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://docs.respan.ai/mcp"
    }
  }
}

​
What is Ollama?

Ollama is a tool for running large language models locally. The Ollama Python SDK lets you interact with locally-hosted models like Llama, Mistral, and Gemma. Respan can auto-instrument all Ollama calls for tracing and observability.
Ollama runs models locally, so only Tracing setup is available. Gateway routing is not applicable for local model servers.

​
Setup

1

Install packages

pip install respan-ai opentelemetry-instrumentation-ollama ollama python-dotenv
2

Set environment variables

export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
No provider API key needed — Ollama runs models locally.
3

Initialize and run

import os
from dotenv import load_dotenv

load_dotenv()

import ollama
from respan import Respan

# Auto-discover and activate all installed instrumentors (Traceloop)
respan = Respan(is_auto_instrument=True)

# Calls go to local Ollama server, auto-traced by Respan
response = ollama.chat(
    model="llama3.1",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response["message"]["content"])
respan.flush()
4

View your trace

Open the Traces page to see your auto-instrumented LLM spans.

​
Configuration

ParameterTypeDefaultDescription
api_keystr | NoneNoneFalls back to RESPAN_API_KEY env var.
base_urlstr | NoneNoneFalls back to RESPAN_BASE_URL env var.
is_auto_instrumentbool | NoneFalseAuto-discover and activate all installed instrumentors via OpenTelemetry entry points.
customer_identifierstr | NoneNoneDefault customer identifier for all spans.
metadatadict | NoneNoneDefault metadata attached to all spans.
environmentstr | NoneNoneEnvironment tag (e.g. "production").

​
Attributes

Attach customer identifiers, thread IDs, and metadata to spans.

​
In Respan()

Set defaults at initialization — these apply to all spans. 
from respan import Respan

respan = Respan(
    is_auto_instrument=True,
    customer_identifier="user_123",
    metadata={"service": "local-chat", "version": "1.0.0"},
)

​
With propagate_attributes

Override per-request using a context manager. 
import ollama
from respan import Respan, workflow, propagate_attributes

respan = Respan(
    is_auto_instrument=True,
    metadata={"service": "local-chat", "version": "1.0.0"},
)

@workflow(name="handle_request")
def handle_request(user_id: str, question: str):
    with propagate_attributes(
        customer_identifier=user_id,
        thread_identifier="conv_001",
        metadata={"plan": "pro"},
    ):
        response = ollama.chat(
            model="llama3.1",
            messages=[{"role": "user", "content": question}],
        )
        print(response["message"]["content"])
AttributeTypeDescription
customer_identifierstrIdentifies the end user in Respan analytics.
thread_identifierstrGroups related messages into a conversation.
metadatadictCustom key-value pairs. Merged with default metadata.

​
Decorators

Use @workflow and @task to create structured trace hierarchies. 
import ollama
from respan import Respan, workflow, task

respan = Respan(is_auto_instrument=True)

@task(name="generate_outline")
def outline(topic: str) -> str:
    response = ollama.chat(
        model="llama3.1",
        messages=[
            {"role": "user", "content": f"Create a brief outline about: {topic}"},
        ],
    )
    return response["message"]["content"]

@workflow(name="content_pipeline")
def pipeline(topic: str):
    plan = outline(topic)
    response = ollama.chat(
        model="llama3.1",
        messages=[
            {"role": "user", "content": f"Write content from this outline: {plan}"},
        ],
    )
    print(response["message"]["content"])

pipeline("Benefits of API gateways")
respan.flush()

​
Examples

​
Basic chat

response = ollama.chat(
    model="llama3.1",
    messages=[{"role": "user", "content": "Say hello in three languages."}],
)
print(response["message"]["content"])

​
Streaming

stream = ollama.chat(
    model="llama3.1",
    messages=[{"role": "user", "content": "Write a haiku about Python."}],
    stream=True,
)
for chunk in stream:
    print(chunk["message"]["content"], end="", flush=True)