Skip to content

Instantly share code, notes, and snippets.

@jwmatthews
Created December 5, 2025 13:33
Show Gist options
  • Select an option

  • Save jwmatthews/67ff87421461fc0896ac8f8d50e05317 to your computer and use it in GitHub Desktop.

Select an option

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 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