LangServe 🦜 🏓 on Railway 🚂

Deploy on Railway

ℹ️ Make sure to set your enviromental variables! The defaults are only placeholders.

Adding packages

Add the package to your local repo

# adding packages from 
# https://github.com/langchain-ai/langchain/tree/master/templates
langchain app add $PROJECT_NAME

# adding custom GitHub repo packages
langchain app add --repo $OWNER/$REPO
# or with whole git string (supports other git providers):
# langchain app add git+https://github.com/hwchase17/chain-of-verification

# with a custom api mount point (defaults to `/{package_name}`)
langchain app add $PROJECT_NAME --api_path=/my/custom/path/rag

Note: you remove packages by their api path

langchain app remove my/custom/path/rag

After adding the project to your local repo you need to add it to your project's pyproject.toml

#
# other packages
$PROJECT_NAME = { path = "packages/$PROJECT_NAME" }
#
#

Then redeploy by pushing these changes to your git repo for this railway service.

Setup LangSmith (Optional)

LangSmith will help us trace, monitor and debug LangChain applications. LangSmith is currently in private beta, you can sign up here. If you don't have access, you can skip this section

# add these to your railway enviromental variables or your local .env
LANGCHAIN_TRACING_V2=true
LANGCHAIN_API_KEY=<your-api-key>
LANGCHAIN_PROJECT=<your-project>  
# if not specified, defaults to "default"