Created
December 5, 2025 13:33
-
-
Save jwmatthews/67ff87421461fc0896ac8f8d50e05317 to your computer and use it in GitHub Desktop.
provider-settings.yaml: Verified Functional - MTA 8.0.2 with podman AI and ibm-granite/granite-3.3-8b-instruct-GGUF
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # This is a sample settings file generated by the extension with a few common providers | |
| # and models defined. To return the file back to default, delete it and restart vscode. | |
| --- | |
| environment: | |
| ALWAYS_APPLIED_KEY: "envvar to be set regardless of which model is active" | |
| # CA_BUNDLE: "" # optional | |
| # ALLOW_INSECURE: "false" # optional | |
| # This is a collection of model configurations that may be used. The `&active` | |
| # anchor is used to reference the model to the active node below. The extension will | |
| # use the active node for configuration the kai-rpc-server. | |
| models: | |
| OpenAI: | |
| environment: | |
| OPENAI_API_KEY: "" # Required | |
| provider: ChatOpenAI | |
| args: | |
| model: gpt-4o # Required | |
| ## Following keys are optional & only exist for documentation purposes | |
| # user: <string> | |
| # temperature: <number> | |
| # maxTokens: <number> | |
| # timeout: <number> | |
| # maxRetries: <number> | |
| # configuration: | |
| # baseURL: <string> | |
| # project: <string> | |
| # organization: <string> | |
| AzureChatOpenAI: | |
| environment: | |
| AZURE_OPENAI_API_KEY: "" # Required | |
| provider: AzureChatOpenAI | |
| args: | |
| azureOpenAIApiDeploymentName: "" # Required | |
| azureOpenAIApiVersion: "" # Required | |
| ## Following keys are optional & only exist for documentation purposes | |
| # azureOpenAIApiInstanceName: <string> | |
| # azureOpenAIBasePath: <string> | |
| # azureOpenAIEndpoint: <string> | |
| # azureOpenAIDeploymentName: <string> | |
| # openAIApiVersion: <string> | |
| # openAIBasePath: <string> | |
| # deploymentName: <string> | |
| # temperature: <number> | |
| # maxTokens: <number> | |
| # timeout: <number> | |
| # maxRetries: <number> | |
| # modelKwargs: <object> | |
| AmazonBedrock: | |
| environment: | |
| AWS_ACCESS_KEY_ID: "" # Required if a global ~/.aws/credentials file is not present | |
| AWS_SECRET_ACCESS_KEY: "" # Required if a global ~/.aws/credentials file is not present | |
| AWS_DEFAULT_REGION: "" # Required | |
| provider: ChatBedrock | |
| args: | |
| model: meta.llama3-70b-instruct-v1:0 # Required | |
| ## Following keys are optional & only exist for documentation purposes | |
| # temperature: <number> | |
| # additionalModelRequestFields: <object> | |
| # configFilepath: <string> | |
| DeepSeek: | |
| environment: | |
| DEEPSEEK_API_KEY: "" # Required | |
| provider: ChatDeepSeek | |
| args: | |
| model: deepseek-chat # Required | |
| ## Following keys are optional & only exist for documentation purposes | |
| # temperature: <number> | |
| # maxTokens: <number> | |
| # timeout: <number> | |
| # maxRetries: <number> | |
| # modelKwargs: <object> | |
| GoogleGenAI: | |
| environment: | |
| GOOGLE_API_KEY: "" # Required | |
| provider: ChatGoogleGenerativeAI | |
| args: | |
| model: gemini-2.5-pro # Required | |
| ## Following keys are optional & only exist for documentation purposes | |
| # apiVersion: <string> | |
| # baseUrl: <string> | |
| # temperature: <number> | |
| # If running locally https://ollama.com/, get the model name via `ollama list` | |
| ChatOllama: | |
| provider: ChatOllama | |
| args: | |
| model: your-model-here # Required | |
| ## Following keys are optional & only exist for documentation purposes | |
| # temperature: <number> | |
| # numPredict: <number> | |
| JustAnExample: | |
| environment: | |
| ANY_KEY_1: "any environment variable needed for this model provider" | |
| ANY_KEY_2: "any environment variable needed for this model provider" | |
| provider: "provider-string" | |
| args: | |
| anyArgumentName1: "argument one" | |
| anyArgumentName2: "argument two" | |
| any-argument-name-3: "argument three" | |
| template: "template string" # optional | |
| llamaHeader: "header string" # optional | |
| llmRetries: 5 # optional number, defaults to 5 | |
| llmRetryDelay: 10.0 # optional float, default is 10.0 | |
| podman_granite: &active | |
| provider: "ChatOpenAI" | |
| environment: | |
| OPENAI_API_KEY: "unused value" | |
| args: | |
| model: "ibm-granite/granite-3.3-8b-instruct-GGUF" | |
| configuration: | |
| baseURL: "http://localhost:56885/v1" | |
| # This is the node used for configuring the server. A simple anchor/reference | |
| # pair is an easy way to to select a configuration. To change configs, move the | |
| # `&active` anchor to the desired block and restart the server. | |
| active: *active |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment