Jump to content

Connect SuperML | Leeroopedia MCP: Equip your AI agents with best practices, code verification, and debugging knowledge. Powered by Leeroo — building Organizational Superintelligence. Contact us at founders@leeroo.com.

Implementation:Open compass VLMEvalKit Reka Wrapper

From Leeroopedia
Revision as of 13:31, 16 February 2026 by Admin (talk | contribs) (Auto-imported from implementations/Open_compass_VLMEvalKit_Reka_Wrapper.md)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
Field Value
source VLMEvalKit
domain Vision, API_Integration

Overview

Reka_Wrapper provides a VLMEvalKit API adapter for Reka AI vision-language models.

Description

Reka_Wrapper inherits from BaseAPI and uses the reka Python SDK to communicate with Reka's chat API. It converts images to base64 data URIs for transmission, supports configurable temperature and output length parameters, and authenticates via the REKA_API_KEY environment variable. The INTERLEAVE flag is set to False.

Usage

Use this adapter when evaluating Reka AI models (such as reka-flash-20240226) through the Reka API.

Code Reference

  • Source: vlmeval/api/reka.py, Lines: L1-59
  • Import: from vlmeval.api.reka import Reka_Wrapper

Signature:

class Reka_Wrapper(BaseAPI):
    def __init__(self, model='reka-flash-20240226', key=None, retry=10,
                 system_prompt=None, verbose=True, temperature=0,
                 max_tokens=1024, **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 = Reka_Wrapper(model='reka-flash-20240226')
response = model.generate(message)

Related Pages

Page Connections

Double-click a node to navigate. Hold to expand connections.
Principle
Implementation
Heuristic
Environment