LLM Gateway
What is an LLM Gateway?
An LLM Gateway simplifies managing large language models, enhancing the performance, security, and scalability of real-world AI applications.
Kavya MD
prompt engineering
Using Prompt Chaining for Complex Tasks
Master prompt chaining to break down complex AI tasks into simple steps. Learn how to build reliable workflows that boost speed and cut errors in your language model applications.
Gen AI
FinOps practices to optimize GenAI costs and maximize efficiency
Learn how to apply FinOps principles to manage your organization's GenAI spending. Discover practical strategies for budget control, cost optimization, and building sustainable AI operations across teams. Essential reading for technology leaders implementing enterprise AI.
integration
Elevate Your ToolJet Experience with Portkey AI
Integrate Portkey with ToolJet to unlock observability, caching, API management, and routing, optimizing app performance, scalability, and reliability.
Chain of Thought
Chain-of-Thought (CoT) Capabilities in O1-mini and O1-preview
Explore O1 Mini & O1 Preview models with Chain-of-Thought (CoT) reasoning, balancing cost-efficiency and deep problem-solving for complex tasks.
Fine-tuning
OpenAI - Fine-tune GPT-4o with images and text
OpenAI’s latest update marks a significant leap in AI capabilities by introducing vision to the fine-tuning API. This update enables developers to fine-tune models that can process and understand visual and textual data, opening up new possibilities for multimodal applications. With AI models now able to "see"
OpenAI
OpenAI’s Prompt Caching: A Deep Dive
This update is welcome news for developers who have been grappling with the challenges of managing API costs and response times. OpenAI's Prompt Caching introduces a mechanism to reuse recently seen input tokens, potentially slashing costs by up to 50% and dramatically reducing latency for repetitive tasks. In
observability
⭐ The Developer’s Guide to OpenTelemetry: A Real-Time Journey into Observability
In today’s fast-paced environment, managing a distributed microservices architecture requires constant vigilance to ensure systems perform reliably at scale. As your application handles thousands of requests every second, problems are bound to arise, with one slow service potentially creating a domino effect across your infrastructure. Finding the root cause