# philschmid/gemini-samples

Repository: https://github.com/philschmid/gemini-samples
Canonical: https://ross.abutalabs.com/products/gemini-samples
Language: Jupyter Notebook
License: MIT
License Family: permissive
Last push: 2026-03-03T14:00:12+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 70, release rhythm 35, longevity 41
- inputs: {"age_days": 574, "days_push": 183, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1372, forks 208 (observed 2026-08-28T04:04:32.355253+00:00)

## What it is
A collection of Jupyter notebook samples, snippets, and guides demonstrating how to use Google DeepMind Gemini models. It covers function calling, agents, structured outputs, MCP, context caching, and other Gemini API capabilities.

## Use cases
- learn how to call Gemini models from Python
- implement function calling with Gemini
- build a ReAct agent with LangGraph and Gemini
- generate structured JSON outputs with Pydantic and Gemini
- use Gemini with the OpenAI SDK
- integrate MCP with Gemini
- reduce Gemini API costs with context caching
- transcribe and analyze YouTube videos with Gemini

## When to choose
- you want practical, runnable notebook examples for the Gemini API
- you are exploring agentic patterns or function calling with Gemini
- you need reference snippets for structured outputs, caching, or batch API usage

## When to avoid
- you need a production-ready library or framework rather than example code
- you work with LLM providers other than Google Gemini
- you need maintained, versioned software with API stability guarantees

## Facets
- artifact type: learning-resource
- maturity: active
- function: llm-inference, agent-framework, prompt-engineering, mcp, rag
- domain: large-language-models, artificial-intelligence, tutorials
- platform: python, jvm-scripting
- tags: gemini, google-deepmind, jupyter-notebooks, samples, function-calling, structured-outputs, ai-agents, nodejs

## Member repositories
- philschmid/gemini-samples (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:32.355253+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:40:47.178658+00:00, confidence not recorded.
  - readme: https://github.com/philschmid/gemini-samples (fetched 2026-08-28T04:04:32.355253+00:00, sha 3e75dbd987c2)
- Data as of 2026-08-30T08:39:29.467469+00:00.