Microsoft.KernelMemory.MemoryDb.Postgres
0.69.240727.1
Prefix Reserved
See the version list below for details.
dotnet add package Microsoft.KernelMemory.MemoryDb.Postgres --version 0.69.240727.1
NuGet\Install-Package Microsoft.KernelMemory.MemoryDb.Postgres -Version 0.69.240727.1
<PackageReference Include="Microsoft.KernelMemory.MemoryDb.Postgres" Version="0.69.240727.1" />
paket add Microsoft.KernelMemory.MemoryDb.Postgres --version 0.69.240727.1
#r "nuget: Microsoft.KernelMemory.MemoryDb.Postgres, 0.69.240727.1"
// Install Microsoft.KernelMemory.MemoryDb.Postgres as a Cake Addin #addin nuget:?package=Microsoft.KernelMemory.MemoryDb.Postgres&version=0.69.240727.1 // Install Microsoft.KernelMemory.MemoryDb.Postgres as a Cake Tool #tool nuget:?package=Microsoft.KernelMemory.MemoryDb.Postgres&version=0.69.240727.1
Kernel Memory with Postgres + pgvector
This project contains the Postgres adapter allowing to use Kernel Memory with Postgres+pgvector.
[!IMPORTANT] Your Postgres instance must support vectors. You can run this SQL to see the list of extensions installed and enabled:
SELECT * FROM pg_extension
To enable the extension this should suffice:
CREATE EXTENSION vector
For more information, check:
To use Postgres with Kernel Memory:
Have a PostgreSQL instance ready, e.g. checkout Azure Database for PostgreSQL
Verify your Postgres instance supports vectors, e.g. run
SELECT * FROM pg_extension
Add Postgres connection string to appsettings.json (or appsettings.development.json), for example:
{ "KernelMemory": { "Services": { "Postgres": { "ConnectionString": "Host=localhost;Port=5432;Username=myuser;Password=mypassword;Database=mydatabase" } } } }
Configure KM builder to store memories in Postgres, and to persist documents, for example:
// using Microsoft.KernelMemory; // using Microsoft.KernelMemory.Postgres; // using Microsoft.Extensions.Configuration; var postgresConfig = new PostgresConfig(); new ConfigurationBuilder() .AddJsonFile("appsettings.json") .AddJsonFile("appsettings.Development.json", optional: true) .Build() .BindSection("KernelMemory:Services:Postgres", postgresConfig); var memory = new KernelMemoryBuilder() .WithPostgresMemoryDb(postgresConfig) .WithSimpleFileStorage(SimpleFileStorageConfig.Persistent) .WithAzureOpenAITextGeneration(azureOpenAIConfig) .WithAzureOpenAITextEmbeddingGeneration(azureOpenAIConfig) .Build();
Neighbor search indexes, quality and performance
The connector does not create IVFFlat or HNSW indexes on Postgres tables, and uses exact nearest neighbor search. HNSW (Hierarchical Navigable Small World) has been introduced in pgvector 0.5.0 and is not available in some Postgres instances.
Depending on your scenario you might want to create these indexes manually, considering precision and performance trade-offs, or you can customize the SQL used to create tables via configuration.
[!NOTE] An IVFFlat index divides vectors into lists, and then searches a subset of those lists that are closest to the query vector. It has faster build times and uses less memory than HNSW, but has lower query performance (in terms of speed-recall tradeoff).
SQL to add IVFFlat: CREATE INDEX ON %%table_name%% USING ivfflat (embedding vector_cosine_ops) WITH (lists = 1000);
[!NOTE] An HNSW index creates a multilayer graph. It has slower build times and uses more memory than IVFFlat, but has better query performance (in terms of speed-recall tradeoff). There’s no training step like IVFFlat, so the index can be created without any data in the table.
SQL to add HNSW: CREATE INDEX ON %%table_name%% USING hnsw (embedding vector_cosine_ops);
See https://github.com/pgvector/pgvector for more information.
Memory Indexes and Postgres tables
The Postgres memory connector will create "memory indexes" automatically, one DB table for each memory index.
Table names have a configurable prefix, used to filter out other tables that
might be present. The prefix is mandatory, cannot be empty, we suggest using
the default km-
prefix. Note that the Postgres connector automatically converts
_
underscores to -
dashes to have a consistent behavior with other storage
types supported by Kernel Memory.
Overall we recommend not mixing external tables in the same DB used for Kernel Memory.
Column names and table schema
The connector uses a default schema with predefined columns and indexes.
You can change the field names, and if you need to add additional columns
or indexes, you can also customize the CREATE TABLE
SQL statement. You
can use this approach, for example, to use IVFFlat or HNSW.
See PostgresConfig
class for more details.
Here's an example where PostgresConfig
is stored in appsettings.json
and
the table schema is customized, with custom names and additional fields.
The SQL statement requires two special placeholders:
%%table_name%%
: replaced at runtime with the table name%%vector_size%%
: replaced at runtime with the embedding vectors size
There's a third optional placeholder we recommend using, to better handle
concurrency, e.g. in combination with pg_advisory_xact_lock
(exclusive transaction
level advisory locks):
%%lock_id%%
: replaced at runtime with a number
Also:
TableNamePrefix
is mandatory string added to all KM tablesColumns
is a required map describing where KM will store its data. If you have additional columns you don't need to list them here, only in SQL statement.CreateTableSql
is your optional custom SQL statement used to create tables. The column names must match those used inColumns
.
{
"KernelMemory": {
"Services": {
"Postgres": {
"TableNamePrefix": "memory_",
"Columns": {
"id": "_pk",
"embedding": "embedding",
"tags": "labels",
"content": "chunk",
"payload": "extras"
},
"CreateTableSql": [
"BEGIN; ",
"SELECT pg_advisory_xact_lock(%%lock_id%%); ",
"CREATE TABLE IF NOT EXISTS %%table_name%% ( ",
" _pk TEXT NOT NULL PRIMARY KEY, ",
" embedding vector(%%vector_size%%), ",
" labels TEXT[] DEFAULT '{}'::TEXT[] NOT NULL, ",
" chunk TEXT DEFAULT '' NOT NULL, ",
" extras JSONB DEFAULT '{}'::JSONB NOT NULL, ",
" my_field1 TEXT DEFAULT '', ",
" _update TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP ",
"); ",
"CREATE INDEX ON %%table_name%% USING GIN(labels); ",
"CREATE INDEX ON %%table_name%% USING ivfflat (embedding vector_cosine_ops); ",
"COMMIT; "
]
}
}
}
}
Product | Versions Compatible and additional computed target framework versions. |
---|---|
.NET | net8.0 is compatible. net8.0-android was computed. net8.0-browser was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed. |
-
net8.0
- Microsoft.Extensions.DependencyInjection.Abstractions (>= 8.0.1)
- Microsoft.KernelMemory.Abstractions (>= 0.69.240727.1)
- Pgvector (>= 0.3.0)
NuGet packages (2)
Showing the top 2 NuGet packages that depend on Microsoft.KernelMemory.MemoryDb.Postgres:
Package | Downloads |
---|---|
Microsoft.KernelMemory.Core
The package contains all the core logic and extensions of Kernel Memory, to index and query any data and documents, using LLM and natural language, tracking sources and showing citations. |
|
Aip.Km.KernelMemoryExtension
Package Description |
GitHub repositories
This package is not used by any popular GitHub repositories.
Version | Downloads | Last updated | |
---|---|---|---|
0.71.240820.1 | 2,957 | 8/21/2024 | |
0.70.240803.1 | 12,660 | 8/3/2024 | |
0.69.240727.1 | 5,039 | 7/27/2024 | |
0.68.240722.1 | 2,534 | 7/22/2024 | |
0.68.240716.1 | 1,698 | 7/16/2024 | |
0.67.240712.1 | 1,295 | 7/12/2024 | |
0.66.240709.1 | 3,257 | 7/9/2024 | |
0.65.240620.1 | 22,135 | 6/21/2024 | |
0.64.240619.1 | 616 | 6/20/2024 | |
0.63.240618.1 | 1,645 | 6/18/2024 | |
0.62.240605.1 | 14,379 | 6/5/2024 | |
0.62.240604.1 | 392 | 6/4/2024 | |
0.61.240524.1 | 8,957 | 5/24/2024 | |
0.61.240519.2 | 8,782 | 5/19/2024 | |
0.60.240517.1 | 183 | 5/18/2024 | |
0.51.240513.2 | 5,356 | 5/13/2024 | |
0.50.240504.7 | 4,213 | 5/4/2024 | |
0.40.240501.1 | 195 | 5/1/2024 | |
0.39.240427.1 | 1,361 | 4/28/2024 | |
0.38.240425.1 | 187 | 4/25/2024 | |
0.38.240423.1 | 490 | 4/24/2024 | |
0.37.240420.2 | 569 | 4/21/2024 | |
0.36.240416.1 | 1,588 | 4/16/2024 | |
0.36.240415.2 | 160 | 4/16/2024 | |
0.36.240415.1 | 97 | 4/15/2024 | |
0.35.240412.2 | 126 | 4/12/2024 | |
0.35.240321.1 | 2,103 | 3/21/2024 | |
0.35.240318.1 | 10,174 | 3/18/2024 | |
0.34.240313.1 | 586 | 3/13/2024 | |
0.33.240312.1 | 156 | 3/12/2024 | |
0.32.240308.1 | 465 | 3/8/2024 | |
0.32.240307.3 | 135 | 3/7/2024 | |
0.32.240307.2 | 93 | 3/7/2024 | |
0.30.240227.1 | 12,643 | 2/28/2024 | |
0.29.240219.2 | 2,962 | 2/20/2024 | |
0.28.240212.1 | 419 | 2/13/2024 | |
0.27.240207.1 | 206 | 2/7/2024 | |
0.27.240205.2 | 223 | 2/6/2024 | |
0.27.240205.1 | 208 | 2/5/2024 | |
0.26.240121.1 | 2,364 | 1/22/2024 | |
0.26.240116.2 | 580 | 1/16/2024 | |
0.26.240115.4 | 265 | 1/16/2024 | |
0.26.240104.1 | 1,228 | 1/5/2024 | |
0.25.240103.1 | 157 | 1/4/2024 | |
0.24.231228.5 | 546 | 12/29/2023 | |
0.24.231228.4 | 433 | 12/29/2023 |