# Genkit

## Docs

- [Flows](https://mintlify.wiki/genkit-ai/genkit/concepts/flows.md): Type-safe, observable functions that wrap AI logic. Flows are the primary unit of deployment in Genkit.
- [Models](https://mintlify.wiki/genkit-ai/genkit/concepts/models.md): A unified interface to call any AI model—Gemini, Claude, Llama, and more—with the same API.
- [Prompts](https://mintlify.wiki/genkit-ai/genkit/concepts/prompts.md): Dotprompt: version-controlled prompt files with model config, input schemas, and Handlebars templates.
- [RAG](https://mintlify.wiki/genkit-ai/genkit/concepts/rag.md): Retrieval-Augmented Generation: index documents, embed them into a vector store, and retrieve relevant context at query time.
- [Sessions](https://mintlify.wiki/genkit-ai/genkit/concepts/sessions.md): Persist multi-turn conversation state across requests with sessions and chat threads.
- [Tools](https://mintlify.wiki/genkit-ai/genkit/concepts/tools.md): Define functions that AI models can call. Genkit automatically handles the tool call / response loop.
- [Deploy to Cloud Run](https://mintlify.wiki/genkit-ai/genkit/deployment/cloud-run.md): Run Genkit flows on Google Cloud Run using Node.js, Python, or Go.
- [Deploy to Firebase](https://mintlify.wiki/genkit-ai/genkit/deployment/firebase.md): Serve Genkit flows as Firebase Cloud Functions for Node.js.
- [Production monitoring and observability](https://mintlify.wiki/genkit-ai/genkit/deployment/observability.md): Configure tracing, metrics, and structured logging for Genkit apps in production.
- [Deployment overview](https://mintlify.wiki/genkit-ai/genkit/deployment/overview.md): Deploy Genkit flows to any platform that runs Node.js, Python, or Go.
- [Agents](https://mintlify.wiki/genkit-ai/genkit/guides/agents.md): Build AI agents — flows that use tools in multi-turn loops to autonomously complete tasks.
- [Developer tools](https://mintlify.wiki/genkit-ai/genkit/guides/devtools.md): Use the Genkit CLI and Developer UI to run, inspect, and debug your AI application locally.
- [Evaluation](https://mintlify.wiki/genkit-ai/genkit/guides/evaluation.md): Measure the quality of your AI outputs with custom and built-in evaluators.
- [Multimodal input](https://mintlify.wiki/genkit-ai/genkit/guides/multimodal.md): Send images, audio, video, and other media to models that support multimodal input.
- [Streaming](https://mintlify.wiki/genkit-ai/genkit/guides/streaming.md): Receive model response chunks as they are generated instead of waiting for the full response.
- [Structured output](https://mintlify.wiki/genkit-ai/genkit/guides/structured-output.md): Get typed, validated JSON responses from AI models using schemas defined in TypeScript, Python, or Go.
- [Introduction](https://mintlify.wiki/genkit-ai/genkit/introduction.md): Genkit is an open-source framework by Google/Firebase for building production-ready AI-powered applications in JavaScript/TypeScript, Go, and Python.
- [Firebase plugin](https://mintlify.wiki/genkit-ai/genkit/plugins/firebase.md): Use Firestore as a vector store for RAG, enable Firebase Genkit Monitoring, and integrate Firebase Auth with Genkit flows.
- [Google AI plugin](https://mintlify.wiki/genkit-ai/genkit/plugins/google-genai.md): Use Gemini models, Imagen image generation, and text embeddings from the Google AI (Gemini Developer API) and Vertex AI through a single unified plugin.
- [Ollama plugin](https://mintlify.wiki/genkit-ai/genkit/plugins/ollama.md): Run Llama, Mistral, Gemma, Phi, and hundreds of other open-source models locally through Ollama — no cloud account required.
- [Plugins overview](https://mintlify.wiki/genkit-ai/genkit/plugins/overview.md): Extend Genkit with official and community plugins for model providers, vector stores, telemetry, and more.
- [Vertex AI plugin](https://mintlify.wiki/genkit-ai/genkit/plugins/vertex-ai.md): Access Gemini, Imagen, and text embeddings on Google Cloud Vertex AI with Application Default Credentials or an Express Mode API key.
- [Writing plugins](https://mintlify.wiki/genkit-ai/genkit/plugins/writing-plugins.md): Build custom Genkit plugins that register models, embedders, retrievers, or any other action type. Learn the plugin lifecycle and how to publish to npm.
- [Go quickstart](https://mintlify.wiki/genkit-ai/genkit/quickstart-go.md): Get up and running with Genkit in Go in under five minutes using Gemini models via the Google AI plugin.
- [JavaScript / TypeScript quickstart](https://mintlify.wiki/genkit-ai/genkit/quickstart-js.md): Get up and running with Genkit in JavaScript or TypeScript in under five minutes using Gemini models via the Google AI plugin.
- [Python quickstart (Alpha)](https://mintlify.wiki/genkit-ai/genkit/quickstart-python.md): Get up and running with Genkit in Python. The Python SDK is currently in alpha — core generation, flows, and tools are functional but APIs may change.