This article details building end-to-end observability for LLM applications using FastAPI and OpenTelemetry. It emphasizes a code-first approach, manually designing traces, spans, and semantic attributes to capture the full lifecycle of LLM-powered requests. The guide advocates for a structured approach to tracing RAG workflows, focusing on clear span boundaries, safe metadata capture (hashing prompts/responses), token usage tracking, and integration with observability backends like Jaeger, Grafana Tempo, or specialized LLM platforms. It highlights the importance of understanding LLM behavior beyond traditional infrastructure metrics.
This article explores the emerging category of AI-powered operations agents, comparing AI DevOps engineers and AI SRE agents, how cloud providers are responding, and what engineers should consider when evaluating these tools.
Logs, metrics, and traces aren't enough. AI apps require visibility into prompts and completions to track everything from security risks to hallucinations.
Nemo Agent Toolkit simplifies building production-ready LLM applications by providing tools for creating, managing, and deploying agents. It offers features like memory management, tool usage, and observability, making it easier to integrate LLMs into real-world applications.
Cisco and Splunk have introduced the Cisco Time Series Model, a univariate zero shot time series foundation model designed for observability and security metrics. It is released as an open weight checkpoint on Hugging Face.
* **Multiresolution data is common:** The model handles data where fine-grained (e.g., 1-minute) and coarse-grained (e.g., hourly) data coexist, a typical pattern in observability platforms where older data is often aggregated.
* **Long context windows are needed:** It's built to leverage longer historical data (up to 16384 points) than many existing time series models, improving forecasting accuracy.
* **Zero-shot forecasting is desired:** The model aims to provide accurate forecasts *without* requiring task-specific fine-tuning, making it readily applicable to a variety of time series datasets.
* **Quantile forecasting is important:** It predicts not just the mean forecast but also a range of quantiles (0.1 to 0.9), providing a measure of uncertainty.
* **Multiresolution data is common:** The model handles data where fine-grained (e.g., 1-minute) and coarse-grained (e.g., hourly) data coexist, a typical pattern in observability platforms where older data is often aggregated.
* **Long context windows are needed:** It's built to leverage longer historical data (up to 16384 points) than many existing time series models, improving forecasting accuracy.
* **Zero-shot forecasting is desired:** The model aims to provide accurate forecasts *without* requiring task-specific fine-tuning, making it readily applicable to a variety of time series datasets.
* **Quantile forecasting is important:** It predicts not just the mean forecast but also a range of quantiles (0.1 to 0.9), providing a measure of uncertainty.
This article details the steps to move a Large Language Model (LLM) from a prototype to a production-ready system, covering aspects like observability, evaluation, cost management, and scalability.
Ship measurable improvements in your GenAI systems with Opik, your open-source LLM observability and agent optimization platform. Trusted by over 150,000 developers and thousands of companies.
Elastic's new Streams feature uses AI to transform noisy logs into actionable insights, helping SREs diagnose and resolve issues faster. The article discusses how AI is poised to become the primary tool for incident diagnosis and address skill shortages in IT infrastructure management.
Here's a breakdown of the technical details:
* **Problem:** Modern IT (especially Kubernetes) generates massive amounts of log data (30-50GB/day per cluster) making manual analysis for root cause identification slow, costly, and prone to errors. Existing observability tools often treat logs as a last resort.
* **Elastic's Solution (Streams):**
* **AI-powered Parsing & Partitioning:** Automatically extracts relevant fields from raw logs, reducing manual effort.
* **Anomaly Detection:** Surfaces critical errors and anomalies from logs, providing early warnings.
* **Automated Remediation:** Aims to not only identify issues but also suggest or automatically implement fixes.
* **Workflow Shift:** Streams aims to move away from the traditional observability workflow (metrics -> alerts -> dashboards -> traces -> logs) to a log-centric approach where AI proactively processes logs to create actionable insights.
* **Future Direction:** The article highlights the potential of **Large Language Models (LLMs)** to further automate observability, including generating automated runbooks and playbooks for remediation. LLMs could also help address the shortage of skilled SREs by augmenting their expertise.
* **Integration:** Streams is integrated into Elastic Observability.
Here's a breakdown of the technical details:
* **Problem:** Modern IT (especially Kubernetes) generates massive amounts of log data (30-50GB/day per cluster) making manual analysis for root cause identification slow, costly, and prone to errors. Existing observability tools often treat logs as a last resort.
* **Elastic's Solution (Streams):**
* **AI-powered Parsing & Partitioning:** Automatically extracts relevant fields from raw logs, reducing manual effort.
* **Anomaly Detection:** Surfaces critical errors and anomalies from logs, providing early warnings.
* **Automated Remediation:** Aims to not only identify issues but also suggest or automatically implement fixes.
* **Workflow Shift:** Streams aims to move away from the traditional observability workflow (metrics -> alerts -> dashboards -> traces -> logs) to a log-centric approach where AI proactively processes logs to create actionable insights.
* **Future Direction:** The article highlights the potential of **Large Language Models (LLMs)** to further automate observability, including generating automated runbooks and playbooks for remediation. LLMs could also help address the shortage of skilled SREs by augmenting their expertise.
* **Integration:** Streams is integrated into Elastic Observability.
This article explores how prompt engineering can be used to improve time-series analysis with Large Language Models (LLMs), covering core strategies, preprocessing, anomaly detection, and feature engineering. It provides practical prompts and examples for various tasks.
A study by ClickHouse found that large language models (LLMs) aren't currently capable of replacing Site Reliability Engineers (SREs) for incident root cause analysis, despite advancements in AI. LLMs can be helpful tools, but require human oversight.
