1 min read
Azure Form Recognizer Prebuilt Models: Quick Document Processing
1. Choose the right model : Use specific models for better accuracy 2. Handle confidence scores : Filter low confidence extractions 3. Validate extracted…
Blog
Thoughts on data engineering, cloud architecture, and technology. 2205 articles and counting.
Showing 24 of 2205 posts — page 52 of 92
1 min read
Custom Models in Azure Form Recognizer for Domain-Specific Documents
Combine multiple models for different document types: 1. Use 5+ training samples : More samples improve accuracy 2. Include edge cases : Train on variations…
1 min read
Azure AI Document Intelligence: Extracting Data from Documents
Use prebuilt models for common document types: Extract document structure: Extract and process tables: Train models for your specific documents: Use…
1 min read
Semantic Kernel Memory: Building AI with Long-Term Context
1. Organize into collections : Separate by topic/domain 2. Use meaningful IDs : Enable updates and deletions 3. Set appropriate relevance thresholds : Too…
1 min read
Semantic Kernel Planners: Automatic AI Orchestration
Creates multi step plans: Selects the single best action: Iteratively reasons through complex problems: 1. Register clear skill descriptions : Planners rely…
1 min read
Semantic Kernel Plugins: Extending AI with Custom Skills
1. Single responsibility : Each plugin should do one thing well 2. Clear descriptions : Help planners understand what functions do 3. Validate inputs :…
1 min read
Semantic Kernel Introduction: Microsoft's AI Orchestration SDK
Define AI functions using natural language prompts: Create reusable prompts: Add Python functions as skills: Combine functions into pipelines: Store and…
4 min read
Kubernetes on Cloud with AWS, Azure, and GCP
Amazon Web Services (AWS) is one of the most popular cloud computing platforms. It offers a wide range of services, such as compute, storage, and databases…
1 min read
LangChain Introduction: Building AI Applications with Python
Create reusable, parameterized prompts: Combine components into workflows: Load content from various sources: Split documents for embedding: Generate…
3 min read
Understanding Automated Market Makers - The Future of Decentralized Trading
Have you ever wondered how decentralized trading works? The backbone of decentralized trading is the Automated Market Maker (AMM). AMM is a game-changing…
2 min read
TDD (Test-Driven Development) Overview with NextJS Example
This will create a new NextJS project with TypeScript in a directory named my-app. Change into the directory and run npm run dev to start the development…
3 min read
Getting Started with GraphQL using TypeScript
TypeScript is a statically typed language that is a popular choice for building large-scale applications. It provides improved reliability, maintainability…
2 min read
Provably in Blockchain Technology: Ensuring Trust and Transparency with Cryptographic Proofs
In a blockchain system, the use of cryptographic proof enables trust and transparency in the network, as it allows users to verify that the information…
3 min read
Creating your own Decentralized Exchange like Uniswap
Uniswap is a well-known decentralized exchange that enables users to trade cryptocurrencies without the involvement of intermediaries. It uses a unique…
2 min read
The IT Market in Decline: The Importance of Upskilling in the AI Era
Artificial intelligence (AI) and machine learning are transforming the way we live and work. The rise of generative AI, such as ChatGPT, is adding a new…
1 min read
TDD (Test-Driven Development) Overview with Python Example
This cycle is repeated for each new piece of functionality. The result is a suite of tests that provide confidence in the code and make it easier to…
4 min read
Creating your own Stablecoin
A stablecoin is a type of cryptocurrency that is designed to maintain a stable value relative to some asset, usually a fiat currency such as the US dollar…
1 min read
Re-ranking Search Results for Better RAG Performance
Cross encoders directly score query document pairs: Use an LLM to judge relevance: Using Cohere's specialized rerank API: 1. Retrieve more, re rank fewer :…
1 min read
Hybrid Search: Combining Vector and Keyword Search
A robust way to combine rankings: Adjust weights based on query characteristics: 1. Start balanced : 50/50 is often a good default 2. Tune on your data :…
1 min read
Embedding Best Practices for Production AI Systems
OpenAI Embeddings Guide MTEB Benchmark Embedding Best Practices
1 min read
Document Chunking Strategies for RAG Systems
Simple but effective for uniform content: Respect sentence boundaries: Natural document structure: Use embeddings to find natural break points: Hierarchical…
1 min read
RAG Architecture Patterns: Building Production-Ready Systems
The basic pattern for straightforward use cases: Transform queries for better retrieval: Generate a hypothetical answer first, then use it for retrieval:…
7 min read
RAG on Azure OpenAI: Grounding GPT-3 Answers in Your Own Documents
What retrieval augmented generation is, why it beats fine-tuning for company knowledge, and a minimal loop on Azure OpenAI completions in January 2023.
7 min read
Azure Cognitive Search and Embeddings Before Native Vector Search
Azure Cognitive Search can't search vectors in January 2023. Here's how to re-rank its keyword results with Azure OpenAI embeddings, and when not to bother.