#llm
36 pages tagged llm.
AI Agents
LLM-driven systems that plan, call tools, and act toward a goal.
AI Agents
LLM-driven systems that pursue a goal by interleaving reasoning, tool calls, and observations inside a loop — and that decide for themselves which step to take next.
transformers
Package-level reference for the Hugging Face transformers library on PyPI — install extras, backend choice, versioning, and alternatives.
sentence-transformers
Package-level reference for the sentence-transformers library on PyPI — install, transformers/torch deps, model registry, and embedding alternatives.
openai
Package-level reference for openai on npm — Chat Completions, the Responses API, streaming, tool calls, structured outputs, embeddings, and the v4→v5 migration.
langsmith
Package-level reference for the langsmith SDK on PyPI — install, versioning, env-var setup, and observability alternatives.
langchain
Package-level reference for the langchain family on PyPI — install variants, partner packages, version churn, and alternatives.
guidance
Package-level reference for the guidance library on PyPI — install, LLM-provider extras, versioning, and alternatives like instructor and outlines.
google-genai
Package-level reference for google-genai (the current Gemini SDK) and its predecessor google-generativeai — install, auth, versioning, and alternatives.
dspy
Package-level reference for DSPy on PyPI — the dspy / dspy-ai rename, install variants, version policy, and alternatives.
crewai
Package-level reference for the crewai library on PyPI plus the crewai-tools companion — install, versioning, and multi-agent alternatives.
autogen-agentchat
Package-level reference for the autogen-agentchat / autogen-core / autogen-ext family on PyPI plus the legacy pyautogen — install, rename history, versioning, and alternatives.
ai
Package-level reference for the Vercel AI SDK — streamText, generateObject, tool calling, structured output, and the multi-provider model interface.
Semantic Kernel
Build LLM-powered applications with Microsoft Semantic Kernel. Covers the kernel, plugins, prompt templates, planners, function calling, Kernel Memory, Python and .NET SDKs.
Retrieval-Augmented Generation (RAG)
Grounding LLM responses in chunks retrieved from an external corpus so the model reasons over real, citable sources instead of parametric memory alone.
RAG Implementation Checklist
End-to-end checklist and code for building reliable Retrieval-Augmented Generation pipelines — chunking, embedding, vector DBs, retrieval, and evaluation.
Prompting
Prompt engineering patterns, RAG, evaluations, few-shot, chain-of-thought, and structured output — foundational techniques for extracting reliable, structured behavior from LLMs.
Prompt Engineering Patterns
Reliable prompt structures for reasoning, extraction, classification, generation, extended thinking, and vision tasks with Claude.
Haystack 2.x
Build production-grade LLM pipelines with Haystack 2.x. Covers components, the pipeline graph, indexing and querying, retrievers, generators, RAG patterns, and evaluation.
Few-Shot Prompting
In-context learning techniques — example selection, format design, count tuning, dynamic retrieval of demonstrations, and pitfalls of few-shot prompting.
DSPy
Build LLM programs in DSPy with declarative signatures, modules, and optimisers. Covers Predict, ChainOfThought, ReAct, BootstrapFewShot, COPRO, MIPRO, MIPROv2, and inference compilation.
Chain-of-Thought Prompting
CoT prompting techniques — zero-shot CoT, few-shot CoT, self-consistency, tree of thoughts, and how reasoning models compare with prompted reasoning.
APIs
A versioned contract between two pieces of software — endpoints, verbs, payload shapes, errors, and auth — that decouples a caller from an implementation.
Agent Frameworks Comparison
Side-by-side comparison of LangChain, LlamaIndex, AutoGen, CrewAI, Haystack, and Semantic Kernel for building LLM-powered applications and agent systems. Covers strengths, weaknesses, and when to pick each.
Frameworks
Hugging Face Transformers, LangChain, Google Gemini SDK, and LangSmith — practical reference for AI/ML frameworks and observability tools.
TruLens
Evaluate and monitor LLM applications with TruLens. Covers the RAG triad, feedback functions, TruChain, TruLlama, custom evaluators, the dashboard, and CI integration.
transformers
Load and run pre-trained models for NLP, vision, and audio with the Hugging Face Transformers library. Covers pipelines, AutoModel, tokenisation, generation, fine-tuning, and device placement.
ragas
Measure and improve RAG pipeline quality with ragas. Covers faithfulness, answer relevancy, context precision, context recall, dataset format, LLM judges, and CI integration.
LlamaIndex
Build RAG pipelines and LLM-powered data applications with LlamaIndex. Covers document loading, indexing, query engines, custom LLMs and embeddings, persistent storage, and agents.
LangSmith
Trace, debug, evaluate, and monitor LLM applications with LangSmith. Covers tracing setup, datasets, evaluators, prompt hub, comparing runs, and CI integration.
LangChain
Build LLM-powered pipelines with LangChain. Covers LCEL chains, chat models, prompts, output parsers, tools, agents, retrievers, memory, and streaming.
guidance
Interleave Python control flow with LLM generation and enforce structured output using guidance. Covers gen(), select(), chat blocks, regex constraints, JSON schemas, and token healing.
google-generativeai
Call Google's Gemini models from Python for text, multimodal, streaming, chat, function calling, and embeddings. Covers the genai SDK, safety settings, file API, and async usage.
crewAI
Orchestrate teams of role-playing AI agents with crewAI. Covers agents, tasks, crews, tools, LLM selection, memory, YAML config, and the kickoff lifecycle.
AutoGen
Build multi-agent AI systems with Microsoft AutoGen. Covers agents, group chats, code execution, tool registration, async runtimes, and LLM configuration.
AI
Claude Code, Codex CLI, the Claude API, and prompt engineering — practical reference for building with and using large language models.