RAG & Retrieval
Retrieval-augmented generation in practice: chunking, embedding models, vector databases, hybrid search, reranking and parsing documents for AI agents.
Most RAG failures happen before the model is called: a chunk boundary splits the one sentence that mattered, or a PDF table turns into unreadable text on the way in. Retrieval quality is decided by those unglamorous steps far more than by the choice of vector database.
These articles test retrieval choices with real corpora: file search against vector search, parsing tools for PDFs and images, and when hybrid search or a reranker earns its latency. When the question shifts from finding documents to remembering users, the memory vs RAG comparison below draws the line.
Start here: Memory vs vector RAG · RAG pipeline (glossary) · Hybrid search (glossary) · Reranking (glossary)
TencentDB Agent Memory, Read From the Source: It Needs a Second LLM and Searches by Keyword by Default
The guides and news pages that rank for TencentDB Agent Memory repeat three claims its source code does not support: that it builds memory without any model API, that it runs hybrid vector search out of the box, and that no conversation data leaves the machine.
Local Embedding Models in 2026: Which to Run, What Hardware They Need, and What They Cost
A local embedding model turns your text into vectors on hardware you control, so no document or query leaves your machine to get embedded.
Best Embedding Models in 2026: Open-Source Picks, Semantic Search, and How to Choose for RAG
As of 26 September 2026, the best open-source embedding model for most teams is Qwen3-Embedding, which is Apache 2.0, reads 32K tokens and ranks 5th on MTEB English v2 and 4th on MTEB Multilingual v2.
How to Give an LLM Long-Term Memory, and Why RAG Alone Is Not It
You give an LLM long-term memory by adding a layer outside the model that decides what is worth keeping from each conversation, stores it against the right person, updates it when a fact changes, and puts only the relevant slice back into the prompt on the next call.
What Is RAG? How Retrieval-Augmented Generation Works, and Where It Stops
RAG, short for retrieval-augmented generation, is a technique that lets a large language model answer from information it was never trained on: when a question arrives, the application searches a knowledge source for the most relevant passages, places them in the prompt next to the question, and the model writes its answer from that material.
Knowledge Graph vs Vector Search for Agent Memory: When to Add a Graph, and Why Time Matters
For agent memory, neither wins on its own: vector search finds past statements that mean something close to the current question, and a knowledge graph connects facts through the same person or company and tells which of two conflicting facts is current.
What Is a Graph Database, and When Should You Use One?
A graph database stores data as nodes and relationships and answers questions by following those relationships instead of joining tables; use one when your main questions are about paths across connected data, and keep a relational database for records and reporting.
Image Processing for AI Agents: Embeddings & Vision Models & When to Use Each
Vision models or embeddings? You need both. Discover the hybrid approach that cuts image analysis costs 87% while maintaining quality—with pricing breakdowns for every tool.
PDF Parsing for AI Agents: The Best MCPs and When to Use Each
Streamline your document workflows by integrating PDF parsing with the Model Context Protocol (MCP). This guide explores how to build a standardized interface that allows AI agents to extract and reason over complex PDF data with precision and ease.
File Search vs Vector Search for RAG: 50,000 Documents, 5,000 Queries, Full Results
We ran exact-match keyword search against vector search across five datasets, 50,000 documents and 5,000 queries, scored by exact document ID with no LLM judge. Vector search wins on average, and the entire margin comes from one dataset.