs MCP to your AI coding tool to get help building with Respan. No API key needed.
{
  "mcpServers": {
    "respan-docs": {
      "url": "https://respan.ai/docs/mcp"
    }
  }
}

​
What is Marqo?

Marqo is a tensor search engine that combines embedding generation, storage, and search in a single API. It handles vectorization automatically — no need to manage embeddings separately.

​
Setup

1

Install packages

pip install respan-tracing marqo openai
2

Set environment variables

export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
export OPENAI_API_KEY="YOUR_OPENAI_API_KEY"
3

Initialize Respan and query Marqo

Respan auto-instruments Marqo — search, add_documents, and index operations are captured as spans.
from respan_tracing import RespanTelemetry
from respan_tracing.decorators import workflow, task
import marqo
from openai import OpenAI

# Initialize — auto-instruments Marqo
telemetry = RespanTelemetry()
client = OpenAI()
mq = marqo.Client(url="http://localhost:8882")

# Create index and add documents (Marqo handles embeddings internally)
mq.create_index("docs")
mq.index("docs").add_documents(
    [
        {"text": "Respan provides observability for LLM applications.", "_id": "doc1"},
        {"text": "Traces capture the full lifecycle of an LLM request.", "_id": "doc2"},
    ],
    tensor_fields=["text"],
)


@task(name="search_docs")
def search_docs(query: str):
    results = mq.index("docs").search(query, limit=3)
    return [hit["text"] for hit in results["hits"]]


@workflow(name="rag_pipeline")
def rag_pipeline(query: str):
    context = search_docs(query)
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[
            {"role": "system", "content": f"Context: {chr(10).join(context)}"},
            {"role": "user", "content": query},
        ],
    )
    return response.choices[0].message.content


result = rag_pipeline("How does tracing work?")
print(result)
4

View your trace

Open the Traces page to see Marqo operations as spans in your trace tree.

​
Configuration

Marqo is auto-instrumented via Instruments.MARQO. No additional configuration is needed.
Marqo tracing is currently available in the Python SDK only.
See the Python Tracing SDK reference for configuration options.