mirror of https://github.com/microsoft/semantic-kernel.git synced 2026-10-12 02:19:06 +00:00

Files

T

Lee MillerandLee Miller 35cb1bf76a Copilot Chat Tasks - Rename CopilotChatApi to CopilotChatWebApi (#1205 )

This commit renames the CopilotChatApi project and related files to
CopilotChatWebApi, to avoid confusion with the CopilotChatApp project
and to follow the naming convention of other webapi projects in the
solution. It also updates the launch and task configurations in VSCode
to reflect the new name.

Co-authored-by: Lee Miller <[email protected]>

2023-05-25 14:01:28 -07:00

3.6 KiB

Raw Blame History

Semantic Kernel Service - CopilotChat

This ASP.Net web application exposes the Semantic Kernel through a REST-like interface.

Configure your environment

Before you get started, make sure you have the following requirements in place:

.NET 6.0 for building and deploying .NET 6 projects.
Update the properties in ./appsettings.json to configure your Azure OpenAI resource or OpenAI account.
Generate and trust a localhost developer certificate.
- For Windows and Mac run
```
dotnet dev-certs https --trust`
```
  Select Yes when asked if you want to install this certificate.
- For Linux run
```
dotnet dev-certs https
```
To verify the certificate has been installed and trusted, run dotnet run dev-certs https --check

To clean your system of the developer certificate, run dotnet run dev-certs https --clean
(Optional) Visual Studio Code or Visual Studio.

Start the WebApi Service

You can start the WebApi service using the command-line, Visual Studio Code, or Visual Studio.

Command-line

Open a terminal
Change directory to the Copilot Chat webapi project directory.
```
cd semantic-kernel/samples/apps/copilot-chat-app/webapi
```
(Optional) Build the service and verify there are no errors.
```
dotnet build
```
Run the service
```
dotnet run
```
Early in the startup, the service will provide a probe endpoint you can use in a web browser to verify the service is running.
```
info: Microsoft.SemanticKernel.Kernel[0]
      Health probe: https://localhost:40443/probe
```

Visual Studio Code

build (CopilotChatWebApi)
run (CopilotChatWebApi)
[optional] watch (CopilotChatWebApi)

Visual Studio (2022 or newer)

Open the solution file in Visual Studio 2022 or newer (semantic-kernel/dotnet/SK-dotnet.sln).
In the solution explorer expand the samples folder.
Right-click on the CopilotChatWebApi and select Set as Startup Project.
Start debugging by pressing F5 or selecting the menu item Debug->Start Debugging.

(Optional) Enabling the Qdrant Memory Store

By default, the service uses an in-memory volatile memory store that, when the service stops or restarts, forgets all memories. Qdrant is a persistent scalable vector search engine that can be deployed locally in a container or at-scale in the cloud.

To enable the Qdrant memory store, you must first deploy Qdrant locally and then configure the Copilot Chat API service to use it.

1. Configure your environment

Before you get started, make sure you have the following additional requirements in place:

Docker Desktop for hosting the Qdrant vector search engine.

2. Deploy Qdrant VectorDB locally

Open a terminal and use Docker to pull down the container image.
```
docker pull qdrant/qdrant
```
Change directory to this repo and create a ./data/qdrant directory to use as persistent storage. Then start the Qdrant container on port 6333 using the ./data/qdrant folder as the persistent storage location.
```
cd /src/semantic-kernel
mkdir ./data/qdrant
docker run --name copilotchat -p 6333:6333 -v "$(pwd)/data/qdrant:/qdrant/storage" qdrant/qdrant
```
To stop the container, in another terminal window run docker container stop copilotchat; docker container rm copilotchat;.

3.6 KiB Raw Blame History