Implementation:Open compass VLMEvalKit RBdashMMChat3Wrapper

Field	Value
source	VLMEvalKit
domain	Vision, API_Integration

Overview

RBdashMMChat3Wrapper provides a VLMEvalKit API adapter for the RBDash-MM Chat 3 vision-language model.

Description

RBdashMMChat3Wrapper inherits from BaseAPI and communicates with an LMDeploy-served RBDash-MM Chat 3 model endpoint. It uses a custom prompt utility (RBdashMMChat3_PromptUtil) that includes dataset-specific prompt construction with chain-of-thought reasoning, boxed answer extraction, and think-tag content processing for structured reasoning outputs.

Usage

Use this adapter when evaluating the RBDash-MM Chat 3 model deployed via an LMDeploy-compatible API server.

Code Reference

Source: vlmeval/api/rbdashmm_chat3_api.py, Lines: L1-527
Import: from vlmeval.api.rbdashmm_chat3_api import RBdashMMChat3Wrapper

Signature:

class RBdashMMChat3Wrapper(BaseAPI):
    def __init__(self, model=None, retry=5, key='sk-123456', verbose=True,
                 temperature=0.0, timeout=300, api_base=None,
                 system_prompt=None, max_tokens=16384, **kwargs): ...
    def generate_inner(self, inputs, **kwargs): ...

I/O Contract

Direction	Description
Inputs	message — text/image/video content list; model-specific params via kwargs
Outputs	generate() returns str prediction; generate_inner() returns (int, str, str) tuple

Usage Examples

# Example instantiation
model = RBdashMMChat3Wrapper(model='rbdash-mm-chat3', api_base='http://localhost:23333/v1')
response = model.generate(message)

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.

Principle

Implementation

Heuristic

Environment