No project description provided
Project description
Jsonformer: A Bulletproof Way to Generate Structured JSON from Language Models.
Problem: Getting models to output structured JSON is hard
Solution: Only generate the content tokens and fill in the fixed tokens
Generating structured JSON from language models is a challenging task. The generated JSON must be syntactically correct, and it must conform to a schema that specifies the structure of the JSON.
Current approaches to this problem are brittle and error-prone. They rely on prompt engineering, fine-tuning, and post-processing, but they still fail to generate syntactically correct JSON in many cases.
Jsonformer is a new approach to this problem. In structured data, many tokens are fixed and predictable. Jsonformer is a wrapper around HuggingFace models that fills in the fixed tokens during the generation process, and only delegates the generation of content tokens to the language model. This makes it more efficient and bulletproof than existing approaches.
This currently supports a subset of JSON Schema. Below is a list of the supported schema types:
- number
- boolean
- string
- array
- object
Example
from jsonformer import Jsonformer
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained("databricks/dolly-v2-12b")
tokenizer = AutoTokenizer.from_pretrained("databricks/dolly-v2-12b")
json_schema = {
"type": "object",
"properties": {
"name": {"type": "string"},
"age": {"type": "number"},
"is_student": {"type": "boolean"},
"courses": {
"type": "array",
"items": {"type": "string"}
}
}
}
prompt = "Generate a person's information based on the following schema:"
jsonformer = Jsonformer(model, tokenizer, json_schema, prompt)
generated_data = jsonformer()
print(generated_data)
Features
- Bulletproof JSON generation: Jsonformer ensures that the generated JSON is always syntactically correct and conforms to the specified schema.
- Efficiency: By generating only the content tokens and filling in the fixed tokens, Jsonformer is more efficient than generating a full JSON string and parsing it.
- Flexible and extendable: Jsonformer is built on top of the HuggingFace transformers library, making it compatible with any model that supports the HuggingFace interface.
Installation
pip install jsonformer
License
Jsonformer is released under the MIT License. You are free to use, modify, and distribute this software for any purpose, commercial or non-commercial, as long as the original copyright and license notice are included.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for jsonformer-0.6.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 8e663efb712a8e040485d8e155599d784752f57eea1acd13c5a585d6d6f1554c |
|
MD5 | 7d7ce163ad7f860eec6a8f82bfbd83a0 |
|
BLAKE2b-256 | 193651e831a27ca83ca991b3af125b3975de400c1e3af055920823812fe5a8f7 |