5545de0466
Updates the bedrock rag template. - Removes pinecone and replaces with FAISS as the vector store - Fixes the environment variables, setting defaults - Adds a `main.py` test file quick sanity testing - Updates README.md with correct instructions |
||
|---|---|---|
| .. | ||
| anthropic-functions | ||
| anthropic-iterative-search | ||
| cassandra-entomology-rag | ||
| cassandra-synonym-caching | ||
| csv-agent | ||
| elastic-query-generator | ||
| extraction-openai-functions | ||
| hyde | ||
| llama2-functions | ||
| neo4j-cypher | ||
| neo4j-cypher-ft | ||
| neo4j-generation | ||
| neo4j-parent | ||
| openai-functions-agent | ||
| rag-aws-bedrock | ||
| rag-chroma | ||
| rag-chroma-private | ||
| rag-conversation | ||
| rag-elasticsearch | ||
| rag-fusion | ||
| rag-pinecone | ||
| rag-pinecone-multi-query | ||
| rag-pinecone-rerank | ||
| rag-semi-structured | ||
| rag-supabase | ||
| rag-weaviate | ||
| rewrite-retrieve-read | ||
| self-query-supabase | ||
| sql-llama2 | ||
| sql-llamacpp | ||
| sql-ollama | ||
| stepback-qa-prompting | ||
| summarize-anthropic | ||
| xml-agent | ||
| .gitignore | ||
| CONTRIBUTING.md | ||
| INDEX.md | ||
| Makefile | ||
| poetry.lock | ||
| pyproject.toml | ||
| README.md | ||
LangServe Templates
Templates for a fully functioning app that can be hosted by LangServe.
Some other helpful docs:
- [Templates]
Usage
To use, first install the LangChain CLI.
pip install -U "langchain-cli[serve]"
Next, create a new LangChain project:
langchain serve new my-app
This will create a new directory called my-app with two folders:
app: This is where LangServe code will livepackages: This is where your chains or agents will live
To pull in an existing template as a package, you first need to go into your new project:
cd my-app
And you can the add a template as a project
langchain serve add $PROJECT_NAME
This will pull in the specified template into packages/$PROJECT_NAME
You then need to install this package so you can use it in the langserve app:
pip install -e packages/$PROJECT_NAME
We install it with -e so that if you modify the template at all (which you likely will) the changes are updated.
In order to have LangServe use this project, you then need to modify app/server.py.
Specifically, you should add something like:
from fastapi import FastAPI
from langserve import add_routes
# This depends on the structure of the package you install
from my_project import chain
app = FastAPI()
add_routes(app, chain)
You can then spin up production-ready endpoints, along with a playground, by running:
langchain start
Adding a template
See here