langchain/templates
2024-02-01 17:29:38 -08:00
..
anthropic-iterative-search templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
basic-critique-revise templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
bedrock-jcvd Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
cassandra-entomology-rag templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
cassandra-synonym-caching templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
chain-of-note-wiki templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
chat-bot-feedback docs: fix broken links (#16855) 2024-02-01 17:29:38 -08:00
cohere-librarian templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
csv-agent templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
docs Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
elastic-query-generator templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
extraction-anthropic-functions templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
extraction-openai-functions templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
guardrails-output-parser templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
hybrid-search-weaviate templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
hyde templates: Minor nit on HyDE (#16478) 2024-01-23 14:23:08 -07:00
llama2-functions templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
mongo-parent-document-retrieval Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
neo4j-advanced-rag templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
neo4j-cypher Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
neo4j-cypher-ft Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
neo4j-cypher-memory Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
neo4j-generation templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
neo4j-parent templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
neo4j-semantic-layer docs: Add neo4j semantic blog post link to templates (#16225) 2024-01-18 18:45:22 -08:00
neo4j-vector-memory templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
nvidia-rag-canonical docs: Fix minor issues in NVIDIA RAG canonical template (#16189) 2024-01-19 09:44:08 -08:00
openai-functions-agent templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
openai-functions-agent-gmail Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
openai-functions-tool-retrieval-agent templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
pii-protected-chatbot templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
pirate-speak templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
pirate-speak-configurable templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
plate-chain templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
propositional-retrieval Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
python-lint templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-astradb templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-aws-bedrock templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-aws-kendra templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-chroma templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-chroma-multi-modal Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
rag-chroma-multi-modal-multi-vector Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
rag-chroma-private templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-codellama-fireworks templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-conversation templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-conversation-zep templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-elasticsearch templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-fusion templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-gemini-multi-modal Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
rag-google-cloud-sensitive-data-protection templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-google-cloud-vertexai-search templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-gpt-crawler templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-matching-engine templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-momento-vector-index templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-mongo Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
rag-multi-index-fusion templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-multi-index-router templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-multi-modal-local Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
rag-multi-modal-mv-local Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00
rag-ollama-multi-query templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-opensearch templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-pinecone templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-pinecone-multi-query templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-pinecone-rerank templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-redis templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-self-query templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-semi-structured templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-singlestoredb templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-supabase templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-timescale-conversation templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-timescale-hybrid-search-time templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-vectara templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
rag-vectara-multiquery template: Update Vectara templates (#15363) 2024-01-19 17:32:33 -08:00
rag-weaviate templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
research-assistant templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
retrieval-agent templates: fix azure params in retrieval agent (#16257) 2024-01-23 14:58:06 -07:00
rewrite-retrieve-read templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
robocorp-action-server templates: robocorp action server template (#15776) 2024-01-09 12:41:20 -08:00
self-query-qdrant templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
self-query-supabase templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
shopping-assistant templates: Ionic Shopping Assistant (#16648) 2024-01-29 11:08:24 -08:00
skeleton-of-thought templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
solo-performance-prompting-agent templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
sql-llama2 templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
sql-llamacpp templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
sql-ollama templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
sql-pgvector docs: fix broken links (#16855) 2024-02-01 17:29:38 -08:00
sql-research-assistant templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
stepback-qa-prompting templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
summarize-anthropic templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
vertexai-chuck-norris templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
xml-agent templates: 0.1 bump (#15648) 2024-01-06 18:31:46 -08:00
.gitignore Adds linter in templates (#12321) 2023-10-26 13:55:07 -07:00
Makefile core[patch], langchain[patch]: fix required deps (#14373) 2023-12-07 14:24:58 -08:00
poetry.lock templates: fix deps (#15439) 2024-01-03 13:28:05 -08:00
pyproject.toml templates: fix deps (#15439) 2024-01-03 13:28:05 -08:00
README.md Batch update of alt text and title attributes for images in md/mdx files across repo (#15357) 2024-01-12 14:37:48 -08:00

LangChain Templates

LangChain Templates are the easiest and fastest way to build a production-ready LLM application. These templates serve as a set of reference architectures for a wide variety of popular LLM use cases. They are all in a standard format which make it easy to deploy them with LangServe.

🚩 We will be releasing a hosted version of LangServe for one-click deployments of LangChain applications. Sign up here to get on the waitlist.

Quick Start

To use, first install the LangChain CLI.

pip install -U langchain-cli

Next, create a new LangChain project:

langchain app new my-app

This will create a new directory called my-app with two folders:

  • app: This is where LangServe code will live
  • packages: 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. In this getting started guide, we will add a simple pirate-speak project. All this project does is convert user input into pirate speak.

langchain app add pirate-speak

This will pull in the specified template into packages/pirate-speak

You will then be prompted if you want to install it. This is the equivalent of running pip install -e packages/pirate-speak. You should generally accept this (or run that same command afterwards). We install it with -e so that if you modify the template at all (which you likely will) the changes are updated.

After that, it will ask you if you want to generate route code for this project. This is code you need to add to your app to start using this chain. If we accept, we will see the following code generated:

from pirate_speak.chain import chain as pirate_speak_chain

add_routes(app, pirate_speak_chain, path="/pirate-speak")

You can now edit the template you pulled down. You can change the code files in packages/pirate-speak to use a different model, different prompt, different logic. Note that the above code snippet always expects the final chain to be importable as from pirate_speak.chain import chain, so you should either keep the structure of the package similar enough to respect that or be prepared to update that code snippet.

Once you have done as much of that as you want, it is In order to have LangServe use this project, you then need to modify app/server.py. Specifically, you should add the above code snippet to app/server.py so that file looks like:

from fastapi import FastAPI
from langserve import add_routes
from pirate_speak.chain import chain as pirate_speak_chain

app = FastAPI()

add_routes(app, pirate_speak_chain, path="/pirate-speak")

(Optional) Let's now configure LangSmith. 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

export LANGCHAIN_TRACING_V2=true
export LANGCHAIN_API_KEY=<your-api-key>
export LANGCHAIN_PROJECT=<your-project>  # if not specified, defaults to "default"

For this particular application, we will use OpenAI as the LLM, so we need to export our OpenAI API key:

export OPENAI_API_KEY=sk-...

You can then spin up production-ready endpoints, along with a playground, by running:

langchain serve

This now gives a fully deployed LangServe application. For example, you get a playground out-of-the-box at http://127.0.0.1:8000/pirate-speak/playground/:

Screenshot of the LangServe Playground interface with input and output fields demonstrating pirate speak conversion.

Access API documentation at http://127.0.0.1:8000/docs

Screenshot of the API documentation interface showing available endpoints for the pirate-speak application.

Use the LangServe python or js SDK to interact with the API as if it were a regular Runnable.

from langserve import RemoteRunnable

api = RemoteRunnable("http://127.0.0.1:8000/pirate-speak")
api.invoke({"text": "hi"})

That's it for the quick start! You have successfully downloaded your first template and deployed it with LangServe.

Additional Resources

Index of Templates

Explore the many templates available to use - from advanced RAG to agents.

Contributing

Want to contribute your own template? It's pretty easy! These instructions walk through how to do that.

Launching LangServe from a Package

You can also launch LangServe from a package directly (without having to create a new project). These instructions cover how to do that.