Outlines — Outlines: structured JSON/regex/Pydantic LLM generation
Outlines — Outlines: structured JSON/regex/Pydantic LLM generation
Start with meaning, then move to detail.
This lesson explains Outlines — Outlines: structured JSON/regex/Pydantic LLM generation as part of getting started with Hermes correctly. You will learn what it does, when it matters, and the smallest safe test that proves it works.
If you are new, do not memorize names. Focus on three questions: what problem does this solve, what access does it need, and how can you verify the result?
For practice, inspect the first example, identify its effects, run it on test data, and compare the result with the source claim.
For advanced readers, inspect Skill metadata, Reference: full SKILL.md, When to Use This Skill, then verify failure modes and version compatibility.
No prior experience is required; follow the steps on a safe test setup first.
A clear outcome before you read.
- Understand Outlines — Outlines: structured JSON/regex/Pydantic LLM generation without assumed prior knowledge.
- Separate the source description from what still needs testing in your environment.
- Read the first command and identify its inputs and outputs before copying it.
Short definitions before the details.
- Provider
- The service that runs or provides access and authentication to a model.
- Skill
- An instruction bundle that teaches Hermes a repeatable workflow without necessarily adding an external service.
Outlines: structured JSON/regex/Pydantic LLM generation
What does the source say, and in what order?
- 01Skill metadata
Start here to understand the core idea or structure.
- 02Reference: full SKILL.md
Read this after the foundation, then connect it to the previous step.
- 03When to Use This Skill
Read this after the foundation, then connect it to the previous step.
- 04Installation
Read this after the foundation, then connect it to the previous step.
- 05Quick Start
Read this after the foundation, then connect it to the previous step.
- 06Basic Example: Classification
Read this after the foundation, then connect it to the previous step.
- 07With Pydantic Models
Read this after the foundation, then connect it to the previous step.
- 08Core Concepts
Read this after the foundation, then connect it to the previous step.
- 091. Constrained Token Sampling
Read this after the foundation, then connect it to the previous step.
- 102. Output Types
Finish here to verify the result and special cases.
Copy only after you understand the effect.
# Base installation
pip install outlines
# With specific backends
pip install outlines transformers # Hugging Face models
pip install outlines llama-cpp-python # llama.cpp
pip install outlines vllm # vLLM for high-throughput### With Pydantic Models## Core Concepts
### 1. Constrained Token Sampling
Outlines constrains token generation at the logit level using a compiled
automaton derived from your output type.
**How it works:**
1. Convert the output type (JSON/Pydantic/regex/`Literal`) to a schema/grammar
2. Compile the grammar into a token-level automaton
3. Filter invalid tokens at each step during generation
4. Fast-forward when only one valid token exists
**Benefits:**
- **Zero overhead**: Filtering happens at token level
- **Speed improvement**: Fast-forward through deterministic paths
- **Guaranteed validity**: Invalid outputs Read the first command and identify its inputs and outputs before copying it.
Match every command to your installed Hermes version, review the files and accounts it can reach, and use non-sensitive data for the first test. If this explanation differs from the source, the official source wins.