# LightOn Documentation: English Paradigm API

## Paradigm API

- [English / Paradigm API / API References (264 pages)](https://docs.lighton.ai/_llms/en/paradigm-api/api-references.md): Documentation for English / Paradigm API / API References.

### Guides

#### API Fundamentals

- [Chat API Endpoint Quick Guide](https://docs.lighton.ai/en/developer-resources/api-fundamentals/quick-guide.md): Welcome to our guide on the Paradigm public API. This powerful interface provides developers with flexible access to our services, enabling seamless integration of our advanced features into your applications.
- [Using the Paradigm API via a Proxy in Python](https://docs.lighton.ai/en/developer-resources/api-fundamentals/proxy-configuration.md): Learn how to configure your requests to work with the Paradigm API when your company uses a proxy.
- [Paradigm usage data](https://docs.lighton.ai/en/developer-resources/api-fundamentals/usage-data.md): The Paradigm API can be used by company or instance administrators to track usage of the platform.
- [OpenAI SDK Compatibility](https://docs.lighton.ai/en/developer-resources/api-fundamentals/openai-compatibility.md): Use the OpenAI Python SDK with our API

#### Agents & Threads

- [Agents](https://docs.lighton.ai/en/developer-resources/agents-and-threads/agents.md): Perform task efficiently by using and creating specialized agents
- [Threads](https://docs.lighton.ai/en/developer-resources/agents-and-threads/threads.md): Perform agentic tasks using the threads system

#### Chat & AI Models

- [Get the list of models](https://docs.lighton.ai/en/developer-resources/chat-and-ai-models/models-list.md): In order to know which models you can have access to through Paradigm, a dedicated endpoint is available for you to get the list of available models.
- [Asynchronous API Requests with aiohttp](https://docs.lighton.ai/en/developer-resources/chat-and-ai-models/async-requests.md): By using aiohttp with the Paradigm API, you can leverage the power of asynchronous programming in Python to improve the speed of your API requests.
- [Get Structured Output Generation](https://docs.lighton.ai/en/developer-resources/chat-and-ai-models/structured-output.md): Enhance your applications with high-quality, structured output using our API's dedicated parameters. This feature is key for creating or parsing structured data, ensuring it meets specific format and validation rules.
- [Regex-Powered Template Filling via API](https://docs.lighton.ai/en/developer-resources/chat-and-ai-models/regex-templates.md): Our API now supports regex-based template filling, enabling precise formatting in generated content. Ideal for data that must conform to specific patterns like credit card numbers, phone numbers, or custom identifiers.
- [Embeddings endpoint](https://docs.lighton.ai/en/developer-resources/chat-and-ai-models/embeddings.md): The embeddings API endpoint allows you to easily convert some text into embedding vectors. This feature gives you the possibility to manage your own vector database while keeping the advantages of Paradigm.
- [Tokenize endpoint](https://docs.lighton.ai/en/developer-resources/chat-and-ai-models/tokenize.md): The tokenize API endpoint allows you to easily convert some text into a list of tokens for a specific model.

#### LightOn models

- [Alfred Sovereign 5](https://docs.lighton.ai/en/developer-resources/lighton-models/alfred-sv5.md): LightOn introduces Alfred-sv5, the latest iteration of its model designed for organizations where the European origin of the LLM is a requirement.
- [Alfred Frontier 5](https://docs.lighton.ai/en/developer-resources/lighton-models/alfred-ft5.md): LightOn introduces Alfred-ft5, the latest high‑performance model built for organizations that prioritize raw quality, advanced reasoning, and best‑in‑class tool usage.

#### Document Management

- [Upload Files to Paradigm](https://docs.lighton.ai/en/developer-resources/files/add-document.md): Upload documents to Paradigm using the V3 Files API - simplified one-step process with support for single files and batch uploads.
- [Get the list of uploaded documents](https://docs.lighton.ai/en/developer-resources/files/list-documents.md): This guide explains how to retrieve and search through uploaded documents in Paradigm using the v3 API.
- [Delete a document](https://docs.lighton.ai/en/developer-resources/files/delete-document.md): The files API endpoint can be used to delete an uploaded document from Paradigm.
- [Document search with Paradigm ](https://docs.lighton.ai/en/developer-resources/files/document-search.md): RAG requests can be 100% done through the Paradigm API. It allows users to submit a query, which the system processes to provide relevant answers by leveraging associated documents or going through the whole knowledge base.

### Use Cases

- [Content Generator - HR Example](https://docs.lighton.ai/en/use-cases/ads.md): Example: Generate professional job offer advertisements from job specifications.
- [Chatbot](https://docs.lighton.ai/en/use-cases/chatbot.md): A conversational chatbot with document context from a dedicated workspace.
- [Procurement Document Verification](https://docs.lighton.ai/en/use-cases/procurement-document-verification.md): Automate multi-document verification by extracting and cross-referencing fields across uploaded documents using Paradigm's Document Search and Chat Completions APIs.
- [NDA Compliance Review](https://docs.lighton.ai/en/use-cases/nda-review.md): Automate compliance review of incoming NDAs by running configurable legal controls over uploaded contracts and proposing rewordings from previously signed references, using Paradigm's agent search and structured Chat Completions.
- [VC Investment Screening](https://docs.lighton.ai/en/use-cases/vc-screening.md): Screen inbound venture-capital opportunities against a fixed rubric of criteria and draft a tone-matched reply email, using a single Paradigm Agent document-search call plus a single Chat Completion.

## OpenAPI Specs

- [openapi-v3](/api-reference/openapi-v3.yaml)
- [openapi-v3-company](/api-reference/openapi-v3-company.yaml)
- [openapi-v3-instance](/api-reference/openapi-v3-instance.yaml)
- [openapi-v2](/api-reference/openapi-v2.yaml)