LLM용 Jev 스타일 단일 함수 래퍼, 비전 모델까지 지원

skip to main | skip to sidebar Allan's Blog Allan Riordan Boll's blog Friday, September 25, 2026 A Jev-like wrapper for LLMs, including vision models I was intrigued by Jev and the self-hostable projects appearing around it, such as OpenJev and SemIf . Reading about them introduced me to a neat trick: reading an LLM's token probabilities. Apparently this is an old trick for some people. See e.g. OpenAI's logprobs cookbook . But it was new to me. I believe the basic idea is to write a prompt like this: State: My order arrived broken and I want a refund. Question: Which team should handle this? [A] billing [B] shipping [C] returns Answer with the letter of the best option only. Then add a few JSON request parameters to a compatible Chat Completions request: { "max_completion_tokens": 1, "logprobs": true, "top_logprobs": 20 } The LLM API will return the letter plus the model's log probabilities for alternative tokens. Repeat for each question. Forcing it to generating only one token avoids a lengthy answer and is super quick, though processing the input still costs time. Though for each of the questions a shared state prefix can be KV-cached if the backend supports it. The fun part: this works with vision models too. Jev's documented request format currently describes only text/JSON state. I added an attachments field for images for my local experiments. My example captures webcam frames, sends base64 JPEGs, and prints a table: is a person visible, are we indoors or outdoors, and how bright is the scene? With Gemma 4 12B on my RTX 3090, I get around 1 frames per second , with three questions per frame. I also ran it against OpenAI gpt-6-luna and got around 0.2 FPS. Presumably because I didn't make any effort to avoid the cost of a separate connection through their system per question per frame. Specialized computer vision models surely are much more efficient, but what I like here is the flexibility: change a condition by describing it in plain text. Here's the standalone Python example (OpenCV is just used for convenient access to the webcam, not for any actual computer vision): #!/usr/bin/env -S uv run --script # /// script # dependencies = ["opencv-python"] # /// """Preview and score webcam frames with llama.cpp or OpenAI. uv run webcam.py uv run webcam.py https://api.openai.com/v1 gpt-6-luna OpenAI reads OPENAI_API_KEY. """ import argparse import base64 import concurrent.futures import datetime import json import math import mimetypes import os import pathlib import time import urllib.parse import urllib.request import cv2 # attachments is our custom addition to the Jev request format. data = json.loads(""" { "state": "Inspect this webcam frame. Judge only what is visibly present.", "attachments": [], "questions": { "person": { "type": "noul", "instructions": "Is a person visible?" }, "plant": { "type": "noul", "instructions": "Is a plant visible?" }, "setting": { "type": "choice", "instructions": "Where is the camera?", "criteria": { "indoors": null, "outdoors": null, "unclear": null } }, "light": { "type": "score", "instructions": "How bright is the scene?", "criteria": [ "dark", "dim", "bright" ] } } } """) def score(data, url, model): state = data["state"] if not isinstance(state, str): state = json.dumps(state) # Attachments are our extension to the Jev-style request format: # image file paths or base64 data URLs. Load them once for all questions. images = [] for attachment in data.get("attachments", []): if attachment.startswith("data:image/"): images.append(attachment) continue path = pathlib.Path(attachment).expanduser() mime_type, _ = mimetypes.guess_type(path) if mime_type not in {"image/png", "image/jpeg", "image/webp", "image/gif"}: raise ValueError(f"Unsupported image file: {path}") encoded = base64.b64encode(path.read_bytes()).decode() images.append(f"data:{mime_type};base64,{encoded}") # Send the API key only to OpenAI. is_openai = urllib.parse.urlsplit(url).hostname == "api.openai.com" headers = {"Content-Type": "application/json"} if is_openai: headers["Authorization"] = "Bearer " + os.environ["OPENAI_API_KEY"] answers = {} for name, question in data["questions"].items(): # Represent choices, booleans, and ordinal levels as lettered options. if question["type"] == "choice": options = question["criteria"] elif question["type"] == "noul": options = {"true": None, "false": None} | question.get("criteria", {}) elif question["type"] == "score": options = {str(i): description for i, description in enumerate(question["criteria"])} else: raise ValueError(f"Unknown question type: {question[&#039;type&#039;]}") if not 2 <= len(options) <= 20: raise ValueError("Provide 2 to 20 criteria per question.") letters = "ABCDEFGHIJKLMNOPQRST"[:len(options)] # Ask for a single option letter, so its logprob represents that option. instructions = question["instructions"] if not isinstance(instructions, str): instructions = json.dumps(instructions) lines = [f"State:\n{state}\n\nQuestion: {instructions}\nOptions:"] for letter, (key, description) in zip(letters, options.items()): line = f"[{letter}] {key}" if description is not None: line += f": {description}" lines.append(line) prompt = "\n".join(lines) + "\n\nAnswer with the letter of the best option only." # OpenAI needs Responses for enough alternatives; llama.cpp needs Chat for logprobs. # top_p=1 avoids pruning alternatives. if is_openai: endpoint = "/responses" content = [{"type": "input_text", "text": prompt}] content.extend({"type": "input_image", "image_url": image} for image in images) body = { "model": model, "input": [{"role": "user", "content": content}], "reasoning": {"effort": "none"}, "max_output_tokens": 16, "top_p": 1, "top_logprobs": 20, "include": ["message.output_text.logprobs"], } else: endpoint = "/chat/completions" content = [{"type": "text", "text": prompt}] content.extend({"type": "image_url", "image_url": {"url": image}} for image in images) body = { "model": model, "messages": [{"role": "user", "content": content}], "max_completion_tokens": 1, "temperature": 0, "reasoning_effort": "none", "logprobs": True, "top_logprobs": 1024, } # Send the request and read the first output token&#039;s alternatives. request = urllib.request.Request( url.rstrip("/") + endpoint, headers=headers, data=json.dumps(body).encode(), ) with urllib.request.urlopen(request) as response: result = json.load(response) if is_openai: message = next(item for item in result["output"] if item["type"] == "message") candidates = message["content"][0]["logprobs"][0]["top_logprobs"] else: candidates = result["choices"][0]["logprobs"]["content"][0]["top_logprobs"] logprobs = {item["token"]: item["logprob"] for item in candidates} # Normalize the returned option scores; missing options initially get zero. missing = [letter for letter in letters if letter not in logprobs or logprobs[letter] <= -9999] if len(missing) == len(letters): raise ValueError("API did not return usable scores for any option") peak = max(logprobs[letter] for letter in letters if letter not in missing) weights = [math.exp(logprobs[letter] - peak) if letter not in missing else 0 for letter in letters] total = sum(weights) # An omitted token cannot outrank the last returned alternative. # Allow zero only when their combined normalized probability is below 1e-6. if missing: cutoff = min(value for value in logprobs.values() if value > -9999) missing_weight = len(missing) * math.exp(cutoff - peak) if missing_weight / (total + missing_weight) >= 1e-6: raise ValueError(f"API omitted non-negligible option scores for: {&#039;, &#039;.join(missing)}") probabilities = {key: weight / total for key, weight in zip(options, weights)} # Return the winning choice, probability of true, or expected ordinal level. if question["type"] == "choice": answers[name] = { "type": "choice", "choice": max(probabilities, key=probabilities.get), "probabilities": probabilities, } elif question["type"] == "noul": answers[name] = {"type": "noul", "noul": probabilities["true"]} else