Connecting to a LangGraph Platform Deployment

Connecting to a LangGraph Platform Deployment Deployment Creation We just created a <!--~deployment~ --> deployment for the task_maistro app from module 5. * We used the the LangGraph CLI to build a Docker image for the LangGraph Server with our task_maistro graph. * We used the provided docker-compose.yml file to create three separate containers based on the services defined: * langgraph-redis: Creates a new container using the official Redis image. * langgraph-postgres: Creates a new container using the official Postgres image. * langgraph-api: Creates a new container using our pre-built task_maistro Docker image. `` $ cd module-6/deployment $ docker compose up `` Once running, we can access the deployment through: * API: http://localhost:8123 * Docs: http://localhost:8123/docs * LangGraph Studio: https://smith.langchain.com/studio/?baseUrl=http://127.0.0.1:8123 Using the API LangGraph Server exposes many API endpoints for interacting with the deployed agent. We can group these endpoints into a few common agent needs: * **Runs**: Atomic agent executions * **Threads**: Multi-turn interactions or human in the loop * **Store**: Long-term memory We can test requests directly in the API docs. SDK The LangGraph SDKs (Python and JS) provide a developer-friendly interface to interact with the LangGraph Server API presented above.