developing-genkit-python skill
Build AI-powered applications in Python including agents, flows, tools, and structured outputs using Genkit 0.13.
- GitHub stars
- 39
- Files
- 18
- Last commit
- Nov 9, 2026
- License
- —
- Allowed tools
- —
What does the developing-genkit-python skill do?
developing-genkit-python builds AI-powered applications in Python including agents, flows, tools, and structured outputs using Genkit 0.13.
Summary generated from the skill's SKILL.md.
About the developing-genkit-python skill
Building AI-powered applications in Python is the primary focus of this skill, specifically for developers using Genkit 0.13. It provides the necessary guidance to create agents, flows, tools, and structured outputs. Developers can use it to manage multi-turn chats with history and state through the experimental genkit.exp module, or to build stateless request/response pipelines using the @ai.flow decorator.
This resource is essential for those migrating projects from Genkit 0.12 to 0.13, as it addresses changes in imports and configuration. It supports various providers including Google AI, Vertex AI, Anthropic, OpenAI, Ollama, and Amazon Bedrock. Users can integrate these features into FastAPI routes or standalone scripts. To ensure successful development, the skill recommends using the Genkit CLI to capture traces and the Dev UI for inspection, rather than relying on standard execution commands.
What an agent can do with it
- 1Developing stateful agentsCreate multi-turn conversational agents that utilize typed state and human-in-the-loop approval.
Written from the skill's SKILL.md. Every use case is checked against a quote from it.
How to install the developing-genkit-python skill
Each command copies the skill folder into the client's skills directory. Restart the client or start a new session to load it.Install the developing-genkit-python skill in Claude Code
~/.claude/skills/developing-genkit-python/SKILL.md
$ npx degit genkit-ai/skills/skills/developing-genkit-python ~/.claude/skills/developing-genkit-pythonInstall the developing-genkit-python skill in Claude Code (project)
.claude/skills/developing-genkit-python/SKILL.md
$ npx degit genkit-ai/skills/skills/developing-genkit-python .claude/skills/developing-genkit-pythonInstall the developing-genkit-python skill in Codex
~/.agents/skills/developing-genkit-python/SKILL.md
$ npx degit genkit-ai/skills/skills/developing-genkit-python ~/.agents/skills/developing-genkit-pythonInstall the developing-genkit-python skill in Gemini CLI
~/.gemini/skills/developing-genkit-python/SKILL.md
$ npx degit genkit-ai/skills/skills/developing-genkit-python ~/.gemini/skills/developing-genkit-pythonInstall the developing-genkit-python skill in Claude.ai
npx degit genkit-ai/skills/skills/developing-genkit-python developing-genkit-python && zip -r developing-genkit-python.zip developing-genkit-python # claude.ai → Customize → Skills → + → Create skill → Upload a skill → developing-genkit-python.zip
Automated checks
Ran Nov 15, 2026Full report →Not verified yet. A skill needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablegenkit-ai/skills/skills/developing-genkit-python is public and reachablegithub.com/genkit-ai/skills/tree/HEAD/skills/developing-genk ↗Pass
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit 2026-11-09github.com/genkit-ai/skills/commits ↗Pass
- No download-and-run or credential theft in scriptsNo scripts in the skill folderPass
- No hidden instructions in SKILL.mdNo override phrases, safeguard switches, credential requests or hidden charactersgithub.com/genkit-ai/skills/blob/HEAD/skills/developing-genk ↗Pass
- Pre-approved tools are scopedNo pre-approved tools; the agent asks before using onegithub.com/genkit-ai/skills/blob/HEAD/skills/developing-genk ↗Pass
- SKILL.md follows the Agent Skills formatValid name and description; says when to use it; 236 linesgithub.com/genkit-ai/skills/blob/HEAD/skills/developing-genk ↗Pass
SKILL.md
View on GitHubGenkit Python
Build AI features in Python — generation, structured output, streaming, tools, flows, and multi-turn agents — with Genkit Python 0.13.
- New project? See Setup and Examples.
- Upgrading from 0.12 or fixing broken 0.12 imports/signatures? Read Migrating from 0.12 to 0.13 first.
Prerequisites
- Python 3.10+ and
uv(install) - Genkit CLI:
npm install -g genkit-cliifgenkit --versionis missing
Hello World
from genkit import Genkit
from genkit_google_genai import GoogleAI
ai = Genkit(
plugins=[GoogleAI()],
model=GoogleAI.gemini('gemini-flash-latest'),
)
async def main() -> None:
response = await ai.generate(prompt='Suggest one seasonal pasta dish.')
if response.error:
raise RuntimeError(response.error.message)
print(response.text)
# => Lemony tagliatelle with asparagus, sweet peas, and herb ricotta
if __name__ == '__main__':
ai.run_main(main())
ai.generate does not raise when the provider rejects or fails a call
(INVALID_ARGUMENT, UNAVAILABLE, rate limits). It returns response.error
(Failure with .status and .message), finish_reason == 'failed', and
empty text. Problems caught before the call raise: GoogleAI() raises
ValueError without GEMINI_API_KEY; an unknown model, invalid key, or unknown
config field raises GenkitError. See
Common Errors.
Agents (Experimental)
Multi-turn chats with history, typed state, human approval, branching, and
background work live under genkit.exp and genkit.exp.agent. Start here:
Agents.
from genkit.exp import Genkit
from genkit.exp.agent import InMemorySessionStore
from genkit_google_genai import GoogleAI
ai = Genkit(plugins=[GoogleAI()], model=GoogleAI.gemini('gemini-flash-latest'))
agent = ai.define_agent(
name='concierge',
system='You are a concise hotel concierge.',
store=InMemorySessionStore(),
)
chat = agent.chat()
res = await chat.send('Recommend a quiet dinner spot.') # AgentResponse
print(res.text)
# => Try Osteria Lume on 5th; it has booths and low music.
turn = chat.send_stream('Is it open past 10pm?') # AgentTurn
async for chunk in turn.stream:
if chunk.text:
print(chunk.text, end='')
final = await turn.response # AgentResponse
More: sessions · HITL · branching · background · state · artifacts · custom · HTTP
Imports
Every symbol lives in one public module (never import private _ submodules;
see Migrating from 0.12 to 0.13 if a 0.12
symbol moved):
- Core app:
from genkit import Genkit, FlowContext, ToolContext, Message, Part, Role, Media, Document, MultipartToolResponse, PublicError, GenkitError, Failure, ErrorReason - Google GenAI & Vertex AI:
from genkit_google_genai import GoogleAI, VertexAI, GeminiConfig, GeminiImageConfig, GeminiTtsConfig - Other providers:
from genkit_vertexai import ModelGarden·from genkit_anthropic import Anthropic, AnthropicConfig·from genkit_openai import OpenAI, OpenAIConfig·from genkit_ollama import Ollama, OllamaConfig·from genkit_amazon_bedrock import Bedrock, BedrockConfig - Built-in middleware:
from genkit_middleware import Middleware, Retry, Fallback, ToolApproval, Skills, Filesystem(plusfrom genkit_middleware.exp import Artifactsfor agent sessions) - Writing custom middleware:
from genkit.middleware import Middleware, MiddlewareContext - FastAPI & HTTP:
from genkit_fastapi import serve_flow, genkit_fastapi_handler, handle_genkit_request·from genkit_fastapi.exp import serve_agent·from genkit.web import RequestData, to_sse, error_body, error_status - Agents (experimental):
from genkit.exp import Genkit, current_session·from genkit.exp.agent import Agent, Session, InMemorySessionStore, FileSessionStore, remote_agent - Telemetry:
from genkit_google_cloud import enable_google_cloud_telemetry·from genkit.telemetry import configure_instrumentation·from genkit_otel import GenAiInstrumentation - MCP (Client & Host):
from genkit_mcp import define_mcp_client, define_mcp_host, McpClient, McpHost - Testing & Mocks:
from genkit.testing import define_echo_model, define_scripted_model, EchoModel, ScriptedModel - Evaluators (0.13 only; cut from 1.0, additive later):
from genkit_evaluators import register_genkit_evaluators·from genkit.evaluator import BaseDataPoint, EvaluatorResponse, Score, ScoreDetails, ScoreStatus
Workflow
- Agent or flow? Use
ai.define_agent(ongenkit.exp.Genkit, see Agents) for multi-turn chats, state, or human-in-the-loop approval instead of hand-rolling a message loop inside a flow. Use@ai.flow()ongenkit.Genkitfor stateless request/response or streaming pipelines. - Configure credentials & model refs. Set
GEMINI_API_KEY. Prefer typed refs (GoogleAI.gemini('gemini-flash-latest')) and typed flat configs (GeminiConfig(...)) so your type checker validates fields before runtime. Prefixed strings ('googleai/gemini-flash-latest') also work. - Enter via
ai.run_main(main())for standalone scripts and CLI apps so the process stays up for the Dev UI undergenkit start. FastAPI apps skiprun_main; uvicorn keeps the process alive:genkit start -- uv run uvicorn main:app --reload. - Run with Dev Workflow (
genkit start+ Dev UI) and type-check withpyright,mypy, orty. - Verify with traces, not a blind
uv run. See Genkit CLI. - Stuck? Check Gotchas, Common Errors, or Migrating from 0.12 to 0.13.
Gotchas
- Agents need
genkit.exp:from genkit.exp import Genkit. Stablegenkit.Genkithas nodefine_agent. - Tools are async:
@ai.tool()raisesTypeErroron a plaindef; useasync def. - Check
response.error: provider failures come back on the response, not as exceptions (see Hello World). - Gemini thinking levels:
GeminiConfig(thinking_level='MINIMAL')fails ongemini-flash-latest; use'LOW','MEDIUM', or'HIGH'. - Vertex AI model IDs: Vertex does not serve
-latestaliases. Pass a pinned model ID toVertexAI.gemini(...). - Logging:
genkit.get_loggeris structlog-based.enable_google_cloud_telemetry()injects trace context for GCP log-trace correlation. - Cloud telemetry auth: call
enable_google_cloud_telemetry()with Application Default Credentials or explicitcredentials=(service account dict orCredentialsinstance).
Genkit CLI (recommended)
genkit start wraps any Python program that uses Genkit, capturing traces from
every action while forwarding stdio cleanly. Running uv run directly skips
trace capture.
Primary pattern (persistent server + Dev UI):
genkit start -- uv run src/main.py
genkit start --noui -- uv run src/main.py # persistent runtime without opening the Dev UI
genkit start runs until stopped with Ctrl+C (even with --noui). Do not
run genkit start as a blocking step in automated/non-interactive scripts; use
flow:run instead.
Non-interactive use (agents/CI): pass --non-interactive before -- so the
CLI never blocks on prompts:
genkit start --non-interactive -- uv run src/main.py
One-shot flow execution (flow:run): spins up the runtime, invokes one
@ai.flow() by name, prints a Trace ID, and exits:
genkit flow:run myFlow '{"data": "input"}' -- uv run src/main.py
Note: flow:run invokes flows (@ai.flow()), not agents (ai.define_agent).
Wrap a single agent turn in a helper flow to exercise it via flow:run (see
Agents).
Inspecting traces:
genkit trace:list # list recent trace IDs
genkit trace:get <traceId> # human-readable trace inspection
genkit trace:get <traceId> --format json # machine-readable JSON for jq / scripts
Always pass --format json when piping into jq or other parsers.
See Dev Workflow for the full pre-run checklist and Dev UI walkthrough.
References
- Migrating from 0.12 to 0.13:
Deterministic 0.12 -> 0.13 renames, config flattening,
PublicError, andexpmoves. - Examples: Structured output, streaming, media parts, flows, tools, interrupts, cancellation, embeddings.
- Setup: Project bootstrap with
uv, version alignment, and provider plugins. - Common Errors: Fast fixes for 0.13 validation errors, HTTP 500 redaction, streaming, and sessions.
- FastAPI:
serve_flow,serve_agent,PublicError, SSE streaming, and parallel flows. - Dotprompt:
.promptfiles, schema validation, variants, partials, and helpers. - Evals: 0.13 evaluator syntax (deprecated; removed in 1.0).
- Dev Workflow:
genkit start, Dev UI, and trace verification checklist. - Agents (Experimental): Multi-turn stateful agents
(
genkit.exp).
Files in this skill
18developing-genkit-python skill questions
How do I install the developing-genkit-python skill in Claude Code?
Run npx degit genkit-ai/skills/skills/developing-genkit-python ~/.claude/skills/developing-genkit-python. Claude Code loads skills from ~/.claude/skills (all projects) or .claude/skills (one project) and uses a skill when its description matches the task.
Which clients can use the developing-genkit-python skill?
Any client that reads the Agent Skills format: Claude Code, Codex, Gemini CLI and claude.ai (upload as a ZIP). Scripts in the skill run only where the client allows code execution.
How can I run multi-turn agents in Genkit?
Multi-turn agents are currently experimental and are located under the genkit.exp module.