# Overview

Fryday is a streamlined platform designed to help product-focused teams fine-tune and optimize specialized LLM models as a cost-effective and efficient alternative to traditional large-scale models.

### What We Provide

Here are some of the features Fryday offers:

* **Proxy API**: Seamlessly collect and utilize interaction data through our proxy API to fine-tune custom models, continually enhancing their performance. Switching requests from your previous LLM provider to your new model is as easy as updating the model name. All our models adhere to the OpenAI inference format, so no changes are needed in how you parse responses.
* **Data Capture**: Fryday captures every request and response, storing them securely for future use.
* **Request Logs**: We automatically log your past requests, allowing you to tag and filter them with ease.
* **Upload Data**: Import fine-tuning data from OpenAI-compatible JSONL files directly into Fryday.
* **Export Data**: Once your request logs are recorded, you can export them anytime.
* **Fine-Tuning**: With all your LLM requests and responses in one place, selecting the data to fine-tune and initiating a job is straightforward.

#### Coming Soon

* **Pruning Rules**: A future feature to reduce inference costs by compacting unchanging text before fine-tuning.
* **Caching**: Boost performance and cut costs by caching previously generated responses.
* **Evaluations**: Easily compare different models and set up custom benchmarks to measure performance against base models.

Welcome to the Fryday community! For more details, visit us at [fryday.ai](https://fryday.ai).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.fryday.ai/introduction/overview.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.