outlines-core

import json from outlines_core.json_schema import build_regex_from_schema from outlines_core.guide import Guide, Index, Vocabulary # Define a JSON schema schema = { "title": "Foo", "type": "object", "properties": { "name": {"type": "string"}, "age": {"type": "integer"} }, "required": ["name", "age"] } # Generate a regular expression from the schema regex = build_regex_from_schema(json.dumps(schema)) # Create Vocabulary from a pretrained model (e.g., GPT-2 for demonstration) vocabulary = Vocabulary.from_pretrained("openai-community/gpt2") # Create an Index from the regex and vocabulary index = Index(regex, vocabulary) # Create a Guide instance guide = Guide(index) # Example interaction with the guide (simplified for quickstart) # In a real scenario, you'd integrate this with an LLM's token generation current_state = guide.get_state() allowed_tokens = guide.get_tokens() print(f"Initial allowed token IDs: {allowed_tokens}") # Simulate advancing the guide with a token (e.g., the first allowed token) if allowed_tokens: first_token_id = allowed_tokens[0] # In a real LLM integration, you'd feed this token to the model # and then get the next state based on the model's output. next_allowed_tokens = guide.advance(first_token_id) print(f"Next allowed token IDs after advancing with {first_token_id}: {next_allowed_tokens}") print(f"Is guide finished? {guide.is_finished()}")