Welcome to local-llm-function-calling’s documentation!

The local-llm-function-calling project is designed to constrain the generation of Hugging Face text generation models by enforcing a JSON schema and facilitating the formulation of prompts for function calls, similar to OpenAI’s function calling feature, but actually enforcing the schema unlike OpenAI.

The project provides a Generator class that allows users to easily generate text while ensuring compliance with the provided prompt and JSON schema. By utilizing the local-llm-function-calling library, users can conveniently control the output of text generation models. It uses my own quickly sketched json-schema-enforcer project as the enforcer.

Features

• Constrains the generation of Hugging Face text generation models to follow a JSON schema.

• Provides a mechanism for formulating prompts for function calls, enabling precise data extraction and formatting.

• Simplifies the text generation process through a user-friendly Generator class.

Table of Contents:

• Quickstart
  • Installation
  • Usage
  • Llama.cpp
• How It Works
• Generating a function call
  • Completion models
  • Instruct models
  • Llama.cpp
  • Your own prompters
• Constrained generation
  • JSON schema
  • Custom constraints
• API Reference
  • CompletionModelPrompter
  • Constrainer
  • ConstrainerError
  • FunctionCallingError
  • FunctionType
  • Generator
  • InstructModelPrompter
  • JsonSchemaConstraint
  • NoValidTokensError
  • SequenceTooLongError
  • TextPrompter
  • HuggingfaceGeneration
  • HuggingfaceModel
  • CodeLlamaFunctionCallingPrompter

• Index

• Search Page