Fara-7B

by microsoft

7B vision-language model for UI, web, and action-oriented visual reasoning

13.6Kdl/month

608likes

7Bparams

HuggingFace Use in Pipeline

Identifiers

Model ID

microsoft/Fara-7B

Feature URI

mixpeek://image_extractor@v1/microsoft_fara_7b_v1

Overview

Fara-7B is Microsoft's compact image-text model for agents that need to inspect visual state before deciding what to do next. It is built on the Qwen2.5-VL family and is tagged for multimodal, conversational image-text reasoning on Hugging Face.

On Mixpeek, Fara-7B is useful for screenshot, web page, and workflow indexing. It can turn screen states, app recordings, and UI evidence into searchable descriptions so an agent can retrieve the exact visual context behind a prior action.

Architecture

Qwen2.5-VL-family image-text-to-text transformer. 7B parameters. Supports conversational visual reasoning over screenshots and images.

Mixpeek SDK Integration

from mixpeek import Mixpeek

mixpeek = Mixpeek(api_key="YOUR_API_KEY")

mixpeek.ingest.images(
    collection="agent_screenshots",
    source={"type": "s3", "bucket": "ui-agent-runs"},
    pipeline={
        "captioning": {
            "model": "mixpeek://image_extractor@v1/microsoft_fara_7b_v1"
        }
    }
)