ai-agentic

This skill provides tools for RAG applications by generating embeddings, storing them in vector databases like pgvector or chromem-go, and retrieving relevant context to augment LLM prompts. It orchestrates the entire pipeline for semantic knowledge retrieval.

Agent orchestration coordinates autonomous agents that reason, plan, and execute tasks using external tools. This skill provides the framework to build these agents, enabling LLMs to move beyond simple text generation to autonomously solving multi-step problems.

Yes, you can use both cloud and local vector stores. The skill supports pgvector for cloud deployments and chromem-go for local vector storage, allowing you to choose the environment that best fits your application's scale and privacy requirements.

Yes, this tool supports multiple AI providers including Anthropic and OpenAI. It integrates LLM capabilities from these providers to facilitate chat, code generation, and autonomous agent features within your applications.

To add a documentation-aware chatbot, you use the RAG features to embed your product docs into a vector store, then pass retrieved context to the LLM chat interface. This allows the bot to answer user queries and suggest code snippets based on your specific documentation.