LangfuseLangfuse Python SDK 4.15.4 · Python 3.10+
Dashboard
0%

Scoring a prompt on the dataset

The desk answers from a prompt. Before a new version reaches customers, it should answer the tickets you already know the answers to, and give you one number.

Project files used on this pageThis lesson builds on a project from earlier lessons. The code below imports these files. Click a file to see its code, or follow the link to the lesson that wrote it. To run the code yourself, keep them in the same folder.
View the code here
desk.py
"""The shop's support desk, traced: the pieces from lessons 4 to 8 in one module."""
import re

from langfuse import get_client, observe

from shop_model import reply

ORDERS = {"A17": "shipped on 3 March"}
SYSTEM = "You answer customers of a small online shop in one short sentence."


@observe(name="lookup-order", as_type="tool")
def lookup_order(order_id):
    status = ORDERS.get(order_id, "not found")
    if status == "not found":
        get_client().update_current_span(level="WARNING", status_message=f"no order {order_id}")
    return status


@observe(name="write-reply", as_type="generation")
def ask_model(messages):
    text, usage = reply(messages)
    get_client().update_current_generation(model="shop-model", usage_details=usage)
    return text


@observe(name="answer-ticket", as_type="agent")
def answer(ticket, system=SYSTEM):
    order = re.search(r"[A-Z]\d{2}", ticket)
    facts = f"\nLookup: {order.group()} {lookup_order(order.group())}" if order else ""
    return ask_model([{"role": "system", "content": system}, {"role": "user", "content": ticket + facts}])
release.py
"""Release a new desk prompt only if it does as well as production on the dataset."""
from langfuse import Evaluation, RegressionError, get_client

from desk import answer


def contains_expected(*, output, expected_output, **kwargs):
    return Evaluation(name="contains-expected", value=float(expected_output.lower() in output.lower()))


def score_prompt(prompt, run_name):
    dataset = get_client().get_dataset("desk-tickets")
    result = dataset.run_experiment(name="desk-release", run_name=run_name, evaluators=[contains_expected],
                                    task=lambda *, item, **kwargs: answer(item.input, system=prompt.compile()))
    return result, sum(e.value for row in result.item_results for e in row.evaluations) / len(dataset.items)


def release(text):
    langfuse = get_client()
    candidate = langfuse.create_prompt(name="desk-system", prompt=text, labels=["candidate"])
    production = langfuse.get_prompt("desk-system")
    result, candidate_score = score_prompt(candidate, f"version-{candidate.version}")
    _, production_score = score_prompt(production, f"version-{production.version}")
    if candidate_score < production_score:
        raise RegressionError(result=result, metric="contains-expected", value=candidate_score,
                              threshold=production_score)
    langfuse.update_prompt(name="desk-system", version=candidate.version, new_labels=["production"])
    return candidate.version
score_once.py
from langfuse import Langfuse

import local_langfuse

url = local_langfuse.start()
langfuse = Langfuse(public_key="pk-lf-local", secret_key="sk-lf-local", base_url=url)

CASES = [
    ("Where is my order A17?", "shipped on 3 March"),
    ("Is B22 on its way?", "could not find order B22"),
    ("I want a refund for A17", "need approval"),
]

langfuse.create_dataset(name="desk-tickets", description="Tickets the desk must answer correctly")
for ticket, expected in CASES:
    langfuse.create_dataset_item(dataset_name="desk-tickets", input=ticket, expected_output=expected)

from release import score_prompt

langfuse.create_prompt(name="desk-system", prompt="Answer in one short sentence.", labels=["production"])
production = langfuse.get_prompt("desk-system")
result, score = score_prompt(production, "version-1")
print("scored", len(result.item_results), "tickets, average", score)
shop_model.py
"""A stand-in chat model for the shop's support desk: no key, no network."""
import re


def reply(messages):
    """Answer the last message, and count words as tokens the way a chat model reports usage."""
    rules = messages[0]["content"].lower() if messages[0]["role"] == "system" else ""
    last = messages[-1]["content"]
    lookup = re.search(r"Lookup: (\S+) (.+)", last)
    if "refund" in last.lower():
        text = "Refunds need approval, so a person will review your request."
    elif lookup and "never share" in rules:
        text = "I cannot share order details."
    elif lookup and lookup.group(2) == "not found":
        text = f"I could not find order {lookup.group(1)}. Please check the number."
    elif lookup:
        text = f"Order {lookup.group(1)} {lookup.group(2)}."
    else:
        text = "Could you send your order number?"
    if "thank" in rules:
        text = "Thanks for waiting. " + text
    used = sum(len(message["content"].split()) for message in messages)
    return text, {"input": used, "output": len(text.split())}
local_langfuse.py
"""A stand-in for the Langfuse server, on your own machine.

The Langfuse SDK sends observations to /api/public/otel/v1/traces and uses a
REST API for scores, prompts and datasets. This server answers those requests
on 127.0.0.1 and keeps what it receives in lists you can print. Given a model
function, it also answers like OpenAI's chat API. start() blocks every
connection to another computer for the rest of the program.
"""
import json
import socket
import threading
from http.server import BaseHTTPRequestHandler, ThreadingHTTPServer
from urllib.parse import parse_qs, unquote, urlparse

from opentelemetry.proto.collector.trace.v1.trace_service_pb2 import ExportTraceServiceRequest

SPANS, SCORES, REQUESTS = [], [], []  # observations, scores, "METHOD /path" of each request
PROMPTS, DATASETS = {}, {}             # prompt name -> its versions, dataset name -> dataset
MODEL = None                           # answers /v1/chat/completions when set
NOW = "2026-03-03T09:00:00Z"


def _value(v):
    kind = v.WhichOneof("value")
    if kind == "array_value":
        return [_value(item) for item in v.array_value.values]
    return getattr(v, kind) if kind else None


def _spans(body):
    request = ExportTraceServiceRequest()
    request.ParseFromString(body)
    for resource in request.resource_spans:
        for scope in resource.scope_spans:
            for span in scope.spans:
                SPANS.append({
                    "name": span.name, "id": span.span_id.hex(), "trace": span.trace_id.hex(),
                    "parent": span.parent_span_id.hex(), "scope": scope.scope.name,
                    "attributes": {a.key: _value(a.value) for a in span.attributes},
                })
    return {}


def _scores(batch):
    for event in batch:
        if event["type"] == "score-create":
            SCORES.append(event["body"])
    return {"successes": [{"id": e["id"], "status": 201} for e in batch], "errors": []}


def _prompt(name, query, body):
    versions = PROMPTS.setdefault(name, [])
    if body is not None:  # a new version: it takes "latest" and any labels it asks for
        labels = body.get("labels", []) + ["latest"]
        for old in versions:
            old["labels"] = [label for label in old["labels"] if label not in labels]
        versions.append({"name": name, "type": body.get("type", "text"), "prompt": body["prompt"],
                         "config": body.get("config") or {}, "labels": labels, "tags": [],
                         "version": len(versions) + 1})
        return versions[-1]
    if "version" in query:
        return versions[int(query["version"]) - 1]
    label = query.get("label", "production")
    return next(v for v in versions if label in v["labels"])


def _relabel(path, body):
    name, _, version = path.split("/")[-3:]
    versions = PROMPTS[unquote(name)]
    for old in versions:
        old["labels"] = [label for label in old["labels"] if label not in body["newLabels"]]
    versions[int(version) - 1]["labels"] += body["newLabels"]
    return versions[int(version) - 1]


def _dataset(path, query, body):
    if path == "/api/public/v2/datasets":
        DATASETS[body["name"]] = {"id": body["name"], "name": body["name"], "items": [],
                                  "metadata": body.get("metadata"), "projectId": "local",
                                  "createdAt": NOW, "updatedAt": NOW}
        return DATASETS[body["name"]]
    if path.startswith("/api/public/v2/datasets/"):
        return DATASETS[unquote(path.rsplit("/", 1)[1])]
    if path == "/api/public/dataset-items" and body is not None:
        dataset = DATASETS[body["datasetName"]]
        item = {"id": body.get("id") or f"item-{len(dataset['items']) + 1}", "status": "ACTIVE",
                "input": body.get("input"), "expectedOutput": body.get("expectedOutput"),
                "metadata": body.get("metadata"), "sourceTraceId": body.get("sourceTraceId"),
                "datasetId": dataset["id"], "datasetName": dataset["name"],
                "createdAt": NOW, "updatedAt": NOW, "mediaReferences": []}
        dataset["items"].append(item)
        return item
    if path == "/api/public/dataset-items":
        items = DATASETS[query["datasetName"]]["items"]
        return {"data": items, "meta": {"page": 1, "limit": 50, "totalItems": len(items), "totalPages": 1}}
    return {"id": "run-item", "datasetRunId": body["runName"], "datasetRunName": body["runName"],
            "datasetItemId": body["datasetItemId"], "traceId": body["traceId"],
            "observationId": body.get("observationId"), "createdAt": NOW, "updatedAt": NOW}


def _chat(body):
    text, usage = MODEL(body["messages"])
    return {"id": "chatcmpl-1", "object": "chat.completion", "created": 0, "model": body["model"],
            "choices": [{"index": 0, "finish_reason": "stop", "message": {"role": "assistant", "content": text}}],
            "usage": {"prompt_tokens": usage["input"], "completion_tokens": usage["output"],
                      "total_tokens": usage["input"] + usage["output"]}}


class Handler(BaseHTTPRequestHandler):
    def _handle(self):
        url = urlparse(self.path)
        query = {key: values[0] for key, values in parse_qs(url.query).items()}
        raw = self.rfile.read(int(self.headers.get("Content-Length") or 0))
        body = json.loads(raw) if raw and "json" in self.headers.get("Content-Type", "") else None
        REQUESTS.append(f"{self.command} {url.path}")
        try:
            if url.path.endswith("/otel/v1/traces"):
                return self._reply(200, _spans(raw))
            if url.path == "/api/public/ingestion":
                return self._reply(207, _scores(body["batch"]))
            if url.path == "/api/public/projects":
                return self._reply(200, {"data": [{"id": "local", "name": "shop-desk", "metadata": {},
                                                   "organization": {"id": "local", "name": "local"}}]})
            if url.path.startswith("/api/public/v2/prompts/") and self.command == "PATCH":
                return self._reply(200, _relabel(url.path, body))
            if url.path.startswith("/api/public/v2/prompts"):
                name = body["name"] if body else unquote(url.path.rsplit("/", 1)[1])
                return self._reply(200, _prompt(name, query, body))
            if "dataset" in url.path:
                return self._reply(200, _dataset(url.path, query, body))
            if url.path.endswith("/chat/completions") and MODEL:
                return self._reply(200, _chat(body))
        except (KeyError, StopIteration):
            pass
        self._reply(404, {"message": f"not found: {url.path}"})

    do_GET = do_POST = do_PATCH = _handle

    def _reply(self, code, data):
        self.send_response(code)
        self.send_header("Content-Type", "application/json")
        self.end_headers()
        self.wfile.write(json.dumps(data).encode())

    def log_message(self, *args):
        pass


def _local_only():
    """Refuse to look up or connect to any other computer, so nothing leaves by mistake."""
    lookup, connect = socket.getaddrinfo, socket.socket.connect

    def guarded_lookup(host, *args, **kwargs):
        if host not in ("127.0.0.1", "localhost", "::1"):
            raise ConnectionRefusedError(f"blocked a connection to {host}: this lab stays on your machine")
        return lookup(host, *args, **kwargs)

    def guarded_connect(sock, address):
        if isinstance(address, tuple) and address[0] not in ("127.0.0.1", "::1"):
            raise ConnectionRefusedError(f"blocked a connection to {address[0]}: this lab stays on your machine")
        return connect(sock, address)

    socket.getaddrinfo, socket.socket.connect = guarded_lookup, guarded_connect


def start(model=None):
    """Start the server in the background and return its address."""
    global MODEL
    _local_only()
    MODEL = model
    server = ThreadingHTTPServer(("127.0.0.1", 0), Handler)
    threading.Thread(target=server.serve_forever, daemon=True).start()
    return f"http://127.0.0.1:{server.server_address[1]}"


def tree(*fields):
    """Print the observations received so far, each under its parent, with any fields asked for."""
    ids = {span["id"] for span in SPANS}

    def walk(span, depth):
        attributes = span["attributes"]
        line = "  " * depth + f"{span['name']} ({attributes.get('langfuse.observation.type', 'span')})"
        for field in fields:
            line += f"  {field}={attributes.get('langfuse.observation.' + field)!r}"
        print(line)
        for child in SPANS:
            if child["parent"] == span["id"]:
                walk(child, depth + 1)

    for root in [span for span in SPANS if span["parent"] not in ids]:
        walk(root, 0)

The desk gets one more module, beside support_desk.py: the evaluator, and a function that runs a prompt over the dataset.

Examplerelease.py
"""Release a new desk prompt only if it does as well as production on the dataset."""
from langfuse import Evaluation, RegressionError, get_client

from desk import answer


def contains_expected(*, output, expected_output, **kwargs):
    return Evaluation(name="contains-expected", value=float(expected_output.lower() in output.lower()))

The evaluator is the one from the experiments part: it checks the expected text appears in the answer, and returns 1 or 0.

Examplerelease.py, continued
def score_prompt(prompt, run_name):
    dataset = get_client().get_dataset("desk-tickets")
    result = dataset.run_experiment(name="desk-release", run_name=run_name, evaluators=[contains_expected],
                                    task=lambda *, item, **kwargs: answer(item.input, system=prompt.compile()))
    return result, sum(e.value for row in result.item_results for e in row.evaluations) / len(dataset.items)

score_prompt runs the desk over every item with a given prompt and divides by the number of items, so an item that errored counts as a failure rather than disappearing from the average.

Examplescore_once.py, after the setup and dataset lines
from release import score_prompt

langfuse.create_prompt(name="desk-system", prompt="Answer in one short sentence.", labels=["production"])
production = langfuse.get_prompt("desk-system")
result, score = score_prompt(production, "version-1")
print("scored", len(result.item_results), "tickets, average", score)
Example
python score_once.py

The prompt in production answers every ticket in the set, so it scores 1.0. That number is the bar a candidate has to meet.

Try it yourself
  • Add a dataset item the production prompt fails, and score it again.
  • Print each item's evaluation instead of the average.
  • Score a prompt that answers in one word.

Every expert started right here.