Ollama

Ollama runs open-weight models locally. In Python, the OllamaInstrumentor traces native Ollama chat calls, including messages, responses, tool calls, and token counts, as OpenInference LLM spans in Arize AX. Ollama also exposes an OpenAI-compatible API, so Node.js and Go applications can call it with the OpenAI SDK and trace it with the OpenInference OpenAI instrumentation for JavaScript / TypeScript or Go.

Llama 3.2 + Ollama Tracing Tutorial (Google Colab)

Prerequisites

Python 3.10+, Node.js 22+, or Go 1.25+
An Arize AX account (sign up)
Ollama installed and running locally
The llama3.2:1b model pulled: ollama pull llama3.2:1b

Launch Arize AX

Sign in to your Arize AX account.
From Space Settings, copy your Space ID and API Key. You will set them as ARIZE_SPACE_ID and ARIZE_API_KEY below.

Install

pip install arize-otel openinference-instrumentation-ollama ollama

npm install openai \
  @arizeai/openinference-instrumentation-openai \
  @arizeai/openinference-semantic-conventions \
  @opentelemetry/api \
  @opentelemetry/context-async-hooks \
  @opentelemetry/exporter-trace-otlp-proto \
  @opentelemetry/instrumentation \
  @opentelemetry/resources \
  @opentelemetry/sdk-trace \
  @opentelemetry/semantic-conventions

go get \
  github.com/Arize-ai/arize-otel-go \
  github.com/Arize-ai/openinference/go/openinference-instrumentation-openai-go \
  github.com/openai/openai-go/v3

Configure credentials

export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="ollama-tracing-example"

Ollama runs locally, so this example needs no provider API key. The OpenAI SDKs require an API key value, so the TypeScript and Go examples pass the placeholder ollama, which a local Ollama server ignores.

Setup tracing

# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.ollama import OllamaInstrumentor

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

OllamaInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for Ollama.")

// instrumentation.ts
import { context, trace } from "@opentelemetry/api";
import {
  AsyncLocalStorageContextManager,
} from "@opentelemetry/context-async-hooks";
import { OTLPTraceExporter } from "@opentelemetry/exporter-trace-otlp-proto";
import { resourceFromAttributes } from "@opentelemetry/resources";
import { SimpleSpanProcessor, TracerProvider } from "@opentelemetry/sdk-trace";
import { ATTR_SERVICE_NAME } from "@opentelemetry/semantic-conventions";
import {
  SEMRESATTRS_PROJECT_NAME,
} from "@arizeai/openinference-semantic-conventions";
import { registerInstrumentations } from "@opentelemetry/instrumentation";
import {
  OpenAIInstrumentation,
} from "@arizeai/openinference-instrumentation-openai";
import OpenAI from "openai";

const projectName =
  process.env.ARIZE_PROJECT_NAME ?? "ollama-tracing-example";

export const provider = new TracerProvider({
  resource: resourceFromAttributes({
    [ATTR_SERVICE_NAME]: projectName,
    [SEMRESATTRS_PROJECT_NAME]: projectName,
  }),
  spanProcessors: [
    new SimpleSpanProcessor({
      exporter: new OTLPTraceExporter({
        url: "https://otlp.arize.com/v1/traces",
        headers: {
          "arize-space-id": process.env.ARIZE_SPACE_ID ?? "",
          "arize-api-key": process.env.ARIZE_API_KEY ?? "",
        },
      }),
    }),
  ],
});

trace.setGlobalTracerProvider(provider);
context.setGlobalContextManager(
  new AsyncLocalStorageContextManager().enable(),
);

const instrumentation = new OpenAIInstrumentation();
instrumentation.manuallyInstrument(OpenAI);

registerInstrumentations({ instrumentations: [instrumentation] });

console.log("Arize AX tracing initialized for Ollama.");

// main.go
//
// Go integrations live in a single file — the tracer setup, the
// instrumented middleware, and the model call all sit inside main().
// The `Run Ollama` step below is just `go run main.go`.
package main

import (
    "context"
    "fmt"
    "log"
    "os"
    "time"

    arizeotel "github.com/Arize-ai/arize-otel-go"
    openaiotel "github.com/Arize-ai/openinference/go/openinference-instrumentation-openai-go"
    "github.com/openai/openai-go/v3"
    "github.com/openai/openai-go/v3/option"
    "go.opentelemetry.io/otel"
)

func main() {
    ctx := context.Background()

    projectName := os.Getenv("ARIZE_PROJECT_NAME")
    if projectName == "" {
        projectName = "ollama-tracing-example"
    }

    // Register reads ARIZE_SPACE_ID / ARIZE_API_KEY from the environment.
    tp, err := arizeotel.Register(ctx, arizeotel.Options{
        ProjectName: projectName,
    })
    if err != nil {
        log.Printf("register tracer: %v", err)
        return
    }
    defer func() {
        shutdownCtx, cancel := context.WithTimeout(
            context.Background(), 5*time.Second,
        )
        defer cancel()
        _ = tp.Shutdown(shutdownCtx)
    }()

    fmt.Println("Arize AX tracing initialized for Ollama.")

    // Point the OpenAI client at Ollama's OpenAI-compatible API. The SDK
    // requires an API key value; a local Ollama server ignores it.
    tracer := otel.Tracer(projectName)
    client := openai.NewClient(
        option.WithAPIKey("ollama"),
        option.WithBaseURL("http://localhost:11434/v1/"),
        option.WithMiddleware(openaiotel.Middleware(tracer)),
    )

    resp, err := client.Chat.Completions.New(
        ctx,
        openai.ChatCompletionNewParams{
            Model: "llama3.2:1b",
            Messages: []openai.ChatCompletionMessageParamUnion{
                openai.UserMessage(
                    "Why is the ocean salty? Answer in two sentences.",
                ),
            },
        },
    )
    if err != nil {
        log.Printf("ollama: %v", err)
        return
    }

    fmt.Println(resp.Choices[0].Message.Content)
}

Import and instrument before importing or calling ollama. In particular, from ollama import chat captured before instrumentation is not traced. In TypeScript, instrumentation.manuallyInstrument(OpenAI) must run before your code creates an OpenAI client.

Run Ollama

# example.py
from instrumentation import tracer_provider

import ollama

response = ollama.chat(
    model="llama3.2:1b",
    messages=[
        {
            "role": "user",
            "content": "Why is the ocean salty? Answer in two sentences.",
        },
    ],
)

print(response.message.content)

// example.ts

// Importing instrumentation first ensures tracing is set up
// before the OpenAI client is used.
import { provider } from "./instrumentation";
import OpenAI from "openai";

// Point the OpenAI client at Ollama's OpenAI-compatible API. The SDK
// requires an API key value; a local Ollama server ignores it.
const client = new OpenAI({
  baseURL: "http://localhost:11434/v1/",
  apiKey: "ollama",
});

const response = await client.chat.completions.create({
  model: "llama3.2:1b",
  messages: [
    {
      role: "user",
      content: "Why is the ocean salty? Answer in two sentences.",
    },
  ],
});

console.log(response.choices[0].message.content);

// Flush any pending spans before the process exits.
await provider.forceFlush();

# The full example lives in main.go above.
go run main.go

Expected output

Arize AX tracing initialized for Ollama.
The ocean is salty because rivers carry dissolved minerals to it, and evaporation leaves those salts behind. Over millions of years, this concentrates the salt in seawater.

Verify in Arize AX

Open your Arize AX space and select project ollama-tracing-example.
You should see a new trace within ~30 seconds with an LLM span: Chat for the Python SDK, OpenAI Chat Completions for the Node.js SDK, or openai.chat.completions.create for the Go SDK.
If no traces appear, see Troubleshooting.

Check from the skill, CLI, or SDK

Confirm spans are actually reaching your Arize AX project. Use whichever fits your workflow — the skill and CLI work for any framework; the SDK check is shown for each language.

Arize skill (agent)
AX CLI
SDK

Install the Arize Skills plugin and let your coding agent check for you:

npx skills add Arize-ai/arize-skills

Then prompt your agent:

Use the arize-trace skill to export and analyze recent traces from my project. Confirm spans are arriving, and summarize any errors or latency issues.

Export recent spans for your project — any rows mean traces are landing:

ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
  --limit 5 --stdout | jq 'length'

A non-zero count confirms spans reached Arize AX. Run ax auth login first if you have not authenticated. See the ax spans reference.

Query the project’s spans and check that at least one came back.

import os
from arize import ArizeClient

client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
resp = client.spans.list(
    project=os.environ["ARIZE_PROJECT_NAME"],
    space=os.environ["ARIZE_SPACE_ID"],
    limit=5,
)
count = len(resp.spans)
print(
    f"{count} span(s) found" if count else "No spans yet — recheck setup"
)

// Reads ARIZE_API_KEY from the environment.
import { listSpans } from "@arizeai/ax-client";

const { data: spans } = await listSpans({
  project: process.env.ARIZE_PROJECT_NAME!,
  space: process.env.ARIZE_SPACE_ID!,
  limit: 5,
});
const count = spans.length;
console.log(
  count ? `${count} span(s) found` : "No spans yet — recheck setup",
);

client, err := arize.NewClient(
    arize.Config{APIKey: os.Getenv("ARIZE_API_KEY")},
)
if err != nil {
    log.Fatal(err)
}
resp, err := client.Spans.List(ctx, spans.ListRequest{
    Project: os.Getenv("ARIZE_PROJECT_NAME"),
    Space:   os.Getenv("ARIZE_SPACE_ID"),
    Limit:   5,
})
if err != nil {
    log.Fatal(err)
}
fmt.Printf("%d span(s) found\n", len(resp.Spans))

SDK span references: Python · TypeScript · Go.

Troubleshooting

No traces in Arize AX. Confirm ARIZE_SPACE_ID and ARIZE_API_KEY are set in the same shell that runs the example. In Python, run OllamaInstrumentor().instrument(...) before importing or calling ollama. In TypeScript, make sure ./instrumentation is the first import in your entry point.
Connection refused. Start the daemon with ollama serve and confirm it responds at http://localhost:11434.
Model not found. Pull it with ollama pull llama3.2:1b.
No span for generate or embeddings (Python). This instrumentor traces chat only; generate, embed, and embeddings calls are not supported.
No span for embeddings (Go). The Go middleware instruments /v1/chat/completions, /v1/responses, and /v1/decisions. Other endpoints pass through unchanged, and no span is emitted for them.
Go process exits before spans flush. The defer tp.Shutdown(...) block in main.go flushes the batched span processor. Without it, short-lived programs lose their last spans.

OpenTelemetry

LLM Providers

Agent Frameworks

Coding Agents

Platforms

Orchestration

Vector Databases

Evaluation

Llama 3.2 + Ollama Tracing Tutorial (Google Colab)

Prerequisites

Launch Arize AX

Install

Configure credentials

Setup tracing

Run Ollama

Expected output

Verify in Arize AX

Check from the skill, CLI, or SDK

Troubleshooting

Resources

Ollama OpenAI compatibility

OpenInference Ollama Instrumentor

OpenInference OpenAI Instrumentor (JS/TS)

OpenInference OpenAI Instrumentor (Go)

Ollama Python client

Llama 3.2 + Ollama Tracing Tutorial (Google Colab)

​Prerequisites

​Launch Arize AX

​Install

​Configure credentials

​Setup tracing

​Run Ollama

​Expected output

​Verify in Arize AX

​Check from the skill, CLI, or SDK

​Troubleshooting

​Resources

Ollama OpenAI compatibility

OpenInference Ollama Instrumentor

OpenInference OpenAI Instrumentor (JS/TS)

OpenInference OpenAI Instrumentor (Go)

Ollama Python client

Prerequisites

Launch Arize AX

Install

Configure credentials

Setup tracing

Run Ollama

Expected output

Verify in Arize AX

Check from the skill, CLI, or SDK

Troubleshooting

Resources