# Quick Start

The Block Entropy API provides interfaces for developers to create intelligence layers in their applications, powered by state-of-the-art, open source language, image, video, and audio models. The BE APIs use a format compatible with OpenAI, allowing developers to use the OpenAI SDK or software compatible with the OpenAI API to access these services.

Key Points:

1. API Compatibility: By modifying the configuration, you can use OpenAI-compatible tools to access Block Entropy APIs.
2. Base URLs:

   `https://api.blockentropy.ai/v1` 
3. API Keys: Services require API keys, which you must apply for and keep secure.
4. Chat Completions:  The API offers chat completion endpoints, which power conversational AI like ChatGPT and provide a way to generate text outputs based on input prompts.
5. Streaming: The API supports streaming responses. Set the `stream` parameter to `true` to enable this feature.

Setup and Usage:

1. Account Setup: Create an account and obtain an API key.
2. Environment Setup:
   * Install Python
   * Set up a virtual environment (optional but recommended)
   * Install the appropriate OpenAI Python library
3. API Key Configuration:
   * Set up the API key for all projects or for a single project
   * Keep the API key secure and do not share it
4. Making API Requests:
   * Use curl, Python, Node.js, or other programming languages to send requests

Example Python Code:

```python
# python3
# Install OpenAI SDK first: `pip3 install openai`
from openai import OpenAI

client = OpenAI(api_key="<blockentropy api key>", base_url="https://api.blockentropy.ai/v1")

response = client.chat.completions.create(
    model="be-405b-base-llama3.1",
    messages=[
        {"role": "system", "content": "You are a helpful assistant"},
        {"role": "user", "content": "Hello"},
    ],
    stream=False
)

print(response.choices[0].message.content)
```


---

# 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.blockentropy.ai/quick-start.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.