Image-Text-to-Text
MLX
Safetensors
qwen3_5
clairic
cloudflare
systemone
structured-output
information-extraction
multimodal
custom-code
conversational
4-bit precision
Instructions to use mlx-community/clairic-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/clairic-4bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("mlx-community/clairic-4bit") config = load_config("mlx-community/clairic-4bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use mlx-community/clairic-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/clairic-4bit"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "mlx-community/clairic-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use mlx-community/clairic-4bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/clairic-4bit"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default mlx-community/clairic-4bit
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use mlx-community/clairic-4bit with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "mlx-community/clairic-4bit"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "mlx-community/clairic-4bit" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download clairic_runtime/documents.py from mlx-community/clairic-4bit: direct link, hf CLI and curl.
- Browser
- Download file 3.49 kB
-
https://huggingface.co/mlx-community/clairic-4bit/resolve/main/clairic_runtime/documents.py
- Command line
-
hf download hf://mlx-community/clairic-4bit/clairic_runtime/documents.py
-
curl -L -o documents.py https://huggingface.co/mlx-community/clairic-4bit/resolve/main/clairic_runtime/documents.py
3.49 kB
| """Validate embedded PDFs and render their pages inside the request encoder.""" | |
| from __future__ import annotations | |
| from typing import TYPE_CHECKING | |
| if TYPE_CHECKING: | |
| from PIL import Image | |
| import base64 | |
| import binascii | |
| import math | |
| import re | |
| from .embedded import MAX_IMAGE_BYTES, MAX_IMAGES | |
| from pydantic import BaseModel, ConfigDict, StrictStr, model_validator | |
| class ClairDocument(BaseModel): | |
| model_config = ConfigDict(extra="forbid", frozen=True) | |
| content_type: StrictStr | |
| base64: StrictStr | |
| def parse_document(cls, value: object) -> dict[str, str]: | |
| if isinstance(value, str): | |
| match = re.fullmatch( | |
| r"data:application/pdf;base64,([A-Za-z0-9+/]*={0,2})", | |
| value, | |
| re.IGNORECASE, | |
| ) | |
| if match is None: | |
| raise ValueError("document must be an embedded PDF data URI") | |
| value = {"content_type": "application/pdf", "base64": match[1]} | |
| if type(value) is not dict or set(value) != {"content_type", "base64"}: | |
| raise ValueError("document object must contain content_type and base64") | |
| if value["content_type"] != "application/pdf" or not isinstance( | |
| value["base64"], str | |
| ): | |
| raise ValueError("document content type must be application/pdf") | |
| try: | |
| data = base64.b64decode(value["base64"], validate=True) | |
| except (binascii.Error, ValueError) as error: | |
| raise ValueError("document base64 is malformed") from error | |
| if not data.startswith(b"%PDF-") or len(data) > MAX_IMAGE_BYTES: | |
| raise ValueError("document must be a PDF within the decoded byte limit") | |
| return { | |
| "content_type": "application/pdf", | |
| "base64": base64.b64encode(data).decode("ascii"), | |
| } | |
| def render(self, available_pages: int = MAX_IMAGES) -> list[Image.Image]: | |
| import pypdfium2 as pdfium | |
| from .orientation import orient_document | |
| try: | |
| pdf = pdfium.PdfDocument(base64.b64decode(self.base64)) | |
| try: | |
| if not 0 < len(pdf) <= available_pages: | |
| raise ValueError( | |
| f"PDF pages and images together must not exceed {MAX_IMAGES}" | |
| ) | |
| images = [] | |
| for index in range(len(pdf)): | |
| page = pdf[index] | |
| try: | |
| width, height = page.get_size() | |
| if not ( | |
| math.isfinite(width * height) and width > 0 and height > 0 | |
| ): | |
| raise ValueError("PDF page has invalid dimensions") | |
| scale = min(2.0, math.sqrt(4_000_000 / (width * height))) | |
| bitmap = page.render(scale=scale) | |
| try: | |
| images.append( | |
| orient_document(bitmap.to_pil().convert("RGB")) | |
| ) | |
| finally: | |
| bitmap.close() | |
| finally: | |
| page.close() | |
| return images | |
| finally: | |
| pdf.close() | |
| except pdfium.PdfiumError as error: | |
| raise ValueError( | |
| "PDF cannot be opened or rendered; encrypted PDFs are unsupported" | |
| ) from error | |