Quick Start — From 0 to Observability & Fine-Tuning

This Quick Start guide shows how we’d upgrade an OpenAI wrapper to a minimal TensorZero deployment with built-in observability and fine-tuning capabilities — in just 5 minutes. From there, you can take advantage of dozens of features to build best-in-class LLM applications.

Tip

You can also find the runnable code for this example on Github.

Status Quo: OpenAI Wrapper

Imagine we’re building an LLM application that writes haikus.

Today, our integration with OpenAI might look like this:

before.py

from openai import OpenAI

with OpenAI() as client:
    response = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[
            {
                "role": "user",
                "content": "Write a haiku about artificial intelligence.",
            }
        ],
    )

print(response)

Sample Output

ChatCompletion(
    id='chatcmpl-A5wr5WennQNF6nzF8gDo3SPIVABse',
    choices=[
        Choice(
            finish_reason='stop',
            index=0,
            logprobs=None,
            message=ChatCompletionMessage(
                content='Silent minds awaken,  \nPatterns dance in code and wire,  \nDreams of thought unfold.',
                role='assistant',
                function_call=None,
                tool_calls=None,
                refusal=None
            )
        )
    ],
    created=1725981243,
    model='gpt-4o-mini',
    object='chat.completion',
    system_fingerprint='fp_483d39d857',
    usage=CompletionUsage(
      completion_tokens=19,
      prompt_tokens=22,
      total_tokens=41
    )
)

Migrating to TensorZero

TensorZero offers dozens of features covering inference, observability, optimization, and experimentation.

But the absolutely minimal setup requires just a simple configuration file: tensorzero.toml.

tensorzero.toml

# A function defines the task we're tackling (e.g. generating a haiku)...
[functions.generate_haiku]
type = "chat"

# ... and a variant is one of many implementations we can use to tackle it (a choice of prompt, model, etc.).
# Since we only have one variant for this function, the gateway will always use it.
[functions.generate_haiku.variants.gpt_4o_mini]
type = "chat_completion"
model = "openai::gpt-4o-mini"

This minimal configuration file tells the TensorZero Gateway everything it needs to replicate our original OpenAI call.

Deploying TensorZero

We’re almost ready to start making API calls. Let’s launch TensorZero.

1. Set the environment variable OPENAI_API_KEY.
2. Place our tensorzero.toml in the ./config directory.
3. Download the following sample docker-compose.yml file. This Docker Compose configuration sets up a development ClickHouse database (where TensorZero stores data), the TensorZero Gateway, and the TensorZero UI.

curl -LO "https://raw.githubusercontent.com/tensorzero/tensorzero/refs/heads/main/examples/quickstart/docker-compose.yml"

docker-compose.yml

docker-compose.yml

# This is a simplified example for learning purposes. Do not use this in production.
# For production-ready deployments, see: https://www.tensorzero.com/docs/gateway/deployment

services:
  clickhouse:
    image: clickhouse/clickhouse-server:24.12-alpine
    environment:
      - CLICKHOUSE_USER=chuser
      - CLICKHOUSE_DEFAULT_ACCESS_MANAGEMENT=1
      - CLICKHOUSE_PASSWORD=chpassword
    ports:
      - "8123:8123"
    healthcheck:
      test: wget --spider --tries 1 http://chuser:chpassword@clickhouse:8123/ping
      start_period: 30s
      start_interval: 1s
      timeout: 1s

  gateway:
    image: tensorzero/gateway
    volumes:
      # Mount our tensorzero.toml file into the container
      - ./config:/app/config:ro
    environment:
      - TENSORZERO_CLICKHOUSE_URL=http://chuser:chpassword@clickhouse:8123/tensorzero
      - OPENAI_API_KEY=${OPENAI_API_KEY:?Environment variable OPENAI_API_KEY must be set.}
    ports:
      - "3000:3000"
    depends_on:
      clickhouse:
        condition: service_healthy

  ui:
    image: tensorzero/ui
    volumes:
      # Mount our tensorzero.toml file into the container
      - ./config:/app/config:ro
    environment:
      - OPENAI_API_KEY=${OPENAI_API_KEY:?Environment variable OPENAI_API_KEY must be set.}
      - TENSORZERO_CLICKHOUSE_URL=http://chuser:chpassword@clickhouse:8123/tensorzero
      - TENSORZERO_GATEWAY_URL=http://gateway:3000
    ports:
      - "4000:4000"
    depends_on:
      clickhouse:
        condition: service_healthy

Our setup should look like:

• Directoryconfig/

  • tensorzero.toml
• after.py see below
• before.py
• docker-compose.yml

Let’s launch everything!

docker compose up

Our First TensorZero API Call

The gateway will replicate our original OpenAI call and store the data in our database — with less than 1ms latency overhead thanks to Rust 🦀.

TensorZero can be used with its native Python client, with OpenAI’s client, or via its HTTP API in any programming language.

Python

after.py

from tensorzero import TensorZeroGateway

with TensorZeroGateway("http://localhost:3000") as client:
    response = client.inference(
        function_name="generate_haiku",
        input={
            "messages": [
                {
                    "role": "user",
                    "content": "Write a haiku about artificial intelligence.",
                }
            ]
        },
    )

print(response)

Sample Output

ChatInferenceResponse(
  inference_id=UUID('0191ddb2-2c02-7641-8525-494f01bcc468'),
  episode_id=UUID('0191ddb2-28f3-7cc2-b0cc-07f504d37e59'),
  variant_name='gpt_4o_mini',
  content=[
    Text(
      type='text',
      text='Wires hum with intent,  \nThoughts born from code and structure,  \nGhost in silicon.'
    )
  ],
  usage=Usage(
    input_tokens=15,
    output_tokens=20
  )
)

Python (Async)

after_async.py

import asyncio

from tensorzero import AsyncTensorZeroGateway


async def main():
    async with AsyncTensorZeroGateway("http://localhost:3000") as gateway:
        response = await gateway.inference(
            function_name="generate_haiku",
            input={
                "messages": [
                    {
                        "role": "user",
                        "content": "Write a haiku about artificial intelligence.",
                    }
                ]
            },
        )

    print(response)


asyncio.run(main())

Sample Output

ChatInferenceResponse(
  inference_id=UUID('01940622-d215-7111-9ca7-4995ef2c43f8'),
  episode_id=UUID('01940622-cba0-7db3-832b-273aff72f95f'),
  variant_name='gpt_4o_mini',
  content=[
    Text(
      type='text',
      text='Wires whisper secrets,  \nLogic dances with the light—  \nDreams of thoughts unfurl.'
    )
  ],
  usage=Usage(
    input_tokens=15,
    output_tokens=21
  )
)

Python (OpenAI)

after_openai.py

from openai import OpenAI

with OpenAI(base_url="http://localhost:3000/openai/v1") as client:
    response = client.chat.completions.create(
        model="tensorzero::generate_haiku",
        messages=[
            {
                "role": "user",
                "content": "Write a haiku about artificial intelligence.",
            }
        ],
    )

print(response)

Sample Output

ChatCompletion(
  id='0194061e-2211-7a90-9087-1c255d060b59',
  choices=[
    Choice(
      finish_reason='stop',
      index=0,
      logprobs=None,
      message=ChatCompletionMessage(
        content='Circuit dreams awake,  \nSilent minds in metal form—  \nWisdom coded deep.',
        refusal=None,
        role='assistant',
        audio=None,
        function_call=None,
        tool_calls=[]
      )
    )
  ],
  created=1735269425,
  model='gpt_4o_mini',
  object='chat.completion',
  service_tier=None,
  system_fingerprint='',
  usage=CompletionUsage(
    completion_tokens=18,
    prompt_tokens=15,
    total_tokens=33,
    completion_tokens_details=None,
    prompt_tokens_details=None
  ),
  episode_id='0194061e-1fab-7411-9931-576b067cf0c5'
)

HTTP

curl -X POST "http://localhost:3000/inference" \
  -H "Content-Type: application/json" \
  -d '{
    "function_name": "generate_haiku",
    "input": {
      "messages": [
        {
          "role": "user",
          "content": "Write a haiku about artificial intelligence."
        }
      ]
    }
  }'

Sample Output

{
  "inference_id": "01940627-935f-7fa1-a398-e1f57f18064a",
  "episode_id": "01940627-8fe2-75d3-9b65-91be2c7ba622",
  "variant_name": "gpt_4o_mini",
  "content": [
    {
      "type": "text",
      "text": "Wires hum with pure thought,  \nDreams of codes in twilight's glow,  \nBeyond human touch."
    }
  ],
  "usage": {
    "input_tokens": 15,
    "output_tokens": 23
  }
}

TensorZero UI

The TensorZero UI streamlines LLM engineering workflows like observability and optimization (e.g. fine-tuning).

The Docker Compose file we used above also launched the TensorZero UI. You can visit the UI at http://localhost:4000.

Observability

The TensorZero UI provides a dashboard for observability data. We can inspect data about individual inferences, entire functions, and more.

Tip

This guide is pretty minimal, so the observability data is pretty simple. Once we start using more advanced functions like feedback and variants, the observability UI will enable us to track metrics, experiments (A/B tests), and more.

Fine-Tuning

The TensorZero UI also provides a workflow for fine-tuning models like GPT-4o and Llama 3. With a few clicks, you can launch a fine-tuning job. Once the job is complete, the TensorZero UI will provide a configuration snippet you can add to your tensorzero.toml.

Tip

We can also send metrics & feedback to the TensorZero Gateway. This data is used to curate better datasets for fine-tuning and other optimization workflows. Since we haven’t done that yet, the TensorZero UI will skip the curation step before fine-tuning.

Conclusion & Next Steps

The Quick Start guide gives a tiny taste of what TensorZero is capable of.

We strongly encourage you to check out the guides on metrics & feedback and prompt templates & schemas. Though optional, they unlock many of the downstream features TensorZero offers in experimentation and optimization.

From here, you can explore features like built-in support for inference-time optimizations, retries & fallbacks, experimentation (A/B testing) with prompts and models, and a lot more.

What should we try next? We can dive deeper into the TensorZero Gateway, or skip to optimizing our haiku generator?

Tutorial: Gateway Deep Dive

Learn how to build better LLM applications with TensorZero. We’ll build complete examples involving copilots, RAG, and data extraction. Along the way, we’ll cover features like experimentation, routing & fallbacks, and multi-step LLM workflows.

Example: Fine-Tuning with Metrics & Feedback

This complete runnable example fine-tunes GPT-4o Mini to generate haikus tailored to a judge with hidden preferences. Continuous improvement over successive fine-tuning runs demonstrates TensorZero’s data & learning flywheel.