Closed
Description
Type of issue
Code doesn't work
Description
If you use any of the arguments from the tutorial to use the dotnet new aichatweb
template, such as:
dotnet new aichatweb --framework "net9.0" --AiServiceProvider "ollama" --VectorStore "local"
This will error out :
Error: Invalid option(s):
--framework
'--framework' is not a valid option
net9.0
'net9.0' is not a valid option
--AiServiceProvider
'--AiServiceProvider' is not a valid option
ollama
'ollama' is not a valid option
--VectorStore
'--VectorStore' is not a valid option
local
'local' is not a valid option
This is apparently because the template has been updated and these parameters have been renamed:
λ dotnet new aichatweb -h
AI Chat Web App (C#)
Author: Microsoft
Description: A project template for creating an AI chat application, which uses retrieval-augmented generation (RAG) to chat with your own data.
Usage:
dotnet new aichatweb [options] [template options]
Options:
-n, --name <name> The name for the output being created. If no name is specified, the name of the output directory is used.
-o, --output <output> Location to place the generated output.
--dry-run Displays a summary of what would happen if the given command line were run if it would result in a template creation.
--force Forces content to be generated even if it would change existing files.
--no-update-check Disables checking for the template package updates when instantiating a template.
--project <project> The project that should be used for context evaluation.
-lang, --language <C#> Specifies the template language to instantiate.
--type <project> Specifies the template type to instantiate.
Template options:
-F, --Framework <net9.0> The target framework for the project.
Type: choice
net9.0 Target net9.0
Default: net9.0
--provider <azureopenai|githubmodels|ollama|openai> Type: choice
azureopenai Uses Azure OpenAI service
githubmodels Uses GitHub Models
ollama Uses Ollama with the llama3.2 and all-minilm models
openai Uses the OpenAI Platform
Default: githubmodels
--vector-store <azureaisearch|local|qdrant> Type: choice
local Uses a JSON file on disk. You can change the implementation to a real vector database
before publishing.
azureaisearch Uses Azure AI Search. This also avoids the need to define a data ingestion pipeline,
since it's managed by Azure AI Search.
qdrant Uses Qdrant in a Docker container, orchestrated using Aspire.
Default: local
--managed-identity Use managed identity to access Azure services
Enabled if: (!UseAspire && VectorStore != "qdrant" && (AiServiceProvider == "azureopenai" ||
AiServiceProvider == "azureaifoundry" || VectorStore == "azureaisearch"))
Type: bool
Default: true
--aspire Create the project as a distributed application using .NET Aspire.
Type: bool
Default: false
-C, --ChatModel <ChatModel> Model/deployment for chat completions. Example: gpt-4o-mini
Type: string
-E, --EmbeddingModel <EmbeddingModel> Model/deployment for embeddings. Example: text-embedding-3-small
Page URL
Content source URL
https://github.com/dotnet/docs/blob/main/docs/ai/quickstarts/ai-templates.md
Document Version Independent Id
fd993daa-ad67-5a5d-873e-96e70b4256c9
Platform Id
0689a818-6031-ad99-46f1-044d1ce482aa
Article author
Metadata
- ID: 9ccd0c8e-4044-19de-f19d-f4478b34e00e
- PlatformId: 0689a818-6031-ad99-46f1-044d1ce482aa
- Service: dotnet
- Sub-service: intelligent-apps