{ "schema_version": 2, "id": "integrate/google-adk/examples", "title": "adk-redis examples", "url": "https://redis.io/docs/latest/integrate/google-adk/examples/", "summary": "Complete examples for every adk-redis capability.", "tags": [ "docs", "integrate", "oss", "rs", "rc" ], "last_updated": "2026-09-17T14:55:03+01:00", "page_type": "content", "content_hash": "a783373ed6bc0b997ba403be339dc57d93942106b9bc2d5bbdeef46d107224f6", "sections": [ { "id": "overview", "title": "Overview", "role": "overview", "text": "The [adk-redis repository](https://github.com/redis-developer/adk-redis/tree/main/examples) includes ten complete examples, each focused on a specific capability. The seven below run on supported backends; the remaining three are listed under [Deprecated backend examples](#deprecated-backend-examples)." }, { "id": "prerequisites", "title": "Prerequisites", "role": "content", "text": "All examples require:\n\n- **Python 3.10+**\n- **Redis 8.4+**: `docker run -d --name redis -p 6379:6379 redis:8.4-alpine`\n- **A memory backend** (for memory examples): a [Redis Agent Memory](https://redis.io/docs/latest/integrate/google-adk/redis-agent-memory) store on Redis Cloud or self-managed.\n- **API keys**: Most examples need a `GOOGLE_API_KEY` for Gemini" }, { "id": "managed_memory_quickstart", "title": "`managed_memory_quickstart`", "role": "content", "text": "**Backend:** `redis-agent-memory` · **Run:** `python main.py`\n\nThe smallest memory example, and the counterpart to `simple_redis_memory`. Uses `redis-agent-memory`, so there is no Agent Memory Server and no Docker to set up. Wires `RedisSessionMemoryService` and `RedisLongTermMemoryService` to an agent with ADK's built-in `preload_memory` and `load_memory` tools.\n\n[View on GitHub](https://github.com/redis-developer/adk-redis/tree/main/examples/managed_memory_quickstart)" }, { "id": "travel_agent_memory_tools", "title": "`travel_agent_memory_tools`", "role": "content", "text": "**Backend:** `redis-agent-memory`, switchable · **Run:** `adk web .`\n\nUses REST-based memory tools exclusively, without framework-managed services. The LLM has full control over when to search, create, update, and delete memories. Set `REDIS_MEMORY_BACKEND` to switch backends.\n\n[View on GitHub](https://github.com/redis-developer/adk-redis/tree/main/examples/travel_agent_memory_tools)" }, { "id": "redis_search_tools", "title": "`redis_search_tools`", "role": "content", "text": "**Capability:** Vector, text, and range search · **Run:** `adk web .`\n\nThree in-process RedisVL [search tools](https://redis.io/docs/latest/integrate/google-adk/search-tools) plugged into a single agent with a product catalog dataset.\n\n[View on GitHub](https://github.com/redis-developer/adk-redis/tree/main/examples/redis_search_tools)" }, { "id": "redis_sql_search", "title": "`redis_sql_search`", "role": "content", "text": "**Capability:** SQL `SELECT` search · **Run:** `adk web .`\n\nA 10-product catalog with the `RedisSQLSearchTool`. The agent emits parameterized SQL (`WHERE category = 'electronics' AND price < :max_price`) to answer structured catalog questions. Requires `pip install 'adk-redis[sql]'`.\n\n[View on GitHub](https://github.com/redis-developer/adk-redis/tree/main/examples/redis_sql_search)" }, { "id": "redisvl_mcp_search", "title": "`redisvl_mcp_search`", "role": "content", "text": "**Capability:** RedisVL MCP server via ADK's `McpToolset` · **Run:** `adk web .`\n\nThe MCP counterpart of `redis_search_tools`. A `rvl mcp` server hosts a knowledge-base index in hybrid (vector + BM25) mode and the agent connects via ADK's native `McpToolset`. No adk-redis wrapper involved; the standard `McpToolset` + `StdioConnectionParams` pattern is used.\n\n[View on GitHub](https://github.com/redis-developer/adk-redis/tree/main/examples/redisvl_mcp_search)" }, { "id": "semantic_cache", "title": "`semantic_cache`", "role": "content", "text": "**Capability:** Local semantic caching (RedisVL) · **Run:** `python main.py`\n\nDemonstrates LLM response caching and tool result caching using the `RedisVLCacheProvider` with local embeddings and ADK callbacks.\n\n[View on GitHub](https://github.com/redis-developer/adk-redis/tree/main/examples/semantic_cache)" }, { "id": "langcache_cache", "title": "`langcache_cache`", "role": "content", "text": "**Capability:** Managed semantic caching (LangCache) · **Run:** `python main.py`\n\nUses the managed [LangCache](https://redis.io/docs/latest/integrate/google-adk/semantic-caching) service for semantic caching with server-side embeddings. No local vectorizer required.\n\n[View on GitHub](https://github.com/redis-developer/adk-redis/tree/main/examples/langcache_cache)" }, { "id": "running-an-example", "title": "Running an example", "role": "content", "text": "Examples marked `python main.py` run as scripts. Examples marked `adk web .`\nrun in the ADK developer UI from inside the example directory.\n\n[code example]" }, { "id": "deprecated-backend-examples", "title": "Deprecated backend examples", "role": "content", "text": "Three examples are written against the deprecated `opensource-agent-memory`\nbackend: `simple_redis_memory`, `travel_agent_memory_hybrid`, and\n`fitness_coach_mcp`. They are listed under\n[Agent Memory Server (deprecated)](https://redis.io/docs/latest/integrate/google-adk/agent-memory-server#examples-still-on-this-backend).\nFor a `redis-agent-memory` starting point, use `managed_memory_quickstart` above." }, { "id": "more-info", "title": "More info", "role": "content", "text": "- [Car dealership tutorial](https://redis.io/tutorials/build-a-car-dealership-agent-with-google-adk-and-redis-agent-memory/): Full walkthrough building an agent from scratch\n- [adk-redis README](https://github.com/redis-developer/adk-redis): Installation and overview" } ], "examples": [ { "id": "running-an-example-ex0", "language": "bash", "code": "pip install adk-redis[all]\ncd examples/managed_memory_quickstart\nexport GOOGLE_API_KEY=your-key\npython main.py", "section_id": "running-an-example" } ] }