Results for “real-esrgan”

Evaluates RAG pipelines using a filesystem-based benchmark with corpus/ and train.json, running evaluate_rag.py to tune retrieval and generation flags and interpret RAGAS metrics.

Generates speech from text using ElevenLabs TTS with local playback, supporting voice selection, pronunciation rules, and audio tags.

Builds or modifies a RAG pipeline with intent-based routing, vector store search, citation rendering, and book fidelity enforcement.

Evaluate RAG pipelines with Ragas — measure faithfulness, answer relevancy, context precision/recall, and noise sensitivity using LLM-as-judge metrics; run automated test suite generation with TestsetGenerator; integrate with LangChain, LlamaIndex, and CI pipelines.

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications.

Probe RAG applications for prompt injection via poisoned retrieved context and embedding manipulation.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search. Use when implementing knowledge-grounded AI, building document Q&A systems, or integrating LLMs with external knowledge bases.

Generates speech from text using ElevenLabs text-to-speech with a command-line interface and local playback.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Expert en AudioCraft avancé (MusicGen text-to-music, AudioGen text-to-sound, fine-tuning)

Expert guidance for architecting, developing, and operating SurrealDB 3, covering SurrealQL, multi-model data modeling, vector search, security, deployment, performance tuning, SDK integration, and ecosystem tools.

Builds Retrieval-Augmented Generation systems with document chunking, embedding generation, vector storage, and retrieval pipelines, including evaluation and optimization.

Scales reinforcement learning with PufferLib — high-throughput parallel training (PuffeRL), vectorized environments, and native multi-agent systems achieving 2-10x speedups over standard implementations. Use when scaling RL to millions of steps per second, running vectorized or multi-agent setups, building custom PufferEnv tasks, or integrating game environments (Atari, Procgen, NetHack, PettingZoo). For standard single-agent algorithm implementations (PPO/SAC/DQN) or quick prototyping prefer alterlab-stable-baselines3. Part of the AlterLab Academic Skills suite.

Produces a machine-validated, auditable JSON decision record with assumptions, risks, recommendation, and review gating for high-stakes decisions.

Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.

Produces auditable, schema-valid JSON decision records with assumptions, risks, recommendations, and review gating for high-stakes choices.