keithchambers

receivers:
  otlp:
    protocols:
      grpc: {}
      http: {}

processors:

  transform/normalise_keys:
    error_mode: ignore

keithchambers

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "AWS Bedrock OpenTelemetry (OTLP/JSON) Schema",
  "description": "Validation schema covering resource and span attributes required for instrumenting Amazon Bedrock calls using OpenTelemetry Gen-AI semantic conventions.",
  "type": "object",
  "properties": {
    "resource": {
      "type": "object",
      "properties": {
        "attributes": { "$ref": "#/$defs/ResourceAttributes" }

keithchambers

// Package genaicleaner provides an OpenTelemetry Collector *processor* that
// sanitises Gen-AI spans in-flight.
//
// The processor performs three operations, all entirely in-memory:
//
//   1. **Validation** – incoming spans are checked against Harrier’s
//      *authoritative* allow-lists (derived from OTEP ≥ 1.43).
//   2. **Cleaning / Forking**
//        • A *clean* copy is forwarded on the same pipeline and tagged
//          `messaging.kafka.destination="input"` so the kafkaexporter can map

keithchambers

{
  "resourceSpans": [
    {
      "resource": {
        "attributes": [
          { "key": "service.name",         "value": { "stringValue": "autonomous_trading_system" } },
          { "key": "service.namespace",    "value": { "stringValue": "trading" } },
          { "key": "service.version",      "value": { "stringValue": "3.2.0" } },
          { "key": "service.instance.id",  "value": { "stringValue": "instance-001" } },
          { "key": "deployment.environment","value":{ "stringValue": "prod" } }

keithchambers

{
  "resourceSpans": [
    {
      "resource": {
        "attributes": [
          { "key": "service.name",            "value": { "stringValue": "genai-demo-app" } },
          { "key": "deployment.environment",  "value": { "stringValue": "prod"           } }
        ]
      },
      "schema_url": "https://opentelemetry.io/schemas/1.5.0",

keithchambers

{
  "resourceSpans": [{
    "schemaUrl": "https://opentelemetry.io/schemas/1.25.0",
    "resource": {
      "attributes": [{
        "key": "service.name", "value": { "stringValue": "llm-gateway" }},{
        "key": "deployment.environment", "value": { "stringValue": "prod" }}]},
    "scopeSpans": [{
      "scope": { "name": "ai.request.pipeline", "version": "2.3.0" },
      "spans": [{

keithchambers

#!/bin/bash
set -e # Exit on error. Use `set -eux` for debugging to print commands and expand variables.

REPO_NAME="kafka-batch-upload"
SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd ) # Get dir where setup.sh is
KAFKA_IMAGE="bitnami/kafka:3.7" # Define Kafka image once

echo "Setting up the Kafka Batch Upload project in ./${REPO_NAME}"
echo "This will create all necessary files and directories."
echo "Attempting to automate KRaft Cluster ID generation..."

keithchambers

// Package main implements a load tester for sending OpenTelemetry (OTLP) data
// via HTTP JSON or gRPC Protobuf, with an option to output generated data to a
// file instead of sending it over the network.
package main

import (
	"bytes"
	"context"
	"crypto/tls"
	"encoding/hex"

keithchambers

#!/bin/bash

# Create directory structure
echo "Creating project directories..."
# Replaced nginx with traefik, added traefik config dir
mkdir -p otel-kafka-clickhouse-stack/{traefik/conf,otel-collector,clickhouse-init,kafka-data,clickhouse-data}

cd otel-kafka-clickhouse-stack || exit 1 # Exit if cd fails

# Create .env file for secrets and configs

keithchambers

#!/usr/bin/env python3
import argparse
import logging
import numpy as np
import pandas as pd
import pyarrow.parquet as pq
from pathlib import Path
from typing import Union
import random