Restructure inference docs (#2225)

* Break Inference page into several pages

* Make all inference code snippets testable and clean up

* Make more snippets testable

* Edits

* Document automatic query and passage prefix injection in Cloud Inference

Qdrant Cloud Inference silently applies model-specific prefixes (e.g.
"query: "/"passage: " for E5, BGE-style instruction prefix for BGE/mxbai/
Snowflake arctic-embed) so users don't need to manage them manually.
Add a section explaining this behavior, the idempotency guarantee, and
the scope (Qdrant-hosted models only; external providers handle their own).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Document short query optimization in Cloud Inference

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

* Update links

* Expand on external provider API key usage

* Add section about external provider API keys

* Default to header for external API keys

---------

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Abdon Pijpelink
2026-06-24 08:11:03 +02:00
committed by GitHub
co-authored by Claude Sonnet 4.6
parent 90d072eb03
commit 478b96554f
250 changed files with 3259 additions and 2187 deletions
@@ -3,20 +3,28 @@ package com.example.snippets_amalgamation;
import static io.qdrant.client.QueryFactory.nearest;
import static io.qdrant.client.ValueFactory.value;
import io.grpc.Context;
import io.qdrant.client.QdrantClient;
import io.qdrant.client.QdrantGrpcClient;
import io.qdrant.client.RequestHeaders;
import io.qdrant.client.grpc.Points.Document;
import io.qdrant.client.grpc.Points.QueryPoints;
import java.util.Map;
public class Snippet {
public static void run() throws Exception {
// @hide-start
QdrantClient client =
new QdrantClient(
QdrantGrpcClient.newBuilder("xyz-example.qdrant.io", 6334, true)
.withApiKey("<your-api-key")
.build());
client
// @hide-end
Context ctx = RequestHeaders.withHeader(
Context.current(), "openai-api-key", "<YOUR_OPENAI_API_KEY>");
ctx.call(() -> client
.queryAsync(
QueryPoints.newBuilder()
.setCollectionName("{collection_name}")
@@ -27,12 +35,10 @@ public class Snippet {
.setText("How to bake cookies?")
.putAllOptions(
Map.of(
"openai-api-key",
value("<YOUR_OPENAI_API_KEY>"),
"dimensions",
value(512)))
.build()))
.build())
.get();
.get());
}
}