OpenSearch vs Chroma

OpenSearch Kubernetes Operator 3.0 is now generally available

The OpenSearch Kubernetes Operator 3.0 GA release delivers production-grade rolling upgrades, TLS lifecycle management, safe scaling, and a tested migration from 2.x.

Expanding the OpenSearch Community: Welcoming our new OpenSearch Ambassadors

The OpenSearch Ambassador Program expands to over 30 global leaders, welcoming 11 new community advocates in our September 2026 cohort. Meet the new ambassadors driving open-source search and AI forward.

Online index migration and shard scaling in OpenSearch with the AOSC plugin

Learn how the open-source AOSC plugin migrates live OpenSearch indexes—changing mappings, settings, or shard counts—without losing writes or requiring downtime.

AI Agents Need Vector Databases for Memory

This technical blog post explains why retrieval-backed long-term memory for AI agents is best implemented with vector databases. It defines three memory types (working, long-term, episodic), outlines the memory stack (embedding model, vector store, chunking, metadata), recommends practical tooling (pgvector, Qdrant, Chroma) and embedding-dimension trade-offs, and provides a minimal Python example using pgvector and OpenAI embeddings. The author lists common production failure modes (stale memory, poor chunking, blind cosine similarity, context overflow, cost, privacy, and silent quality rot) and a practitioner's checklist for safe, private, and maintainable memory-enabled agents.

• Vector databases enable retrieval-backed long-term memory for agents by returning semantically similar chunks via embeddings and ANN search.
• Author recommends tooling trade-offs: pgvector (Postgres extension) for most production cases, Qdrant for heavy metadata filtering/scale, and Chroma for quick prototypes.
• Embedding dimension and model choice trade quality against cost; 768 dimensions is suggested as a sane production default.

Local RAG Evolved into Agentic AI with LangGraph

A developer describes converting a locally hosted RAG assistant (built with Ollama, ChromaDB, LangChain, Docker) into an agentic AI architecture using LangGraph. The author introduces a shared AgentState contract and implements three single-purpose agents — a RAG agent for documentation lookup, a Diagnostic agent with a fast known-error lookup and LLM fallback, and an Escalation agent that generates structured tickets when human intervention is required. An orchestrator uses a classifier to route queries conditionally through a state graph. The article discusses design lessons (classifier fragility, embedding initialization overhead, hardcoded escalation thresholds) and recommends starting with RAG and adding agents where needed.

• Author converted a local RAG assistant into an agentic AI architecture using LangGraph.
• The original local stack included Ollama, ChromaDB, LangChain, all running in Docker.
• The solution defines a shared AgentState TypedDict that agents read and update (fields include messages, question, plan, past_steps, response, next_agent, niveau_support).

Local RAG Assistant with Ollama, ChromaDB, LangChain

A Master's student built a local Retrieval-Augmented Generation (RAG) assistant to let technicians query private PDF manuals without sending data to cloud providers. The pipeline uses 300-character chunking, all-MiniLM-L6-v2 embeddings stored in ChromaDB, retrieval of the top 3 chunks, and local Llama 3 inference via Ollama. The system runs as four Docker Compose services (Ollama, ChromaDB, FastAPI, Streamlit). The author documents three practical failures and fixes: ChromaDB v2 silently storing data without an explicit HttpClient, LangChain refactoring into langchain_core, and slow Llama 3 CPU inference (mitigated by reducing retrieved chunks, capping responses with num_predict, and adding RAM). The project is open-source on GitHub and the author plans to evolve the pipeline toward an agentic architecture.

• Built a fully local RAG assistant using Ollama (Llama 3), ChromaDB, LangChain, FastAPI, and Streamlit, deployed via Docker Compose.
• Ingested 2,111 PDF pages split into 9,669 chunks using 300-character chunking and embedded with all-MiniLM-L6-v2.
• ChromaDB v2 required an explicit chromadb.HttpClient(host='chromadb', port=8000); old client_settings caused vectors to be silently not stored and /api/v2/heartbeat is the current health endpoint.