Skip to main content


This template performs self-querying using Qdrant and OpenAI. By default, it uses an artificial dataset of 10 documents, but you can replace it with your own dataset.

Environment Setup​

Set the OPENAI_API_KEY environment variable to access the OpenAI models.

Set the QDRANT_URL to the URL of your Qdrant instance. If you use Qdrant Cloud you have to set the QDRANT_API_KEY environment variable as well. If you do not set any of them, the template will try to connect a local Qdrant instance at http://localhost:6333.

export QDRANT_URL=



To use this package, install the LangChain CLI first:

pip install -U "langchain-cli[serve]"

Create a new LangChain project and install this package as the only one:

langchain app new my-app --package self-query-qdrant

To add this to an existing project, run:

langchain app add self-query-qdrant


Before you launch the server, you need to create a Qdrant collection and index the documents. It can be done by running the following command:

from self_query_qdrant.chain import initialize


Add the following code to your app/ file:

from self_query_qdrant.chain import chain

add_routes(app, chain, path="/self-query-qdrant")

The default dataset consists 10 documents about dishes, along with their price and restaurant information. You can find the documents in the packages/self-query-qdrant/self_query_qdrant/ file. Here is one of the documents:

from langchain_core.documents import Document

page_content="Spaghetti with meatballs and tomato sauce",
"price": 12.99,
"restaurant": {
"name": "Olive Garden",
"location": ["New York", "Chicago", "Los Angeles"],
API Reference:Document

The self-querying allows performing semantic search over the documents, with some additional filtering based on the metadata. For example, you can search for the dishes that cost less than $15 and are served in New York.


All the examples above assume that you want to launch the template with just the defaults. If you want to customize the template, you can do it by passing the parameters to the create_chain function in the app/ file:

from langchain_community.llms import Cohere
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain.chains.query_constructor.schema import AttributeInfo

from self_query_qdrant.chain import create_chain

chain = create_chain(
document_contents="Descriptions of cats, along with their names and breeds.",
AttributeInfo(name="name", description="Name of the cat", type="string"),
AttributeInfo(name="breed", description="Cat's breed", type="string"),

The same goes for the initialize function that creates a Qdrant collection and indexes the documents:

from langchain_core.documents import Document
from langchain_community.embeddings import HuggingFaceEmbeddings

from self_query_qdrant.chain import initialize

page_content="A mean lazy old cat who destroys furniture and eats lasagna",
metadata={"name": "Garfield", "breed": "Tabby"},

The template is flexible and might be used for different sets of documents easily.


(Optional) If you have access to LangSmith, configure it to help trace, monitor and debug LangChain applications. If you don't have access, skip this section.

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

If you are inside this directory, then you can spin up a LangServe instance directly by:

langchain serve

Local Server​

This will start the FastAPI app with a server running locally at http://localhost:8000

You can see all templates at Access the playground at

Access the template from code with:

from langserve.client import RemoteRunnable

runnable = RemoteRunnable("http://localhost:8000/self-query-qdrant")

Was this page helpful?

You can also leave detailed feedback on GitHub.