AI Resources

Generative AI Systems Stack

LLMs / Foundation Models

• OpenAI — GPT-5, o3, o4-mini
• Anthropic — Claude Opus 4.6, Sonnet 4.5
• Google Gemini — Gemini 3, Gemini 2.5 Pro
• Meta Llama — Llama 4 (Maverick, Scout)
• DeepSeek — DeepSeek R1

AI Frameworks

• LangChain — LLM orchestration and chaining
• LlamaIndex — Data-centric RAG and document processing
• Haystack — Production RAG and search pipelines
• Semantic Kernel — Microsoft’s enterprise AI SDK

AI Coding Assistants

• GitHub Copilot — Inline code completion
• Cursor — AI-native code editor
• Claude Code — CLI-based coding assistant

Text Embeddings

• OpenAI Embeddings — text-embedding-3-large
• Cohere Embed — Multilingual and multimodal
• Mistral Embed — Retrieval-optimized
• Voyage AI — Domain-specific embeddings

Vector Databases

• Pinecone — Fully managed, serverless
• Weaviate — Open-source with hybrid search
• Qdrant — High-performance, Rust-based
• Chroma — Lightweight, developer-friendly
• Milvus — Billion-scale vector search
• pgvector — PostgreSQL extension

RAG (Retrieval-Augmented Generation)

• Agentic RAG — LLM-driven query decomposition
• HiFi-RAG — Multi-stage hierarchical filtering
• Bidirectional RAG — Controlled write-back with grounding checks
• LlamaIndex Workflows — Event-driven RAG pipelines
• LangChain LCEL — Chain-based RAG orchestration

AI Agents

• LangGraph — Stateful multi-actor workflows
• CrewAI — Role-based multi-agent collaboration
• AutoGen — Microsoft’s multi-agent conversation framework
• AutoGPT — Autonomous long-running agents

LLM Serving / Inference

• vLLM — PagedAttention, high-throughput serving
• TGI — Hugging Face’s production inference server
• Ollama — Local model serving
• TensorRT-LLM — NVIDIA-optimized inference
• SGLang — Structured generation for constrained outputs

Fine-Tuning

• Axolotl — Multi-GPU, supports LoRA/QLoRA/SFT/RLHF
• Unsloth — 2-5x faster fine-tuning, 80% less memory
• Torchtune — Deep customization and scalability
• PEFT — Hugging Face parameter-efficient fine-tuning

LLM Monitoring / Observability

• LangSmith — Tracing, cost, and latency tracking
• Weights & Biases Weave — Multi-agent execution traces
• Arize Phoenix — Open-source drift and bias monitoring
• Langfuse — Open-source LLM observability
• AgentOps — Agentic workflow monitoring

Evaluation and Testing

• RAGAS — RAG-specific evaluation (faithfulness, relevancy, recall)
• DeepEval — 60+ metrics, Pytest-like LLM testing
• PromptFoo — Prompt A/B testing via YAML/CLI
• OpenAI Evals — Open-source evaluation framework