Semantic Memory

Semantic Memory (SM) is an open-source service and plugin specialized in the efficient indexing of datasets through custom continuous data hybrid pipelines. For some scenarios SM is also available as a library, and soon as a Docker container.

Utilizing advanced embeddings and LLMs, the system enables Natural Language querying for obtaining answers from the indexed data, complete with citations and links to the original sources.

Designed for seamless integration as a Plugin with Semantic Kernel, Microsoft Copilot and ChatGPT, Semantic Memory enhances data-driven features in applications built for most popular AI platforms.

Supported backends

• ↗️ Vector storage
  • Azure Cognitive Search
  • Qdrant
• 📀 Content storage
  • Azure Blobs
  • Local file system
• ⏳ Asynchronous ingestion queues
  • Azure Queues
  • RabbitMQ
  • Local file based queue

ℹ️ NOTE: the documentation below is work in progress, will evolve quickly as is not fully functional yet.

Semantic Memory in serverless mode

Semantic Memory works and scales at best when running as a service, allowing to ingest thousands of documents and information without blocking your app.

However, you can use Semantic Memory also serverless, embedding the MemoryServerlessClient in your app.

Importing documents into your Semantic Memory can be as simple as this:

var memory = new MemoryClientBuilder()
    .WithOpenAIDefaults(Env.Var("OPENAI_API_KEY"))
    .Build();

// Import a file
await memory.ImportDocumentAsync("meeting-transcript.docx", tags: new() { { "user", "Blake" } });

// Import multiple files and apply multiple tags
await memory.ImportDocumentAsync(new Document("file001")
    .AddFile("business-plan.docx")
    .AddFile("project-timeline.pdf")
    .AddTag("user", "Blake")
    .AddTag("collection", "business")
    .AddTag("collection", "plans")
    .AddTag("fiscalYear", "2023"));

Asking questions:

var answer1 = await memory.AskAsync("How many people attended the meeting?");

var answer2 = await memory.AskAsync("what's the project timeline?", filter: new MemoryFilter().ByTag("user", "Blake"));

The code leverages the default documents ingestion pipeline:

1. Extract text: recognize the file format and extract the information
2. Partition the text in small chunks, to optimize search
3. Extract embedding using an LLM embedding generator
4. Save embedding into a vector index such as Azure Cognitive Search, Qdrant or other DBs.

Documents are organized by users, safeguarding their private information. Furthermore, memories can be categorized and structured using tags, enabling efficient search and retrieval through faceted navigation.

Data lineage, citations

All memories and answers are fully correlated to the data provided. When producing an answer, Semantic Memory includes all the information needed to verify its accuracy:

await memory.ImportFileAsync("NASA-news.pdf");

var answer = await memory.AskAsync("Any news from NASA about Orion?");

Console.WriteLine(answer.Result + "/n");

foreach (var x in answer.RelevantSources)
{
    Console.WriteLine($"  * {x.SourceName} -- {x.Partitions.First().LastUpdate:D}");
}

Yes, there is news from NASA about the Orion spacecraft. NASA has invited the media to see a new test version of the Orion spacecraft and the hardware that will be used to recover the capsule and astronauts upon their return from space during the Artemis II mission. The event is scheduled to take place at Naval Base San Diego on Wednesday, August 2, at 11 a.m. PDT. Personnel from NASA, the U.S. Navy, and the U.S. Air Force will be available to speak with the media. Teams are currently conducting tests in the Pacific Ocean to demonstrate and evaluate the processes, procedures, and hardware for recovery operations for crewed Artemis missions. These tests will help prepare the team for Artemis II, which will be NASA's first crewed mission under the Artemis program. The Artemis II crew, consisting of NASA astronauts Reid Wiseman, Victor Glover, and Christina Koch, and Canadian Space Agency astronaut Jeremy Hansen, will participate in recovery testing at sea next year. For more information about the Artemis program, you can visit the NASA website.

• NASA-news.pdf -- Tuesday, August 1, 2023

Using Semantic Memory Service

Depending on your scenarios, you might want to run all the code locally inside your process, or remotely through an asynchronous service.

If you're importing small files, and need only C# or only Python, and can block the process during the import, local-in-process execution can be fine, using the MemoryServerlessClient seen above.

However, if you are in one of these scenarios:

• I'd just like a web service to import data and send queries to answer
• My app is written in TypeScript, Java, Rust, or some other language
• I want to define custom pipelines mixing multiple languages like Python, TypeScript, etc
• I'm importing big documents that can require minutes to process, and I don't want to block the user interface
• I need memory import to run independently, supporting failures and retry logic

then you can deploy Semantic Memory as a service, plugging in the default handlers or your custom Python/TypeScript/Java/etc. handlers, and leveraging the asynchronous non-blocking memory encoding process, sending documents and asking questions using the MemoryWebClient.

Here you can find a complete set of instruction about how to run the Semantic Memory service.

If you want to give the service a quick test, use the following command to start the Semantic Memory Service:

On WSL / Linux / MacOS:

cd dotnet/Service
./setup.sh
./run.sh

On Windows:

cd dotnet\Service
setup.cmd
run.cmd

To import files using Semantic Memory web service, use MemoryWebClient:

#reference dotnet/ClientLib/ClientLib.csproj

var memory = new MemoryWebClient("http://127.0.0.1:9001"); // <== URL where the web service is running

// Import a file (default user)
await memory.ImportDocumentAsync("meeting-transcript.docx");

// Import a file specifying a Document ID, User and Tags
await memory.ImportDocumentAsync("business-plan.docx",
    new DocumentDetails("[email protected]", "file001")
        .AddTag("collection", "business")
        .AddTag("collection", "plans")
        .AddTag("fiscalYear", "2023"));

Getting answers via the web service

curl http://127.0.0.1:9001/ask -d'{"query":"Any news from NASA about Orion?"}' -H 'Content-Type: application/json'

{
  "Query": "Any news from NASA about Orion?",
  "Text": "Yes, there is news from NASA about the Orion spacecraft. NASA has invited the media to see a new test version of the Orion spacecraft and the hardware that will be used to recover the capsule and astronauts upon their return from space during the Artemis II mission. The event is scheduled to take place at Naval Base San Diego on August 2nd at 11 a.m. PDT. Personnel from NASA, the U.S. Navy, and the U.S. Air Force will be available to speak with the media. Teams are currently conducting tests in the Pacific Ocean to demonstrate and evaluate the processes, procedures, and hardware for recovery operations for crewed Artemis missions. These tests will help prepare the team for Artemis II, which will be NASA's first crewed mission under the Artemis program. The Artemis II crew, consisting of NASA astronauts Reid Wiseman, Victor Glover, and Christina Koch, and Canadian Space Agency astronaut Jeremy Hansen, will participate in recovery testing at sea next year. For more information about the Artemis program, you can visit the NASA website.",
  "RelevantSources": [
    {
      "Link": "...",
      "SourceContentType": "application/pdf",
      "SourceName": "file5-NASA-news.pdf",
      "Partitions": [
        {
          "Text": "Skip to main content\nJul 28, 2023\nMEDIA ADVISORY M23-095\nNASA Invites Media to See Recovery Craft for\nArtemis Moon Mission\n(/sites/default/files/thumbnails/image/ksc-20230725-ph-fmx01_0003orig.jpg)\nAboard the USS John P. Murtha, NASA and Department of Defense personnel practice recovery operations for Artemis II in July. A\ncrew module test article is used to help verify the recovery team will be ready to recovery the Artemis II crew and the Orion spacecraft.\nCredits: NASA/Frank Michaux\nMedia are invited to see the new test version of NASA’s Orion spacecraft and the hardware teams will use\nto recover the capsule and astronauts upon their return from space during the Artemis II\n(http://www.nasa.gov/artemis-ii) mission. The event will take place at 11 a.m. PDT on Wednesday, Aug. 2,\nat Naval Base San Diego.\nPersonnel involved in recovery operations from NASA, the U.S. Navy, and the U.S. Air Force will be\navailable to speak with media.\nU.S. media interested in attending must RSVP by 4 p.m., Monday, July 31, to the Naval Base San Diego\nPublic Affairs (mailto:[email protected]) or 619-556-7359.\nOrion Spacecraft (/exploration/systems/orion/index.html)\nNASA Invites Media to See Recovery Craft for Artemis Moon Miss... https://www.nasa.gov/press-release/nasa-invites-media-to-see-recov...\n1 of 3 7/28/23, 4:51 PMTeams are currently conducting the first in a series of tests in the Pacific Ocean to demonstrate and\nevaluate the processes, procedures, and hardware for recovery operations (https://www.nasa.gov\n/exploration/systems/ground/index.html) for crewed Artemis missions. The tests will help prepare the\nteam for Artemis II, NASA’s first crewed mission under Artemis that will send four astronauts in Orion\naround the Moon to checkout systems ahead of future lunar missions.\nThe Artemis II crew – NASA astronauts Reid Wiseman, Victor Glover, and Christina Koch, and CSA\n(Canadian Space Agency) astronaut Jeremy Hansen – will participate in recovery testing at sea next year.\nFor more information about Artemis, visit:\nhttps://www.nasa.gov/artemis (https://www.nasa.gov/artemis)\n-end-\nRachel Kraft\nHeadquarters, Washington\n202-358-1100\[email protected] (mailto:[email protected])\nMadison Tuttle\nKennedy Space Center, Florida\n321-298-5868\[email protected] (mailto:[email protected])\nLast Updated: Jul 28, 2023\nEditor: Claire O’Shea\nTags:  Artemis (/artemisprogram),Ground Systems (http://www.nasa.gov/exploration/systems/ground\n/index.html),Kennedy Space Center (/centers/kennedy/home/index.html),Moon to Mars (/topics/moon-to-\nmars/),Orion Spacecraft (/exploration/systems/orion/index.html)\nNASA Invites Media to See Recovery Craft for Artemis Moon Miss... https://www.nasa.gov/press-release/nasa-invites-media-to-see-recov...\n2 of 3 7/28/23, 4:51 PM",
          "Relevance": 0.8430657,
          "SizeInTokens": 863,
          "LastUpdate": "2023-08-01T08:15:02-07:00"
        }
      ]
    }
  ]
}

You can find a full example here.

Custom memory ingestion pipelines

On the other hand, if you need a custom data pipeline, you can also customize the steps, which will be handled by your custom business logic:

// Memory setup, e.g. how to calculate and where to store embeddings
var memoryBuilder = new MemoryClientBuilder().WithOpenAIDefaults(Env.Var("OPENAI_API_KEY"));
memoryBuilder.Build();
var orchestrator = memoryBuilder.GetOrchestrator();

// Define custom .NET handlers
var step1 = new MyHandler1("step1", orchestrator);
var step2 = new MyHandler2("step2", orchestrator);
var step3 = new MyHandler3("step3", orchestrator);
await orchestrator.AddHandlerAsync(step1);
await orchestrator.AddHandlerAsync(step2);
await orchestrator.AddHandlerAsync(step3);

// Instantiate a custom pipeline
var pipeline = orchestrator
    .PrepareNewFileUploadPipeline("user-id-1", "mytest", new[] { "memory-collection" })
    .AddUploadFile("file1", "file1.docx", "file1.docx")
    .AddUploadFile("file2", "file2.pdf", "file2.pdf")
    .Then("step1")
    .Then("step2")
    .Then("step3")
    .Build();

// Execute in process, process all files with all the handlers
await orchestrator.RunPipelineAsync(pipeline);

Web API specs

The API schema is available at http://127.0.0.1:9001/swagger/index.html when running the service locally with OpenAPI enabled.

Examples and Tools

Examples

1. Collection of Jupyter notebooks with various tests
2. Importing files and asking question without running the service (serverless mode)
3. Using the Semantic Memory web service
4. How to upload files from command line with curl
5. Processing files with custom steps
6. Using a custom pipeline handler with serverless memory class
7. Writing a custom async pipeline handler

Tools

1. Curl script to upload files
2. Curl script to ask questions
3. Curl script to search documents
4. Script to start Qdrant for development tasks
5. Script to start RabbitMQ for development tasks