> ## Documentation Index
> Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# चैट कम्प्लीशन

> TypeScript SDK से /chat/completions कॉल करें।

**तरीका**: `client.generateText()` (पार्स किए गए हिस्सों को स्ट्रीम करने के लिए `client.streamChat()`).

### उदाहरण

```typescript theme={null}
const chat = await client.generateText({
  model: "openai/gpt-4o-mini",
  messages: [
    { role: "system", content: "You are helpful." },
    { role: "user", content: "Write a limerick about lighthouses." },
  ],
  temperature: 0.5,
});
```

### स्ट्रीमिंग

```typescript theme={null}
for await (const chunk of client.streamChat({
  model: "openai/gpt-4o-mini",
  messages: [{ role: "user", content: "Stream a story" }],
})) {
  if (chunk.text) process.stdout.write(chunk.text);
}
```

### मुख्य पैरामीटर

* `model` (required): लक्ष्य मॉडल ID।
* `messages` (required): `system|user|assistant|tool` भूमिकाओं वाले क्रमबद्ध संदेश; कंटेंट स्ट्रिंग या हिस्सों में हो सकता है।
* सैंपलिंग: `temperature` (0–2), `top_p` (0–1), `top_k` (>=1), `seed` (int, optional).
* लंबाई/पेनल्टी: `max_output_tokens` (int), `presence_penalty` and `frequency_penalty` (-2 to 2), `stop` (string|string\[]).
* टूल: `tools` (परिभाषाएँ), `tool_choice` (`auto`/`none`/विशिष्ट टूल), `max_tool_calls` (पूर्णांक), `parallel_tool_calls` (बूलियन)।
* लॉग प्रायिकताएँ: `logprobs` (बूलियन), `top_logprobs` (0–20)।
* आउटपुट: `response_format` (json/text), `metadata` (पास-थ्रू ऑब्जेक्ट), `stream` (बूलियन), `service_tier`।
* गेटवे के अतिरिक्त विकल्प: `usage` (उपयोग माँगने के लिए बूलियन), `meta` (मेटाडेटा ब्लॉक शामिल करने के लिए बूलियन)।

### रिटर्न

`ChatCompletionsResponse`

```json theme={null}
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-0125",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello there, how may I assist you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}
```

या `stream: true` होने पर SSE फ़्रेम:

```
data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-3.5-turbo-0125","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-3.5-turbo-0125","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}

data: {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1677652288,"model":"gpt-3.5-turbo-0125","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":9,"completion_tokens":12,"total_tokens":21}}

data: [DONE]
```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.