krzysztof/landing_page
1
0
Fork 0
mirror of https://github.com/qdrant/landing_page.git synced 2026-10-09 21:08:31 +02:00
Code Issues Packages Projects Releases Wiki Activity

update snippets and descpription

Browse Source
This commit is contained in:
generall
2025-07-15 00:53:26 +02:00
parent 274dec0c25
commit 305e6969d7
9 changed files with 141 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/_description.md
+8 -1
View File
@@ -1 +1,8 @@
This code snippet demonstrates how to use cloud inference in Qdrant Cloud to automatically create vector embeddings from text or image documents during upseart and query operations.
This code snippet demonstrates how to use cloud inference in Qdrant Cloud to automatically create vector embeddings from text documents during upseart and query operations.
In this example we create a new point with a new vector, generated on the qdrant cloud side.
`Document` object contains the text which will be used as an input for inference model.
Specific model which should be used for inference is defined in the `model` parameter.
After point is inserted is becomes searchable.
Snippet contains an example of search query request, that uses cloud-side inferene.
`Document` object is used to obtain query vector.
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/bash.md
+11 -11
View File
@@ -1,29 +1,29 @@
```bash
# Create a new vector
curl -X PUT "https://xyz-example.cloud-region.cloud-provider.cloud.qdrant.io:6333/collections/<your-collection>/points?wait=true" \\
-H "Content-Type: application/json" \\
-H "api-key: <paste-your-api-key-here>" \\
# Create a new vector
curl -X PUT "https://xyz-example.qdrant.io:6333/collections/<your-collection>/points?wait=true" \
-H "Content-Type: application/json" \
-H "api-key: <paste-your-api-key-here>" \
-d '{
"points": [
{
"id": 1,
"payload": { "topic": "cooking", "type": "dessert" },
"vector": {
"text": "Recipe for baking chocolate chip cookies requires flour, sugar, eggs, and chocolate chips.",
"text": "Recipe for baking chocolate chip cookies",
"model": "<the-model-to-use>"
}
}
]
}'
# Perform a search query
curl -X POST "https://xyz-example.cloud-region.cloud-provider.cloud.qdrant.io:6333/collections/<your-collection>/points/query" \\
-H "Content-Type: application/json" \\
-H "api-key: <paste-your-api-key-here>" \\
curl -X POST "https://xyz-example.qdrant.io:6333/collections/<your-collection>/points/query" \
-H "Content-Type: application/json" \
-H "api-key: <paste-your-api-key-here>" \
-d '{
"query": {
"text": "Recipe for baking chocolate chip cookies",
"text": "How to bake cookies?",
"model": "<the-model-to-use>"
}
}'
}'
```
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/csharp.md
+5 -5
View File
@@ -4,7 +4,7 @@ using Qdrant.Client.Grpc;
using Value = Qdrant.Client.Grpc.Value;
var client = new QdrantClient(
host: "xyz-example.cloud-region.cloud-provider.cloud.qdrant.io",
host: "xyz-example.qdrant.io",
port: 6334,
https: true,
apiKey: "<paste-your-api-key-here>"
@@ -16,9 +16,8 @@ await client.UpsertAsync(
new() {
Id = 1,
Vectors = new Document() {
Text =
"Recipe for baking chocolate chip cookies requires flour, sugar, eggs, and chocolate chips.",
Model = "<the-model-to-use>",
Text = "Recipe for baking chocolate chip cookies",
Model = "<the-model-to-use>",
},
Payload = {
["topic"] = "cooking",
@@ -31,7 +30,8 @@ await client.UpsertAsync(
var points = await client.QueryAsync(
collectionName: "<your-collection>",
query: new Document() {
Text = "Recipe for baking chocolate chip cookies", Model = "<the-model-to-use>"
Text = "How to bake cookies?",
Model = "<the-model-to-use>"
}
);
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/go.md
+45 -46
View File
@@ -2,58 +2,57 @@
package main
import (
"context"
"log"
"time"
"context"
"log"
"time"
"github.com/qdrant/go-client/qdrant"
"github.com/qdrant/go-client/qdrant"
)
func main() {
ctx, cancel := context.WithTimeout(context.Background(), time.Second)
defer cancel()
ctx, cancel := context.WithTimeout(context.Background(), time.Second)
defer cancel()
client, err := qdrant.NewClient(&qdrant.Config{
Host: "xyz-example.cloud-region.cloud-provider.cloud.qdrant.io",
Port: 6334,
APIKey: "<paste-your-api-key-here>",
UseTLS: true,
})
if err != nil {
log.Fatalf("did not connect: %v", err)
}
defer client.Close()
client, err := qdrant.NewClient(&qdrant.Config{
Host: "xyz-example.qdrant.io",
Port: 6334,
APIKey: "<paste-your-api-key-here>",
UseTLS: true,
})
if err != nil {
log.Fatalf("did not connect: %v", err)
}
defer client.Close()
_, err = client.GetPointsClient().Upsert(ctx, &qdrant.UpsertPoints{
CollectionName: "<your-collection>",
Points: []*qdrant.PointStruct{
{
Id: qdrant.NewIDNum(uint64(1)),
Vectors: qdrant.NewVectorsDocument(&qdrant.Document{
Text: "Recipe for baking chocolate chip cookies requires flour, sugar, eggs, and chocolate chips.",
Model: "<the-model-to-use>",
}),
Payload: qdrant.NewValueMap(map[string]any{
"topic": "cooking",
"type": "dessert",
}),
},
},
})
if err != nil {
log.Fatalf("error creating point: %v", err)
}
_, err = client.GetPointsClient().Upsert(ctx, &qdrant.UpsertPoints{
CollectionName: "<your-collection>",
Points: []*qdrant.PointStruct{
{
Id: qdrant.NewIDNum(uint64(1)),
Vectors: qdrant.NewVectorsDocument(&qdrant.Document{
Text: "Recipe for baking chocolate chip cookies",
Model: "<the-model-to-use>",
}),
Payload: qdrant.NewValueMap(map[string]any{
"topic": "cooking",
"type": "dessert",
}),
},
},
})
if err != nil {
log.Fatalf("error creating point: %v", err)
}
points, err := client.Query(ctx, &qdrant.QueryPoints{
CollectionName: "<your-collection>",
Query: qdrant.NewQueryNearest(
qdrant.NewVectorInputDocument(&qdrant.Document{
Text: "Recipe for baking chocolate chip cookies",
Model: "<the-model-to-use>",
}),
),
})
log.Printf("List of points: %s", points)
points, err := client.Query(ctx, &qdrant.QueryPoints{
CollectionName: "<your-collection>",
Query: qdrant.NewQueryNearest(
qdrant.NewVectorInputDocument(&qdrant.Document{
Text: "How to bake cookies?",
Model: "<the-model-to-use>",
}),
),
})
log.Printf("List of points: %s", points)
}
})
```
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/http.md
+25
View File
@@ -0,0 +1,25 @@
```http
# Insert new points with cloud-side inference
PUT /collections/<your-collection>/points?wait=true
{
"points": [
{
"id": 1,
"payload": { "topic": "cooking", "type": "dessert" },
"vector": {
"text": "Recipe for baking chocolate chip cookies",
"model": "<the-model-to-use>"
}
}
]
}
# Search in the collection using cloud-side inference
POST /collections/<your-collection>/points/query
{
"query": {
"text": "How to bake cookies?",
"model": "<the-model-to-use>"
}
}
```
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/java.md
+5 -5
View File
@@ -14,10 +14,11 @@ import java.util.Map;
import java.util.concurrent.ExecutionException;
public class Main {
public static void main(String[] args) throws ExecutionException, InterruptedException {
public static void main(String[] args)
throws ExecutionException, InterruptedException {
QdrantClient client =
new QdrantClient(
QdrantGrpcClient.newBuilder("xyz-example.cloud-region.cloud-provider.cloud.qdrant.io", 6334, true)
QdrantGrpcClient.newBuilder("xyz-example.qdrant.io", 6334, true)
.withApiKey("<paste-your-api-key-here>")
.build());
@@ -30,8 +31,7 @@ public class Main {
.setVectors(
vectors(
Document.newBuilder()
.setText(
"Recipe for baking chocolate chip cookies requires flour, sugar, eggs, and chocolate chips.")
.setText("Recipe for baking chocolate chip cookies")
.setModel("<the-model-to-use>")
.build()))
.putAllPayload(Map.of("topic", value("cooking"), "type", value("dessert")))
@@ -46,7 +46,7 @@ public class Main {
.setQuery(
nearest(
Document.newBuilder()
.setText("Recipe for baking chocolate chip cookies")
.setText("How to bake cookies?")
.setModel("<the-model-to-use>")
.build()))
.build())
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/python.md
+13 -8
View File
@@ -1,10 +1,12 @@
```python
from qdrant_client import QdrantClient
from qdrant_client.http.models import PointStruct, Document
from qdrant_client.models import PointStruct, Document
client = QdrantClient(
url="https://xyz-example.cloud-region.cloud-provider.cloud.qdrant.io:6333",
url="https://xyz-example.qdrant.io:6333",
api_key="<paste-your-api-key-here>",
# IMPORTANT
# If not enabled, inference will be performed locally
cloud_inference=True,
)
@@ -13,7 +15,7 @@ points = [
id=1,
payload={"topic": "cooking", "type": "dessert"},
vector=Document(
text="Recipe for baking chocolate chip cookies requires flour, sugar, eggs, and chocolate chips.",
text="Recipe for baking chocolate chip cookies",
model="<the-model-to-use>"
)
)
@@ -21,10 +23,13 @@ points = [
client.upsert(collection_name="<your-collection>", points=points)
points = client.query_points(collection_name="<your-collection>", query=Document(
text="Recipe for baking chocolate chip cookies requires flour",
model="<the-model-to-use>"
))
result = client.query_points(
collection_name="<your-collection>",
query=Document(
text="How to bake cookies?",
model="<the-model-to-use>"
)
)
print(points)
print(result)
```
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/rust.md
+26 -29
View File
@@ -1,9 +1,6 @@
```rust
use qdrant_client::qdrant::vector;
use qdrant_client::qdrant::vector_input;
use qdrant_client::qdrant::Query;
use qdrant_client::qdrant::QueryPointsBuilder;
use qdrant_client::qdrant::Vector;
use qdrant_client::qdrant::VectorInput;
use qdrant_client::Payload;
use qdrant_client::Qdrant;
use qdrant_client::qdrant::{Document};
@@ -11,40 +8,40 @@ use qdrant_client::qdrant::{PointStruct, UpsertPointsBuilder};
#[tokio::main]
async fn main() {
let client = Qdrant::from_url("https://xyz-example.cloud-region.cloud-provider.cloud.qdrant.io:6334")
let client = Qdrant::from_url("https://xyz-example.qdrant.io:6334")
.api_key("<paste-your-api-key-here>")
.build()
.unwrap();
let mut points = Vec::new();
let points = vec![
PointStruct::new(
1,
Document::new(
"Recipe for baking chocolate chip cookies",
"<the-model-to-use>"
),
Payload::try_from(serde_json::json!(
{"topic": "cooking", "type": "dessert"}
)).unwrap(),
)
];
let vector = Vector {
vector: Some(vector::Vector::Document(Document {
text: "Recipe for baking chocolate chip cookies requires flour, sugar, eggs, and chocolate chips.".to_string(),
model: "<the-model-to-use>".to_string(),
options: Default::default(),
})),
..Default::default()
};
let upsert_request = UpsertPointsBuilder::new(
"<your-collection>",
points
).wait(true);
points.push(PointStruct::new(1, vector, Payload::default()));
let _ = client.upsert_points(upsert_request).await;
let _ = client
.upsert_points(UpsertPointsBuilder::new("<your-collection>", points).wait(true))
.await;
let query_document = Document::new(
"How to bake cookies?",
"<the-model-to-use>"
);
let document = Document {
text: "Recipe for baking chocolate chip cookies".to_string(),
model: "<the-model-to-use>".to_string(),
options: Default::default(),
};
let query = VectorInput {
variant: Some(vector_input::Variant::Document(document)),
};
let query_request = QueryPointsBuilder::new("<your-collection>").query(query);
let query_request = QueryPointsBuilder::new("<your-collection>")
.query(Query::new_nearest(query_document));
let result = client.query(query_request).await.unwrap();
println!("Result: {:?}", result);
}
```
qdrant-landing/content/documentation/headless/snippets/cloud-inference/simple/typescript.md
+3 -3
View File
@@ -2,7 +2,7 @@
import {QdrantClient} from "@qdrant/js-client-rest";
const client = new QdrantClient({
url: 'https://xyz-example.cloud-region.cloud-provider.cloud.qdrant.io:6333',
url: 'https://xyz-example.qdrant.io:6333',
apiKey: '<paste-your-api-key-here>',
});
@@ -11,7 +11,7 @@ const points = [
id: 1,
payload: { topic: "cooking", type: "dessert" },
vector: {
text: "Recipe for baking chocolate chip cookies requires flour, sugar, eggs, and chocolate chips.",
text: "Recipe for baking chocolate chip cookies",
model: "<the-model-to-use>"
}
}
@@ -23,7 +23,7 @@ const result = await client.query(
"<your-collection>",
{
query: {
text: "What ingredients are needed for baking chocolate chip cookies?",
text: "How to bake cookies?",
model: "<the-model-to-use>"
},
}