LangStream Documentation
Langstream.aiLangStream GitHub RepoChangelog
  • LangStream Documentation
  • ❤️Langstream.ai
  • ⭐LangStream GitHub Repo
  • 📜Changelog
  • about
    • What is LangStream?
    • License
  • Get Started
  • installation
    • LangStream CLI
    • Docker
    • Minikube (mini-langstream)
    • Kubernetes
    • Build and install from source
  • Building Applications
    • Vector Databases
    • Application structure
      • Pipelines
      • Instances
      • Configuration
      • Topics
      • Assets
      • Secrets
      • YAML templating
      • Error Handling
      • Stateful agents
      • .langstreamignore
    • Sample App
    • Develop, test and deploy
    • Application Lifecycle
    • Expression Language
    • API Gateways
      • Websocket
      • HTTP
      • Message filtering
      • Gateway authentication
    • API Reference
      • Agents
      • Resources
      • Assets
  • LangStream CLI
    • CLI Commands
    • CLI Configuration
    • Web interface
  • Integrations
    • Large Language Models (LLMs)
      • OpenAI
      • Hugging Face
      • Google Vertex AI
      • Amazon Bedrock
      • Ollama
    • Data storage
      • Astra Vector DB
      • Astra
      • Cassandra
      • Pinecone
      • Milvus
      • Solr
      • JDBC
      • OpenSearch
    • Integrations
      • Apache Kafka Connect
      • Apache Camel
    • LangServe
  • Pipeline Agents
    • Agent Messaging
    • Builtin agents
      • Input & Output
        • webcrawler-source
        • s3-source
        • azure-blob-storage-source
        • sink
        • vector-db-sink
        • camel-source
      • AI Agents
        • ai-chat-completions
        • ai-text-completions
        • compute-ai-embeddings
        • flare-controller
      • Text Processors
        • document-to-json
        • language-detector
        • query
        • query-vector-db
        • re-rank
        • text-normaliser
        • text-extractor
        • text-splitter
        • http-request
      • Data Transform
        • cast
        • compute
        • drop
        • drop-fields
        • merge-key-value
        • unwrap-key-value
      • Flow control
        • dispatch
        • timer-source
        • trigger-event
    • Custom Agents
      • Python sink
      • Python source
      • Python processor
      • Python service
    • Agent Developer Guide
      • Agent Types
      • Agent Creation
      • Configuration and Testing
      • Environment variables
  • Messaging
    • Messaging
      • Apache Pulsar
      • Apache Kafka
      • Pravega.io
  • Patterns
    • RAG pattern
    • FLARE pattern
  • Examples
    • LangServe chatbot
    • LlamaIndex Cassandra sink
Powered by GitBook
On this page
  • Langstream profiles
  • Multi tenancy
Edit on GitHub
  1. LangStream CLI

CLI Configuration

PreviousCLI CommandsNextWeb interface

Last updated 1 year ago

Use the LangStream CLI to manage your control plane, deploy applications, and interact with an application's gateway.

For LangStream CLI commands, see .

To install the CLI, see .

Langstream profiles

LangStream profiles replace the langstream configure option, which is now deprecated.

Profiles are created by users to interact with different LangStream environments. For example, you could have a "local" profile to test your application locally, and a "stage" profile to deploy your changes to a shared development space.

The default LangStream profile values for a local deployment are:

webServiceUrl: "http://localhost:8090"
apiGatewayUrl: "ws://localhost:8091"
tenant: "default"
token: null

To create a new profile for a staging environment and set it as the current LangStream profile, use:

langstream profiles create staging \
--web-service-url="https://pulsar-gcp-useast1.api.streaming.datastax.com" \
--tenant="staging-tenant" \
--set-current

To update these values in the "staging" profile, use langstream profiles update staging --command-option="value".

Command Option
Description

--set-current

Set this profile as current

--web-service-url

webServiceUrl of the profile

--api-gateway-url

apiGatewayUrl of the profile

--tenant

tenant of the profile

--token

token of the profile

Instead of manually setting values, you can use langstream import to create a new CLI profile from a JSON file.

langstream profiles import staging -f <file.json>

To update this file:

langstream profiles import staging --file="my-file.json" --update="true"

The existing LangStream configuration file is OVERWRITTEN, not MERGED.

Multi tenancy

LangStream is multi-tenant. You can create multiple tenants and deploy applications to them. Each tenant has its own control plane and API gateway. When you first install LangStream, a default tenant is created for you. You can use this tenant or create a new one. This works well if you are running LangStream locally, but if you are running LangStream in a cluster, you will need to create a new tenant.

The CLI is able to handle multiple profiles, and each profile defines:

  • the tenant

  • the control plane URL

  • the API gateway URL

  • the credentials to connect to the control plane (currently there is support for a token, that can be a JWT or OAuth2 token, depending on the authentication method used by the control plane)

These commands will help you manage your profiles and the tenant you are currenly using:

langstream profiles list
langstream profiles get-current
langstream profiles get default

All the other commands always refer to the current tenant configured in the current profile.

For more profile commands, see .

CLI Commands
Installation
Profiles