Skip to main content
AI · components

Component explorer

22 components across 12 kinds. Each entry documents: why it exists, how it works internally, head-to-head product comparison with pricing, when to use / not to use, failure modes, production usage with citations.

LLM providers

0/6 authored
Author me

OpenAI API (GPT-4o, GPT-4o-mini, o1, o3)

The reference LLM provider — pricing, capabilities, quirks.

Author me

Anthropic API (Claude 3.5 Sonnet, Opus, Haiku)

The frontier lab whose models most closely rival GPT-4 — and often beat it on reasoning.

Author me

Google Gemini API (2.5 Pro, Flash)

The multimodal-first LLM with the largest context windows in the industry.

Author me

Azure OpenAI Service

OpenAI models with enterprise compliance, regional deployment, and Microsoft billing.

Author me

AWS Bedrock

Multi-provider LLM gateway with IAM, VPC, and PrivateLink.

Author me

Llama, Mistral, Qwen, DeepSeek (open-weight models)

When self-hosting wins over API — cost, latency, control.

Embedding models

0/3 authored
Author me

OpenAI embeddings (text-embedding-3-small/large)

The default embedding model for RAG.

Author me

Cohere Embed (v3, multilingual)

The multilingual specialist and reranker vendor.

Author me

Voyage embeddings

The retrieval-optimized embedding vendor that often beats OpenAI on benchmarks.

Vector databases

0/5 authored
Author me

Pinecone

The managed vector DB pioneer — pricing, features, ops story.

Author me

Weaviate

Open-source hybrid search with graph relations.

Author me

Qdrant

The Rust-based vector DB with strong filter performance.

Author me

pgvector (Postgres extension)

The 'just use Postgres' answer to vector search — and when it wins.

Author me

Chroma

The embedded / dev-first vector DB for prototypes.

MCP servers

0/1 authored
Author me

MCP servers (Anthropic Model Context Protocol)

The 2024 standard for LLM ↔ tool interoperability.

Agent frameworks

0/4 authored
Author me

LangChain

The most-adopted (and most-criticized) LLM framework — when to use, when to skip.

Author me

LlamaIndex

The RAG-focused alternative to LangChain.

Author me

LangGraph

Stateful multi-agent orchestration on top of LangChain.

Author me

CrewAI

Role-based multi-agent orchestration.

Eval tools

0/1 authored
Author me

Ragas (RAG evaluation)

The default RAG-evaluation framework — faithfulness, answer relevance, context precision.

LLM observability

0/1 authored
Author me

Langfuse (LLM observability)

Open-source LLM tracing, prompt versioning, evaluation dashboards.

Guardrails

0/1 authored
Author me

NVIDIA NeMo Guardrails

The programmable-guardrails framework — Colang policies.