1. Docs
2. Send Data to Honeycomb
3. LLMs
4. Text to JSON Quick Start

Text to JSON Quick Start

Table of Contents

An extremely common use case for large language models (LLMs) is to convert text to JSON where the LLM:

• generates a JSON object from user input
• parses that object
• validates its contents
• uses the content elsewhere in the application

Collecting observability data for this process is a great fit as clear and measurable outcomes are present for each step. This data answers questions like:

• Do some user inputs result in higher latency or more errors?
• Was the JSON object structurally valid as per the JSON schema?
• Did the JSON object contain expected fields?
• Did the new version of our prompt result in more invalid JSON objects?
• Are there particular patterns in the user input that result in invalid JSON objects?

Adding telemetry to your LLM and then analyzing with Honeycomb provides a flexible way to contribute towards and measure the overall user experience. Use our Quick Start to instrument your LLM application.

Before You Begin 

Before instrumenting your LLM application, you’ll need to do a few things:

1. Create a Honeycomb Account. Signup is free!
2. Create a Honeycomb Team. Complete your account creation by giving us a team name. Honeycomb uses teams to organize groups of users, grant them access to data, and create a shared work history in Honeycomb.
   Tip

   We recommend using your company or organization name as your Honeycomb team name.
3. Get Your Honeycomb API Key. To send data to Honeycomb, you’ll need your Honeycomb API Key. Once you create your team, you will be able to view or copy your API key. Make note of it; you will need it later! You can also find your Honeycomb API Key any time in your Environment Settings.

Send Telemetry Data to Honeycomb 

Once you have your Honeycomb API key and your LLM application to instrument, it’s time to send telemetry data to Honeycomb!

To instrument your LLM, you will add automatic instrumentation to your code for standard trace data telemetry, and then add custom instrumentation specifically for your LLM.

Add Automatic Instrumentation to Your Code 

The quickest way to start seeing your trace data in Honeycomb is to use OpenTelemetry, an open-source collection of tools, APIs, and SDKs, to automatically inject instrumentation code into your application without requiring explicit changes to your codebase.

When you add automatic instrumentation to your code, OpenTelemetry will inject spans, which represent units of work or operations within your application that you want to capture and analyze for observability purposes.

npm install --save @opentelemetry/auto-instrumentations-node

// Example filename: tracing.js
'use strict';

const opentelemetry = require('@opentelemetry/sdk-node');
const { OTLPTraceExporter } =  require('@opentelemetry/exporter-trace-otlp-http');
const { getNodeAutoInstrumentations } = require('@opentelemetry/auto-instrumentations-node');

const sdk = new opentelemetry.NodeSDK({
    traceExporter: new OTLPTraceExporter(),
    instrumentations: [
        getNodeAutoInstrumentations({
            // we recommend disabling fs autoinstrumentation since it can be noisy
            // and expensive during startup
            '@opentelemetry/instrumentation-fs': {
                enabled: false,
            },
        }),
    ],
});

sdk.start();

export OTEL_SERVICE_NAME="your-service-name"
export OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf"
export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.honeycomb.io:443" # US instance
#export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.eu1.honeycomb.io:443" # EU instance
export OTEL_EXPORTER_OTLP_HEADERS="x-honeycomb-team=your-api-key"

export OTEL_EXPORTER_OTLP_HEADERS="x-honeycomb-team=your-api-key,x-honeycomb-dataset=your-dataset"

node -r ./tracing.js YOUR_APPLICATION_NAME.js

export OTEL_SERVICE_NAME="your-service-name"
export OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf"
export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.honeycomb.io:443" # US instance
#export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.eu1.honeycomb.io:443" # EU instance
export OTEL_EXPORTER_OTLP_HEADERS="x-honeycomb-team=<your-api-key>"

export OTEL_EXPORTER_OTLP_HEADERS="x-honeycomb-team=your-api-key,x-honeycomb-dataset=your-dataset"

opentelemetry-instrument python YOUR_APPLICATION_NAME.py

curl -L -O https://github.com/open-telemetry/opentelemetry-java-instrumentation/releases/latest/download/opentelemetry-javaagent.jar

java -javaagent:opentelemetry-javaagent.jar -jar /path/to/myapp.jar

java \
-Dotel.javaagent.configuration-file=/path/to/properties/file \
-javaagent:opentelemetry-javaagent.jar \
-jar /path/to/myapp.jar

dotnet add package OpenTelemetry
dotnet add package OpenTelemetry.Extensions.Hosting
dotnet add package OpenTelemetry.Instrumentation.AspNetCore
dotnet add package OpenTelemetry.Instrumentation.Http

services.AddOpenTelemetry().WithTracing(builder => builder
    .AddAspNetCoreInstrumentation()
    .AddHttpClientInstrumentation()
    .AddOtlpExporter());

export OTEL_SERVICE_NAME="your-service-name"
export OTEL_EXPORTER_OTLP_PROTOCOL="http/protobuf"
export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.honeycomb.io:443" # US instance
#export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.eu1.honeycomb.io:443" # EU instance
export OTEL_EXPORTER_OTLP_HEADERS="x-honeycomb-team=<your-api-key>"

dotnet run

go get \
  github.com/honeycombio/otel-config-go/otelconfig \
  go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp

package main

import (
    "fmt"
    "log"
    "net/http"

    "github.com/honeycombio/otel-config-go/otelconfig"
    "go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp"
)

// Implement an HTTP Handler function to be instrumented
func httpHandler(w http.ResponseWriter, r *http.Request) {
    fmt.Fprintf(w, "Hello, World")
}

func main() {
    // use otelconfig to set up OpenTelemetry SDK
    otelShutdown, err := otelconfig.ConfigureOpenTelemetry()
    if err != nil {
        log.Fatalf("error setting up OTel SDK - %e", err)
    }
    defer otelShutdown()

    // Initialize HTTP handler instrumentation
    handler := http.HandlerFunc(httpHandler)
    wrappedHandler := otelhttp.NewHandler(handler, "hello")
    http.Handle("/hello", wrappedHandler)

    // Serve HTTP server
    log.Fatal(http.ListenAndServe(":3030", nil))
}

export OTEL_SERVICE_NAME="your-service-name"
export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.honeycomb.io:443" # US instance
#export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.eu1.honeycomb.io:443" # EU instance
export OTEL_EXPORTER_OTLP_HEADERS="x-honeycomb-team=your-api-key"

go run YOUR_APPLICATION_NAME.go

gem 'opentelemetry-sdk'
gem 'opentelemetry-exporter-otlp'
gem 'opentelemetry-instrumentation-all'

bundle install

# config/initializers/opentelemetry.rb
require 'opentelemetry/sdk'
require 'opentelemetry/exporter/otlp'
require 'opentelemetry/instrumentation/all'

OpenTelemetry::SDK.configure do |c|
    c.use_all() # enables all instrumentation!
end

export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.honeycomb.io" # US instance
#export OTEL_EXPORTER_OTLP_ENDPOINT="https://api.eu1.honeycomb.io" # EU instance
export OTEL_EXPORTER_OTLP_HEADERS="x-honeycomb-team=your-api-key"
export OTEL_SERVICE_NAME="your-service-name"

Generate Automated Data 

Now that you have added automatic instrumentation to your application and have it running in your development environment, interact with your application by making a few requests. Making requests to your service will generate telemetry data and send it to Honeycomb where it will appear in the Honeycomb UI within seconds.

Add Custom Instrumentation for LLMs 

With OpenTelemetry’s automatic instrumentation now installed in your application, trace data is being sent to Honeycomb.

The next step is to add custom instrumentation that tracks all relevant information related to your LLM feature. In OpenTelemetry, custom instrumentation is called manual instrumentation. To get the most out of your traces, you must use OpenTelemetry APIs to instrument.

To add custom instrumentation, create a single span that tracks all relevant information related to your LLM feature. Specifically, the minimum information to track must include:

• User ID
• Prompt version
• User input
• Full prompt text
• Full LLM response
• Any error including parsing JSON and/or validating it
• Error message
• Token count

Examples 

The following code examples show how to capture the correct information on an OpenTelemetry span:

import { trace, Span, SpanStatusCode } from "@opentelemetry/api";

const tracer = trace.getTracer("llm.tracer");

function getJsonFromText(
  userInput: string,
  userId: string,
  promptTemplate: string,
  promptVersion: string
) {
  return tracer.startActiveSpan("app.get_json_from_text", (span: Span) => {
    span.setAttribute("app.user_id", userId);
    span.setAttribute("app.llm.prompt_version", promptVersion);
    span.setAttribute("app.llm.user_input", userInput);

    try {
        // Programmatically build the full prompt.
        // The output is the entire prompt you'd send to the LLM,
        // after RAG or any other context-building operations.
        const fullPrompt = buildFullPrompt(promptTemplate, userInput);

        span.setAttribute("app.llm.prompt_text", fullPrompt);

        // Call the LLM and get back the text of the result
        // and the number of tokens used.
        const { response, tokenCount } = callLLM(full_prompt);

        span.setAttribute("app.llm.response", response);
        span.setAttribute("app.llm.token_count", tokenCount);

        // Parse the JSON object and validate it,
        // capturing any errors you might encounter.
        const result = parseAndValidateResponse(response);

        return result;
    } catch (ex) {
        // Track any unexpected errors.
        span.setStatus({ code: SpanStatusCode.ERROR });
        span.recordException(ex);
    } finally {
        span.end();
    }
  });
}

function parseAndValidateResponse(llmResult: string) {
  const currentSpan = trace.getActiveSpan();

  // Extract and parse the JSON object from the LLM response.
  const { extracted, result, extractionError } = extractAndParseJson(llmResult);
  if (!extracted) {
    currentSpan.setAttribute("error.message", extractionError);
    currentSpan.setStatus({ code: SpanStatusCode.ERROR });
    return null;
  }

  // Validate the structure of the result, capturing
  // any validation errors you might encounter.
  const { validated, validationError } = validateResult(result);
  if (!validated) {
    currentSpan.setAttribute("error.message", validationError);
  }

  return result;
}

from opentelemetry import trace
from opentelemetry.trace import Status, StatusCode

tracer = trace.get_tracer("llm.tracer")

def get_json_from_text(user_input, user_id, prompt_template, prompt_version):
    with tracer.start_as_current_span("app.get_json_from_text") as span:
        span.set_attribute("app.user_id", user_id)
        span.set_attribute("app.llm.prompt_version", prompt_version)
        span.set_attribute("app.llm.user_input", user_input)

        try:
            # Programmatically build the full prompt.
            # The output is the entire prompt you'd send to the LLM,
            # after RAG or any other context-building operations.
            full_prompt = build_full_prompt(prompt_template, user_input)

            span.set_attribute("app.llm.prompt_text", full_prompt)

            # Call the LLM and get back the text of the result
            # and the number of tokens used.
            llm_result, token_count = call_llm(full_prompt)

            span.set_attribute("app.llm.response", response)
            span.set_attribute("app.llm.token_count", token_count)

            # Parse the JSON object and validate it,
            # capturing any errors you might encounter.
            result = parse_and_validate_response(llm_result)

            return result
        except Exception as ex:
            # Track any unexpected errors.
            current_span.set_status(Status(StatusCode.ERROR))
            current_span.record_exception(ex)

def parse_and_validate_response(llm_result):
    current_span = trace.get_current_span()

    # Extract and parse the JSON object from the LLM response.
    extracted, result, extraction_error = extract_and_parse_json(llm_result)
    if not extracted:
        current_span.set_attribute("error.message", extraction_error)
        current_span.set_status(Status(StatusCode.ERROR))
        return None

    # Validate the structure of the result, capturing
    # any validation errors you might encounter.
    validated, validation_error = validate_result(result)
    if not validated:
        current_span.set_attribute("error.message", validation_error)

    return result

Explore Your Data 

With your app running and telemetry being sent to Honeycomb, it’s time to explore your data.

Create a Board 

For quick reference over time, you should create a Board to show LLM-specific queries of interest. We recommend creating a Board first before trying queries, so you can save with ease later.

To create a Board:

1. In the Honeycomb UI’s left navigation menu, select Boards with its Bulletin Board icon. When the left navigation menu is compact, only the icon appears.
2. Select New Board.
3. In the modal that appears, name your new board, such as “LLM Dashboard.” Optionally, give your Board a description to help others find and use it. Determine the board’s Sharing setting - Public to the Team or Limited to Collaborators.
4. Select Create to finish. Your new board appears next.

Next Steps 

1. Select Add Query to go to the Query Builder display.
2. Use the example queries in the next section to populate your LLM Board.
3. Follow the directions to add queries to an existing Board.

Create Queries 

Now it’s time to create your first queries for LLMs!

Use the query examples below to explore the performance and behavior of your LLM application. The specific attributes should exist in your data and environment if you added custom instrumentation for LLMs in the previous step.

Enter each example query using the Query Builder. These example queries use two to three of the VISUALIZE, WHERE, and GROUP BY clauses, located at the top of the Query Builder.

• VISUALIZE - Performs a calculation and displays a corresponding graph over time. Most VISUALIZE queries return a line graph while the HEATMAP visualization shows the distribution of data over time
• WHERE - Filters based on attribute parameter(s)
• GROUP BY - Groups fields by attribute parameter(s)

Track Overall Latency 

This query tracks overall latency of all LLM-related operations and the slowest requests.

Use to identify any spikes in latency, or if latency is increasing over time. In the event of a spike, you can investigate what happened by using BubbleUp to find outliers.

Track Invalid JSON Objects 

This query shows each instance that a user input led to a bad JSON object, whether that was because of a parsing error or a validation error.

Use to identify exactly which inputs lead to bad behavior, which makes it easier to identify specific bugs to solve.

Track all User Inputs Grouped by Response and Errors 

This query shows groups of all inputs and LLM outputs that succeeded.

Use to understand general user behavior, and to identify any patterns in user input that leads to a particularly useful response. It’s just as helpful to understand what’s working as it is to understand what isn’t.

Show Token Usage Over Time 

This query tracks token use over time, grouped by user ID.

Use to understand how many tokens being used over time, but also to identify that usage down to specific users, as often a small number of users is responsible for the majority of usage.

Investigate Specific Traces 

The queries on our LLM Board act as a starting point. If curious about specific behavior, you can view a specific trace that represents one request. Select any point on a graph, and in the menu that appears, select View trace. The next screen displays a trace detail view that lets you see what happened step by step.

Next Steps 

The queries on our LLM board act as a referenceable starting point. If you’re curious about specific behavior(s), start with any query and:

1. Add additional fields in the GROUP BY clause to slice your data into revealing interesting field values.
2. Use BubbleUp to find outlier behavior and identify its contributing characteristics.
3. Select a specific trace that represents one request to see what happened step-by-step.

Did you find what you were looking for?

Yes No

---

If you have questions, join our Pollinators Community Slack!
Pro/Enterprise users can visit Honeycomb Support or email support@honeycomb.io.

Submit