api-docs

"use strict";
Object.defineProperty(exports, "__esModule", { value: true });
exports.groqDocs = void 0;
exports.groqDocs = [
    {
        id: "groq-chat",
        title: "Groq Chat API",
        category: "chat",
        provider: "groq",
        keywords: ["groq", "chat", "completions", "fast", "inference", "llm"],
        content: `# Groq Chat API

Groq uses OpenAI-compatible API format with ultra-fast inference.

## Endpoint
POST https://api.groq.com/openai/v1/chat/completions

## Headers
- Authorization: Bearer YOUR_API_KEY
- Content-Type: application/json

## Request Body
\`\`\`json
{
  "model": "llama-3.3-70b-versatile" | "llama-3.1-8b-instant" | "llama-3.2-90b-vision-preview" | "llama-guard-3-8b" | "mixtral-8x7b-32768" | "gemma2-9b-it" | "deepseek-r1-distill-llama-70b",
  "messages": [
    {
      "role": "system" | "user" | "assistant" | "tool",
      "content": "string"
    }
  ],
  "temperature": number (0-2, default 1),
  "max_tokens": number,
  "top_p": number (0-1),
  "stream": boolean,
  "stop": string | string[],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "string",
        "description": "string",
        "parameters": {JSON Schema}
      }
    }
  ],
  "tool_choice": "auto" | "none" | "required" | {"type": "function", "function": {"name": "string"}},
  "response_format": {"type": "text" | "json_object"},
  "seed": number
}
\`\`\`

## Response
Same format as OpenAI:
\`\`\`json
{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "llama-3.3-70b-versatile",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "string",
        "tool_calls": [...]
      },
      "finish_reason": "stop" | "length" | "tool_calls"
    }
  ],
  "x_groq": {
    "id": "req_xxx",
    "usage": {
      "queue_time": 0.01,
      "prompt_tokens": 10,
      "prompt_time": 0.001,
      "completion_tokens": 50,
      "completion_time": 0.05,
      "total_tokens": 60,
      "total_time": 0.051
    }
  }
}
\`\`\`

## Available Models
- llama-3.3-70b-versatile: Latest 70B, best quality
- llama-3.1-8b-instant: Fast 8B model
- llama-3.2-90b-vision-preview: Vision capabilities
- mixtral-8x7b-32768: MoE model, 32K context
- gemma2-9b-it: Google's Gemma 2
- deepseek-r1-distill-llama-70b: DeepSeek reasoning

## Python SDK Example
\`\`\`python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",
    api_key="gsk_..."
)

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
    temperature=0.7,
    max_tokens=1024
)

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

## Node.js Example
\`\`\`javascript
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.groq.com/openai/v1",
  apiKey: "gsk_..."
});

const response = await client.chat.completions.create({
  model: "llama-3.3-70b-versatile",
  messages: [{ role: "user", content: "Hello!" }],
  max_tokens: 1024
});

console.log(response.choices[0].message.content);
\`\`\`

## cURL Example
\`\`\`bash
curl https://api.groq.com/openai/v1/chat/completions \\
  -H "Authorization: Bearer $GROQ_API_KEY" \\
  -H "Content-Type: application/json" \\
  -d '{
    "model": "llama-3.3-70b-versatile",
    "messages": [{"role": "user", "content": "Hello!"}],
    "temperature": 0.7
  }'
\`\`\``
    },
    {
        id: "groq-rate-limits",
        title: "Groq Rate Limits & Pricing",
        category: "limits",
        provider: "groq",
        keywords: ["groq", "rate limit", "pricing", "cost", "free", "limits"],
        content: `# Groq Rate Limits & Pricing

## Free Tier Rate Limits
- llama-3.3-70b: 30 RPM, 14,400 RPD, 6,000 TPM
- llama-3.1-8b: 30 RPM, 14,400 RPD, 6,000 TPM
- mixtral-8x7b: 30 RPM, 14,400 RPD, 6,000 TPM
- gemma2-9b: 30 RPM, 14,400 RPD, 6,000 TPM

## Paid Tier
Higher limits available with billing.

## Pricing (per 1M tokens)
- llama-3.3-70b: Input $0.59, Output $0.79
- llama-3.1-8b: Input $0.05, Output $0.08
- mixtral-8x7b: Input $0.24, Output $0.24
- gemma2-9b: Input $0.20, Output $0.20
- llama-3.2-90b-vision: Input $0.90, Output $0.90

## Key Features
- Ultra-fast inference (LPUs)
- OpenAI-compatible API
- Free tier available
- No context window limits beyond model specs

## Context Windows
- llama-3.3-70b: 128K tokens
- llama-3.1-8b: 128K tokens
- mixtral-8x7b: 32K tokens
- gemma2-9b: 8K tokens

## Error Codes
- 400: Bad Request
- 401: Invalid API key
- 429: Rate limit exceeded (includes retry-after header)
- 500: Internal error`
    },
    {
        id: "groq-function-calling",
        title: "Groq Function Calling",
        category: "tools",
        provider: "groq",
        keywords: ["groq", "function", "tools", "tool calling", "function calling"],
        content: `# Groq Function Calling

Groq supports function calling with OpenAI-compatible format.

## Supported Models
- llama-3.3-70b-versatile
- llama-3.1-8b-instant
- mixtral-8x7b-32768

## Tool Definition
\`\`\`json
{
  "type": "function",
  "function": {
    "name": "get_weather",
    "description": "Get weather for location",
    "parameters": {
      "type": "object",
      "properties": {
        "location": {"type": "string"},
        "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]}
      },
      "required": ["location"]
    }
  }
}
\`\`\`

## Python Example
\`\`\`python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.groq.com/openai/v1",
    api_key="gsk_..."
)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get weather",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {"type": "string"}
                },
                "required": ["location"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="llama-3.3-70b-versatile",
    messages=[{"role": "user", "content": "Weather in Tokyo?"}],
    tools=tools
)

# Handle tool calls same as OpenAI
if response.choices[0].message.tool_calls:
    for tc in response.choices[0].message.tool_calls:
        result = execute_tool(tc.function.name, tc.function.arguments)
        
        response2 = client.chat.completions.create(
            model="llama-3.3-70b-versatile",
            messages=[
                {"role": "user", "content": "Weather in Tokyo?"},
                {"role": "assistant", "content": None, "tool_calls": [tc]},
                {"role": "tool", "tool_call_id": tc.id, "content": str(result)}
            ],
            tools=tools
        )
\`\`\``
    }
];
//# sourceMappingURL=groq.js.map