1 min read
Retrieval-Augmented Generation: Chunking Strategies for Better Results
The best chunking strategy depends on your document types. Technical documentation benefits from header-aware chunking. Conversational content works well…
Embeddings
24 articles
1 min read
Vector Database Selection: Choosing the Right Solution for RAG
The best vector database depends on your specific requirements. Azure AI Search excels for hybrid search with integrated semantic ranking. Pinecone offers…
1 min read
Embedding Models: Choosing Between OpenAI, Azure, and Open Source
The text-embedding-ada-002 and newer text-embedding-3 models provide high-quality embeddings with minimal setup.
1 min read
Embedding Models Comparison: Choosing the Right Model for Your Use Case
Balance quality, speed, and cost based on your specific retrieval needs.
1 min read
Vector Search in Databricks: Semantic Search at Scale
Databricks Vector Search enables semantic similarity search over your lakehouse data. Build RAG applications, recommendation systems, and intelligent search…
1 min read
Cohere on Azure: Enterprise Search and RAG Solutions
Cohere's models are now available on Azure AI, offering specialized capabilities for enterprise search and retrieval-augmented generation (RAG). This guide…
1 min read
Semantic Caching: Intelligent Response Reuse for LLMs
1. Start conservative Higher threshold (0.95+) for critical applications 2. Tune with data Evaluate on your actual query patterns 3. Monitor quality Track…
1 min read
Integrated Vectorization in Azure AI Search: Simplifying RAG Pipelines
Integrated vectorization removed an entire pipeline step in a recent project. I'll show how it simplifies RAG pipelines and where to be cautious when…
1 min read
Vector Store Integrations: Choosing and Using Vector Databases
This concludes our August 2023 series on LLM optimization and vector stores.
1 min read
Azure Cognitive Search Vector Search: Building Semantic Search Applications
Vector search enables powerful semantic search capabilities. Tomorrow, I will cover hybrid retrieval patterns in more detail.
1 min read
Semantic Search for Enterprise: Beyond Keyword Matching
Enterprise semantic search transforms how organizations find and use knowledge. By understanding meaning rather than just matching keywords, these systems…
1 min read
Vector Databases for AI Applications
Vectors (embeddings) represent meaning in high-dimensional space. Similar items have similar vectors.
1 min read
Building Semantic Search with Azure OpenAI Embeddings
Embeddings are numerical representations of text that capture semantic meaning. Similar concepts have similar vectors. Azure OpenAI provides the…
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
Azure Cognitive Search Vector Search Preview: Native Azure Vector DB
Native Azure Integration : Works seamlessly with Azure services Hybrid Search : Combine vectors with full text search Enterprise Ready : Security,…
1 min read
Qdrant Vector Database: Fast and Efficient Similarity Search
1. Index payload fields : For frequently filtered fields 2. Use appropriate distance : Cosine for normalized, Dot for raw 3. Tune HNSW params : Balance…
1 min read
Milvus Vector Database: High-Performance Similarity Search
1. Choose index wisely : HNSW for low latency, IVF for memory efficiency 2. Tune search parameters : Balance accuracy and speed 3. Use partitions : For…
1 min read
Weaviate Vector Database: Open Source Semantic Search
Weaviate uses a schema first approach: Combine vector search with keyword search: 1. Define schema carefully : Properties and types matter 2. Use batching :…
1 min read
Pinecone Vector Database: Getting Started Guide
1. Use batching : Upsert in batches of 100+ for efficiency 2. Store text in metadata : Include searchable text in metadata 3. Use namespaces : Organize data…
1 min read
Introduction to Vector Databases for AI Applications
Traditional databases are optimized for exact matches and range queries. Vector search requires finding approximate nearest neighbors in high-dimensional…
1 min read
Building Semantic Search with Azure OpenAI Embeddings
Combine semantic search with keyword matching: Expand queries for better recall: 1. Pre compute embeddings : Don't embed at query time for documents 2. Use…
1 min read
Introduction to Text Embeddings with Azure OpenAI
Embeddings are dense vector representations of text where: Similar meanings are close together in vector space Different meanings are far apart…
1 min read
Vector Search Preview in Azure Cognitive Search
Vector search enables powerful similarity-based retrieval that complements traditional keyword search.