diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/_description.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/_description.md index c18eb88c8..927bf2ad0 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/_description.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/_description.md @@ -1 +1,3 @@ -This code snippet shows the canonical pattern for combining hybrid search fusion with business-logic ranking. The inner prefetch fuses sparse and dense results with RRF, then the outer `FormulaQuery` applies exponential decay on a `published_at` payload field to boost recent documents. Use this pattern any time you want fusion plus recency, popularity, geo decay, or category-conditional multipliers, rather than trying to encode those signals as fusion weights. \ No newline at end of file +This code snippet shows the canonical pattern for combining hybrid search fusion with business-logic ranking. The inner prefetch fuses sparse and dense results with RRF, then the outer `FormulaQuery` applies exponential decay on a `published_at` payload field to boost recent documents. The decay term is wrapped in `mult` with a `0.1` coefficient so it nudges the ranking rather than crowding out the small RRF scores. Use this pattern any time you want fusion plus recency, popularity, geo decay, or category-conditional multipliers, rather than trying to encode those signals as fusion weights. + +For production: `published_at` must exist on every point, or supply `defaults` in the `FormulaQuery` to fill missing values. A datetime payload index on `published_at` keeps query latency low. \ No newline at end of file diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/csharp.cs b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/csharp.cs index 07e015794..3f51a5619 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/csharp.cs +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/csharp.cs @@ -35,15 +35,22 @@ public class Snippet Sum = { "$score", // the fused score from the RRF prefetch - Expression.FromExpDecay( - new() + new MultExpression + { + Mult = { - X = Expression.FromDateTimeKey("published_at"), - Target = Expression.FromDateTime("YYYY-MM-DDT00:00:00Z"), - Scale = 86400 * 180, // 180 days in seconds - Midpoint = 0.5f + 0.1f, // caps decay contribution + Expression.FromExpDecay( + new() + { + X = Expression.FromDateTimeKey("published_at"), + Target = Expression.FromDateTime("YYYY-MM-DDT00:00:00Z"), + Scale = 86400 * 180, // 180 days in seconds + Midpoint = 0.5f + } + ) } - ) + } } } }, diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/csharp.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/csharp.md index 09c63fd82..407a2d8df 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/csharp.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/csharp.md @@ -32,15 +32,22 @@ await client.QueryAsync( Sum = { "$score", // the fused score from the RRF prefetch - Expression.FromExpDecay( - new() + new MultExpression + { + Mult = { - X = Expression.FromDateTimeKey("published_at"), - Target = Expression.FromDateTime("YYYY-MM-DDT00:00:00Z"), - Scale = 86400 * 180, // 180 days in seconds - Midpoint = 0.5f + 0.1f, // caps decay contribution + Expression.FromExpDecay( + new() + { + X = Expression.FromDateTimeKey("published_at"), + Target = Expression.FromDateTime("YYYY-MM-DDT00:00:00Z"), + Scale = 86400 * 180, // 180 days in seconds + Midpoint = 0.5f + } + ) } - ) + } } } }, diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/go.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/go.md index fcba8cd9e..7676e1892 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/go.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/go.md @@ -34,11 +34,16 @@ client.Query(context.Background(), &qdrant.QueryPoints{ Expression: qdrant.NewExpressionSum(&qdrant.SumExpression{ Sum: []*qdrant.Expression{ qdrant.NewExpressionVariable("$score"), // the fused score from the RRF prefetch - qdrant.NewExpressionExpDecay(&qdrant.DecayParamsExpression{ - X: qdrant.NewExpressionDatetimeKey("published_at"), - Target: qdrant.NewExpressionDatetime("YYYY-MM-DDT00:00:00Z"), - Scale: qdrant.PtrOf(float32(86400 * 180)), // 180 days in seconds - Midpoint: qdrant.PtrOf(float32(0.5)), + qdrant.NewExpressionMult(&qdrant.MultExpression{ + Mult: []*qdrant.Expression{ + qdrant.NewExpressionConstant(0.1), // caps decay contribution + qdrant.NewExpressionExpDecay(&qdrant.DecayParamsExpression{ + X: qdrant.NewExpressionDatetimeKey("published_at"), + Target: qdrant.NewExpressionDatetime("YYYY-MM-DDT00:00:00Z"), + Scale: qdrant.PtrOf(float32(86400 * 180)), // 180 days in seconds + Midpoint: qdrant.PtrOf(float32(0.5)), + }), + }, }), }, }), diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/java.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/java.md index 93ecaae6c..673f99623 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/java.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/java.md @@ -1,7 +1,9 @@ ```java +import static io.qdrant.client.ExpressionFactory.constant; import static io.qdrant.client.ExpressionFactory.datetime; import static io.qdrant.client.ExpressionFactory.datetimeKey; import static io.qdrant.client.ExpressionFactory.expDecay; +import static io.qdrant.client.ExpressionFactory.mult; import static io.qdrant.client.ExpressionFactory.sum; import static io.qdrant.client.ExpressionFactory.variable; import static io.qdrant.client.QueryFactory.formula; @@ -12,6 +14,7 @@ import io.qdrant.client.QdrantClient; import io.qdrant.client.QdrantGrpcClient; import io.qdrant.client.grpc.Points.DecayParamsExpression; import io.qdrant.client.grpc.Points.Formula; +import io.qdrant.client.grpc.Points.MultExpression; import io.qdrant.client.grpc.Points.PrefetchQuery; import io.qdrant.client.grpc.Points.QueryPoints; import io.qdrant.client.grpc.Points.Rrf; @@ -49,13 +52,18 @@ client.queryAsync( SumExpression.newBuilder() .addSum(variable("$score")) .addSum( - expDecay( - DecayParamsExpression.newBuilder() - .setX(datetimeKey("published_at")) - .setTarget( - datetime("YYYY-MM-DDT00:00:00Z")) - .setScale(86400 * 180) - .setMidpoint(0.5f) + mult( + MultExpression.newBuilder() + .addMult(constant(0.1f)) + .addMult( + expDecay( + DecayParamsExpression.newBuilder() + .setX(datetimeKey("published_at")) + .setTarget( + datetime("YYYY-MM-DDT00:00:00Z")) + .setScale(86400 * 180) + .setMidpoint(0.5f) + .build())) .build())) .build())) .build())) diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/python.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/python.md index d5a61d8b4..81e1eb488 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/python.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/python.md @@ -25,14 +25,17 @@ client.query_points( formula=models.SumExpression( sum=[ "$score", # the fused score from the RRF prefetch - models.ExpDecayExpression( - exp_decay=models.DecayParamsExpression( - x=models.DatetimeKeyExpression(datetime_key="published_at"), - target=models.DatetimeExpression(datetime="YYYY-MM-DDT00:00:00Z"), - scale=86400 * 180, # 180 days in seconds - midpoint=0.5, - ) - ), + models.MultExpression(mult=[ + 0.1, # caps decay contribution; un-weighted decay [0, 1] would otherwise crowd out small RRF scores + models.ExpDecayExpression( + exp_decay=models.DecayParamsExpression( + x=models.DatetimeKeyExpression(datetime_key="published_at"), + target=models.DatetimeExpression(datetime="YYYY-MM-DDT00:00:00Z"), + scale=86400 * 180, # 180 days in seconds + midpoint=0.5, + ) + ), + ]), ] ) ), diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/rust.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/rust.md index 137dd15b2..f95fce9a2 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/rust.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/rust.md @@ -29,12 +29,15 @@ client.query( .query( FormulaBuilder::new(Expression::sum_with([ Expression::score(), - Expression::exp_decay( - DecayParamsExpressionBuilder::new(Expression::datetime_key("published_at")) - .target(Expression::datetime("YYYY-MM-DDT00:00:00Z")) - .scale(86400.0 * 180.0) - .midpoint(0.5), - ), + Expression::mult_with([ + Expression::constant(0.1), + Expression::exp_decay( + DecayParamsExpressionBuilder::new(Expression::datetime_key("published_at")) + .target(Expression::datetime("YYYY-MM-DDT00:00:00Z")) + .scale(86400.0 * 180.0) + .midpoint(0.5), + ), + ]), ])), ) .limit(10u64), diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/typescript.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/typescript.md index 17fdeff74..c16db69b0 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/typescript.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/generated/typescript.md @@ -28,12 +28,17 @@ await client.query("{collection_name}", { sum: [ "$score", // the fused score from the RRF prefetch { - exp_decay: { - x: { datetime_key: "published_at" }, - target: { datetime: "YYYY-MM-DDT00:00:00Z" }, - scale: 86400 * 180, // 180 days in seconds - midpoint: 0.5, - }, + mult: [ + 0.1, // caps decay contribution; un-weighted decay [0, 1] would otherwise crowd out small RRF scores + { + exp_decay: { + x: { datetime_key: "published_at" }, + target: { datetime: "YYYY-MM-DDT00:00:00Z" }, + scale: 86400 * 180, // 180 days in seconds + midpoint: 0.5, + }, + }, + ], }, ], }, diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/go.go b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/go.go index 4647fc1fc..1f21ea3a1 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/go.go +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/go.go @@ -38,11 +38,16 @@ func Main() { Expression: qdrant.NewExpressionSum(&qdrant.SumExpression{ Sum: []*qdrant.Expression{ qdrant.NewExpressionVariable("$score"), // the fused score from the RRF prefetch - qdrant.NewExpressionExpDecay(&qdrant.DecayParamsExpression{ - X: qdrant.NewExpressionDatetimeKey("published_at"), - Target: qdrant.NewExpressionDatetime("YYYY-MM-DDT00:00:00Z"), - Scale: qdrant.PtrOf(float32(86400 * 180)), // 180 days in seconds - Midpoint: qdrant.PtrOf(float32(0.5)), + qdrant.NewExpressionMult(&qdrant.MultExpression{ + Mult: []*qdrant.Expression{ + qdrant.NewExpressionConstant(0.1), // caps decay contribution + qdrant.NewExpressionExpDecay(&qdrant.DecayParamsExpression{ + X: qdrant.NewExpressionDatetimeKey("published_at"), + Target: qdrant.NewExpressionDatetime("YYYY-MM-DDT00:00:00Z"), + Scale: qdrant.PtrOf(float32(86400 * 180)), // 180 days in seconds + Midpoint: qdrant.PtrOf(float32(0.5)), + }), + }, }), }, }), diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/http.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/http.md index 648d1ad4e..ede05b23e 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/http.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/http.md @@ -25,16 +25,21 @@ POST /collections/{collection_name}/points/query "sum": [ "$score", // the fused score from the RRF prefetch { - "exp_decay": { - "x": { - "datetime_key": "published_at" - }, - "target": { - "datetime": "YYYY-MM-DDT00:00:00Z" - }, - "scale": 15552000, // 180 days in seconds - "midpoint": 0.5 - } + "mult": [ + 0.1, // caps decay contribution + { + "exp_decay": { + "x": { + "datetime_key": "published_at" + }, + "target": { + "datetime": "YYYY-MM-DDT00:00:00Z" + }, + "scale": 15552000, // 180 days in seconds + "midpoint": 0.5 + } + } + ] } ] } diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/java.java b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/java.java index 46cc0cb92..f00f739c8 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/java.java +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/java.java @@ -1,8 +1,10 @@ package com.example.snippets_amalgamation; +import static io.qdrant.client.ExpressionFactory.constant; import static io.qdrant.client.ExpressionFactory.datetime; import static io.qdrant.client.ExpressionFactory.datetimeKey; import static io.qdrant.client.ExpressionFactory.expDecay; +import static io.qdrant.client.ExpressionFactory.mult; import static io.qdrant.client.ExpressionFactory.sum; import static io.qdrant.client.ExpressionFactory.variable; import static io.qdrant.client.QueryFactory.formula; @@ -13,6 +15,7 @@ import io.qdrant.client.QdrantClient; import io.qdrant.client.QdrantGrpcClient; import io.qdrant.client.grpc.Points.DecayParamsExpression; import io.qdrant.client.grpc.Points.Formula; +import io.qdrant.client.grpc.Points.MultExpression; import io.qdrant.client.grpc.Points.PrefetchQuery; import io.qdrant.client.grpc.Points.QueryPoints; import io.qdrant.client.grpc.Points.Rrf; @@ -52,13 +55,18 @@ public class Snippet { SumExpression.newBuilder() .addSum(variable("$score")) .addSum( - expDecay( - DecayParamsExpression.newBuilder() - .setX(datetimeKey("published_at")) - .setTarget( - datetime("YYYY-MM-DDT00:00:00Z")) - .setScale(86400 * 180) - .setMidpoint(0.5f) + mult( + MultExpression.newBuilder() + .addMult(constant(0.1f)) + .addMult( + expDecay( + DecayParamsExpression.newBuilder() + .setX(datetimeKey("published_at")) + .setTarget( + datetime("YYYY-MM-DDT00:00:00Z")) + .setScale(86400 * 180) + .setMidpoint(0.5f) + .build())) .build())) .build())) .build())) diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/python.py b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/python.py index a23105a43..2ddcfd91a 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/python.py +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/python.py @@ -24,14 +24,17 @@ client.query_points( formula=models.SumExpression( sum=[ "$score", # the fused score from the RRF prefetch - models.ExpDecayExpression( - exp_decay=models.DecayParamsExpression( - x=models.DatetimeKeyExpression(datetime_key="published_at"), - target=models.DatetimeExpression(datetime="YYYY-MM-DDT00:00:00Z"), - scale=86400 * 180, # 180 days in seconds - midpoint=0.5, - ) - ), + models.MultExpression(mult=[ + 0.1, # caps decay contribution; un-weighted decay [0, 1] would otherwise crowd out small RRF scores + models.ExpDecayExpression( + exp_decay=models.DecayParamsExpression( + x=models.DatetimeKeyExpression(datetime_key="published_at"), + target=models.DatetimeExpression(datetime="YYYY-MM-DDT00:00:00Z"), + scale=86400 * 180, # 180 days in seconds + midpoint=0.5, + ) + ), + ]), ] ) ), diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/rust.rs b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/rust.rs index 04c76d114..aaef749a7 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/rust.rs +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/rust.rs @@ -29,12 +29,15 @@ pub async fn main() -> anyhow::Result<()> { .query( FormulaBuilder::new(Expression::sum_with([ Expression::score(), - Expression::exp_decay( - DecayParamsExpressionBuilder::new(Expression::datetime_key("published_at")) - .target(Expression::datetime("YYYY-MM-DDT00:00:00Z")) - .scale(86400.0 * 180.0) - .midpoint(0.5), - ), + Expression::mult_with([ + Expression::constant(0.1), + Expression::exp_decay( + DecayParamsExpressionBuilder::new(Expression::datetime_key("published_at")) + .target(Expression::datetime("YYYY-MM-DDT00:00:00Z")) + .scale(86400.0 * 180.0) + .midpoint(0.5), + ), + ]), ])), ) .limit(10u64), diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/typescript.ts b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/typescript.ts index bcf7ec925..69a637adc 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/typescript.ts +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-formula-decay/typescript.ts @@ -27,12 +27,17 @@ await client.query("{collection_name}", { sum: [ "$score", // the fused score from the RRF prefetch { - exp_decay: { - x: { datetime_key: "published_at" }, - target: { datetime: "YYYY-MM-DDT00:00:00Z" }, - scale: 86400 * 180, // 180 days in seconds - midpoint: 0.5, - }, + mult: [ + 0.1, // caps decay contribution; un-weighted decay [0, 1] would otherwise crowd out small RRF scores + { + exp_decay: { + x: { datetime_key: "published_at" }, + target: { datetime: "YYYY-MM-DDT00:00:00Z" }, + scale: 86400 * 180, // 180 days in seconds + midpoint: 0.5, + }, + }, + ], }, ], }, diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/generated/go.md b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/generated/go.md index d1cc442bc..0788b690b 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/generated/go.md +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/generated/go.md @@ -16,10 +16,12 @@ client.Query(context.Background(), &qdrant.QueryPoints{ { Query: qdrant.NewQuerySparse([]uint32{1, 42}, []float32{0.22, 0.8}), Using: qdrant.PtrOf("sparse"), + Limit: qdrant.PtrOf(uint64(20)), }, { Query: qdrant.NewQueryDense([]float32{0.01, 0.45, 0.67}), Using: qdrant.PtrOf("dense"), + Limit: qdrant.PtrOf(uint64(20)), }, }, Query: qdrant.NewQueryRRF(&qdrant.Rrf{}), diff --git a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/go.go b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/go.go index 2366db952..ff3006250 100644 --- a/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/go.go +++ b/qdrant-landing/content/documentation/headless/snippets/query-points/hybrid-rrf/go.go @@ -20,10 +20,12 @@ func Main() { { Query: qdrant.NewQuerySparse([]uint32{1, 42}, []float32{0.22, 0.8}), Using: qdrant.PtrOf("sparse"), + Limit: qdrant.PtrOf(uint64(20)), }, { Query: qdrant.NewQueryDense([]float32{0.01, 0.45, 0.67}), Using: qdrant.PtrOf("dense"), + Limit: qdrant.PtrOf(uint64(20)), }, }, Query: qdrant.NewQueryRRF(&qdrant.Rrf{}), diff --git a/qdrant-landing/content/documentation/search/hybrid-queries.md b/qdrant-landing/content/documentation/search/hybrid-queries.md index b5f8546f3..e3cd6fc05 100644 --- a/qdrant-landing/content/documentation/search/hybrid-queries.md +++ b/qdrant-landing/content/documentation/search/hybrid-queries.md @@ -53,6 +53,8 @@ Where: - $r_d$ is the rank of document $d$ in ranking $r$ - $w_r$ is the weight of ranking $r$ (set to 1 by default) +_Qdrant uses zero-based rank positions; the top result has $r_d = 0$._ + Because $w_r$ defaults to 1, without setting explicit weights, the formula can be simplified to the original RRF function: $$ score(d\in D) = \sum_{r_d\in R(d)} \frac{1}{k + r_d} $$ @@ -71,7 +73,7 @@ To change the value of constant $k$ in the formula, use the dedicated `rrf` quer #### Weighted RRF _Available as of v1.17.0_ -By default, each query is assigned an equal weight. In reality, some queries are stronger, more discriminative, or more domain-specific than others. For example, a semantic search model understands meaning better than a simple keyword matcher. Assigning equal weight to both can cause the weaker model to negatively influence results, leading to a suboptimal search experience. To address this, you can assign greater weight to rankers that perform well. +By default, each query is assigned an equal weight. In reality, one retriever is often stronger than the other for a given workload. For example, a dense retriever may dominate on natural-language queries, while BM25 may win on identifier-heavy ones. Assigning equal weight to both can let the weaker retriever drag down results. To address this, you can assign greater weight to rankers that perform well on your evaluation set. The `rrf` query allows you to configure relative weights for each of the prefetches. For example, if you have two prefetches and assign a weight of 3.0 to the first and 1.0 to the second, a document ranked third in the first query scores the same as a document ranked first in the second query. In the case of non-overlapping result sets, these weights return three results from the first set for every one result from the second set. @@ -81,7 +83,7 @@ Weights should be provided as an array of numbers, where each weight is applied Weights are a hyperparameter, not a free knob. A held-out eval is the most defensible way to set them. -- **With an eval set (queries paired with known-relevant docs):** split your eval queries in two. Search the weight space on the first half, then report metrics on the second half (held out from the search). Reporting on the same set you tuned on inflates the result. The [Choosing a Fusion Method notebook](https://githubtocolab.com/qdrant/examples/blob/master/fusion-methods/Choosing_a_Fusion_Method.ipynb) demonstrates this with a reusable `tune_rrf_weights` grid-search helper. Random search and Bayesian optimization (Optuna, hyperopt) work equally well for two-retriever fusion. +- **With an eval set (queries paired with known-relevant docs):** split your eval queries in two. Search the weight space on the first half, then report metrics on the second half (held out from the search). Reporting on the same set you tuned on inflates the result. The [Choosing a Fusion Method notebook](https://githubtocolab.com/qdrant/examples/blob/master/fusion-methods/Choosing_a_Fusion_Method.ipynb) provides a reusable `tune_rrf_weights` grid-search helper you can adapt to a train/val split. Random search and Bayesian optimization (Optuna, hyperopt) work equally well for two-retriever fusion. - **Without an eval set:** leave weights at the default `(1.0, 1.0)`. Hand-tuned weights without measurement are unlikely to beat the default reliably. Retune when your retrievers change (new embedding model, new chunking), when your corpus drifts substantially, or on a fixed cadence with a fresh eval sample. @@ -130,7 +132,7 @@ For a deeper breakdown of when to prefer each, see the [FAQ on RRF vs. DBSF](/do -## Multi-stage queries +## Multi-Stage Queries In general, larger vector representations give more accurate search results, but makes them more expensive to compute. @@ -150,7 +152,7 @@ such that the coarse results are fetched first, and then they are refined later -### Re-scoring examples +### Re-Scoring Examples Fetch 1000 results using a shorter MRL byte vector, then re-score them using the full vector and get the top 10. @@ -160,7 +162,7 @@ Fetch 100 results using the default vector, then re-score them using a multi-vec {{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-rescoring-multivector/" >}} -It is possible to combine all the above techniques in a single query: +You can combine all of these techniques in a single query: {{< code-snippet path="/documentation/headless/snippets/query-points/hybrid-rescoring-multistage/" >}}