Vector set embeddings
Index and query embeddings with Redis vector sets
A Redis vector set lets you store a set of unique keys, each with its own associated vector. You can then retrieve keys from the set according to the similarity between their stored vectors and a query vector that you specify.
You can use vector sets to store any type of numeric vector but they are
particularly optimized to work with text embedding vectors (see
Redis for AI to learn more about text
embeddings). The example below shows how to use the
Microsoft.ML
library to generate vector embeddings and then
store and retrieve them using a vector set with StackExchange.Redis.
Initialize
Start by installing StackExchange.Redis with the following
command (version 2.9.17 or later is required for vector sets):
dotnet add package StackExchange.Redis --version 2.9.17
Also, install Microsoft.ML:
dotnet add package Microsoft.ML
In a new C# file, import the required classes. Note that the #pragma
directive suppresses warnings about the experimental status of the vector set API:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
Access the model
Use the GetPredictionEngine() helper function declared in the example below to load the model that creates the embeddings:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
The GetPredictionEngine() function uses two classes, TextData and TransformedTextData,
to specify the PredictionEngine model. These have a very simple definition
and are required because the model expects the input and output to be
passed in named object fields:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
Note that you must declare these classes at the end of the source file if you are using a console app without a main class.
The GetEmbedding() function declared below can then use this model to
generate an embedding from a section of text and return it as a float[] array,
which is the format required by the vector set API:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
Create the data
The example data is contained a Dictionary object with some brief
descriptions of famous people:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
Add the data to a vector set
The next step is to connect to Redis and add the data to a new vector set.
The code below iterates through peopleData and adds corresponding
elements to a vector set called famousPeople.
Use the GetEmbedding() function declared above to generate the
embedding as a byte array that you can pass to the
VectorSetAdd() command to set the embedding.
The call to VectorSetAdd() also adds the born and died values from the
original dictionary as attribute data. You can access this during a query
or by using the VectorSetGetAttributesJson() method.
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
Query the vector set
You can now query the data in the set. The basic approach is to use the
GetEmbedding() function to generate another embedding vector for the query text.
(This is the same method used to add the elements to the set.) Then, pass
the query vector to VectorSetSimilaritySearch() to
return elements of the set, ranked in order of similarity to the query.
Start with a simple query for "actors":
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
This returns the following list of elements (formatted slightly for clarity):
'actors': ['Masako Natsume', 'Chaim Topol', 'Linus Pauling',
'Marie Fredriksson', 'Maryam Mirzakhani', 'Marie Curie',
'Freddie Mercury', 'Paul Erdos']
The first two people in the list are the two actors, as expected, but none of the
people from Linus Pauling onward was especially well-known for acting (and there certainly
isn't any information about that in the short description text).
As it stands, the search attempts to rank all the elements in the set, based
on the information contained in the embedding model.
You can use the Count property of VectorSetSimilaritySearchRequest to limit the
list of elements to just the most relevant few items:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
The reason for using text embeddings rather than simple text search is that the embeddings represent semantic information. This allows a query to find elements with a similar meaning even if the text is different. For example, the word "entertainer" doesn't appear in any of the descriptions but if you use it as a query, the actors and musicians are ranked highest in the results list:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
Similarly, if you use "science" as a query, you get the following results:
'science': ['Marie Curie', 'Linus Pauling', 'Maryam Mirzakhani',
'Paul Erdos', 'Marie Fredriksson', 'Freddie Mercury', 'Masako Natsume',
'Chaim Topol']
The scientists are ranked highest but they are then followed by the mathematicians. This seems reasonable given the connection between mathematics and science.
You can also use
filter expressions
with VectorSetSimilaritySearch() to restrict the search further. For example,
repeat the "science" query, but this time limit the results to people
who died before the year 2000:
// Suppress experimental API warnings for VectorSet
#pragma warning disable SER001
using StackExchange.Redis;
using Microsoft.ML;
using Microsoft.ML.Transforms.Text;
static PredictionEngine<TextData, TransformedTextData> GetPredictionEngine()
{
// Create a new ML context, for ML.NET operations. It can be used for
// exception tracking and logging, as well as the source of randomness.
var mlContext = new MLContext();
// Create an empty list as the dataset
var emptySamples = new List<TextData>();
// Convert sample list to an empty IDataView.
var emptyDataView = mlContext.Data.LoadFromEnumerable(emptySamples);
// A pipeline for converting text into a 150-dimension embedding vector
var textPipeline = mlContext.Transforms.Text.NormalizeText("Text")
.Append(mlContext.Transforms.Text.TokenizeIntoWords("Tokens",
"Text"))
.Append(mlContext.Transforms.Text.ApplyWordEmbedding("Features",
"Tokens", WordEmbeddingEstimator.PretrainedModelKind
.SentimentSpecificWordEmbedding));
// Fit to data.
var textTransformer = textPipeline.Fit(emptyDataView);
// Create the prediction engine to get the embedding vector from the input text/string.
var predictionEngine = mlContext.Model.CreatePredictionEngine<TextData,
TransformedTextData>(textTransformer);
return predictionEngine;
}
static float[] GetEmbedding(
PredictionEngine<TextData, TransformedTextData> model, string sentence
)
{
// Call the prediction API to convert the text into embedding vector.
var data = new TextData()
{
Text = sentence
};
var prediction = model.Predict(data);
float[] floatArray = Array.ConvertAll(prediction.Features, x => (float)x);
return floatArray;
}
Dictionary<string, dynamic> peopleData = new Dictionary<string, dynamic>
{
["Marie Curie"] = new
{
born = 1867,
died = 1934,
description = @"
Polish-French chemist and physicist. The only person ever to win
two Nobel prizes for two different sciences.
"
},
["Linus Pauling"] = new
{
born = 1901,
died = 1994,
description = @"
American chemist and peace activist. One of only two people to win two
Nobel prizes in different fields (chemistry and peace).
"
},
["Freddie Mercury"] = new
{
born = 1946,
died = 1991,
description = @"
British musician, best known as the lead singer of the rock band
Queen.
"
},
["Marie Fredriksson"] = new
{
born = 1958,
died = 2019,
description = @"
Swedish multi-instrumentalist, mainly known as the lead singer and
keyboardist of the band Roxette.
"
},
["Paul Erdos"] = new
{
born = 1913,
died = 1996,
description = @"
Hungarian mathematician, known for his eccentric personality almost
as much as his contributions to many different fields of mathematics.
"
},
["Maryam Mirzakhani"] = new
{
born = 1977,
died = 2017,
description = @"
Iranian mathematician. The first woman ever to win the Fields medal
for her contributions to mathematics.
"
},
["Masako Natsume"] = new
{
born = 1957,
died = 1985,
description = @"
Japanese actress. She was very famous in Japan but was primarily
known elsewhere in the world for her portrayal of Tripitaka in the
TV series Monkey.
"
},
["Chaim Topol"] = new
{
born = 1935,
died = 2023,
description = @"
Israeli actor and singer, usually credited simply as 'Topol'. He was
best known for his many appearances as Tevye in the musical Fiddler
on the Roof.
"
}
};
ConnectionMultiplexer muxer = ConnectionMultiplexer.Connect("localhost:6379");
IDatabase db = muxer.GetDatabase();
PredictionEngine<TextData, TransformedTextData> model = GetPredictionEngine();
foreach (KeyValuePair<string, dynamic> person in peopleData)
{
string name = person.Key;
dynamic details = person.Value;
float[] embedding = GetEmbedding(model, details.description);
VectorSetAddRequest addRequest = VectorSetAddRequest.Member(name, embedding, null);
db.VectorSetAdd("famousPeople", addRequest);
// Set attributes separately
string attributesJson = $"{{\"born\": {details.born}, \"died\": {details.died}}}";
db.VectorSetSetAttributesJson("famousPeople", name, attributesJson);
}
string queryValue = "actors";
float[] queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest basicQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? actorsResults = db.VectorSetSimilaritySearch("famousPeople", basicQuery))
{
IEnumerable<string> resultIds = actorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors': [{string.Join(", ", resultIds)}]");
}
queryValue = "actors";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest limitedQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
limitedQuery.Count = 2;
using (Lease<VectorSetSimilaritySearchResult>? twoActorsResults = db.VectorSetSimilaritySearch("famousPeople", limitedQuery))
{
IEnumerable<string> resultIds = twoActorsResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'actors (2)': [{string.Join(", ", resultIds)}]");
// >>> 'actors (2)': ['Masako Natsume', 'Chaim Topol']
}
queryValue = "entertainer";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest entertainerQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? entertainerResults = db.VectorSetSimilaritySearch("famousPeople", entertainerQuery))
{
IEnumerable<string> resultIds = entertainerResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'entertainer': [{string.Join(", ", resultIds)}]");
// >>> 'entertainer': ['Chaim Topol', 'Freddie Mercury',
// 'Marie Fredriksson', 'Masako Natsume', 'Linus Pauling',
// 'Paul Erdos', 'Maryam Mirzakhani', 'Marie Curie']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest scienceQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
using (Lease<VectorSetSimilaritySearchResult>? scienceResults = db.VectorSetSimilaritySearch("famousPeople", scienceQuery))
{
IEnumerable<string> resultIds = scienceResults!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science': [{string.Join(", ", resultIds)}]");
// >>> 'science': ['Marie Curie', 'Linus Pauling',
// 'Maryam Mirzakhani', 'Paul Erdos', 'Marie Fredriksson',
// 'Freddie Mercury', 'Masako Natsume', 'Chaim Topol']
}
queryValue = "science";
queryEmbedding = GetEmbedding(model, queryValue);
VectorSetSimilaritySearchRequest filteredQuery = VectorSetSimilaritySearchRequest.ByVector(queryEmbedding);
filteredQuery.FilterExpression = ".died < 2000";
using (Lease<VectorSetSimilaritySearchResult>? science2000Results = db.VectorSetSimilaritySearch("famousPeople", filteredQuery))
{
IEnumerable<string> resultIds = science2000Results!.Span.ToArray()
.Select(r => (string?)r.Member)
.Where(id => id != null)
.Select(id => $"'{id!}'");
Console.WriteLine($"'science2000': [{string.Join(", ", resultIds)}]");
// >>> 'science2000': ['Marie Curie', 'Linus Pauling',
// 'Paul Erdos', 'Freddie Mercury', 'Masako Natsume']
}
class TextData
{
public string Text { get; set; } = string.Empty;
}
class TransformedTextData : TextData
{
public float[] Features { get; set; } = Array.Empty<float>();
}
Note that the boolean filter expression is applied to items in the list before the vector distance calculation is performed. Items that don't pass the filter test are removed from the results completely, rather than just reduced in rank. This can help to improve the performance of the search because there is no need to calculate the vector distance for elements that have already been filtered out of the search.
More information
See the vector sets docs for more information and code examples. See the Redis for AI section for more details about text embeddings and other AI techniques you can use with Redis.
You may also be interested in vector search. This is a feature of the Redis query engine that lets you retrieve JSON and hash documents based on vector data stored in their fields.