diff --git a/qdrant-landing/content/documentation/quick-start.md b/qdrant-landing/content/documentation/quick-start.md index e97a715ab..92736c044 100644 --- a/qdrant-landing/content/documentation/quick-start.md +++ b/qdrant-landing/content/documentation/quick-start.md @@ -4,47 +4,28 @@ weight: 11 aliases: - quick_start --- - # Quickstart -## Installation +## Recommended Workflow -The easiest way to use Qdrant is to run a pre-built image. To do this, make sure Docker is installed on your system. +There are two ways of using Qdrant locally: [1) Local Mode](#option-1-local-mode) and [2) Docker Mode](#option-2-docker-mode). We recommend that you first try Local Mode in [Qdrant Client](https://github.com/qdrant/qdrant-client), as it only takes a few moments to get setup. Then, you may further experiment with Qdrant Docker containers. When you are more comfortable with Qdrant, then you should deploy your app to a Free Tier [Qdrant Cloud](../cloud/quickstart-cloud/) cluster. -Download image from [DockerHub](https://hub.docker.com/r/qdrant/qdrant): +|[Local Mode](#option-1-local-mode)|[Docker Mode](#option-2-docker-mode)|[Qdrant Cloud](../cloud/quickstart-cloud/)| +|:-:|:-:|:-:| -```bash -docker pull qdrant/qdrant -``` +![Local mode workflow](/docs/recommended.png) -And run the service inside the docker: +## Option 1: Local Mode -```bash -docker run -p 6333:6333 \ - -v $(pwd)/qdrant_storage:/qdrant/storage \ - qdrant/qdrant -``` +**Prerequisite:** First make sure you have the latest version of Python installed. -In this case Qdrant will use default configuration and store all data under `./qdrant_storage` directory. - -Now Qdrant should be accessible at [localhost:6333](http://localhost:6333) - - - -### Local mode - -![Local mode workflow](https://raw.githubusercontent.com/qdrant/qdrant-client/master/docs/images/try-develop-deploy.png) - - -With python client it is possible to try Qdrant without running docker container at all. - -Simply install it +### Install Qdrant ```bash pip install qdrant-client ``` -and initialize client like this: +### Initialize Qdrant Client ```python from qdrant_client import QdrantClient @@ -54,151 +35,61 @@ client = QdrantClient(":memory:") client = QdrantClient(path="path/to/db") # Persists changes to disk ``` -Local mode is useful for development, prototyping and testing. +## Option 2: Docker Mode -* You can use it to run tests in your CI/CD pipeline. -* Run it in Colab or Jupyter Notebook, no extra dependencies required. See a [Colab Example](https://colab.research.google.com/drive/1Bz8RSVHwnNDaNtDwotfPj0w7AYzsdXZ-?usp=sharing) -* When you need to scale, simply switch to server mode. +**Prerequisite:** First make sure Docker is installed and running on your system. - -## API - -All interaction with Qdrant takes place via the REST API. - -This example covers the most basic use-case - collection creation and basic vector search. -For additional information please refer to the [API documentation](https://qdrant.github.io/qdrant/redoc/index.html). - -### gRPC - -In addition to REST API, Qdrant also supports gRPC interface. -To enable gPRC interface, specify the following lines in the [configuration file](https://github.com/qdrant/qdrant/blob/master/config/config.yaml): - -```yaml -service: - grpc_port: 6334 -``` - -gRPC interface will be available on the specified port. -The gRPC methods follow the same principles as REST. For each REST endpoint, there is a corresponding gRPC method. -Documentation on all available gRPC methods and structures is available here - [gRPC Documentation](https://github.com/qdrant/qdrant/blob/master/docs/grpc/docs.md). - -The choice between gRPC and the REST API is a trade-off between convenience and speed. -gRPC is a binary protocol and can be more challenging to debug. -We recommend switching to it if you are already familiar with Qdrant and are trying to optimize the performance of your application. - -If you are applying Qdrant for the first time or working on a prototype, you might prefer to use REST. - -### Clients - -Qdrant provides a set of clients for different programming languages. You can find them here: - -* [Python](https://github.com/qdrant/qdrant-client) - `pip install qdrant-client` -* [Rust](https://github.com/qdrant/rust-client) - `cargo add qdrant-client` -* [Go](https://github.com/qdrant/go-client) - `go get github.com/qdrant/go-client` -* [Javascript](https://github.com/qdrant/qdrant-js) - `npm install @qdrant/js-client-rest` - -If you are using a language that is not listed here, you can use the REST API directly or generate a client for your language -using [OpenAPI](https://github.com/qdrant/qdrant/blob/master/docs/redoc/master/openapi.json) -or [protobuf](https://github.com/qdrant/qdrant/tree/master/lib/api/src/grpc/proto) definitions. - -### Create collection - -First - let's create a collection with dot-production metric. +### Download the image ```bash -curl -X PUT 'http://localhost:6333/collections/test_collection' \ - -H 'Content-Type: application/json' \ - --data-raw '{ - "vectors": { - "size": 4, - "distance": "Dot" - } - }' +docker pull qdrant/qdrant ``` +### Run the service + +```bash +docker run -p 6333:6333 \ + -v $(pwd)/qdrant_storage:/qdrant/storage \ + qdrant/qdrant +``` + +Under the default configuration all data will be stored in the `./qdrant_storage` directory. + +Qdrant should now be accessible at [localhost:6333](http://localhost:6333) + + + +# Running vector search queries + +In this simple example, you will create a Qdrant collection, load data into it and run a basic search query. + +![Qdrant Quickstart](/docs/quickstart.png) + +## Step 1. Create a collection + +You will be storing all of your vector data in a Qdrant collection. Let's call it `test_collection`. This collection will be using a doc production metric. + ```python from qdrant_client import QdrantClient from qdrant_client.http.models import Distance, VectorParams -client = QdrantClient("localhost", port=6333) +# specify port if using Docker +# client = QdrantClient("localhost", port=6333) client.recreate_collection( collection_name="test_collection", vectors_config=VectorParams(size=4, distance=Distance.DOT), ) ``` -Expected response: - -```json -{ - "result": true, - "status": "ok", - "time": 0.031095451 -} -``` - -We can ensure that collection was created: - -```bash -curl 'http://localhost:6333/collections/test_collection' -``` +**Response:** ```python -collection_info = client.get_collection(collection_name="test_collection") +True ``` -Expected response: +## Step 2: Add vectors -```json -{ - "result": { - "status": "green", - "vectors_count": 0, - "segments_count": 5, - "disk_data_size": 0, - "ram_data_size": 0, - "config": { - "params": { - "vectors": { - "size": 4, - "distance": "Dot" - } - }, - "hnsw_config": { ... }, - "optimizer_config": { ... }, - "wal_config": { ... } - } - }, - "status": "ok", - "time": 2.1199e-05 -} -``` - -```python -from qdrant_client.http.models import CollectionStatus - -assert collection_info.status == CollectionStatus.GREEN -assert collection_info.vectors_count == 0 -``` - -### Add points - -Let's now add vectors with some payload: - -```bash -curl -L -X PUT 'http://localhost:6333/collections/test_collection/points?wait=true' \ - -H 'Content-Type: application/json' \ - --data-raw '{ - "points": [ - {"id": 1, "vector": [0.05, 0.61, 0.76, 0.74], "payload": {"city": "Berlin" }}, - {"id": 2, "vector": [0.19, 0.81, 0.75, 0.11], "payload": {"city": ["Berlin", "London"] }}, - {"id": 3, "vector": [0.36, 0.55, 0.47, 0.94], "payload": {"city": ["Berlin", "Moscow"] }}, - {"id": 4, "vector": [0.18, 0.01, 0.85, 0.80], "payload": {"city": ["London", "Moscow"] }}, - {"id": 5, "vector": [0.24, 0.18, 0.22, 0.44], "payload": {"count": [0] }}, - {"id": 6, "vector": [0.35, 0.08, 0.11, 0.44]} - ] - }' -``` +Let's now add a few vectors with a payload: ```python from qdrant_client.http.models import PointStruct @@ -215,40 +106,17 @@ operation_info = client.upsert( PointStruct(id=6, vector=[0.35, 0.08, 0.11, 0.44]), ] ) +print(operation_info) ``` - -Expected response: - -```json -{ - "result": { - "operation_id": 0, - "status": "completed" - }, - "status": "ok", - "time": 0.000206061 -} -``` +**Response:** ```python -from qdrant_client.http.models import UpdateStatus - -assert operation_info.status == UpdateStatus.COMPLETED +operation_id=0 status= ``` -### Search with filtering - -Let's start with a basic request: - -```bash -curl -L -X POST 'http://localhost:6333/collections/test_collection/points/search' \ - -H 'Content-Type: application/json' \ - --data-raw '{ - "vector": [0.2,0.1,0.9,0.7], - "limit": 3 - }' -``` +## Step 3: Run a query +Let's ask a basic question - Which of our stored vectors are most similar to the query vector `[0.2, 0.1, 0.9, 0.7]`? ```python search_result = client.search( @@ -256,58 +124,23 @@ search_result = client.search( query_vector=[0.2, 0.1, 0.9, 0.7], limit=3 ) +print(search_result) ``` -Expected response: - -```json -{ - "result": [ - { "id": 4, "score": 1.362 }, - { "id": 1, "score": 1.273 }, - { "id": 3, "score": 1.208 } - ], - "status": "ok", - "time": 0.000055785 -} -``` +**Response:** ```python -assert len(search_result) == 3 - -print(search_result[0]) -# ScoredPoint(id=4, score=1.362, ...) - -print(search_result[1]) -# ScoredPoint(id=1, score=1.273, ...) - -print(search_result[2]) -# ScoredPoint(id=3, score=1.208, ...) +ScoredPoint(id=4, version=0, score=1.362000031210482, payload={'city': ['London', 'Moscow']}, vector=None), +ScoredPoint(id=1, version=0, score=1.2729999996721744, payload={'city': 'Berlin'}, vector=None), +ScoredPoint(id=3, version=0, score=1.2080000013113021, payload={'city': ['Berlin', 'Moscow']}, vector=None) ``` Note that payload and vector data is missing in these results by default. See [payload and vector in the result](../concepts/search#payload-and-vector-in-the-result) on how to enable it. -But the result is different if we add a filter: +## Step 4: Add a filter -```bash -curl -L -X POST 'http://localhost:6333/collections/test_collection/points/search' \ - -H 'Content-Type: application/json' \ - --data-raw '{ - "filter": { - "should": [ - { - "key": "city", - "match": { - "value": "London" - } - } - ] - }, - "vector": [0.2, 0.1, 0.9, 0.7], - "limit": 3 - }' -``` +We can narrow down the results further by filtering by payload. Let's find the closest results that include "London". ```python from qdrant_client.http.models import Filter, FieldCondition, MatchValue @@ -326,28 +159,20 @@ search_result = client.search( ), limit=3 ) +print(search_result) ``` -Expected response: - -```json -{ - "result": [ - { "id": 4, "score": 1.362 }, - { "id": 2, "score": 0.871 } - ], - "status": "ok", - "time": 0.000093972 -} -``` - +**Response:** ```python -assert len(search_result) == 2 - -print(search_result[0]) -# ScoredPoint(id=4, score=1.362, ...) - -print(search_result[1]) -# ScoredPoint(id=2, score=0.871, ...) +ScoredPoint(id=4, version=0, score=1.362000031210482, payload={'city': ['London', 'Moscow']}, vector=None), +ScoredPoint(id=2, version=0, score=0.8709999993443489, payload={'city': ['Berlin', 'London']}, vector=None) ``` + +You have just conducted vector search. You loaded vectors into a database and queried the database with a vector of your own. Qdrant found the closest results and presented you with a similarity score. + +## Next Steps + +Now you know how Qdrant works. Getting started with [Qdrant Cloud](../cloud/quickstart-cloud/)| is even simpler. [Create an account](https://qdrant.to/cloud) and use our SaaS completely free. We will take care of infrastructure maintenance and software updates. + +To move onto some more complex examples of vector search, read our [Tutorials](tutorials/) and create your own app with the help of our [Examples](examples/). diff --git a/qdrant-landing/static/docs/quickstart.png b/qdrant-landing/static/docs/quickstart.png new file mode 100644 index 000000000..f9ea02e4b Binary files /dev/null and b/qdrant-landing/static/docs/quickstart.png differ diff --git a/qdrant-landing/static/docs/recommended.png b/qdrant-landing/static/docs/recommended.png new file mode 100644 index 000000000..9a59f0a09 Binary files /dev/null and b/qdrant-landing/static/docs/recommended.png differ