Class Assistant

  • All Implemented Interfaces:

    @Deprecated(message = "deprecated") 
    public final class Assistant
    
                        

    Represents an assistant that can call the model and use tools.

    • Constructor Detail

    • Method Detail

      • id

         final String id()

        The identifier, which can be referenced in API endpoints.

      • createdAt

         final Long createdAt()

        The Unix timestamp (in seconds) for when the assistant was created.

      • instructions

         final Optional<String> instructions()

        The system instructions that the assistant uses. The maximum length is 256,000 characters.

      • metadata

         final Optional<Assistant.Metadata> metadata()

        Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

        Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.

      • name

         final Optional<String> name()

        The name of the assistant. The maximum length is 256 characters.

      • _object_

         final JsonValue _object_()

        The object type, which is always assistant.

        Expected to always return the following:

        JsonValue.from("assistant")

        However, this method can be useful for debugging and logging (e.g. if the server responded with an unexpected value).

      • tools

         final List<AssistantTool> tools()

        A list of tool enabled on the assistant. There can be a maximum of 128 tools per assistant. Tools can be of types code_interpreter, file_search, or function.

      • responseFormat

         final Optional<AssistantResponseFormatOption> responseFormat()

        Specifies the format that the model must output. Compatible with GPT-4o, GPT-4 * Turbo, and all GPT-3.5 Turbo models since gpt-3.5-turbo-1106.

        Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.

        Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON.

        Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length.

      • temperature

         final Optional<Double> temperature()

        What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic.

      • toolResources

         final Optional<Assistant.ToolResources> toolResources()

        A set of resources that are used by the assistant's tools. The resources are specific to the type of tool. For example, the code_interpreter tool requires a list of file IDs, while the file_search tool requires a list of vector store IDs.

      • topP

         final Optional<Double> topP()

        An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered.

        We generally recommend altering this or temperature but not both.

      • _id

         final JsonField<String> _id()

        Returns the raw JSON value of id.

        Unlike id, this method doesn't throw if the JSON field has an unexpected type.

      • _model

         final JsonField<String> _model()

        Returns the raw JSON value of model.

        Unlike model, this method doesn't throw if the JSON field has an unexpected type.

      • _name

         final JsonField<String> _name()

        Returns the raw JSON value of name.

        Unlike name, this method doesn't throw if the JSON field has an unexpected type.

      • _topP

         final JsonField<Double> _topP()

        Returns the raw JSON value of topP.

        Unlike topP, this method doesn't throw if the JSON field has an unexpected type.

      • validate

         final Assistant validate()

        Validates that the types of all values in this object match their expected types recursively.

        This method is not forwards compatible with new types from the API for existing fields.

      • builder

         final static Assistant.Builder builder()

        Returns a mutable builder for constructing an instance of Assistant.

        The following fields are required:

        .id()
        .createdAt()
        .description()
        .instructions()
        .metadata()
        .model()
        .name()
        .tools()