Chat Models¶

Forage supports multiple LLM providers. Select one with the model.kind property.

Available Providers¶

Name	Description
`azure-openai`	OpenAI models hosted on Microsoft Azure
`openai`	OpenAI API-compatible models
`ollama`	Locally-hosted models via Ollama (Llama, Mistral, etc.)
`google-gemini`	Google Gemini models
`anthropic`	Anthropic Claude models
`bedrock`	Amazon Bedrock multi-model provider supporting Claude, Llama, Titan, Cohere, and Mistral
`dashscope`	Alibaba Cloud Qwen models via DashScope (placeholder)
`hugging-face`	Open-source models via HuggingFace Inference API
`local-ai`	Self-hosted models via LocalAI (OpenAI-compatible)
`mistral-ai`	Mistral AI models
`watsonx-ai`	IBM Watsonx.ai models

Ollama¶

Locally-hosted models via Ollama.

forage.myAgent.agent.model.kind=ollama
forage.myAgent.agent.model.name=granite4:3b
forage.myAgent.agent.base.url=http://localhost:11434

Property	Description	Type	Default
`forage.ollama.base.url`	The base URL of the Ollama server	`string`	`http://localhost:11434`
`forage.ollama.model.name`	The Ollama model to use	`string`	`llama3`
`forage.ollama.temperature`	Temperature for response randomness (0.0-2.0)	`double`
`forage.ollama.num.ctx`	Context window size	`integer`
`forage.ollama.timeout`	Request timeout duration in ISO-8601 format (e.g. PT120S for 120 seconds)	`string`

Advanced

Property	Description	Type
`forage.ollama.top.k`	Top-K sampling parameter	`integer`
`forage.ollama.top.p`	Top-P (nucleus) sampling parameter (0.0-1.0)	`double`
`forage.ollama.min.p`	Minimum probability threshold (0.0-1.0)	`double`
`forage.ollama.log.requests`	Enable request logging	`boolean`
`forage.ollama.log.responses`	Enable response logging	`boolean`

OpenAI¶

OpenAI API and compatible endpoints.

forage.myAgent.agent.model.kind=openai
forage.myAgent.agent.model.name=gpt-4o
forage.myAgent.agent.api.key=${OPENAI_API_KEY}

Property	Description	Type	Default	Required
`forage.openai.model.name`	The specific OpenAI model to use	`string`	`gpt-3.5-turbo`	Yes
`forage.openai.base.url`	Custom base URL for OpenAI API	`string`
`forage.openai.temperature`	Temperature for response randomness (0.0-2.0)	`double`

Security

Property	Description	Type	Default	Required
`forage.openai.api.key`	OpenAI API key for authentication	`password`		Yes

Advanced

Property	Description	Type
`forage.openai.max.tokens`	Maximum number of tokens to generate	`integer`
`forage.openai.top.p`	Top-P (nucleus) sampling parameter (0.0-1.0)	`double`
`forage.openai.frequency.penalty`	Frequency penalty (-2.0 to 2.0)	`double`
`forage.openai.presence.penalty`	Presence penalty (-2.0 to 2.0)	`double`
`forage.openai.log.requests`	Enable request logging	`boolean`
`forage.openai.log.responses`	Enable response logging	`boolean`
`forage.openai.timeout`	Request timeout duration	`string`
`forage.openai.http1`	Use HTTP/1.1 instead of HTTP/2	`boolean`

Google Gemini¶

Google's Gemini models.

forage.myAgent.agent.model.kind=google-gemini
forage.myAgent.agent.model.name=gemini-2.5-flash-lite
forage.myAgent.agent.api.key=${GOOGLE_API_KEY}

Property	Description	Type	Required
`forage.google.api.key`	Google AI API key for authentication	`password`	Yes
`forage.google.model.name`	Google Gemini model name (e.g., gemini-pro, gemini-pro-vision, gemini-1.5-pro)	`string`	Yes
`forage.google.temperature`	Temperature for response randomness (0.0-2.0)	`double`

Advanced

Property	Description	Type	Default	Required
`forage.google.timeout`	Request timeout in seconds	`integer`
`forage.google.log.requests`	Enable request and response logging	`boolean`

Anthropic¶

Anthropic's Claude models.

forage.myAgent.agent.model.kind=anthropic
forage.myAgent.agent.model.name=claude-sonnet-4-20250514
forage.myAgent.agent.api.key=${ANTHROPIC_API_KEY}

Property	Description	Type	Default	Required
`forage.anthropic.api.key`	Anthropic API key for authentication	`password`		Yes
`forage.anthropic.model.name`	Claude model name (e.g., claude-3-haiku-20240307, claude-3-sonnet-20240229, claude-3-opus-20240229)	`string`	`claude-3-haiku-20240307`
`forage.anthropic.temperature`	Temperature for response generation (0.0-1.0): lower values are more deterministic, higher values are more creative	`double`
`forage.anthropic.max.tokens`	Maximum number of tokens in the model's response	`integer`

Advanced

Property	Description	Type
`forage.anthropic.top.p`	Top-p (nucleus sampling) probability threshold (0.0-1.0)	`double`
`forage.anthropic.top.k`	Top-k sampling parameter: limits the model to consider only the top-k most probable tokens	`integer`
`forage.anthropic.stop.sequences`	Comma-separated stop sequences that cause the model to stop generating further tokens	`string`
`forage.anthropic.timeout`	Request timeout in seconds	`integer`
`forage.anthropic.max.retries`	Maximum number of retry attempts for failed requests	`integer`
`forage.anthropic.log.requests.and.responses`	Enable logging of requests and responses (warning: may log sensitive data)	`boolean`

Azure OpenAI¶

Azure-hosted OpenAI models.

forage.myAgent.agent.model.kind=azure-openai
forage.myAgent.agent.endpoint=https://my-resource.openai.azure.com
forage.myAgent.agent.deployment.name=my-deployment
forage.myAgent.agent.api.key=${AZURE_OPENAI_KEY}

Property	Description	Type	Required
`forage.azure.openai.api.key`	Azure OpenAI API key for authentication	`password`	Yes
`forage.azure.openai.endpoint`	Azure OpenAI resource endpoint URL (e.g., https://your-resource.openai.azure.com/)	`string`	Yes
`forage.azure.openai.deployment.name`	Azure OpenAI deployment name (e.g., gpt-35-turbo, gpt-4)	`string`	Yes
`forage.azure.openai.service.version`	Azure OpenAI API service version (e.g., 2024-02-01)	`string`
`forage.azure.openai.temperature`	Temperature for response generation (0.0-2.0): lower values are more deterministic, higher values are more creative	`double`
`forage.azure.openai.max.tokens`	Maximum number of tokens in the model's response	`integer`

Advanced

Property	Description	Type
`forage.azure.openai.top.p`	Top-p (nucleus sampling) probability threshold (0.0-1.0)	`double`
`forage.azure.openai.presence.penalty`	Presence penalty for discouraging new topic introduction (-2.0 to 2.0)	`double`
`forage.azure.openai.frequency.penalty`	Frequency penalty for discouraging token repetition (-2.0 to 2.0)	`double`
`forage.azure.openai.seed`	Seed for deterministic response generation (same seed + same input = similar output)	`integer`
`forage.azure.openai.user`	User identifier for tracking and monitoring API usage	`string`
`forage.azure.openai.timeout`	Request timeout in seconds	`integer`
`forage.azure.openai.max.retries`	Maximum number of retry attempts for failed requests	`integer`
`forage.azure.openai.log.requests.and.responses`	Enable logging of requests and responses (warning: may log sensitive data)	`boolean`

Amazon Bedrock¶

AWS Bedrock models.

forage.myAgent.agent.model.kind=bedrock
forage.myAgent.agent.model.name=anthropic.claude-v2

Property	Description	Type	Default	Required
`forage.bedrock.region`	AWS region where Bedrock is available	`string`	`us-east-1`	Yes
`forage.bedrock.model.id`	Bedrock model identifier (e.g., anthropic.claude-3-5-sonnet-20240620-v1:0)	`string`
`forage.bedrock.temperature`	Sampling temperature for response randomness (0.0-1.0)	`double`		Yes

Security

Property	Description	Type	Default	Required
`forage.bedrock.access.key.id`	AWS access key ID (optional, uses default credential chain if not provided)	`password`		Yes
`forage.bedrock.secret.access.key`	AWS secret access key (optional, uses default credential chain if not provided)	`password`		Yes

Advanced

Property	Description	Type	Default	Required
`forage.bedrock.max.tokens`	Maximum number of tokens to generate	`integer`		Yes
`forage.bedrock.top.p`	Top-P (nucleus) sampling parameter (0.0-1.0)	`double`		Yes

WatsonX AI¶

IBM WatsonX AI models.

forage.myAgent.agent.model.kind=watsonx-ai
forage.myAgent.agent.model.name=ibm/granite-34b-code-instruct
forage.myAgent.agent.api.key=${WATSONX_API_KEY}

Property	Description	Type	Default	Required
`forage.watsonxai.api.key`	IBM Cloud API key for authentication	`password`		Yes
`forage.watsonxai.url`	The Watsonx.ai service URL (e.g., https://us-south.ml.cloud.ibm.com)	`string`		Yes
`forage.watsonxai.project.id`	The Watsonx.ai project ID	`string`		Yes
`forage.watsonxai.model.name`	The foundation model to use	`string`	`llama-3-405b-instruct`
`forage.watsonxai.temperature`	Temperature for response generation (0.0-2.0)	`double`

Advanced

Property	Description	Type
`forage.watsonxai.max.new.tokens`	Maximum number of new tokens in response	`integer`
`forage.watsonxai.top.p`	Top-p (nucleus sampling) parameter (0.0-1.0)	`double`
`forage.watsonxai.top.k`	Top-k sampling parameter	`integer`
`forage.watsonxai.random.seed`	Random seed for reproducible results	`integer`
`forage.watsonxai.repetition.penalty`	Penalty for repetition (1.0-2.0)	`double`
`forage.watsonxai.min.new.tokens`	Minimum number of new tokens in response	`integer`
`forage.watsonxai.stop.sequences`	Stop sequences for response generation (comma-separated)	`string`
`forage.watsonxai.timeout`	Request timeout in seconds	`integer`
`forage.watsonxai.max.retries`	Maximum number of retry attempts	`integer`
`forage.watsonxai.log.requests.and.responses`	Enable request and response logging	`boolean`

Mistral AI¶

forage.myAgent.agent.model.kind=mistral-ai
forage.myAgent.agent.model.name=mistral-large-latest
forage.myAgent.agent.api.key=${MISTRAL_API_KEY}

Property	Description	Type	Default	Required
`forage.mistralai.api.key`	MistralAI API key for authentication	`password`		Yes
`forage.mistralai.model.name`	The MistralAI model to use	`string`	`mistral-large-latest`
`forage.mistralai.temperature`	Temperature for response generation (0.0-1.0)	`double`

Advanced

Property	Description	Type
`forage.mistralai.max.tokens`	Maximum number of tokens for model responses	`integer`
`forage.mistralai.top.p`	Top-p (nucleus sampling) parameter (0.0-1.0)	`double`
`forage.mistralai.random.seed`	Random seed for reproducible results	`integer`
`forage.mistralai.timeout`	Request timeout in seconds	`integer`
`forage.mistralai.max.retries`	Maximum number of retry attempts	`integer`
`forage.mistralai.log.requests.and.responses`	Enable request and response logging	`boolean`

Hugging Face¶

forage.myAgent.agent.model.kind=hugging-face
forage.myAgent.agent.model.name=meta-llama/Llama-2-7b-chat-hf
forage.myAgent.agent.api.key=${HF_API_KEY}

Property	Description	Type	Required
`forage.huggingface.api.key`	HuggingFace API key for authentication	`password`	Yes
`forage.huggingface.model.id`	The HuggingFace model ID to use (e.g., microsoft/DialoGPT-medium)	`string`
`forage.huggingface.temperature`	Temperature for response generation (0.0-2.0)	`double`
`forage.huggingface.max.new.tokens`	Maximum number of new tokens to generate	`integer`

Advanced

Property	Description	Type
`forage.huggingface.top.k`	Top-k sampling parameter	`integer`
`forage.huggingface.top.p`	Top-p (nucleus) sampling parameter	`double`
`forage.huggingface.do.sample`	Whether to use sampling for text generation	`boolean`
`forage.huggingface.repetition.penalty`	Penalty for repeating tokens (1.0-2.0)	`double`
`forage.huggingface.return.full.text`	Whether to return full text including input	`boolean`
`forage.huggingface.wait.for.model`	Whether to wait for the model to load if it's not ready	`boolean`
`forage.huggingface.timeout`	Request timeout in seconds	`integer`
`forage.huggingface.max.retries`	Maximum number of retry attempts	`integer`
`forage.huggingface.log.requests.and.responses`	Enable request and response logging	`boolean`

DashScope¶

Alibaba Cloud's DashScope models.

forage.myAgent.agent.model.kind=dashscope
forage.myAgent.agent.model.name=qwen-turbo
forage.myAgent.agent.api.key=${DASHSCOPE_API_KEY}

Property	Description	Type	Default	Required
`forage.dashscope.api.key`	Alibaba Dashscope API key for authentication	`password`		Yes
`forage.dashscope.model.name`	Qwen model name (e.g., qwen-turbo, qwen-plus, qwen-max, qwen-max-longcontext)	`string`	`qwen-turbo`
`forage.dashscope.temperature`	Temperature for response generation (0.0-2.0): lower values are more deterministic, higher values are more creative	`double`
`forage.dashscope.max.tokens`	Maximum number of tokens in the model's response	`integer`

Advanced

Property	Description	Type
`forage.dashscope.top.p`	Top-p (nucleus sampling) probability threshold (0.0-1.0)	`double`
`forage.dashscope.top.k`	Top-k sampling parameter: limits the model to consider only the top-k most probable tokens	`integer`
`forage.dashscope.repetition.penalty`	Repetition penalty for discouraging token repetition (0.0-2.0)	`double`
`forage.dashscope.seed`	Seed for deterministic response generation (same seed + same input = similar output)	`integer`
`forage.dashscope.enable.search`	Enable web search functionality to provide more up-to-date information	`boolean`
`forage.dashscope.timeout`	Request timeout in seconds	`integer`
`forage.dashscope.max.retries`	Maximum number of retry attempts for failed requests	`integer`
`forage.dashscope.log.requests.and.responses`	Enable logging of requests and responses (warning: may log sensitive data)	`boolean`

LocalAI¶

Self-hosted models via LocalAI.

forage.myAgent.agent.model.kind=local-ai
forage.myAgent.agent.model.name=gpt-4
forage.myAgent.agent.base.url=http://localhost:8080

Property	Description	Type	Required
`forage.localai.base.url`	The LocalAI server endpoint URL	`string`	Yes
`forage.localai.model.name`	The model to use (must be available on LocalAI server)	`string`
`forage.localai.temperature`	Temperature for response generation (0.0-2.0)	`double`
`forage.localai.user`	User identifier for tracking and monitoring	`string`

Security

Property	Description	Type	Default	Required
`forage.localai.api.key`	LocalAI API key for authentication (optional)	`password`

Advanced

Property	Description	Type
`forage.localai.max.tokens`	Maximum number of tokens for model responses	`integer`
`forage.localai.top.p`	Top-p (nucleus sampling) probability threshold (0.0-1.0)	`double`
`forage.localai.presence.penalty`	Presence penalty for discouraging new topic introduction (-2.0 to 2.0)	`double`
`forage.localai.frequency.penalty`	Frequency penalty for discouraging token repetition (-2.0 to 2.0)	`double`
`forage.localai.seed`	Seed for deterministic response generation	`integer`
`forage.localai.timeout`	Request timeout in seconds	`integer`
`forage.localai.max.retries`	Maximum number of retry attempts for failed requests	`integer`
`forage.localai.log.requests.and.responses`	Enable request and response logging	`boolean`