Results for “production”

Diagnoses Qdrant production issues using metrics and observability tools, covering optimizer problems, memory spikes, and slow queries.

Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend.

Perform efficient pandas DataFrame operations for data analysis, manipulation, and transformation with production-grade patterns.

Provides MySQL and MariaDB schema, query, indexing, transaction, replication, and connection-pool patterns for production backends.

Design, tune, and evaluate production RAG pipelines with deterministic tools for chunking, pipeline design, and retrieval evaluation.

Analyze engineering delivery throughput, hiring funnel health, team structure, and production discipline for startup VPEs and founders.

Provides MySQL and MariaDB schema, query, indexing, transaction, replication, and connection-pool patterns for production backends.

Build and run evaluators for AI/LLM applications using Phoenix, covering error analysis, custom evaluators, experiments, and production monitoring.

Design production-ready observability strategies combining metrics, logs, and traces, including SLI/SLO design, golden-signals monitoring, and alert optimization.

Guides monitoring and observability setup for Qdrant vector search deployments, including Prometheus scraping, health checks, and metric-based debugging of production issues.

Generate production-ready Dataverse SDK solutions with architecture recommendations, data models, and implementation code for common business use cases.

Build real-time streaming applications with the Azure Event Hubs SDK for Java, including sending and receiving events, batch processing, and production-ready event processors.

Provides code examples and best practices for using Pinecone, a managed vector database for production RAG, recommendation, and semantic search applications.

Provides expert guidance on modern Julia 1.10+ development, covering performance optimization, multiple dispatch, tooling, testing, and production-ready practices.

Generate production-ready Python code for Dataverse SDK with advanced patterns including error handling, batch operations, OData optimization, and Pandas integration.

Provides production patterns and non-obvious traps for Prisma ORM in TypeScript backends, covering schema design, query optimization, transactions, pagination, and common pitfalls.

Store and query embeddings with metadata filtering, vector search, and full-text search using an open-source database that scales from notebooks to production.

Manages SurrealDB schemas as desired-state .surql files, with sync for disposable databases and reviewed rollouts for shared or production environments, plus seeding and declarative testing.

Production patterns and non-obvious traps for Prisma ORM in TypeScript backends, covering schema design, query optimization, transactions, pagination, and serverless connection handling.

Implements production LLM operations: RAG pipelines, embeddings, vector databases, fine-tuning, advanced prompt engineering, cost estimation, quality evals, semantic caching, streaming, and agents.

Provides guidance and code for production AI workflows including RAG pipelines, vector databases, embedding indexing, prompt engineering, cost estimation, semantic caching, and quality evaluation.

Designs and implements production-grade RAG systems by chunking documents, generating embeddings, configuring vector stores, building hybrid search pipelines, applying reranking, and evaluating retrieval quality.

Builds production RAG and semantic search systems with Qdrant, covering collection setup, vector indexing, filtered and hybrid search, and integration with LangChain and LlamaIndex.

Guides selection of Qdrant deployment options: local mode, Docker, self-hosted, Qdrant Cloud, Hybrid Cloud, or Qdrant EDGE based on latency, control, and production needs.

Use this skill for on-chain data, explorers, Dune-style queries, wallets, transfers, contract events. Trigger when the task involves crypto work related to Onchain Data Analytics, production implementation, audits, debugging, strategy, or validation.

Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking, creates orchestration DAGs, builds feature store schemas, deploys model registries, and automates retraining and validation workflows.

Resolve timezone questions for .NET and C# code with production-safe guidance and copy-paste-ready snippets, including address-to-timezone lookup, cross-platform ID mapping, and DST-safe scheduling.

Build production RAG and semantic search systems with a high-performance vector database written in Rust, supporting hybrid search, filtering, and horizontal scaling.

Manage vector database operations across Pinecone, Weaviate, Qdrant, and ChromaDB, including embedding generation, index creation, metadata filtering, hybrid search, and production deployment for RAG and similarity search.

Generate optimized SQL queries from natural language descriptions across multiple database platforms including BigQuery, PostgreSQL, MySQL, and Snowflake. Reads database schemas from uploaded files or diagrams to produce accurate, production-ready queries.