How to Distill Gemini Into an Edge Model Roboflow published a guide for distilling Gemini into an edge inspection model: Gemini auto-labels screw images through a class description, the Auto Label agent, or an Open Prompt Workflow, a human reviews and corrects the boxes, and a compact RF-DETR Small detector is then trained to run next to the camera while uncertain cases route back to Gemini or a person. The guide specifies one bounding box per full visible fastener region and warns that the expected count of four screws is an application rule that should not force the teacher model to produce four boxes when a screw is missing. To distill Gemini into an edge model, have Gemini label your images, review and correct those labels, then train a small detector that runs next to the camera and does the routine inspections. In Roboflow, auto-label with Gemini through a class description, the Auto Label agent or an Open Prompt Workflow. Then train RF-DETR Small on the reviewed dataset, run it with Inference on your edge device, and route uncertain cases back to Gemini or a human reviewer. Checking an assembly for missing screws takes more than counting detections. A model might miss one screw and mistake a reflection for another, returning the expected count while overlooking an incomplete product. A useful inspection system needs to locate the visible screws at each mounting position and flag images that need further review. With Roboflow, you can use Gemini to help build the training dataset for that system, then train a compact RF-DETR opens in a new tab model to detect screws near the camera. In this approach to model distillation, Gemini generates candidate bounding boxes, you review and correct the annotations, and RF-DETR learns the specific detection task. At deployment, the smaller model handles routine detection, while routing logic sends selected difficult images to Gemini or a person for review. In this guide, you’ll explore three ways to prompt Gemini for screw annotations: class descriptions in Roboflow Auto Label, conversational feedback with the Auto Label agent, and an Open Prompt Workflow that returns boxes for inspection in Python. You’ll then review the labels, train RF-DETR Small, test it on your edge hardware, and configure a fallback for uncertain results. Prompting Gemini for boxes in a consistent format Before generating labels, decide exactly what one object means. In our reference image, each screw annotation covers the full visible fastener region, including its outer exposed end and inner metal feature. One screw receives one box. This definition must stay the same across the dataset. Paste the description below into Describe what it looks like optional . Gemini searches using that description, and Auto Label saves each resulting annotation as screw. A vertically oriented metal screw at an upper or lower mounting position on the product's central structure. Draw one box around the full visible fastener region, including the outer exposed end and inner metal feature. Keep the visible components of one screw inside one box. Exclude empty positions, plastic ribs, circular plastic features, and reflections. Label only screws that are visible. Do not add a box just because a screw is expected at that position. The expected count of four is an application rule. It should not force the teacher to produce four boxes when a screw is missing. Option B: Use the Auto Label agent You can also describe the labeling task through Chat with Auto Label agent. The agent builds a labeling Workflow from the model and classes and shows a preview. Use the conversation to refine what it should label. The saved annotations still need a class name, which remains screw in this example. See labeling with the Auto Label agent opens in a new tab . With Gemini 4 Carbon selected, open Chat with Auto Label agent and enter the following request. Use Gemini 4 Carbon to label the screws in these assembly-station images. Use one class named screw. Draw one bounding box around each full visible fastener region, including its outer exposed end and inner metal feature. Keep the components of one screw together in one box. The complete assembly has four screw positions, but label only screws that are visible. Do not add boxes for empty positions. Exclude plastic ribs, circular plastic features, and reflections. Show a preview first. Check the preview and request specific corrections. You can use the following correction when that error appears. The lower-left screw is missing a box. Include its full visible fastener region. Keep the class name screw and show the updated preview. You can also click an incorrect label or use Flag missing object. Once the preview matches the annotation rule, choose Use this Workflow, confirm the output-class mapping to screw, and select Label batch. Review the job estimate before starting. Continue with the label review in Section 2. This conversation configures the Auto Label Workflow. Gemini 4 Carbon remains the requested annotation model. Check that the saved Workflow uses it. Either setup option produces the same kind of training data for RF-DETR Small. The training examples contain reviewed screw bounding boxes. Option C: Use Open Prompt in a Roboflow Workflow For this option, you can choose any Gemini model available in the Roboflow Google Gemini block opens in a new tab that supports image input and Open Prompt. You can also try different available models with the same prompt and images to compare their bounding boxes. Understand Gemini's normalized box format For the Auto Label process above, Roboflow manages the saved annotations. Use the description field or the Auto Label agent conversation above. Neither option requires you to enter a JSON-format prompt or convert coordinates yourself. If you inspect raw Gemini detection output, Google's official object detection documentation opens in a new tab specifies box 2d in ymin, xmin, ymax, xmax order, normalized to 0–1000. Normalization expresses a position relative to the image dimensions. A value of 500 is halfway across the relevant dimension, regardless of image size. Use the following conversion for an image of width W and height H. xmin pixels = xmin × W / 1000 xmax pixels = xmax × W / 1000 ymin pixels = ymin × H / 1000 ymax pixels = ymax × H / 1000 For example, 100, 200, 300, 250 on a 1000-pixel-wide, 600-pixel-high image gives pixel bounds xmin=200, ymin=60, xmax=250, ymax=180. This is a coordinate example, not a measured screw prediction. Build the Workflow Prompting Gemini for boxes in a consistent format gives the visualization code a clear schema to check. Gemini models can still format their answers differently even when they receive the same instructions. This Open Prompt test uses a consistent box 2d schema and a model-independent parser. The prompt requests the screw label and ymin, xmin, ymax, xmax coordinates normalized to 0–1000. The script accepts known JSON formatting differences, but checks the coordinates before drawing them. This follows Gemini’s object-detection coordinate convention opens in a new tab . The parser uses the requested coordinate order and scale. Numeric checks alone cannot prove that Gemini followed those instructions, so inspect the drawn boxes. Build this small test separately from Auto Label. Use an image input, a text input for the prompt, one Google Gemini block, and two outputs. Follow Build a Workflow opens in a new tab . Create a Workflow with an image input named image and a text parameter input named prompt. Keep these names exactly as written so the Python code can pass both values. Add the Google Gemini block opens in a new tab and name it gemini boxes. Connect images to $inputs.image. Select Open Prompt unconstrained . For the block’s prompt property, select $inputs.prompt as an input reference rather than entering fixed text. Select any available Gemini model that can analyze the image. Use settings supported by that model and leave model-specific options at their defaults if unsure. For an editor test, paste the exact instructions below into the Workflow’s prompt input. The Python script uses the identical text in its PROMPT variable. Create two Workflow outputs. Name the first boxes json and select $steps.gemini boxes.output. Name the second prompt echo and select $inputs.prompt. The first returns Gemini’s raw answer and the second echoes the received prompt. Python checks prompt echo == PROMPT before parsing. This verifies the Workflow input, but you must still confirm that the Gemini block’s prompt property is actually connected to $inputs.prompt. Detect visible screws at the upper and lower mounting positions on the product's central structure. Use one box for each full visible fastener region, including its outer exposed end and inner metal feature. Exclude empty positions, plastic ribs, circular plastic features, and reflections. Do not add a screw because it is expected there. Return only a JSON list without Markdown fences or extra explanation. Use the key "label" with the value "screw" for every object. Use the key "box 2d" with ymin, xmin, ymax, xmax coordinates. Use integers normalized to 0–1000 relative to the full image. Return if no screw is visible. Test with an assembly image and supply the example text in the Workflow’s prompt input. Confirm that both outputs, boxes json and prompt echo, appear in the test response. Save the Workflow and use Deploy opens in a new tab to copy its workspace slug, Workflow ID, and API URL for Python. Open Prompt returns raw text, so it may contain a JSON array, a Markdown JSON code block, or an object with a boxes field. The same model may return a string nested under boxes json in a Workflow response. The script below removes recognized wrappers, parses one JSON result, and validates each box without depending on a model name. It also accepts recognized Gemini text-part wrappers and small amounts of text around one JSON value. The parser rejects malformed boxes and ambiguous output fields. Arrays must use box 2d. Alternate box fields must name their coordinates explicitly. Visualize the returned screw boxes Install the Inference SDK, Pillow, and NumPy in your Python environment. Shell python -m pip install inference-sdk Set ROBOFLOW API KEY in the same terminal using the commands in Section 4. Save the following code as visualize gemini boxes.py and put an input image beside it as inspection.jpg. Replace the workspace slug and Workflow ID. The example uses the hosted API, but you should use the API URL shown by Deploy. Make sure that gemini boxes.prompt uses $inputs.prompt, and that the Workflow returns prompt echo from $inputs.prompt. Otherwise, the script will not have evidence that the intended prompt was received. Python """Run a Roboflow Gemini Open Prompt Workflow and draw validated screw boxes. The parser depends on a documented JSON schema, not on a Gemini model name. The Workflow needs two outputs: boxes json and prompt echo. """ import json import math import os import re from pathlib import Path from PIL import Image, ImageDraw, ImageOps Configure the Gemini block's prompt as $inputs.prompt not hardcoded text . Use these same instructions for the editor's prompt input during testing. PROMPT = """Detect visible screws at the upper and lower mounting positions on the product's central structure. Use one box for each full visible fastener region, including its outer exposed end and inner metal feature. Exclude empty positions, plastic ribs, circular plastic features, and reflections. Do not add a screw because it is expected there. Return only a JSON list without Markdown fences or extra explanation. Use the key "label" with the value "screw" for every object. Use the key "box 2d" with ymin, xmin, ymax, xmax coordinates. Use integers normalized to 0–1000 relative to the full image. Return if no screw is visible.""" MAX TEXT = 1 000 000 MAX DEPTH = 15 MAX BOXES = 1000 WRAPPER KEYS = "boxes json", "boxes", "detections", "objects", "predictions", "output", "output text", "response", "result", "results", "data", "text", "message", "content", "candidates", "parts", def parse text text : """Accept JSON, one JSON fence, or prose surrounding one JSON value.""" source = text.strip .lstrip "\ufeff" .strip if not source or len source MAX TEXT: raise ValueError "Gemini response is empty or too long" try: return json.loads source except json.JSONDecodeError: if source.startswith " ", "{" : raise ValueError "Malformed JSON or multiple JSON values" fenced = list re.finditer r" ?:json ?\s \s\S ? \s ", source, flags=re.I if fenced: if len fenced = 1: raise ValueError "Expected exactly one JSON code block" block = fenced 0 outside = source :block.start + source block.end : if any char in outside for char in " {} " : raise ValueError "Ambiguous content outside the JSON code block" return json.loads block.group 1 .strip Parse from the first opening bracket. Never salvage an inner object from a malformed outer array or silently choose among multiple results. openings = p for p in source.find " " , source.find "{" if p = 0 if not openings: raise ValueError "Gemini did not return a JSON array or object" position = min openings value, consumed = json.JSONDecoder .raw decode source position: if any char in source position + consumed: for char in " {}" : raise ValueError "Multiple or malformed JSON values" return value def check coordinate metadata item : """Reject declared pixel, 0-1, or XYXY coordinates rather than misplot.""" for key in "coordinate system", "coordinate units", "units", "coordinate format", "box format", "coordinate order" : if key not in item: continue hint = str item key .strip .lower .replace " ", "" scale 01 = bool re.search r" ?< \d 0 ?:-|\.\. 1 ? \d ", hint if "pixel" in hint or "xyxy" in hint or "xmin,ymin" in hint or scale 01 or " 0,1 " in hint : raise ValueError f"Unsupported coordinate format specified in {key}: {item key r}" def unwrap value, depth=0 : """Remove common Roboflow, Gemini, and Open Prompt response wrappers.""" if depth = MAX DEPTH: raise ValueError "Gemini response has too many nested wrappers" if isinstance value, str : return unwrap parse text value , depth + 1 if isinstance value, list : if not value: return if all isinstance item, dict and "box 2d" in item or "bbox 2d" in item or "bounding box" in item for item in value : return value if len value == 1: return unwrap value 0 , depth + 1 raise ValueError "Expected detections or one Workflow response, not multiple responses" if isinstance value, dict : check coordinate metadata value if value.get "error status" is True: raise ValueError "The Gemini block reported an output-decoding error" if any k in value for k in "box 2d", "bbox 2d", "bounding box" : return value if "parts" in value and isinstance value "parts" , list : parts = value "parts" if all isinstance p, dict and isinstance p.get "text" , str for p in parts : return unwrap "".join p "text" for p in parts , depth + 1 keys = key for key in WRAPPER KEYS if key in value if len keys 1: raise ValueError "Multiple output fields; cannot choose a result safely" if keys: return unwrap value keys 0 , depth + 1 raise ValueError "No boxes json, boxes, or recognizable Gemini output field" raise ValueError f"Unsupported Gemini response type: {type value . name }" def number value, label : if isinstance value, bool : raise ValueError f"{label} must be a number" Gemini occasionally returns numeric JSON strings. Accept only simple numeric strings, not text, units, or expressions. if isinstance value, str and re.fullmatch r"\s +- ? ?:\d+ ?:\.\d ?|\.\d+ \s ", value : value = float value if not isinstance value, int, float or not math.isfinite value : raise ValueError f"{label} must be a finite number" if not 0 <= value <= 1000: raise ValueError f"{label} must be normalized between 0 and 1000" return value def coordinates item, index : keys = key for key in "box 2d", "bbox 2d", "bounding box" if key in item if len keys = 1: raise ValueError f"Detection {index} needs exactly one coordinate field" coords = item keys 0 if keys 0 = "box 2d" and not isinstance coords, dict : raise ValueError "Alternate box fields must use explicitly named coordinates" if isinstance coords, dict : Named coordinates make the order unambiguous. aliases = "ymin", "xmin", "ymax", "xmax" , "y min", "x min", "y max", "x max" , for names in aliases: if all name in coords for name in names : coords = coords name for name in names break if not isinstance coords, list, tuple or len coords = 4: raise ValueError f"Detection {index} needs box 2d ymin, xmin, ymax, xmax " "or a bounding box object with explicitly named coordinates" vals = number v, f"Detection {index} coordinate {i}" for i, v in enumerate coords, 1 ymin, xmin, ymax, xmax = vals if ymin = ymax or xmin = xmax: raise ValueError f"Detection {index} has a reversed or empty box" return vals def decode boxes response : """Normalize valid Gemini box JSON to {label, box 2d} . Assumes the prompt's ymin, xmin, ymax, xmax ordering and 0..1000 units. Unrecognized schemas fail clearly rather than drawing incorrect boxes. """ boxes = unwrap response if len boxes MAX BOXES: raise ValueError "Unexpectedly large number of detections" normalized = for index, item in enumerate boxes, 1 : if not isinstance item, dict : raise ValueError f"Detection {index} is not a JSON object" label = next item.get k for k in "label", "class", "class name" if k in item , None if not isinstance label, str or label.strip .casefold = "screw": raise ValueError f"Detection {index} has missing or unexpected label {label r}" check coordinate metadata item normalized.append {"label": "screw", "box 2d": coordinates item, index } return normalized def visualize image, boxes, output path : image = image.copy width, height = image.size draw = ImageDraw.Draw image for item in boxes: ymin, xmin, ymax, xmax = item "box 2d" left = min width - 1, max 0, math.floor xmin width / 1000 right = min width - 1, max left, math.ceil xmax width / 1000 - 1 top = min height - 1, max 0, math.floor ymin height / 1000 bottom = min height - 1, max top, math.ceil ymax height / 1000 - 1 draw.rectangle left, top, right, bottom , outline=" 6706CE", width=3 caption top = max 0, top - 18 draw.rectangle left, caption top, left + 45, caption top + 17 , fill=" 6706CE" draw.text left + 3, caption top + 2 , "screw", fill="white" image.save output path def verify workflow response results, prompt : """Check the same text reached the Workflow's named prompt input.""" if not isinstance results, list or len results = 1 or not isinstance results 0 , dict : raise ValueError "Expected one Roboflow Workflow result for one image" result = results 0 if "prompt echo" not in result: raise ValueError "Add a Workflow output named prompt echo selecting $inputs.prompt" if result "prompt echo" = prompt: raise ValueError "Prompt mismatch. Check the Workflow's prompt input and its output binding" if "boxes json" not in result: raise ValueError "Add a Workflow output named boxes json selecting $steps.gemini boxes.output" return result "boxes json" def main : import numpy as np from inference sdk import InferenceConfiguration, InferenceHTTPClient if not PROMPT.strip : raise ValueError "PROMPT must not be empty" image = ImageOps.exif transpose Image.open "inspection.jpg" .convert "RGB" client = InferenceHTTPClient api url="https://serverless.roboflow.com", api key=os.environ "ROBOFLOW API KEY" , .configure InferenceConfiguration api key transport="header" results = client.run workflow workspace name="YOUR WORKSPACE", workflow id="YOUR WORKFLOW ID", images={"image": np.asarray image :, :, ::-1 .copy }, parameters={"prompt": PROMPT}, use cache=False, Save the complete response and supplied prompt even if parsing fails. Path "gemini workflow response.json" .write text json.dumps results, ensure ascii=False, indent=2, default=str , encoding="utf-8" Path "gemini prompt.txt" .write text PROMPT, encoding="utf-8" raw = verify workflow response results, PROMPT Path "gemini boxes.txt" .write text raw if isinstance raw, str else json.dumps raw, ensure ascii=False, indent=2 , encoding="utf-8", boxes = decode boxes raw Path "gemini boxes normalized.json" .write text json.dumps boxes, indent=2 , encoding="utf-8" visualize image, boxes, "gemini boxes preview.png" print f"Saved gemini boxes preview.png with {len boxes } boxes for review" if not boxes: print "Gemini returned no boxes. This does not prove that screws are absent." if name == " main ": main Run the script in the same terminal. Shell python visualize gemini boxes.py Open gemini boxes preview.png to review each mounting position. The script saves the full result as gemini workflow response.json, the raw Gemini answer as gemini boxes.txt, the submitted text as gemini prompt.txt, and the checked detections as gemini boxes normalized.json. It stops if the prompt echo does not match or the JSON is malformed. use cache=False bypasses the normal Workflow definition cache for these tests. Save Workflow edits before running the script again. The parser handles direct JSON arrays, a single Markdown JSON fence, recognized nested wrappers, empty lists, and numeric strings. It checks labels, finite values, coordinate bounds, and box order. This is model-independent JSON parsing, not a guarantee that every Gemini model will detect the same objects or follow the schema. It can reject declared pixel or 0-1 coordinates, but cannot reliably identify an undeclared change in scale or order. Always compare the preview with the original image. An empty list does not prove that screws are absent. This check helps separate formatting mistakes from localization mistakes before teacher labels are used for student training. If you do not need Open Prompt for this test, the current Google Gemini Workflow block also provides an Object Detection task that decodes model responses into predictions. This article keeps Open Prompt to show how a consistent prompting and JSON parsing work across different model selections. The test saves local inspection files. It does not add annotations to your dataset. Continue with either Auto Label option and review the labels before training. Using this workflow you may test how different models detect and label the image. I tested it using four Gemini models such as Gemini 2.5 Pro, Gemini 3.1 Pro, Gemini 3.5 Flash-Lite and Gemini 4 Carbon. The results are following: Among these I found, Gemini 4 Carbon working best for my use case. For your use case there may be other cheaper model. You may also try other Gemini models available for the Google Gemini Block. This example workflow may further be enhanced to annotate the dataset. Know the teacher's limits A teacher can return a plausible object name and still place its box incorrectly. Consider the face-landmark comparison. Gemini 2.5 Flash Lite confuses side labels and places some regions away from the corresponding features. Its LEFT EYE box sits above the visible eye, while RIGHT CHEEK CENTER appears high on the forehead. Gemini 3.1 Pro places the regions more closely around the facial features in this example. This is a qualitative, single-image example. It does not establish a general accuracy ranking or measure Gemini 4 Carbon on the assembly task. The lesson for manufacturing is to check location as carefully as class. A screw label on a reflection, a missed mounting position, or two boxes on one fastener can produce the wrong inspection result. Pro's higher token cost also matters when generating many labels. Google's published standard paid API rates, in USD per million tokens, provide a direct cost comparison. Model Input Output, including thinking tokens Gemini 2.5 Flash-Lite $0.10 for text, image, and video $0.40 Gemini 3.1 Pro Preview, prompts up to 200,000 tokens $2.00 $12.00 Review the teacher on your own task Run the Auto Label preview on complete and incomplete products. Use Change to inspect other images and Run again after revising the description. Gemini box labels do not provide an adjustable confidence threshold in this interface, so inspect their locations and coverage directly. See evaluating Auto Label results opens in a new tab . Check every visible screw, including the upper and lower mounting positions. Look for missed targets, duplicate boxes, incorrect extents, and false detections on the surrounding structure. A total of four boxes can hide a missed screw and an extra false detection. Once the preview is satisfactory, choose Label batch, review the estimate, and run the job. Correct its labels in Roboflow Annotate. Add missed objects, remove false boxes, and resize boxes to match the reference rule. Add the checked images to the dataset. Optionally use a cheaper dedicated annotator for common classes A manufacturing dataset may contain common objects such as cartons, pallets, or people alongside product-specific components. If an existing dedicated detector recognizes the required common classes reliably and at lower measured cost, use it for those labels. Reserve Gemini for targets that need a custom visual description, such as the complete screw regions in this assembly. This is an option to compare, not a guaranteed saving. A dedicated model is useful only if its learned classes and box definitions match the dataset. A face detector cannot become a screw detector by renaming its output. Compare candidate annotators on a small human-labeled sample and include correction effort in the cost comparison. In Roboflow Auto Label, you can select a trained model from the same dataset or a saved Workflow compatible with the project type. Trained models use their learned classes rather than the description field. A Workflow requires output-class mapping before its labels are applied. For this tutorial, Gemini 4 Carbon is the selected teacher for the screw regions on the product. Test its preview against the reference annotations before proceeding. The dedicated-annotator route is optional. If a suitable detector later becomes available, compare it with Gemini using the same images and annotation rule. Review either source before training, and record which annotator produced each batch so repeated errors can be traced. Train RF-DETR and deploy on-device The teacher has now supplied task-specific training examples. RF-DETR Small learns to predict the screw boxes directly from images. The expected count remains separate application logic. Prepare the training and evaluation data Split images by product or capture session to keep near-duplicates out of different splits. Use corrected teacher labels for training and independent human annotations for validation and testing. Include missing screws at different mounting positions. Keep the final test set separate from prompt changes and threshold selection. Choose a single architecture, select RF-DETR, and choose Small. Select the reviewed dataset version, or choose Current Dataset and check its splits. Open Customize Training Recipe. Start with the Public checkpoint, review preprocessing and augmentation, and retain the supported defaults for a first run. Check the estimated duration and credit cost, then select Start Training. Training cost depends on job duration. Inspect precision, recall, and mAP in Training Results. Use Model Evaluation opens in a new tab to inspect per-class errors and threshold behavior. Automatic evaluations are available for versioned models trained or uploaded by paid users. Its confusion matrix includes validation and test images, so retain an untouched final holdout if you use those results for tuning. Then evaluate the assembly inspection task with the following checks. Inspect validation predictions for missed screws, duplicate boxes, and detections on plastic features. Choose the detector cutoff and fallback rules using validation images. A detector cutoff removes low-score predictions; a separate review threshold decides which returned predictions need more attention. Freeze those settings and evaluate the held-out test images against human annotations. Use the same intersection-over-union matching rule when comparing teacher and student boxes. Check the number and location of screws per product. Measure how often incomplete products are accepted and complete products are rejected or sent for review. Measure latency and completed images per second on the deployment device after warm-up. Include image capture and downstream processing when timing the complete inspection system. Four detections alone do not establish that every mounting position contains a screw. For a fixed camera, test a rule that requires one valid detection in each expected region. This is an application rule to validate with your images. For the Docker installation, prepare Docker and the GPU support required by your device. Then install the Inference CLI and the Inference SDK opens in a new tab . Shell pip install inference-cli inference-sdk inference server start The CLI selects the container for the machine and starts the local server on port 9001. Set your Roboflow API key in the same terminal where you will run the script. Use this command in Windows Anaconda Prompt. Shell set ROBOFLOW API KEY=YOUR ROBOFLOW API KEY Use this command on Linux or macOS. Shell export ROBOFLOW API KEY="YOUR ROBOFLOW API KEY" Save the following as run edge.py. Replace the model ID with the RF-DETR Small model ID you copied. Replace 0.20 with your validation-selected detector cutoff, and place a test image at inspection.jpg. Python python import json import os from inference sdk import InferenceHTTPClient, InferenceConfiguration client = InferenceHTTPClient api url="http://localhost:9001", api key=os.environ "ROBOFLOW API KEY" , .configure InferenceConfiguration api key transport="header", confidence threshold=0.20, Replace with your validated cutoff. result = client.infer "inspection.jpg", model id="YOUR RFDETR SMALL MODEL ID", predictions = result "predictions" screws = p for p in predictions if p "class" == "screw" expected count = 4 screw count = len screws print json.dumps { "expected count": expected count, "screw count": screw count, "count matches": screw count == expected count, "predictions": screws, }, indent=2 This example assumes a clear image of one product in the fixed inspection view. It counts the returned screw predictions after the configured detector cutoff. count matches is a count comparison, not a final assembly approval. Use the review rules in Section 5 before accepting the product. Missing or malformed responses must be handled as errors, not as a successful zero-screw inspection. Run the script. Shell python run edge.py The SDK sends the image to the local server, which runs the student. The first request downloads and initializes the model. Wait for this to finish before measuring normal request latency. The SDK configuration guide opens in a new tab covers the confidence setting and header authentication, which requires Inference Server opens in a new tab . Test a sequence of representative images after warm-up. Record median and 95th-percentile latency, then measure sustained completed images per second. For the full camera application, include capture, queues, and downstream processing in the timing. Additionally you can use benchmark edge.py for measuring sequential local image requests. Put representative images in a folder, then run the following command. Shell python code/benchmark edge.py test-images --model YOUR COPIED RFDETR SMALL MODEL ID --confidence 0.20 --output edge-benchmark.json Replace the model ID and set --confidence to the same cutoff used for evaluation. The output includes successful and failed request counts, median and 95th-percentile latency, and completed images per second. This benchmark measures requests to the server; it does not include camera capture or machine actions. Keep Gemini as the fallback for hard cases Distillation and routing work together. Distillation gives us a smaller model for the repeated task. Routing decides when that model's result needs a more expensive review. This extends How to Route Images Between Cheap and Expensive AI Models. That tutorial runs RF-DETR first, validates its predictions, and uses routing signals to choose a downstream model or human review. Here, RF-DETR Small can finish routine screw inspections locally, while selected hard cases go to Gemini. We adapt the routing signals to screw count, detection confidence, and mounting position instead of copying the wood-defect classes or thresholds. Student result Route Four valid screw detections satisfy the tested confidence and mounting-position rules Record the local screw-presence result. Unexpected count, low-confidence detection, or questionable box location in a usable image Send the original image and detection hints to Gemini. Invalid prediction data or an unusable image Capture another image or request human review. Gemini returns an invalid answer, remains uncertain, or disagrees with the evidence Keep the inspection unresolved for human review. Connect the fallback in Roboflow Workflows Use the Routing Images tutorial for the branching, response parsing, and validation pattern. Add a Google Gemini opens in a new tab block. Supply the original image, the expected mounting positions, and the student's detections as hints. Use structured answering for the review fields and validate the returned answer before acting on it. In the fallback Gemini block, select Structured Output Generation structured-answering , put the following text in prompt, and define the expected review fields in output structure. Include the student detection hints and their coordinate convention in the prompt. Use the following review prompt. Inspect the four screw mounting positions in this product image. The detector boxes are hints and may contain errors. Use image-left and image-right for all position names. For upper left, upper right, lower left, and lower right, report present, missing, or uncertain and describe the visible evidence. Do not infer a screw from the expected count. If glare, blur, or occlusion prevents a decision, report uncertain. The Auto Label teacher and this runtime reviewer are separate components. Selecting Gemini 4 Carbon during annotation does not create the fallback Workflow. Configure and evaluate the deployment-stage Gemini model separately. Follow Deploy a Workflow opens in a new tab to run the detector and routing logic through local Inference. Gemini calls still require network access. If review cannot complete, retain an unresolved result for later or human review. Finally, collect hard images for another labeling cycle. The Roboflow Dataset Upload block opens in a new tab can save images with Persist predictions set to false. Review their labels before adding them to training. This connects routing back to distillation. Difficult production cases help improve the next student model. Conclusion At a manufacturing inspection station, a small detector can handle the repeated task of locating screws while selected uncertain images receive further review. Consistent teacher annotations, independent evaluation, and clear fallback rules make this approach practical to test on the assembly line. Gemini helps build and improve the training data. RF-DETR small or nano runs the routine detection task near the camera. Start with a small batch in Roboflow, check the teacher's boxes, and train an RF-DETR baseline. Use the routing pattern to keep hard cases on a review path and feed corrected examples into the next training cycle.