Microsoft.KernelMemory.MongoDbAtlas
0.68.240722.1
Prefix Reserved
See the version list below for details.
dotnet add package Microsoft.KernelMemory.MongoDbAtlas --version 0.68.240722.1
NuGet\Install-Package Microsoft.KernelMemory.MongoDbAtlas -Version 0.68.240722.1
<PackageReference Include="Microsoft.KernelMemory.MongoDbAtlas" Version="0.68.240722.1" />
paket add Microsoft.KernelMemory.MongoDbAtlas --version 0.68.240722.1
#r "nuget: Microsoft.KernelMemory.MongoDbAtlas, 0.68.240722.1"
// Install Microsoft.KernelMemory.MongoDbAtlas as a Cake Addin #addin nuget:?package=Microsoft.KernelMemory.MongoDbAtlas&version=0.68.240722.1 // Install Microsoft.KernelMemory.MongoDbAtlas as a Cake Tool #tool nuget:?package=Microsoft.KernelMemory.MongoDbAtlas&version=0.68.240722.1
Developing with MongoDB Atlas
While MongoDB Atlas is a cloud only deployment, recently MongoDb added the ability to create local installation of Atlas thanks to Atlas Command line.
You can install Atlas Command Line Directly from MongoDB Web Site. Thanks to this tool you can create a local MongoDB atlas installation with few lines of CLI.
This local cluster is managed by podman, we need to investigate if we can create one on Docker.
Local cluster offers all the Search Capabilities of MongoDB Atlas, including Atlas Search.
Docker support
You can find all detail for recent docker support here
docker run -p 27777:27017 --privileged -it mongodb/atlas sh \
-c "atlas deployments setup --bindIpAll --username root --password root --type local --force && tail -f /dev/null"
The original 27017 port is mapped to 27777, so it does not conflict with standard MongoDb installation you can have in the local machine.
You can change the username and password if you like, then the connection string will be
mongodb://user:password@localhost:27777/?authSource=admin
Better docker support
If you start container as shown in previous chapter, the problem is that, after you stop and restart container another instance of atlas will be created. To have a better docker support you need to create a Dockerfile with the following content
FROM mongodb/atlas
COPY startatlas.sh /usr/startatlas.sh
CMD /usr/startatlas.sh
Then you can create a startatlas.sh file with the following content
#!/bin/bash
# The name of the deployment to search for
# Run the command and save the output
OUTPUT=$(atlas deployments list)
echo "Output: "
echo $OUTPUT
# count line of output
LINE=$(echo "$OUTPUT" | wc -l)
echo "Count line of output: $LINE "
if [ $LINE -lt 2 ]; then
echo "No deployment found. create a new one"
atlas deployments setup local --bindIpAll --username root --password root --type local --force
else
echo "Deployment found. Start it"
atlas deployments start local
fi
function pause_atlas() {
atlas deployments pause local
}
# This will call the 'on_exit' function when the container exits
trap pause_atlas EXIT
tail -f /dev/null
This will create a base image that can support stop/start of the container.
Creating local cluster
Once you installed Atlas CLI you can create a local MongoDB Atlas cluster with this simple instruction
atlas deployments setup --type local
You can follow instruction, you can use both 6 or 7 version of MongoDB Atlas.
You can then list all of your environment with
atlas deployments list
And you can start/stop atlas deployment with
atlas deployment start <deployment-name>
atlas deployment pause <deployment-name>
You can then connect with the standard connection string
mongodb://localhost:27017/?directConnection=true&serverSelectionTimeoutMS=2000
Some useful commands
If in local atlas installation tests fails or you have some strange error, it could happen that the search index is corrupted. To manually delete an index, first of all list all available vector and search indexes inside the collection
db.getCollection("_ix__kernel_memory_single_index").aggregate([
{"$listSearchIndexes" : {}}
])
This will return the list of all indexes that are defined in the collection, you can delete an index using the command
db.runCommand({"dropSearchIndex" : "_ix__kernel_memory_single_index", "id" : "65e4ae1623dd55119d74571e"})
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.KernelMemory.Abstractions (>= 0.68.240722.1)
- MongoDB.Driver.GridFS (>= 2.27.0)
NuGet packages (1)
Showing the top 1 NuGet packages that depend on Microsoft.KernelMemory.MongoDbAtlas:
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. |
GitHub repositories
This package is not used by any popular GitHub repositories.
Version | Downloads | Last updated | |
---|---|---|---|
0.73.240906.1 | 83 | 9/7/2024 | |
0.72.240904.1 | 550 | 9/5/2024 | |
0.71.240820.1 | 5,429 | 8/21/2024 | |
0.70.240803.1 | 15,391 | 8/3/2024 | |
0.69.240727.1 | 5,427 | 7/27/2024 | |
0.68.240722.1 | 2,596 | 7/22/2024 | |
0.68.240716.1 | 1,686 | 7/16/2024 | |
0.67.240712.1 | 1,254 | 7/12/2024 | |
0.66.240709.1 | 3,422 | 7/9/2024 | |
0.65.240620.1 | 22,846 | 6/21/2024 | |
0.64.240619.1 | 647 | 6/20/2024 | |
0.63.240618.1 | 1,687 | 6/18/2024 | |
0.62.240605.1 | 15,215 | 6/5/2024 | |
0.62.240604.1 | 420 | 6/4/2024 | |
0.61.240524.1 | 9,064 | 5/24/2024 | |
0.61.240519.2 | 8,923 | 5/19/2024 | |
0.60.240517.1 | 182 | 5/18/2024 | |
0.51.240513.2 | 5,475 | 5/13/2024 | |
0.50.240504.7 | 3,805 | 5/4/2024 | |
0.40.240501.1 | 49 | 5/1/2024 | |
0.39.240427.1 | 190 | 4/28/2024 | |
0.38.240425.1 | 111 | 4/25/2024 | |
0.38.240423.1 | 125 | 4/24/2024 | |
0.37.240420.2 | 177 | 4/21/2024 |