ObservabilityGo

Getting started

Before you start logging you will have to create a LogRepository on the Maxim dashboard. To create a log repository,click on Logs and the click on + icon on the sidebar. You can use the ID of that repository to push logs.

Tracing one shot logs

Initializing Maxim Go SDK

import "github.com/maximhq/maxim-go/logging"
 
trace := logger.Trace(&logging.TraceConfig{
    Id: "trace-id", 
    Name: "trace-name", 
    Tags: map[string]string{"key": "value"}
})

Tracing multi-turn logs

Creating a Session

session := logger.Session(&logging.SessionConfig{
    Id: "session-id", 
    Name: "session-name", 
    Tags: map[string]string{"key": "value"}
})

Once session object is created, you can add multiple traces across the lifecycle of the conversation.

Create a Session and add a Trace to it

import "github.com/maximhq/maxim-go/logging"
 
session := logger.Session(&logging.SessionConfig{Id: "session-id"})
trace:= session.Trace(&logging.TraceConfig{Id: "trace-id"})

Using custom ids for Traces/Sessions

Using custom ids allows you to fetch a trace in any function using the same id. This can be useful in updating trace across your workflow.

Trace

Using custom ids for Traces

import "github.com/maximhq/maxim-go/logging"
 
// ... in function 1
trace := logger.Trace(&logging.TraceConfig{Id: "trace-id"})
// ... in function 2
trace := logger.Trace(&logging.TraceConfig{Id: "trace-id"})
// it returns the same trace object
trace.AddTag("key", "value")

Session

Using custom ids for Sessions

import "github.com/maximhq/maxim-go/logging"
 
// ... in function 1
session := logger.Session(&logging.SessionConfig{Id: "session-id"})
// ... in function 2
session := logger.Session(&logging.SessionConfig{Id: "session-id"})
// it returns the same session object
session.AddTag("key", "value")

Elements of Traces

Once you have a trace object, you can add

Span

A Span (short for timespan), groups a bunch of items (Events, Retrieval, Generation, Feedback).

Adding a span to a Trace

import "github.com/maximhq/maxim-go/logging"
 
span := trace.AddSpan(&logging.SpanConfig{
    Id: "span-id", 
    Name: "name", 
    Tags: map[string]string{"key": "value"}
})
span.AddEvent("event-id","event-name", map[string]string{"tag-key": "tag-values"})
span.End()

Event

An Event is a point in time when something happened in the system.

Adding an Event to a Trace

import "github.com/maximhq/maxim-go/logging"
 
trace.AddEvent("event-id", "event name", map[string]string{"key": "value"})

Retrieval

A Retrieval is a special type of Span in Maxim, which represents a retrieval query to a knowledge base or vector database.

Adding a Retrieval to a Trace

import "github.com/maximhq/maxim-go/logging"
 
retrieval := span.AddRetrieval(&logging.RetrievalConfig{
    Id: "retrieval-id", 
    Name: "name", 
    Metadata: map[string]string{"key": "value"}
})
retrieval.SetInput("How many PTO days do I have?")
retrieval.SetOutput([]string{"doc1", "doc2"})
retrieval.End()

Generation

A Generation is a special type of Span in Maxim, which represents a call to an LLM.

generation.result expects result to be in OpenAI response format. Here is the reference to the OpenAI response format

Adding a Generation to a Trace

import "github.com/maximhq/maxim-go/logging"
 
generation := span.AddGeneration(&logging.GenerationConfig{
	Id: "generation-id",
	Name: "name",
	Provider: "openai",
	Model: "gpt-3.5-turbo-16k",
	ModelParameters: map[string]interface{}{"temperature": 3},
	Messages: []logging.CompletionRequest{
		{
			Role:    "system",
			Content: "You are a helpful assistant",
		},
	},
})
 
generation.AddMessages([]logging.CompletionRequest{
		{
			Role:    "user",
			Content: "Do this and that",
		},
})
 
// This shows TextCompletionExample
generation.SetResult(&logging.GenerationResult{
	Id: "cmpl-uN1k3lnZkTlZg8GHt4Vtd1aB",
	Object: "text_completion",
	Created: 1718393286,
	Model: "gpt-3.5-turbo-16k",
	Choices: []logging.Choice{
		{
			Index:        0,
			Text:         "\n Here is the response\n",
			Logprobs:     nil,
			FinishReason: "stop",
		},
	},
	Usage: &logging.Usage{
		PromptTokens:     7,
		CompletionTokens: 105,
		TotalTokens:      112,
	},
})

Feedback

A Feedback is a special type of Event in Maxim, which is a point in time when feedback was given in the system.

Adding a Feedback to a Trace

import "github.com/maximhq/maxim-go/logging"
 
trace.SetFeedback(&logging.Feedback{
	Score:   0.5,
	Comment: StrPtr("string feedback"),
})

Overview

Getting started

On this page