# Text Generation

Harness the power of large language models to generate any type of text content - from creative writing and code to structured data formats and technical documentation.

## Basic Usage

Generate text responses using our chat completion endpoint:

```python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.neura-ai.app/v1"
)

response = client.chat.completions.create(
    model="mistral-medium-latest",
    messages=[
        {"role": "user", "content": "Explain quantum computing in simple terms"}
    ],
    temperature=0.7
)

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

## Controlling Output Style

### Temperature

Adjust the `temperature` parameter to control creativity vs. consistency:

```python
# More focused and deterministic
response = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "What is 2+2?"}],
    temperature=0.1
)

# More creative and varied
response = client.chat.completions.create(
    model="gpt-5", 
    messages=[{"role": "user", "content": "Write a creative story opening"}],
    temperature=1.5
)
```

### System Messages

Guide the model's behavior with system instructions:

```python
response = client.chat.completions.create(
    model="gpt-5",
    messages=[
        {
            "role": "system", 
            "content": "You are a helpful coding assistant specializing in Python"
        },
        {
            "role": "user",
            "content": "How do I read a CSV file?"
        }
    ]
)
```

## Use Cases

### Code Generation

```python
response = client.chat.completions.create(
    model="gpt-5",
    messages=[{
        "role": "user",
        "content": "Write a Python function to calculate fibonacci numbers with memoization"
    }],
    temperature=0.2
)
```

### Content Summarization

```python
long_article = "..." # Your long text here

response = client.chat.completions.create(
    model="mistral-medium-latest",
    messages=[{
        "role": "user",
        "content": f"Provide a concise summary of this article:\n\n{long_article}"
    }],
    temperature=0.3
)
```

### Structured Output

Generate JSON or other structured formats:

```python
response = client.chat.completions.create(
    model="gpt-5",
    messages=[{
        "role": "user",
        "content": "Generate a JSON object with 5 fake user profiles including name, email, and age"
    }],
    temperature=0.7
)
```

## Streaming Responses

For real-time output, enable streaming:

```python
stream = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Write a poem about the ocean"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")
```

## Best Practices

* Use lower temperatures (0.1-0.3) for factual or deterministic tasks
* Use higher temperatures (0.7-1.2) for creative or varied outputs
* Include clear, specific instructions in your prompts
* Use system messages to set consistent behavior
* Consider token limits when working with large inputs or outputs