Package ai.docling.serve.api.convert.request.options

Class VlmModelApi

java.lang.Object
ai.docling.serve.api.convert.request.options.VlmModelApi
public class VlmModelApi extends Object
API details for using a vision-language model for the VLM pipeline.

  • Method Details

    • builder

      public static @NonNull VlmModelApi.Builder builder()

    • toBuilder

      public @NonNull VlmModelApi.Builder toBuilder()

    • getUrl

      public @Nullable URI getUrl()
      Endpoint which accepts openai-api compatible requests.
      Returns:
      the API endpoint URL, or null if not specified

    • getHeaders

      public Map<String,Object> getHeaders()
      Headers used for calling the API endpoint. For example, it could include authentication headers.
      Returns:
      the map of HTTP headers

    • getParams

      public Map<String,Object> getParams()
      Model parameters.
      Returns:
      the map of model parameters

    • getTimeout

      public @Nullable Duration getTimeout()
      Timeout for the API request.
      Returns:
      the timeout duration, or null if not specified

    • getConcurrency

      public @Nullable Integer getConcurrency()
      Maximum number of concurrent requests to the API.
      Returns:
      the maximum concurrency, or null if not specified

    • getPrompt

      public @Nullable String getPrompt()
      Prompt used when calling the vision-language model.
      Returns:
      the prompt text, or null if not specified

    • getScale

      public @Nullable Integer getScale()
      Scale factor of the images used.
      Returns:
      the image scale factor, or null if not specified

    • getResponseFormat

      public @Nullable ResponseFormat getResponseFormat()
      Type of response generated by the model.
      Returns:
      the response format, or null if not specified

    • toString

      public @NonNull String toString()
      Overrides:
      toString in class Object