Image-Text-to-Text
Transformers
Safetensors
qwen3_5
clairic
cloudflare
systemone
multimodal
structured-output
information-extraction
custom-code
conversational
Instructions to use Cloudflare/clairic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Cloudflare/clairic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-text-to-text", model="Cloudflare/clairic") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Cloudflare/clairic") model = AutoModelForMultimodalLM.from_pretrained("Cloudflare/clairic", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=256) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Cloudflare/clairic with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Cloudflare/clairic" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cloudflare/clairic", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker
docker model run hf.co/Cloudflare/clairic
- SGLang
How to use Cloudflare/clairic with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Cloudflare/clairic" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cloudflare/clairic", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Cloudflare/clairic" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Cloudflare/clairic", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "Describe this image in one sentence." }, { "type": "image_url", "image_url": { "url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg" } } ] } ] }' - Docker Model Runner
How to use Cloudflare/clairic with Docker Model Runner:
docker model run hf.co/Cloudflare/clairic
Download clairic_runtime/financial_scope.py from Cloudflare/clairic: direct link, hf CLI and curl.
- Browser
- Download file 4.07 kB
-
https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/financial_scope.py
- Command line
-
hf download hf://Cloudflare/clairic/clairic_runtime/financial_scope.py
-
curl -L -o financial_scope.py https://huggingface.co/Cloudflare/clairic/resolve/main/clairic_runtime/financial_scope.py
4.07 kB
| from __future__ import annotations | |
| import re | |
| from typing import Any | |
| TAX_INSTRUCTION = " A separately printed tax row is present even when its amount is zero or negative, including a tax refund. Copy every matching printed tax row. Do not return null or end the list while a matching printed tax row remains." | |
| FEE_INSTRUCTION = " A separately printed fee or surcharge row is present even when its amount is zero or negative, including a fee refund. Copy every matching printed fee or surcharge row. Do not return null or end the list while a matching printed fee or surcharge row remains." | |
| SERVICE_INSTRUCTION = " Use the row's own printed label. Include an ordinary billed product or service charge. Exclude a row whose own label identifies it as a separately printed tax, fee, surcharge, subtotal, total or payment. A neighboring fee or tax does not exclude an otherwise eligible service row." | |
| def prepare( | |
| fields: dict[str, dict[str, Any]], | |
| *, | |
| has_media: bool = False, | |
| fee_guidance: bool = False, | |
| service_guidance: bool = False, | |
| ) -> dict[str, dict[str, Any]]: | |
| if has_media: | |
| return fields | |
| result = dict(fields) | |
| for name, spec in fields.items(): | |
| item = spec.get("items") | |
| instructions = spec.get("instructions", "") | |
| if ( | |
| spec.get("type") != "list" | |
| or not isinstance(item, dict) | |
| or item.get("type") != "object" | |
| or (not isinstance(instructions, str)) | |
| or (not isinstance(item.get("properties"), dict)) | |
| ): | |
| continue | |
| properties = list(item["properties"].values()) | |
| if ( | |
| len(properties) != 2 | |
| or not all((isinstance(child, dict) for child in properties)) | |
| or sum((child.get("type") == "number" for child in properties)) != 1 | |
| or (sum((child.get("type") == "text" for child in properties)) != 1) | |
| or spec.get("knowledge") | |
| or any((child.get("knowledge") for child in properties)) | |
| ): | |
| continue | |
| positive = re.split( | |
| "[.\\n]|\\bExclude\\b", instructions, maxsplit=1, flags=re.IGNORECASE | |
| )[0] | |
| if re.match( | |
| "\\s*Only\\b[^.\\n]*\\btax(?:es)?\\b[^.\\n]*\\brows\\b", | |
| positive, | |
| re.IGNORECASE, | |
| ) and ( | |
| not re.search( | |
| "\\b(?:fees?|products?|services?|goods|summar\\w*|calculat\\w*|group\\w*)\\b", | |
| positive, | |
| re.IGNORECASE, | |
| ) | |
| ): | |
| result[name] = {**spec, "instructions": instructions + TAX_INSTRUCTION} | |
| elif ( | |
| fee_guidance | |
| and re.match( | |
| "\\s*Only\\b[^.\\n]*\\bfees?\\b[^.\\n]*\\brows\\b", | |
| positive, | |
| re.IGNORECASE, | |
| ) | |
| and ( | |
| not re.search( | |
| "\\b(?:tax(?:es)?|products?|services?|goods|summar\\w*|calculat\\w*|group\\w*|deduplicat\\w*|aggregat\\w*|combin\\w*|normaliz\\w*)\\b", | |
| positive, | |
| re.IGNORECASE, | |
| ) | |
| ) | |
| ): | |
| result[name] = {**spec, "instructions": instructions + FEE_INSTRUCTION} | |
| elif ( | |
| service_guidance | |
| and re.match( | |
| "\\s*Only\\s+billed\\b[^.\\n]*\\brows\\b", positive, re.IGNORECASE | |
| ) | |
| and re.search( | |
| "\\b(?:goods|products?|services?)\\b", positive, re.IGNORECASE | |
| ) | |
| and ( | |
| not re.search( | |
| "\\b(?:tax(?:es)?|fees?|surcharges?|summar\\w*|calculat\\w*|group\\w*|deduplicat\\w*|aggregat\\w*|combin\\w*|normaliz\\w*)\\b", | |
| positive, | |
| re.IGNORECASE, | |
| ) | |
| ) | |
| and re.search( | |
| "\\bExclude\\b[^.\\n]*\\b(?:fees?|surcharges?)\\b", | |
| instructions, | |
| re.IGNORECASE, | |
| ) | |
| ): | |
| result[name] = {**spec, "instructions": instructions + SERVICE_INSTRUCTION} | |
| return result | |