convex-agent
This Skill adds an AI agent and RAG backend to a Convex app via @convex-dev/agent, covering agent definition with tools and instructions, durable threads, streamed messages, persisted history, and vector-search retrieval. Model calls default to the Convex AI Gateway, so credentials stay server-side and there is no LLM key to obtain, store, or rotate; keys needed for embeddings or gateway fallback live in Convex env. It suits teams that want in-app chat, document question answering, or tool-calling agents on durable, reactive storage.
npx skills add https://github.com/convex/agent-skills --skill convex-agentBefore / After Comparison
1 组Developers pick an LLM SDK themselves, apply for and store provider keys, hand-roll thread and message tables, glue together streaming, and bolt on a separate vector search — days of wiring, with keys scattered around.
This Skill lays out install, agent definition, thread creation, streamed messages and vector retrieval in one path; provider credentials stay server-side, so a durable, reactive agent plus RAG backend runs within half a day.
Add an AI agent / RAG backend
Install @convex-dev/agent for durable threads, message history, tool-calls, and vector search/RAG — the backend for an in-app AI agent. Call models through the Convex AI Gateway by default: Convex holds the provider credentials, so there is no LLM key to obtain, store, or rotate.
Workflow
- Install @convex-dev/agent + @convex-dev/ai-sdk-provider; add the agent component to convex.config.ts.
- Define the agent (tools, instructions) with
languageModel: convexGateway("provider/model")— no API key needed (needs convex 1.45+ on a Convex Cloud deployment, paid plan). - Create threads + stream messages; persist history in Convex.
- For RAG: embed docs into a vector index and retrieve in the tool. The gateway does not serve embeddings yet, so store the embedding provider's key via the
envmicro power. - Only if the gateway is unavailable (free plan, self-hosted, local backend): call the provider SDK with a key stored via the
envmicro power.
Rules
- Default to the Convex AI Gateway (
convexGatewayfrom @convex-dev/ai-sdk-provider) for model calls; fall back to a provider key in Convex env only where the gateway is unavailable (free plan, self-hosted, local backend). - Never expose a provider API key client-side; when one is needed (embeddings, gateway fallback), keep it in Convex env via the
envmicro power. - Run model calls in actions ('use node' if the SDK needs it).
- Persist threads/messages in Convex for durability + reactivity.
User Reviews (0)
Write a Review
No reviews yet
Statistics
User Rating
Rate this Skill