respan-instrumentation-ollama

Respan instrumentation plugin for Ollama. It instruments the official Ollama Python client and emits chat, completion, and embedding spans into the Respan tracing pipeline.

Chat spans include canonical request tool definitions and only the tool calls emitted by the current response turn. Streamed calls are marked with llm.is_streaming, and provider HTTP failures retain their explicit status code.

Configuration

1. Install

pip install respan-ai respan-instrumentation-ollama ollama

ollama is the official Ollama Python client. A running Ollama server is required for real model calls.

2. Set Environment Variables

Quickstart

import os

from dotenv import load_dotenv
from ollama import Client
from respan import Respan, workflow
from respan_instrumentation_ollama import OllamaInstrumentor

load_dotenv()

respan = Respan(
    api_key=os.environ["RESPAN_API_KEY"],
    base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
    instrumentations=[OllamaInstrumentor()],
)
client = Client(host=os.getenv("OLLAMA_HOST"))


@workflow(name="ollama_quickstart")
def run() -> str:
    response = client.chat(
        model=os.getenv("OLLAMA_MODEL", "llama3.2"),
        messages=[{"role": "user", "content": "Reply with one concise sentence."}],
    )
    return response["message"]["content"]


print(run())
respan.flush()
respan.shutdown()

Further Reading

See the Respan example projects for runnable scripts.