DeepFellow DOCS

OllamaChatRequest

PropertyTypeRequiredDescription
modelstringYesModel ID used to generate the response, like gemma3 or llama3.2. Deepfellow supports a wide range of models with different capabilities, and performance characteristics.
messagesOllamaChatMessage[]YesA list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text and images.
toolsOllamaToolDefinition[] | nullNoA list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.
thinkboolean | enum | nullNoFor thinking models: whether the model should think before responding. Can be a boolean or effort level.
formatstring | object | nullNoThe format to return a response in. Can be json or a JSON schema object.
optionsOllamaOptions | nullNoAdditional model parameters such as temperature, top_k, top_p and others.
streambooleanNoIf false the response will be returned as a single response object, rather than a stream of objects. Default: true.
keep_alivestring | integer | nullNoControls how long the model will stay loaded into memory following the request (default: 5m).
logprobsboolean | nullNoReturn log probabilities of the output tokens.
top_logprobsinteger | nullNoNumber of most likely tokens to return at each token position.

We use cookies on our website. We use them to ensure proper functioning of the site and, if you agree, for purposes such as analytics, marketing, and targeting ads.